Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +7 -0
- README.md +0 -0
- adapter_config.json +37 -0
- adapter_model.safetensors +3 -0
- checkpoint-run1-124/README.md +202 -0
- checkpoint-run1-124/adapter_config.json +37 -0
- checkpoint-run1-124/adapter_model.safetensors +3 -0
- checkpoint-run1-124/optimizer.bin +3 -0
- checkpoint-run1-124/pytorch_model_fsdp.bin +3 -0
- checkpoint-run1-124/rng_state_0.pth +3 -0
- checkpoint-run1-124/rng_state_1.pth +3 -0
- checkpoint-run1-124/scheduler.pt +3 -0
- checkpoint-run1-124/special_tokens_map.json +23 -0
- checkpoint-run1-124/tokenizer.json +3 -0
- checkpoint-run1-124/tokenizer_config.json +2075 -0
- checkpoint-run1-124/trainer_state.json +1893 -0
- checkpoint-run1-124/training_args.bin +3 -0
- checkpoint-run1-186/README.md +202 -0
- checkpoint-run1-186/adapter_config.json +37 -0
- checkpoint-run1-186/adapter_model.safetensors +3 -0
- checkpoint-run1-186/optimizer.bin +3 -0
- checkpoint-run1-186/pytorch_model_fsdp.bin +3 -0
- checkpoint-run1-186/rng_state_0.pth +3 -0
- checkpoint-run1-186/rng_state_1.pth +3 -0
- checkpoint-run1-186/scheduler.pt +3 -0
- checkpoint-run1-186/special_tokens_map.json +23 -0
- checkpoint-run1-186/tokenizer.json +3 -0
- checkpoint-run1-186/tokenizer_config.json +2075 -0
- checkpoint-run1-186/trainer_state.json +2823 -0
- checkpoint-run1-186/training_args.bin +3 -0
- checkpoint-run1-246/README.md +202 -0
- checkpoint-run1-246/adapter_config.json +37 -0
- checkpoint-run1-246/adapter_model.safetensors +3 -0
- checkpoint-run1-246/optimizer.bin +3 -0
- checkpoint-run1-246/pytorch_model_fsdp.bin +3 -0
- checkpoint-run1-246/rng_state_0.pth +3 -0
- checkpoint-run1-246/rng_state_1.pth +3 -0
- checkpoint-run1-246/scheduler.pt +3 -0
- checkpoint-run1-246/special_tokens_map.json +23 -0
- checkpoint-run1-246/tokenizer.json +3 -0
- checkpoint-run1-246/tokenizer_config.json +2075 -0
- checkpoint-run1-246/trainer_state.json +0 -0
- checkpoint-run1-246/training_args.bin +3 -0
- checkpoint-run1-62/README.md +202 -0
- checkpoint-run1-62/adapter_config.json +37 -0
- checkpoint-run1-62/adapter_model.safetensors +3 -0
- checkpoint-run1-62/optimizer.bin +3 -0
- checkpoint-run1-62/pytorch_model_fsdp.bin +3 -0
- checkpoint-run1-62/rng_state_0.pth +3 -0
- checkpoint-run1-62/rng_state_1.pth +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
checkpoint-run1-124/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
checkpoint-run1-186/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
38 |
+
checkpoint-run1-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
39 |
+
checkpoint-run1-62/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
40 |
+
checkpoint_run2-123/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
41 |
+
checkpoint_run2-62/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
42 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
The diff for this file is too large to render.
See raw diff
|
|
adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "/cpool/DeepSeek-R1-Distill-Llama-70B-Uncensored-v2-Unbiased",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": null,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 32,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"up_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"v_proj",
|
29 |
+
"q_proj",
|
30 |
+
"k_proj",
|
31 |
+
"o_proj",
|
32 |
+
"down_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bbff3982971bdd45de26c98c878c31a8c5c7ac7a2bb82d3bee6cae81ec85b39
|
3 |
+
size 1656902648
|
checkpoint-run1-124/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: /cpool/DeepSeek-R1-Distill-Llama-70B-Uncensored-v2
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.14.0
|
checkpoint-run1-124/adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "/cpool/DeepSeek-R1-Distill-Llama-70B-Uncensored-v2",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": null,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 32,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"v_proj",
|
27 |
+
"o_proj",
|
28 |
+
"q_proj",
|
29 |
+
"k_proj",
|
30 |
+
"gate_proj",
|
31 |
+
"down_proj",
|
32 |
+
"up_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
checkpoint-run1-124/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac44102a44a992ec3ce2443d5ab54d7373f81de77cd8f2d3c9b4a060a8d602dc
|
3 |
+
size 1656902648
|
checkpoint-run1-124/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb156ab573f08f4af36e0854ea1989d5e84ed256ee93d999d54bc0f849190179
|
3 |
+
size 3314505202
|
checkpoint-run1-124/pytorch_model_fsdp.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f29a4c650058b1cef152bf319c26b45df43fc880b721239db8a1efce52bb7b6a
|
3 |
+
size 1657168758
|
checkpoint-run1-124/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cb795a5cea0baa625c50007a6c9da09c6bbb5c16b560424070384a479e7d8a6
|
3 |
+
size 14512
|
checkpoint-run1-124/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f19604377bd828eb366c68946ad997a4ff4d69beaeea93ee58915135768ec63
|
3 |
+
size 14512
|
checkpoint-run1-124/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1e9129b40c6a675007da0067569f7360333ba3a8723ae955f6a7f4122eb27be
|
3 |
+
size 1064
|
checkpoint-run1-124/special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end_of_text|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
checkpoint-run1-124/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16f2ebc8d9a7de55360d83ea69f97916a1389f0a72264664d4d6c4db6da8d0b8
|
3 |
+
size 17209722
|
checkpoint-run1-124/tokenizer_config.json
ADDED
@@ -0,0 +1,2075 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"128000": {
|
7 |
+
"content": "<|begin▁of▁sentence|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"128001": {
|
15 |
+
"content": "<|end▁of▁sentence|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"128002": {
|
23 |
+
"content": "<|reserved_special_token_0|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"128003": {
|
31 |
+
"content": "<|reserved_special_token_1|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"128004": {
|
39 |
+
"content": "<|finetune_right_pad_id|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"128005": {
|
47 |
+
"content": "<|reserved_special_token_2|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"128006": {
|
55 |
+
"content": "<|start_header_id|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"128007": {
|
63 |
+
"content": "<|end_header_id|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"128008": {
|
71 |
+
"content": "<|eom_id|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"128009": {
|
79 |
+
"content": "<|eot_id|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"128010": {
|
87 |
+
"content": "<|python_tag|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"128011": {
|
95 |
+
"content": "<|User|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"128012": {
|
103 |
+
"content": "<|Assistant|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"128013": {
|
111 |
+
"content": "<think>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"128014": {
|
119 |
+
"content": "</think>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"128015": {
|
127 |
+
"content": "<|▁pad▁|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"128016": {
|
135 |
+
"content": "<|reserved_special_token_8|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"128017": {
|
143 |
+
"content": "<|reserved_special_token_9|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"128018": {
|
151 |
+
"content": "<|reserved_special_token_10|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"128019": {
|
159 |
+
"content": "<|reserved_special_token_11|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"128020": {
|
167 |
+
"content": "<|reserved_special_token_12|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"128021": {
|
175 |
+
"content": "<|reserved_special_token_13|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"128022": {
|
183 |
+
"content": "<|reserved_special_token_14|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"128023": {
|
191 |
+
"content": "<|reserved_special_token_15|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"128024": {
|
199 |
+
"content": "<|reserved_special_token_16|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"128025": {
|
207 |
+
"content": "<|reserved_special_token_17|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"128026": {
|
215 |
+
"content": "<|reserved_special_token_18|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"128027": {
|
223 |
+
"content": "<|reserved_special_token_19|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"128028": {
|
231 |
+
"content": "<|reserved_special_token_20|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"128029": {
|
239 |
+
"content": "<|reserved_special_token_21|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"128030": {
|
247 |
+
"content": "<|reserved_special_token_22|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"128031": {
|
255 |
+
"content": "<|reserved_special_token_23|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"128032": {
|
263 |
+
"content": "<|reserved_special_token_24|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"128033": {
|
271 |
+
"content": "<|reserved_special_token_25|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"128034": {
|
279 |
+
"content": "<|reserved_special_token_26|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"128035": {
|
287 |
+
"content": "<|reserved_special_token_27|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"128036": {
|
295 |
+
"content": "<|reserved_special_token_28|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"128037": {
|
303 |
+
"content": "<|reserved_special_token_29|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"128038": {
|
311 |
+
"content": "<|reserved_special_token_30|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"128039": {
|
319 |
+
"content": "<|reserved_special_token_31|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"128040": {
|
327 |
+
"content": "<|reserved_special_token_32|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"128041": {
|
335 |
+
"content": "<|reserved_special_token_33|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"128042": {
|
343 |
+
"content": "<|reserved_special_token_34|>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"128043": {
|
351 |
+
"content": "<|reserved_special_token_35|>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"128044": {
|
359 |
+
"content": "<|reserved_special_token_36|>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"128045": {
|
367 |
+
"content": "<|reserved_special_token_37|>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"128046": {
|
375 |
+
"content": "<|reserved_special_token_38|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"128047": {
|
383 |
+
"content": "<|reserved_special_token_39|>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"128048": {
|
391 |
+
"content": "<|reserved_special_token_40|>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"128049": {
|
399 |
+
"content": "<|reserved_special_token_41|>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"128050": {
|
407 |
+
"content": "<|reserved_special_token_42|>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"128051": {
|
415 |
+
"content": "<|reserved_special_token_43|>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"128052": {
|
423 |
+
"content": "<|reserved_special_token_44|>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"128053": {
|
431 |
+
"content": "<|reserved_special_token_45|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"128054": {
|
439 |
+
"content": "<|reserved_special_token_46|>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"128055": {
|
447 |
+
"content": "<|reserved_special_token_47|>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"128056": {
|
455 |
+
"content": "<|reserved_special_token_48|>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"128057": {
|
463 |
+
"content": "<|reserved_special_token_49|>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"128058": {
|
471 |
+
"content": "<|reserved_special_token_50|>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"128059": {
|
479 |
+
"content": "<|reserved_special_token_51|>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"128060": {
|
487 |
+
"content": "<|reserved_special_token_52|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"128061": {
|
495 |
+
"content": "<|reserved_special_token_53|>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"128062": {
|
503 |
+
"content": "<|reserved_special_token_54|>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"128063": {
|
511 |
+
"content": "<|reserved_special_token_55|>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"128064": {
|
519 |
+
"content": "<|reserved_special_token_56|>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"128065": {
|
527 |
+
"content": "<|reserved_special_token_57|>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"128066": {
|
535 |
+
"content": "<|reserved_special_token_58|>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
},
|
542 |
+
"128067": {
|
543 |
+
"content": "<|reserved_special_token_59|>",
|
544 |
+
"lstrip": false,
|
545 |
+
"normalized": false,
|
546 |
+
"rstrip": false,
|
547 |
+
"single_word": false,
|
548 |
+
"special": true
|
549 |
+
},
|
550 |
+
"128068": {
|
551 |
+
"content": "<|reserved_special_token_60|>",
|
552 |
+
"lstrip": false,
|
553 |
+
"normalized": false,
|
554 |
+
"rstrip": false,
|
555 |
+
"single_word": false,
|
556 |
+
"special": true
|
557 |
+
},
|
558 |
+
"128069": {
|
559 |
+
"content": "<|reserved_special_token_61|>",
|
560 |
+
"lstrip": false,
|
561 |
+
"normalized": false,
|
562 |
+
"rstrip": false,
|
563 |
+
"single_word": false,
|
564 |
+
"special": true
|
565 |
+
},
|
566 |
+
"128070": {
|
567 |
+
"content": "<|reserved_special_token_62|>",
|
568 |
+
"lstrip": false,
|
569 |
+
"normalized": false,
|
570 |
+
"rstrip": false,
|
571 |
+
"single_word": false,
|
572 |
+
"special": true
|
573 |
+
},
|
574 |
+
"128071": {
|
575 |
+
"content": "<|reserved_special_token_63|>",
|
576 |
+
"lstrip": false,
|
577 |
+
"normalized": false,
|
578 |
+
"rstrip": false,
|
579 |
+
"single_word": false,
|
580 |
+
"special": true
|
581 |
+
},
|
582 |
+
"128072": {
|
583 |
+
"content": "<|reserved_special_token_64|>",
|
584 |
+
"lstrip": false,
|
585 |
+
"normalized": false,
|
586 |
+
"rstrip": false,
|
587 |
+
"single_word": false,
|
588 |
+
"special": true
|
589 |
+
},
|
590 |
+
"128073": {
|
591 |
+
"content": "<|reserved_special_token_65|>",
|
592 |
+
"lstrip": false,
|
593 |
+
"normalized": false,
|
594 |
+
"rstrip": false,
|
595 |
+
"single_word": false,
|
596 |
+
"special": true
|
597 |
+
},
|
598 |
+
"128074": {
|
599 |
+
"content": "<|reserved_special_token_66|>",
|
600 |
+
"lstrip": false,
|
601 |
+
"normalized": false,
|
602 |
+
"rstrip": false,
|
603 |
+
"single_word": false,
|
604 |
+
"special": true
|
605 |
+
},
|
606 |
+
"128075": {
|
607 |
+
"content": "<|reserved_special_token_67|>",
|
608 |
+
"lstrip": false,
|
609 |
+
"normalized": false,
|
610 |
+
"rstrip": false,
|
611 |
+
"single_word": false,
|
612 |
+
"special": true
|
613 |
+
},
|
614 |
+
"128076": {
|
615 |
+
"content": "<|reserved_special_token_68|>",
|
616 |
+
"lstrip": false,
|
617 |
+
"normalized": false,
|
618 |
+
"rstrip": false,
|
619 |
+
"single_word": false,
|
620 |
+
"special": true
|
621 |
+
},
|
622 |
+
"128077": {
|
623 |
+
"content": "<|reserved_special_token_69|>",
|
624 |
+
"lstrip": false,
|
625 |
+
"normalized": false,
|
626 |
+
"rstrip": false,
|
627 |
+
"single_word": false,
|
628 |
+
"special": true
|
629 |
+
},
|
630 |
+
"128078": {
|
631 |
+
"content": "<|reserved_special_token_70|>",
|
632 |
+
"lstrip": false,
|
633 |
+
"normalized": false,
|
634 |
+
"rstrip": false,
|
635 |
+
"single_word": false,
|
636 |
+
"special": true
|
637 |
+
},
|
638 |
+
"128079": {
|
639 |
+
"content": "<|reserved_special_token_71|>",
|
640 |
+
"lstrip": false,
|
641 |
+
"normalized": false,
|
642 |
+
"rstrip": false,
|
643 |
+
"single_word": false,
|
644 |
+
"special": true
|
645 |
+
},
|
646 |
+
"128080": {
|
647 |
+
"content": "<|reserved_special_token_72|>",
|
648 |
+
"lstrip": false,
|
649 |
+
"normalized": false,
|
650 |
+
"rstrip": false,
|
651 |
+
"single_word": false,
|
652 |
+
"special": true
|
653 |
+
},
|
654 |
+
"128081": {
|
655 |
+
"content": "<|reserved_special_token_73|>",
|
656 |
+
"lstrip": false,
|
657 |
+
"normalized": false,
|
658 |
+
"rstrip": false,
|
659 |
+
"single_word": false,
|
660 |
+
"special": true
|
661 |
+
},
|
662 |
+
"128082": {
|
663 |
+
"content": "<|reserved_special_token_74|>",
|
664 |
+
"lstrip": false,
|
665 |
+
"normalized": false,
|
666 |
+
"rstrip": false,
|
667 |
+
"single_word": false,
|
668 |
+
"special": true
|
669 |
+
},
|
670 |
+
"128083": {
|
671 |
+
"content": "<|reserved_special_token_75|>",
|
672 |
+
"lstrip": false,
|
673 |
+
"normalized": false,
|
674 |
+
"rstrip": false,
|
675 |
+
"single_word": false,
|
676 |
+
"special": true
|
677 |
+
},
|
678 |
+
"128084": {
|
679 |
+
"content": "<|reserved_special_token_76|>",
|
680 |
+
"lstrip": false,
|
681 |
+
"normalized": false,
|
682 |
+
"rstrip": false,
|
683 |
+
"single_word": false,
|
684 |
+
"special": true
|
685 |
+
},
|
686 |
+
"128085": {
|
687 |
+
"content": "<|reserved_special_token_77|>",
|
688 |
+
"lstrip": false,
|
689 |
+
"normalized": false,
|
690 |
+
"rstrip": false,
|
691 |
+
"single_word": false,
|
692 |
+
"special": true
|
693 |
+
},
|
694 |
+
"128086": {
|
695 |
+
"content": "<|reserved_special_token_78|>",
|
696 |
+
"lstrip": false,
|
697 |
+
"normalized": false,
|
698 |
+
"rstrip": false,
|
699 |
+
"single_word": false,
|
700 |
+
"special": true
|
701 |
+
},
|
702 |
+
"128087": {
|
703 |
+
"content": "<|reserved_special_token_79|>",
|
704 |
+
"lstrip": false,
|
705 |
+
"normalized": false,
|
706 |
+
"rstrip": false,
|
707 |
+
"single_word": false,
|
708 |
+
"special": true
|
709 |
+
},
|
710 |
+
"128088": {
|
711 |
+
"content": "<|reserved_special_token_80|>",
|
712 |
+
"lstrip": false,
|
713 |
+
"normalized": false,
|
714 |
+
"rstrip": false,
|
715 |
+
"single_word": false,
|
716 |
+
"special": true
|
717 |
+
},
|
718 |
+
"128089": {
|
719 |
+
"content": "<|reserved_special_token_81|>",
|
720 |
+
"lstrip": false,
|
721 |
+
"normalized": false,
|
722 |
+
"rstrip": false,
|
723 |
+
"single_word": false,
|
724 |
+
"special": true
|
725 |
+
},
|
726 |
+
"128090": {
|
727 |
+
"content": "<|reserved_special_token_82|>",
|
728 |
+
"lstrip": false,
|
729 |
+
"normalized": false,
|
730 |
+
"rstrip": false,
|
731 |
+
"single_word": false,
|
732 |
+
"special": true
|
733 |
+
},
|
734 |
+
"128091": {
|
735 |
+
"content": "<|reserved_special_token_83|>",
|
736 |
+
"lstrip": false,
|
737 |
+
"normalized": false,
|
738 |
+
"rstrip": false,
|
739 |
+
"single_word": false,
|
740 |
+
"special": true
|
741 |
+
},
|
742 |
+
"128092": {
|
743 |
+
"content": "<|reserved_special_token_84|>",
|
744 |
+
"lstrip": false,
|
745 |
+
"normalized": false,
|
746 |
+
"rstrip": false,
|
747 |
+
"single_word": false,
|
748 |
+
"special": true
|
749 |
+
},
|
750 |
+
"128093": {
|
751 |
+
"content": "<|reserved_special_token_85|>",
|
752 |
+
"lstrip": false,
|
753 |
+
"normalized": false,
|
754 |
+
"rstrip": false,
|
755 |
+
"single_word": false,
|
756 |
+
"special": true
|
757 |
+
},
|
758 |
+
"128094": {
|
759 |
+
"content": "<|reserved_special_token_86|>",
|
760 |
+
"lstrip": false,
|
761 |
+
"normalized": false,
|
762 |
+
"rstrip": false,
|
763 |
+
"single_word": false,
|
764 |
+
"special": true
|
765 |
+
},
|
766 |
+
"128095": {
|
767 |
+
"content": "<|reserved_special_token_87|>",
|
768 |
+
"lstrip": false,
|
769 |
+
"normalized": false,
|
770 |
+
"rstrip": false,
|
771 |
+
"single_word": false,
|
772 |
+
"special": true
|
773 |
+
},
|
774 |
+
"128096": {
|
775 |
+
"content": "<|reserved_special_token_88|>",
|
776 |
+
"lstrip": false,
|
777 |
+
"normalized": false,
|
778 |
+
"rstrip": false,
|
779 |
+
"single_word": false,
|
780 |
+
"special": true
|
781 |
+
},
|
782 |
+
"128097": {
|
783 |
+
"content": "<|reserved_special_token_89|>",
|
784 |
+
"lstrip": false,
|
785 |
+
"normalized": false,
|
786 |
+
"rstrip": false,
|
787 |
+
"single_word": false,
|
788 |
+
"special": true
|
789 |
+
},
|
790 |
+
"128098": {
|
791 |
+
"content": "<|reserved_special_token_90|>",
|
792 |
+
"lstrip": false,
|
793 |
+
"normalized": false,
|
794 |
+
"rstrip": false,
|
795 |
+
"single_word": false,
|
796 |
+
"special": true
|
797 |
+
},
|
798 |
+
"128099": {
|
799 |
+
"content": "<|reserved_special_token_91|>",
|
800 |
+
"lstrip": false,
|
801 |
+
"normalized": false,
|
802 |
+
"rstrip": false,
|
803 |
+
"single_word": false,
|
804 |
+
"special": true
|
805 |
+
},
|
806 |
+
"128100": {
|
807 |
+
"content": "<|reserved_special_token_92|>",
|
808 |
+
"lstrip": false,
|
809 |
+
"normalized": false,
|
810 |
+
"rstrip": false,
|
811 |
+
"single_word": false,
|
812 |
+
"special": true
|
813 |
+
},
|
814 |
+
"128101": {
|
815 |
+
"content": "<|reserved_special_token_93|>",
|
816 |
+
"lstrip": false,
|
817 |
+
"normalized": false,
|
818 |
+
"rstrip": false,
|
819 |
+
"single_word": false,
|
820 |
+
"special": true
|
821 |
+
},
|
822 |
+
"128102": {
|
823 |
+
"content": "<|reserved_special_token_94|>",
|
824 |
+
"lstrip": false,
|
825 |
+
"normalized": false,
|
826 |
+
"rstrip": false,
|
827 |
+
"single_word": false,
|
828 |
+
"special": true
|
829 |
+
},
|
830 |
+
"128103": {
|
831 |
+
"content": "<|reserved_special_token_95|>",
|
832 |
+
"lstrip": false,
|
833 |
+
"normalized": false,
|
834 |
+
"rstrip": false,
|
835 |
+
"single_word": false,
|
836 |
+
"special": true
|
837 |
+
},
|
838 |
+
"128104": {
|
839 |
+
"content": "<|reserved_special_token_96|>",
|
840 |
+
"lstrip": false,
|
841 |
+
"normalized": false,
|
842 |
+
"rstrip": false,
|
843 |
+
"single_word": false,
|
844 |
+
"special": true
|
845 |
+
},
|
846 |
+
"128105": {
|
847 |
+
"content": "<|reserved_special_token_97|>",
|
848 |
+
"lstrip": false,
|
849 |
+
"normalized": false,
|
850 |
+
"rstrip": false,
|
851 |
+
"single_word": false,
|
852 |
+
"special": true
|
853 |
+
},
|
854 |
+
"128106": {
|
855 |
+
"content": "<|reserved_special_token_98|>",
|
856 |
+
"lstrip": false,
|
857 |
+
"normalized": false,
|
858 |
+
"rstrip": false,
|
859 |
+
"single_word": false,
|
860 |
+
"special": true
|
861 |
+
},
|
862 |
+
"128107": {
|
863 |
+
"content": "<|reserved_special_token_99|>",
|
864 |
+
"lstrip": false,
|
865 |
+
"normalized": false,
|
866 |
+
"rstrip": false,
|
867 |
+
"single_word": false,
|
868 |
+
"special": true
|
869 |
+
},
|
870 |
+
"128108": {
|
871 |
+
"content": "<|reserved_special_token_100|>",
|
872 |
+
"lstrip": false,
|
873 |
+
"normalized": false,
|
874 |
+
"rstrip": false,
|
875 |
+
"single_word": false,
|
876 |
+
"special": true
|
877 |
+
},
|
878 |
+
"128109": {
|
879 |
+
"content": "<|reserved_special_token_101|>",
|
880 |
+
"lstrip": false,
|
881 |
+
"normalized": false,
|
882 |
+
"rstrip": false,
|
883 |
+
"single_word": false,
|
884 |
+
"special": true
|
885 |
+
},
|
886 |
+
"128110": {
|
887 |
+
"content": "<|reserved_special_token_102|>",
|
888 |
+
"lstrip": false,
|
889 |
+
"normalized": false,
|
890 |
+
"rstrip": false,
|
891 |
+
"single_word": false,
|
892 |
+
"special": true
|
893 |
+
},
|
894 |
+
"128111": {
|
895 |
+
"content": "<|reserved_special_token_103|>",
|
896 |
+
"lstrip": false,
|
897 |
+
"normalized": false,
|
898 |
+
"rstrip": false,
|
899 |
+
"single_word": false,
|
900 |
+
"special": true
|
901 |
+
},
|
902 |
+
"128112": {
|
903 |
+
"content": "<|reserved_special_token_104|>",
|
904 |
+
"lstrip": false,
|
905 |
+
"normalized": false,
|
906 |
+
"rstrip": false,
|
907 |
+
"single_word": false,
|
908 |
+
"special": true
|
909 |
+
},
|
910 |
+
"128113": {
|
911 |
+
"content": "<|reserved_special_token_105|>",
|
912 |
+
"lstrip": false,
|
913 |
+
"normalized": false,
|
914 |
+
"rstrip": false,
|
915 |
+
"single_word": false,
|
916 |
+
"special": true
|
917 |
+
},
|
918 |
+
"128114": {
|
919 |
+
"content": "<|reserved_special_token_106|>",
|
920 |
+
"lstrip": false,
|
921 |
+
"normalized": false,
|
922 |
+
"rstrip": false,
|
923 |
+
"single_word": false,
|
924 |
+
"special": true
|
925 |
+
},
|
926 |
+
"128115": {
|
927 |
+
"content": "<|reserved_special_token_107|>",
|
928 |
+
"lstrip": false,
|
929 |
+
"normalized": false,
|
930 |
+
"rstrip": false,
|
931 |
+
"single_word": false,
|
932 |
+
"special": true
|
933 |
+
},
|
934 |
+
"128116": {
|
935 |
+
"content": "<|reserved_special_token_108|>",
|
936 |
+
"lstrip": false,
|
937 |
+
"normalized": false,
|
938 |
+
"rstrip": false,
|
939 |
+
"single_word": false,
|
940 |
+
"special": true
|
941 |
+
},
|
942 |
+
"128117": {
|
943 |
+
"content": "<|reserved_special_token_109|>",
|
944 |
+
"lstrip": false,
|
945 |
+
"normalized": false,
|
946 |
+
"rstrip": false,
|
947 |
+
"single_word": false,
|
948 |
+
"special": true
|
949 |
+
},
|
950 |
+
"128118": {
|
951 |
+
"content": "<|reserved_special_token_110|>",
|
952 |
+
"lstrip": false,
|
953 |
+
"normalized": false,
|
954 |
+
"rstrip": false,
|
955 |
+
"single_word": false,
|
956 |
+
"special": true
|
957 |
+
},
|
958 |
+
"128119": {
|
959 |
+
"content": "<|reserved_special_token_111|>",
|
960 |
+
"lstrip": false,
|
961 |
+
"normalized": false,
|
962 |
+
"rstrip": false,
|
963 |
+
"single_word": false,
|
964 |
+
"special": true
|
965 |
+
},
|
966 |
+
"128120": {
|
967 |
+
"content": "<|reserved_special_token_112|>",
|
968 |
+
"lstrip": false,
|
969 |
+
"normalized": false,
|
970 |
+
"rstrip": false,
|
971 |
+
"single_word": false,
|
972 |
+
"special": true
|
973 |
+
},
|
974 |
+
"128121": {
|
975 |
+
"content": "<|reserved_special_token_113|>",
|
976 |
+
"lstrip": false,
|
977 |
+
"normalized": false,
|
978 |
+
"rstrip": false,
|
979 |
+
"single_word": false,
|
980 |
+
"special": true
|
981 |
+
},
|
982 |
+
"128122": {
|
983 |
+
"content": "<|reserved_special_token_114|>",
|
984 |
+
"lstrip": false,
|
985 |
+
"normalized": false,
|
986 |
+
"rstrip": false,
|
987 |
+
"single_word": false,
|
988 |
+
"special": true
|
989 |
+
},
|
990 |
+
"128123": {
|
991 |
+
"content": "<|reserved_special_token_115|>",
|
992 |
+
"lstrip": false,
|
993 |
+
"normalized": false,
|
994 |
+
"rstrip": false,
|
995 |
+
"single_word": false,
|
996 |
+
"special": true
|
997 |
+
},
|
998 |
+
"128124": {
|
999 |
+
"content": "<|reserved_special_token_116|>",
|
1000 |
+
"lstrip": false,
|
1001 |
+
"normalized": false,
|
1002 |
+
"rstrip": false,
|
1003 |
+
"single_word": false,
|
1004 |
+
"special": true
|
1005 |
+
},
|
1006 |
+
"128125": {
|
1007 |
+
"content": "<|reserved_special_token_117|>",
|
1008 |
+
"lstrip": false,
|
1009 |
+
"normalized": false,
|
1010 |
+
"rstrip": false,
|
1011 |
+
"single_word": false,
|
1012 |
+
"special": true
|
1013 |
+
},
|
1014 |
+
"128126": {
|
1015 |
+
"content": "<|reserved_special_token_118|>",
|
1016 |
+
"lstrip": false,
|
1017 |
+
"normalized": false,
|
1018 |
+
"rstrip": false,
|
1019 |
+
"single_word": false,
|
1020 |
+
"special": true
|
1021 |
+
},
|
1022 |
+
"128127": {
|
1023 |
+
"content": "<|reserved_special_token_119|>",
|
1024 |
+
"lstrip": false,
|
1025 |
+
"normalized": false,
|
1026 |
+
"rstrip": false,
|
1027 |
+
"single_word": false,
|
1028 |
+
"special": true
|
1029 |
+
},
|
1030 |
+
"128128": {
|
1031 |
+
"content": "<|reserved_special_token_120|>",
|
1032 |
+
"lstrip": false,
|
1033 |
+
"normalized": false,
|
1034 |
+
"rstrip": false,
|
1035 |
+
"single_word": false,
|
1036 |
+
"special": true
|
1037 |
+
},
|
1038 |
+
"128129": {
|
1039 |
+
"content": "<|reserved_special_token_121|>",
|
1040 |
+
"lstrip": false,
|
1041 |
+
"normalized": false,
|
1042 |
+
"rstrip": false,
|
1043 |
+
"single_word": false,
|
1044 |
+
"special": true
|
1045 |
+
},
|
1046 |
+
"128130": {
|
1047 |
+
"content": "<|reserved_special_token_122|>",
|
1048 |
+
"lstrip": false,
|
1049 |
+
"normalized": false,
|
1050 |
+
"rstrip": false,
|
1051 |
+
"single_word": false,
|
1052 |
+
"special": true
|
1053 |
+
},
|
1054 |
+
"128131": {
|
1055 |
+
"content": "<|reserved_special_token_123|>",
|
1056 |
+
"lstrip": false,
|
1057 |
+
"normalized": false,
|
1058 |
+
"rstrip": false,
|
1059 |
+
"single_word": false,
|
1060 |
+
"special": true
|
1061 |
+
},
|
1062 |
+
"128132": {
|
1063 |
+
"content": "<|reserved_special_token_124|>",
|
1064 |
+
"lstrip": false,
|
1065 |
+
"normalized": false,
|
1066 |
+
"rstrip": false,
|
1067 |
+
"single_word": false,
|
1068 |
+
"special": true
|
1069 |
+
},
|
1070 |
+
"128133": {
|
1071 |
+
"content": "<|reserved_special_token_125|>",
|
1072 |
+
"lstrip": false,
|
1073 |
+
"normalized": false,
|
1074 |
+
"rstrip": false,
|
1075 |
+
"single_word": false,
|
1076 |
+
"special": true
|
1077 |
+
},
|
1078 |
+
"128134": {
|
1079 |
+
"content": "<|reserved_special_token_126|>",
|
1080 |
+
"lstrip": false,
|
1081 |
+
"normalized": false,
|
1082 |
+
"rstrip": false,
|
1083 |
+
"single_word": false,
|
1084 |
+
"special": true
|
1085 |
+
},
|
1086 |
+
"128135": {
|
1087 |
+
"content": "<|reserved_special_token_127|>",
|
1088 |
+
"lstrip": false,
|
1089 |
+
"normalized": false,
|
1090 |
+
"rstrip": false,
|
1091 |
+
"single_word": false,
|
1092 |
+
"special": true
|
1093 |
+
},
|
1094 |
+
"128136": {
|
1095 |
+
"content": "<|reserved_special_token_128|>",
|
1096 |
+
"lstrip": false,
|
1097 |
+
"normalized": false,
|
1098 |
+
"rstrip": false,
|
1099 |
+
"single_word": false,
|
1100 |
+
"special": true
|
1101 |
+
},
|
1102 |
+
"128137": {
|
1103 |
+
"content": "<|reserved_special_token_129|>",
|
1104 |
+
"lstrip": false,
|
1105 |
+
"normalized": false,
|
1106 |
+
"rstrip": false,
|
1107 |
+
"single_word": false,
|
1108 |
+
"special": true
|
1109 |
+
},
|
1110 |
+
"128138": {
|
1111 |
+
"content": "<|reserved_special_token_130|>",
|
1112 |
+
"lstrip": false,
|
1113 |
+
"normalized": false,
|
1114 |
+
"rstrip": false,
|
1115 |
+
"single_word": false,
|
1116 |
+
"special": true
|
1117 |
+
},
|
1118 |
+
"128139": {
|
1119 |
+
"content": "<|reserved_special_token_131|>",
|
1120 |
+
"lstrip": false,
|
1121 |
+
"normalized": false,
|
1122 |
+
"rstrip": false,
|
1123 |
+
"single_word": false,
|
1124 |
+
"special": true
|
1125 |
+
},
|
1126 |
+
"128140": {
|
1127 |
+
"content": "<|reserved_special_token_132|>",
|
1128 |
+
"lstrip": false,
|
1129 |
+
"normalized": false,
|
1130 |
+
"rstrip": false,
|
1131 |
+
"single_word": false,
|
1132 |
+
"special": true
|
1133 |
+
},
|
1134 |
+
"128141": {
|
1135 |
+
"content": "<|reserved_special_token_133|>",
|
1136 |
+
"lstrip": false,
|
1137 |
+
"normalized": false,
|
1138 |
+
"rstrip": false,
|
1139 |
+
"single_word": false,
|
1140 |
+
"special": true
|
1141 |
+
},
|
1142 |
+
"128142": {
|
1143 |
+
"content": "<|reserved_special_token_134|>",
|
1144 |
+
"lstrip": false,
|
1145 |
+
"normalized": false,
|
1146 |
+
"rstrip": false,
|
1147 |
+
"single_word": false,
|
1148 |
+
"special": true
|
1149 |
+
},
|
1150 |
+
"128143": {
|
1151 |
+
"content": "<|reserved_special_token_135|>",
|
1152 |
+
"lstrip": false,
|
1153 |
+
"normalized": false,
|
1154 |
+
"rstrip": false,
|
1155 |
+
"single_word": false,
|
1156 |
+
"special": true
|
1157 |
+
},
|
1158 |
+
"128144": {
|
1159 |
+
"content": "<|reserved_special_token_136|>",
|
1160 |
+
"lstrip": false,
|
1161 |
+
"normalized": false,
|
1162 |
+
"rstrip": false,
|
1163 |
+
"single_word": false,
|
1164 |
+
"special": true
|
1165 |
+
},
|
1166 |
+
"128145": {
|
1167 |
+
"content": "<|reserved_special_token_137|>",
|
1168 |
+
"lstrip": false,
|
1169 |
+
"normalized": false,
|
1170 |
+
"rstrip": false,
|
1171 |
+
"single_word": false,
|
1172 |
+
"special": true
|
1173 |
+
},
|
1174 |
+
"128146": {
|
1175 |
+
"content": "<|reserved_special_token_138|>",
|
1176 |
+
"lstrip": false,
|
1177 |
+
"normalized": false,
|
1178 |
+
"rstrip": false,
|
1179 |
+
"single_word": false,
|
1180 |
+
"special": true
|
1181 |
+
},
|
1182 |
+
"128147": {
|
1183 |
+
"content": "<|reserved_special_token_139|>",
|
1184 |
+
"lstrip": false,
|
1185 |
+
"normalized": false,
|
1186 |
+
"rstrip": false,
|
1187 |
+
"single_word": false,
|
1188 |
+
"special": true
|
1189 |
+
},
|
1190 |
+
"128148": {
|
1191 |
+
"content": "<|reserved_special_token_140|>",
|
1192 |
+
"lstrip": false,
|
1193 |
+
"normalized": false,
|
1194 |
+
"rstrip": false,
|
1195 |
+
"single_word": false,
|
1196 |
+
"special": true
|
1197 |
+
},
|
1198 |
+
"128149": {
|
1199 |
+
"content": "<|reserved_special_token_141|>",
|
1200 |
+
"lstrip": false,
|
1201 |
+
"normalized": false,
|
1202 |
+
"rstrip": false,
|
1203 |
+
"single_word": false,
|
1204 |
+
"special": true
|
1205 |
+
},
|
1206 |
+
"128150": {
|
1207 |
+
"content": "<|reserved_special_token_142|>",
|
1208 |
+
"lstrip": false,
|
1209 |
+
"normalized": false,
|
1210 |
+
"rstrip": false,
|
1211 |
+
"single_word": false,
|
1212 |
+
"special": true
|
1213 |
+
},
|
1214 |
+
"128151": {
|
1215 |
+
"content": "<|reserved_special_token_143|>",
|
1216 |
+
"lstrip": false,
|
1217 |
+
"normalized": false,
|
1218 |
+
"rstrip": false,
|
1219 |
+
"single_word": false,
|
1220 |
+
"special": true
|
1221 |
+
},
|
1222 |
+
"128152": {
|
1223 |
+
"content": "<|reserved_special_token_144|>",
|
1224 |
+
"lstrip": false,
|
1225 |
+
"normalized": false,
|
1226 |
+
"rstrip": false,
|
1227 |
+
"single_word": false,
|
1228 |
+
"special": true
|
1229 |
+
},
|
1230 |
+
"128153": {
|
1231 |
+
"content": "<|reserved_special_token_145|>",
|
1232 |
+
"lstrip": false,
|
1233 |
+
"normalized": false,
|
1234 |
+
"rstrip": false,
|
1235 |
+
"single_word": false,
|
1236 |
+
"special": true
|
1237 |
+
},
|
1238 |
+
"128154": {
|
1239 |
+
"content": "<|reserved_special_token_146|>",
|
1240 |
+
"lstrip": false,
|
1241 |
+
"normalized": false,
|
1242 |
+
"rstrip": false,
|
1243 |
+
"single_word": false,
|
1244 |
+
"special": true
|
1245 |
+
},
|
1246 |
+
"128155": {
|
1247 |
+
"content": "<|reserved_special_token_147|>",
|
1248 |
+
"lstrip": false,
|
1249 |
+
"normalized": false,
|
1250 |
+
"rstrip": false,
|
1251 |
+
"single_word": false,
|
1252 |
+
"special": true
|
1253 |
+
},
|
1254 |
+
"128156": {
|
1255 |
+
"content": "<|reserved_special_token_148|>",
|
1256 |
+
"lstrip": false,
|
1257 |
+
"normalized": false,
|
1258 |
+
"rstrip": false,
|
1259 |
+
"single_word": false,
|
1260 |
+
"special": true
|
1261 |
+
},
|
1262 |
+
"128157": {
|
1263 |
+
"content": "<|reserved_special_token_149|>",
|
1264 |
+
"lstrip": false,
|
1265 |
+
"normalized": false,
|
1266 |
+
"rstrip": false,
|
1267 |
+
"single_word": false,
|
1268 |
+
"special": true
|
1269 |
+
},
|
1270 |
+
"128158": {
|
1271 |
+
"content": "<|reserved_special_token_150|>",
|
1272 |
+
"lstrip": false,
|
1273 |
+
"normalized": false,
|
1274 |
+
"rstrip": false,
|
1275 |
+
"single_word": false,
|
1276 |
+
"special": true
|
1277 |
+
},
|
1278 |
+
"128159": {
|
1279 |
+
"content": "<|reserved_special_token_151|>",
|
1280 |
+
"lstrip": false,
|
1281 |
+
"normalized": false,
|
1282 |
+
"rstrip": false,
|
1283 |
+
"single_word": false,
|
1284 |
+
"special": true
|
1285 |
+
},
|
1286 |
+
"128160": {
|
1287 |
+
"content": "<|reserved_special_token_152|>",
|
1288 |
+
"lstrip": false,
|
1289 |
+
"normalized": false,
|
1290 |
+
"rstrip": false,
|
1291 |
+
"single_word": false,
|
1292 |
+
"special": true
|
1293 |
+
},
|
1294 |
+
"128161": {
|
1295 |
+
"content": "<|reserved_special_token_153|>",
|
1296 |
+
"lstrip": false,
|
1297 |
+
"normalized": false,
|
1298 |
+
"rstrip": false,
|
1299 |
+
"single_word": false,
|
1300 |
+
"special": true
|
1301 |
+
},
|
1302 |
+
"128162": {
|
1303 |
+
"content": "<|reserved_special_token_154|>",
|
1304 |
+
"lstrip": false,
|
1305 |
+
"normalized": false,
|
1306 |
+
"rstrip": false,
|
1307 |
+
"single_word": false,
|
1308 |
+
"special": true
|
1309 |
+
},
|
1310 |
+
"128163": {
|
1311 |
+
"content": "<|reserved_special_token_155|>",
|
1312 |
+
"lstrip": false,
|
1313 |
+
"normalized": false,
|
1314 |
+
"rstrip": false,
|
1315 |
+
"single_word": false,
|
1316 |
+
"special": true
|
1317 |
+
},
|
1318 |
+
"128164": {
|
1319 |
+
"content": "<|reserved_special_token_156|>",
|
1320 |
+
"lstrip": false,
|
1321 |
+
"normalized": false,
|
1322 |
+
"rstrip": false,
|
1323 |
+
"single_word": false,
|
1324 |
+
"special": true
|
1325 |
+
},
|
1326 |
+
"128165": {
|
1327 |
+
"content": "<|reserved_special_token_157|>",
|
1328 |
+
"lstrip": false,
|
1329 |
+
"normalized": false,
|
1330 |
+
"rstrip": false,
|
1331 |
+
"single_word": false,
|
1332 |
+
"special": true
|
1333 |
+
},
|
1334 |
+
"128166": {
|
1335 |
+
"content": "<|reserved_special_token_158|>",
|
1336 |
+
"lstrip": false,
|
1337 |
+
"normalized": false,
|
1338 |
+
"rstrip": false,
|
1339 |
+
"single_word": false,
|
1340 |
+
"special": true
|
1341 |
+
},
|
1342 |
+
"128167": {
|
1343 |
+
"content": "<|reserved_special_token_159|>",
|
1344 |
+
"lstrip": false,
|
1345 |
+
"normalized": false,
|
1346 |
+
"rstrip": false,
|
1347 |
+
"single_word": false,
|
1348 |
+
"special": true
|
1349 |
+
},
|
1350 |
+
"128168": {
|
1351 |
+
"content": "<|reserved_special_token_160|>",
|
1352 |
+
"lstrip": false,
|
1353 |
+
"normalized": false,
|
1354 |
+
"rstrip": false,
|
1355 |
+
"single_word": false,
|
1356 |
+
"special": true
|
1357 |
+
},
|
1358 |
+
"128169": {
|
1359 |
+
"content": "<|reserved_special_token_161|>",
|
1360 |
+
"lstrip": false,
|
1361 |
+
"normalized": false,
|
1362 |
+
"rstrip": false,
|
1363 |
+
"single_word": false,
|
1364 |
+
"special": true
|
1365 |
+
},
|
1366 |
+
"128170": {
|
1367 |
+
"content": "<|reserved_special_token_162|>",
|
1368 |
+
"lstrip": false,
|
1369 |
+
"normalized": false,
|
1370 |
+
"rstrip": false,
|
1371 |
+
"single_word": false,
|
1372 |
+
"special": true
|
1373 |
+
},
|
1374 |
+
"128171": {
|
1375 |
+
"content": "<|reserved_special_token_163|>",
|
1376 |
+
"lstrip": false,
|
1377 |
+
"normalized": false,
|
1378 |
+
"rstrip": false,
|
1379 |
+
"single_word": false,
|
1380 |
+
"special": true
|
1381 |
+
},
|
1382 |
+
"128172": {
|
1383 |
+
"content": "<|reserved_special_token_164|>",
|
1384 |
+
"lstrip": false,
|
1385 |
+
"normalized": false,
|
1386 |
+
"rstrip": false,
|
1387 |
+
"single_word": false,
|
1388 |
+
"special": true
|
1389 |
+
},
|
1390 |
+
"128173": {
|
1391 |
+
"content": "<|reserved_special_token_165|>",
|
1392 |
+
"lstrip": false,
|
1393 |
+
"normalized": false,
|
1394 |
+
"rstrip": false,
|
1395 |
+
"single_word": false,
|
1396 |
+
"special": true
|
1397 |
+
},
|
1398 |
+
"128174": {
|
1399 |
+
"content": "<|reserved_special_token_166|>",
|
1400 |
+
"lstrip": false,
|
1401 |
+
"normalized": false,
|
1402 |
+
"rstrip": false,
|
1403 |
+
"single_word": false,
|
1404 |
+
"special": true
|
1405 |
+
},
|
1406 |
+
"128175": {
|
1407 |
+
"content": "<|reserved_special_token_167|>",
|
1408 |
+
"lstrip": false,
|
1409 |
+
"normalized": false,
|
1410 |
+
"rstrip": false,
|
1411 |
+
"single_word": false,
|
1412 |
+
"special": true
|
1413 |
+
},
|
1414 |
+
"128176": {
|
1415 |
+
"content": "<|reserved_special_token_168|>",
|
1416 |
+
"lstrip": false,
|
1417 |
+
"normalized": false,
|
1418 |
+
"rstrip": false,
|
1419 |
+
"single_word": false,
|
1420 |
+
"special": true
|
1421 |
+
},
|
1422 |
+
"128177": {
|
1423 |
+
"content": "<|reserved_special_token_169|>",
|
1424 |
+
"lstrip": false,
|
1425 |
+
"normalized": false,
|
1426 |
+
"rstrip": false,
|
1427 |
+
"single_word": false,
|
1428 |
+
"special": true
|
1429 |
+
},
|
1430 |
+
"128178": {
|
1431 |
+
"content": "<|reserved_special_token_170|>",
|
1432 |
+
"lstrip": false,
|
1433 |
+
"normalized": false,
|
1434 |
+
"rstrip": false,
|
1435 |
+
"single_word": false,
|
1436 |
+
"special": true
|
1437 |
+
},
|
1438 |
+
"128179": {
|
1439 |
+
"content": "<|reserved_special_token_171|>",
|
1440 |
+
"lstrip": false,
|
1441 |
+
"normalized": false,
|
1442 |
+
"rstrip": false,
|
1443 |
+
"single_word": false,
|
1444 |
+
"special": true
|
1445 |
+
},
|
1446 |
+
"128180": {
|
1447 |
+
"content": "<|reserved_special_token_172|>",
|
1448 |
+
"lstrip": false,
|
1449 |
+
"normalized": false,
|
1450 |
+
"rstrip": false,
|
1451 |
+
"single_word": false,
|
1452 |
+
"special": true
|
1453 |
+
},
|
1454 |
+
"128181": {
|
1455 |
+
"content": "<|reserved_special_token_173|>",
|
1456 |
+
"lstrip": false,
|
1457 |
+
"normalized": false,
|
1458 |
+
"rstrip": false,
|
1459 |
+
"single_word": false,
|
1460 |
+
"special": true
|
1461 |
+
},
|
1462 |
+
"128182": {
|
1463 |
+
"content": "<|reserved_special_token_174|>",
|
1464 |
+
"lstrip": false,
|
1465 |
+
"normalized": false,
|
1466 |
+
"rstrip": false,
|
1467 |
+
"single_word": false,
|
1468 |
+
"special": true
|
1469 |
+
},
|
1470 |
+
"128183": {
|
1471 |
+
"content": "<|reserved_special_token_175|>",
|
1472 |
+
"lstrip": false,
|
1473 |
+
"normalized": false,
|
1474 |
+
"rstrip": false,
|
1475 |
+
"single_word": false,
|
1476 |
+
"special": true
|
1477 |
+
},
|
1478 |
+
"128184": {
|
1479 |
+
"content": "<|reserved_special_token_176|>",
|
1480 |
+
"lstrip": false,
|
1481 |
+
"normalized": false,
|
1482 |
+
"rstrip": false,
|
1483 |
+
"single_word": false,
|
1484 |
+
"special": true
|
1485 |
+
},
|
1486 |
+
"128185": {
|
1487 |
+
"content": "<|reserved_special_token_177|>",
|
1488 |
+
"lstrip": false,
|
1489 |
+
"normalized": false,
|
1490 |
+
"rstrip": false,
|
1491 |
+
"single_word": false,
|
1492 |
+
"special": true
|
1493 |
+
},
|
1494 |
+
"128186": {
|
1495 |
+
"content": "<|reserved_special_token_178|>",
|
1496 |
+
"lstrip": false,
|
1497 |
+
"normalized": false,
|
1498 |
+
"rstrip": false,
|
1499 |
+
"single_word": false,
|
1500 |
+
"special": true
|
1501 |
+
},
|
1502 |
+
"128187": {
|
1503 |
+
"content": "<|reserved_special_token_179|>",
|
1504 |
+
"lstrip": false,
|
1505 |
+
"normalized": false,
|
1506 |
+
"rstrip": false,
|
1507 |
+
"single_word": false,
|
1508 |
+
"special": true
|
1509 |
+
},
|
1510 |
+
"128188": {
|
1511 |
+
"content": "<|reserved_special_token_180|>",
|
1512 |
+
"lstrip": false,
|
1513 |
+
"normalized": false,
|
1514 |
+
"rstrip": false,
|
1515 |
+
"single_word": false,
|
1516 |
+
"special": true
|
1517 |
+
},
|
1518 |
+
"128189": {
|
1519 |
+
"content": "<|reserved_special_token_181|>",
|
1520 |
+
"lstrip": false,
|
1521 |
+
"normalized": false,
|
1522 |
+
"rstrip": false,
|
1523 |
+
"single_word": false,
|
1524 |
+
"special": true
|
1525 |
+
},
|
1526 |
+
"128190": {
|
1527 |
+
"content": "<|reserved_special_token_182|>",
|
1528 |
+
"lstrip": false,
|
1529 |
+
"normalized": false,
|
1530 |
+
"rstrip": false,
|
1531 |
+
"single_word": false,
|
1532 |
+
"special": true
|
1533 |
+
},
|
1534 |
+
"128191": {
|
1535 |
+
"content": "<|reserved_special_token_183|>",
|
1536 |
+
"lstrip": false,
|
1537 |
+
"normalized": false,
|
1538 |
+
"rstrip": false,
|
1539 |
+
"single_word": false,
|
1540 |
+
"special": true
|
1541 |
+
},
|
1542 |
+
"128192": {
|
1543 |
+
"content": "<|reserved_special_token_184|>",
|
1544 |
+
"lstrip": false,
|
1545 |
+
"normalized": false,
|
1546 |
+
"rstrip": false,
|
1547 |
+
"single_word": false,
|
1548 |
+
"special": true
|
1549 |
+
},
|
1550 |
+
"128193": {
|
1551 |
+
"content": "<|reserved_special_token_185|>",
|
1552 |
+
"lstrip": false,
|
1553 |
+
"normalized": false,
|
1554 |
+
"rstrip": false,
|
1555 |
+
"single_word": false,
|
1556 |
+
"special": true
|
1557 |
+
},
|
1558 |
+
"128194": {
|
1559 |
+
"content": "<|reserved_special_token_186|>",
|
1560 |
+
"lstrip": false,
|
1561 |
+
"normalized": false,
|
1562 |
+
"rstrip": false,
|
1563 |
+
"single_word": false,
|
1564 |
+
"special": true
|
1565 |
+
},
|
1566 |
+
"128195": {
|
1567 |
+
"content": "<|reserved_special_token_187|>",
|
1568 |
+
"lstrip": false,
|
1569 |
+
"normalized": false,
|
1570 |
+
"rstrip": false,
|
1571 |
+
"single_word": false,
|
1572 |
+
"special": true
|
1573 |
+
},
|
1574 |
+
"128196": {
|
1575 |
+
"content": "<|reserved_special_token_188|>",
|
1576 |
+
"lstrip": false,
|
1577 |
+
"normalized": false,
|
1578 |
+
"rstrip": false,
|
1579 |
+
"single_word": false,
|
1580 |
+
"special": true
|
1581 |
+
},
|
1582 |
+
"128197": {
|
1583 |
+
"content": "<|reserved_special_token_189|>",
|
1584 |
+
"lstrip": false,
|
1585 |
+
"normalized": false,
|
1586 |
+
"rstrip": false,
|
1587 |
+
"single_word": false,
|
1588 |
+
"special": true
|
1589 |
+
},
|
1590 |
+
"128198": {
|
1591 |
+
"content": "<|reserved_special_token_190|>",
|
1592 |
+
"lstrip": false,
|
1593 |
+
"normalized": false,
|
1594 |
+
"rstrip": false,
|
1595 |
+
"single_word": false,
|
1596 |
+
"special": true
|
1597 |
+
},
|
1598 |
+
"128199": {
|
1599 |
+
"content": "<|reserved_special_token_191|>",
|
1600 |
+
"lstrip": false,
|
1601 |
+
"normalized": false,
|
1602 |
+
"rstrip": false,
|
1603 |
+
"single_word": false,
|
1604 |
+
"special": true
|
1605 |
+
},
|
1606 |
+
"128200": {
|
1607 |
+
"content": "<|reserved_special_token_192|>",
|
1608 |
+
"lstrip": false,
|
1609 |
+
"normalized": false,
|
1610 |
+
"rstrip": false,
|
1611 |
+
"single_word": false,
|
1612 |
+
"special": true
|
1613 |
+
},
|
1614 |
+
"128201": {
|
1615 |
+
"content": "<|reserved_special_token_193|>",
|
1616 |
+
"lstrip": false,
|
1617 |
+
"normalized": false,
|
1618 |
+
"rstrip": false,
|
1619 |
+
"single_word": false,
|
1620 |
+
"special": true
|
1621 |
+
},
|
1622 |
+
"128202": {
|
1623 |
+
"content": "<|reserved_special_token_194|>",
|
1624 |
+
"lstrip": false,
|
1625 |
+
"normalized": false,
|
1626 |
+
"rstrip": false,
|
1627 |
+
"single_word": false,
|
1628 |
+
"special": true
|
1629 |
+
},
|
1630 |
+
"128203": {
|
1631 |
+
"content": "<|reserved_special_token_195|>",
|
1632 |
+
"lstrip": false,
|
1633 |
+
"normalized": false,
|
1634 |
+
"rstrip": false,
|
1635 |
+
"single_word": false,
|
1636 |
+
"special": true
|
1637 |
+
},
|
1638 |
+
"128204": {
|
1639 |
+
"content": "<|reserved_special_token_196|>",
|
1640 |
+
"lstrip": false,
|
1641 |
+
"normalized": false,
|
1642 |
+
"rstrip": false,
|
1643 |
+
"single_word": false,
|
1644 |
+
"special": true
|
1645 |
+
},
|
1646 |
+
"128205": {
|
1647 |
+
"content": "<|reserved_special_token_197|>",
|
1648 |
+
"lstrip": false,
|
1649 |
+
"normalized": false,
|
1650 |
+
"rstrip": false,
|
1651 |
+
"single_word": false,
|
1652 |
+
"special": true
|
1653 |
+
},
|
1654 |
+
"128206": {
|
1655 |
+
"content": "<|reserved_special_token_198|>",
|
1656 |
+
"lstrip": false,
|
1657 |
+
"normalized": false,
|
1658 |
+
"rstrip": false,
|
1659 |
+
"single_word": false,
|
1660 |
+
"special": true
|
1661 |
+
},
|
1662 |
+
"128207": {
|
1663 |
+
"content": "<|reserved_special_token_199|>",
|
1664 |
+
"lstrip": false,
|
1665 |
+
"normalized": false,
|
1666 |
+
"rstrip": false,
|
1667 |
+
"single_word": false,
|
1668 |
+
"special": true
|
1669 |
+
},
|
1670 |
+
"128208": {
|
1671 |
+
"content": "<|reserved_special_token_200|>",
|
1672 |
+
"lstrip": false,
|
1673 |
+
"normalized": false,
|
1674 |
+
"rstrip": false,
|
1675 |
+
"single_word": false,
|
1676 |
+
"special": true
|
1677 |
+
},
|
1678 |
+
"128209": {
|
1679 |
+
"content": "<|reserved_special_token_201|>",
|
1680 |
+
"lstrip": false,
|
1681 |
+
"normalized": false,
|
1682 |
+
"rstrip": false,
|
1683 |
+
"single_word": false,
|
1684 |
+
"special": true
|
1685 |
+
},
|
1686 |
+
"128210": {
|
1687 |
+
"content": "<|reserved_special_token_202|>",
|
1688 |
+
"lstrip": false,
|
1689 |
+
"normalized": false,
|
1690 |
+
"rstrip": false,
|
1691 |
+
"single_word": false,
|
1692 |
+
"special": true
|
1693 |
+
},
|
1694 |
+
"128211": {
|
1695 |
+
"content": "<|reserved_special_token_203|>",
|
1696 |
+
"lstrip": false,
|
1697 |
+
"normalized": false,
|
1698 |
+
"rstrip": false,
|
1699 |
+
"single_word": false,
|
1700 |
+
"special": true
|
1701 |
+
},
|
1702 |
+
"128212": {
|
1703 |
+
"content": "<|reserved_special_token_204|>",
|
1704 |
+
"lstrip": false,
|
1705 |
+
"normalized": false,
|
1706 |
+
"rstrip": false,
|
1707 |
+
"single_word": false,
|
1708 |
+
"special": true
|
1709 |
+
},
|
1710 |
+
"128213": {
|
1711 |
+
"content": "<|reserved_special_token_205|>",
|
1712 |
+
"lstrip": false,
|
1713 |
+
"normalized": false,
|
1714 |
+
"rstrip": false,
|
1715 |
+
"single_word": false,
|
1716 |
+
"special": true
|
1717 |
+
},
|
1718 |
+
"128214": {
|
1719 |
+
"content": "<|reserved_special_token_206|>",
|
1720 |
+
"lstrip": false,
|
1721 |
+
"normalized": false,
|
1722 |
+
"rstrip": false,
|
1723 |
+
"single_word": false,
|
1724 |
+
"special": true
|
1725 |
+
},
|
1726 |
+
"128215": {
|
1727 |
+
"content": "<|reserved_special_token_207|>",
|
1728 |
+
"lstrip": false,
|
1729 |
+
"normalized": false,
|
1730 |
+
"rstrip": false,
|
1731 |
+
"single_word": false,
|
1732 |
+
"special": true
|
1733 |
+
},
|
1734 |
+
"128216": {
|
1735 |
+
"content": "<|reserved_special_token_208|>",
|
1736 |
+
"lstrip": false,
|
1737 |
+
"normalized": false,
|
1738 |
+
"rstrip": false,
|
1739 |
+
"single_word": false,
|
1740 |
+
"special": true
|
1741 |
+
},
|
1742 |
+
"128217": {
|
1743 |
+
"content": "<|reserved_special_token_209|>",
|
1744 |
+
"lstrip": false,
|
1745 |
+
"normalized": false,
|
1746 |
+
"rstrip": false,
|
1747 |
+
"single_word": false,
|
1748 |
+
"special": true
|
1749 |
+
},
|
1750 |
+
"128218": {
|
1751 |
+
"content": "<|reserved_special_token_210|>",
|
1752 |
+
"lstrip": false,
|
1753 |
+
"normalized": false,
|
1754 |
+
"rstrip": false,
|
1755 |
+
"single_word": false,
|
1756 |
+
"special": true
|
1757 |
+
},
|
1758 |
+
"128219": {
|
1759 |
+
"content": "<|reserved_special_token_211|>",
|
1760 |
+
"lstrip": false,
|
1761 |
+
"normalized": false,
|
1762 |
+
"rstrip": false,
|
1763 |
+
"single_word": false,
|
1764 |
+
"special": true
|
1765 |
+
},
|
1766 |
+
"128220": {
|
1767 |
+
"content": "<|reserved_special_token_212|>",
|
1768 |
+
"lstrip": false,
|
1769 |
+
"normalized": false,
|
1770 |
+
"rstrip": false,
|
1771 |
+
"single_word": false,
|
1772 |
+
"special": true
|
1773 |
+
},
|
1774 |
+
"128221": {
|
1775 |
+
"content": "<|reserved_special_token_213|>",
|
1776 |
+
"lstrip": false,
|
1777 |
+
"normalized": false,
|
1778 |
+
"rstrip": false,
|
1779 |
+
"single_word": false,
|
1780 |
+
"special": true
|
1781 |
+
},
|
1782 |
+
"128222": {
|
1783 |
+
"content": "<|reserved_special_token_214|>",
|
1784 |
+
"lstrip": false,
|
1785 |
+
"normalized": false,
|
1786 |
+
"rstrip": false,
|
1787 |
+
"single_word": false,
|
1788 |
+
"special": true
|
1789 |
+
},
|
1790 |
+
"128223": {
|
1791 |
+
"content": "<|reserved_special_token_215|>",
|
1792 |
+
"lstrip": false,
|
1793 |
+
"normalized": false,
|
1794 |
+
"rstrip": false,
|
1795 |
+
"single_word": false,
|
1796 |
+
"special": true
|
1797 |
+
},
|
1798 |
+
"128224": {
|
1799 |
+
"content": "<|reserved_special_token_216|>",
|
1800 |
+
"lstrip": false,
|
1801 |
+
"normalized": false,
|
1802 |
+
"rstrip": false,
|
1803 |
+
"single_word": false,
|
1804 |
+
"special": true
|
1805 |
+
},
|
1806 |
+
"128225": {
|
1807 |
+
"content": "<|reserved_special_token_217|>",
|
1808 |
+
"lstrip": false,
|
1809 |
+
"normalized": false,
|
1810 |
+
"rstrip": false,
|
1811 |
+
"single_word": false,
|
1812 |
+
"special": true
|
1813 |
+
},
|
1814 |
+
"128226": {
|
1815 |
+
"content": "<|reserved_special_token_218|>",
|
1816 |
+
"lstrip": false,
|
1817 |
+
"normalized": false,
|
1818 |
+
"rstrip": false,
|
1819 |
+
"single_word": false,
|
1820 |
+
"special": true
|
1821 |
+
},
|
1822 |
+
"128227": {
|
1823 |
+
"content": "<|reserved_special_token_219|>",
|
1824 |
+
"lstrip": false,
|
1825 |
+
"normalized": false,
|
1826 |
+
"rstrip": false,
|
1827 |
+
"single_word": false,
|
1828 |
+
"special": true
|
1829 |
+
},
|
1830 |
+
"128228": {
|
1831 |
+
"content": "<|reserved_special_token_220|>",
|
1832 |
+
"lstrip": false,
|
1833 |
+
"normalized": false,
|
1834 |
+
"rstrip": false,
|
1835 |
+
"single_word": false,
|
1836 |
+
"special": true
|
1837 |
+
},
|
1838 |
+
"128229": {
|
1839 |
+
"content": "<|reserved_special_token_221|>",
|
1840 |
+
"lstrip": false,
|
1841 |
+
"normalized": false,
|
1842 |
+
"rstrip": false,
|
1843 |
+
"single_word": false,
|
1844 |
+
"special": true
|
1845 |
+
},
|
1846 |
+
"128230": {
|
1847 |
+
"content": "<|reserved_special_token_222|>",
|
1848 |
+
"lstrip": false,
|
1849 |
+
"normalized": false,
|
1850 |
+
"rstrip": false,
|
1851 |
+
"single_word": false,
|
1852 |
+
"special": true
|
1853 |
+
},
|
1854 |
+
"128231": {
|
1855 |
+
"content": "<|reserved_special_token_223|>",
|
1856 |
+
"lstrip": false,
|
1857 |
+
"normalized": false,
|
1858 |
+
"rstrip": false,
|
1859 |
+
"single_word": false,
|
1860 |
+
"special": true
|
1861 |
+
},
|
1862 |
+
"128232": {
|
1863 |
+
"content": "<|reserved_special_token_224|>",
|
1864 |
+
"lstrip": false,
|
1865 |
+
"normalized": false,
|
1866 |
+
"rstrip": false,
|
1867 |
+
"single_word": false,
|
1868 |
+
"special": true
|
1869 |
+
},
|
1870 |
+
"128233": {
|
1871 |
+
"content": "<|reserved_special_token_225|>",
|
1872 |
+
"lstrip": false,
|
1873 |
+
"normalized": false,
|
1874 |
+
"rstrip": false,
|
1875 |
+
"single_word": false,
|
1876 |
+
"special": true
|
1877 |
+
},
|
1878 |
+
"128234": {
|
1879 |
+
"content": "<|reserved_special_token_226|>",
|
1880 |
+
"lstrip": false,
|
1881 |
+
"normalized": false,
|
1882 |
+
"rstrip": false,
|
1883 |
+
"single_word": false,
|
1884 |
+
"special": true
|
1885 |
+
},
|
1886 |
+
"128235": {
|
1887 |
+
"content": "<|reserved_special_token_227|>",
|
1888 |
+
"lstrip": false,
|
1889 |
+
"normalized": false,
|
1890 |
+
"rstrip": false,
|
1891 |
+
"single_word": false,
|
1892 |
+
"special": true
|
1893 |
+
},
|
1894 |
+
"128236": {
|
1895 |
+
"content": "<|reserved_special_token_228|>",
|
1896 |
+
"lstrip": false,
|
1897 |
+
"normalized": false,
|
1898 |
+
"rstrip": false,
|
1899 |
+
"single_word": false,
|
1900 |
+
"special": true
|
1901 |
+
},
|
1902 |
+
"128237": {
|
1903 |
+
"content": "<|reserved_special_token_229|>",
|
1904 |
+
"lstrip": false,
|
1905 |
+
"normalized": false,
|
1906 |
+
"rstrip": false,
|
1907 |
+
"single_word": false,
|
1908 |
+
"special": true
|
1909 |
+
},
|
1910 |
+
"128238": {
|
1911 |
+
"content": "<|reserved_special_token_230|>",
|
1912 |
+
"lstrip": false,
|
1913 |
+
"normalized": false,
|
1914 |
+
"rstrip": false,
|
1915 |
+
"single_word": false,
|
1916 |
+
"special": true
|
1917 |
+
},
|
1918 |
+
"128239": {
|
1919 |
+
"content": "<|reserved_special_token_231|>",
|
1920 |
+
"lstrip": false,
|
1921 |
+
"normalized": false,
|
1922 |
+
"rstrip": false,
|
1923 |
+
"single_word": false,
|
1924 |
+
"special": true
|
1925 |
+
},
|
1926 |
+
"128240": {
|
1927 |
+
"content": "<|reserved_special_token_232|>",
|
1928 |
+
"lstrip": false,
|
1929 |
+
"normalized": false,
|
1930 |
+
"rstrip": false,
|
1931 |
+
"single_word": false,
|
1932 |
+
"special": true
|
1933 |
+
},
|
1934 |
+
"128241": {
|
1935 |
+
"content": "<|reserved_special_token_233|>",
|
1936 |
+
"lstrip": false,
|
1937 |
+
"normalized": false,
|
1938 |
+
"rstrip": false,
|
1939 |
+
"single_word": false,
|
1940 |
+
"special": true
|
1941 |
+
},
|
1942 |
+
"128242": {
|
1943 |
+
"content": "<|reserved_special_token_234|>",
|
1944 |
+
"lstrip": false,
|
1945 |
+
"normalized": false,
|
1946 |
+
"rstrip": false,
|
1947 |
+
"single_word": false,
|
1948 |
+
"special": true
|
1949 |
+
},
|
1950 |
+
"128243": {
|
1951 |
+
"content": "<|reserved_special_token_235|>",
|
1952 |
+
"lstrip": false,
|
1953 |
+
"normalized": false,
|
1954 |
+
"rstrip": false,
|
1955 |
+
"single_word": false,
|
1956 |
+
"special": true
|
1957 |
+
},
|
1958 |
+
"128244": {
|
1959 |
+
"content": "<|reserved_special_token_236|>",
|
1960 |
+
"lstrip": false,
|
1961 |
+
"normalized": false,
|
1962 |
+
"rstrip": false,
|
1963 |
+
"single_word": false,
|
1964 |
+
"special": true
|
1965 |
+
},
|
1966 |
+
"128245": {
|
1967 |
+
"content": "<|reserved_special_token_237|>",
|
1968 |
+
"lstrip": false,
|
1969 |
+
"normalized": false,
|
1970 |
+
"rstrip": false,
|
1971 |
+
"single_word": false,
|
1972 |
+
"special": true
|
1973 |
+
},
|
1974 |
+
"128246": {
|
1975 |
+
"content": "<|reserved_special_token_238|>",
|
1976 |
+
"lstrip": false,
|
1977 |
+
"normalized": false,
|
1978 |
+
"rstrip": false,
|
1979 |
+
"single_word": false,
|
1980 |
+
"special": true
|
1981 |
+
},
|
1982 |
+
"128247": {
|
1983 |
+
"content": "<|reserved_special_token_239|>",
|
1984 |
+
"lstrip": false,
|
1985 |
+
"normalized": false,
|
1986 |
+
"rstrip": false,
|
1987 |
+
"single_word": false,
|
1988 |
+
"special": true
|
1989 |
+
},
|
1990 |
+
"128248": {
|
1991 |
+
"content": "<|reserved_special_token_240|>",
|
1992 |
+
"lstrip": false,
|
1993 |
+
"normalized": false,
|
1994 |
+
"rstrip": false,
|
1995 |
+
"single_word": false,
|
1996 |
+
"special": true
|
1997 |
+
},
|
1998 |
+
"128249": {
|
1999 |
+
"content": "<|reserved_special_token_241|>",
|
2000 |
+
"lstrip": false,
|
2001 |
+
"normalized": false,
|
2002 |
+
"rstrip": false,
|
2003 |
+
"single_word": false,
|
2004 |
+
"special": true
|
2005 |
+
},
|
2006 |
+
"128250": {
|
2007 |
+
"content": "<|reserved_special_token_242|>",
|
2008 |
+
"lstrip": false,
|
2009 |
+
"normalized": false,
|
2010 |
+
"rstrip": false,
|
2011 |
+
"single_word": false,
|
2012 |
+
"special": true
|
2013 |
+
},
|
2014 |
+
"128251": {
|
2015 |
+
"content": "<|reserved_special_token_243|>",
|
2016 |
+
"lstrip": false,
|
2017 |
+
"normalized": false,
|
2018 |
+
"rstrip": false,
|
2019 |
+
"single_word": false,
|
2020 |
+
"special": true
|
2021 |
+
},
|
2022 |
+
"128252": {
|
2023 |
+
"content": "<|reserved_special_token_244|>",
|
2024 |
+
"lstrip": false,
|
2025 |
+
"normalized": false,
|
2026 |
+
"rstrip": false,
|
2027 |
+
"single_word": false,
|
2028 |
+
"special": true
|
2029 |
+
},
|
2030 |
+
"128253": {
|
2031 |
+
"content": "<|reserved_special_token_245|>",
|
2032 |
+
"lstrip": false,
|
2033 |
+
"normalized": false,
|
2034 |
+
"rstrip": false,
|
2035 |
+
"single_word": false,
|
2036 |
+
"special": true
|
2037 |
+
},
|
2038 |
+
"128254": {
|
2039 |
+
"content": "<|reserved_special_token_246|>",
|
2040 |
+
"lstrip": false,
|
2041 |
+
"normalized": false,
|
2042 |
+
"rstrip": false,
|
2043 |
+
"single_word": false,
|
2044 |
+
"special": true
|
2045 |
+
},
|
2046 |
+
"128255": {
|
2047 |
+
"content": "<|reserved_special_token_247|>",
|
2048 |
+
"lstrip": false,
|
2049 |
+
"normalized": false,
|
2050 |
+
"rstrip": false,
|
2051 |
+
"single_word": false,
|
2052 |
+
"special": true
|
2053 |
+
},
|
2054 |
+
"128256": {
|
2055 |
+
"content": "<|end_of_text|>",
|
2056 |
+
"lstrip": false,
|
2057 |
+
"normalized": false,
|
2058 |
+
"rstrip": false,
|
2059 |
+
"single_word": false,
|
2060 |
+
"special": true
|
2061 |
+
}
|
2062 |
+
},
|
2063 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
2064 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2065 |
+
"clean_up_tokenization_spaces": false,
|
2066 |
+
"eos_token": "<|end▁of▁sentence|>",
|
2067 |
+
"extra_special_tokens": {},
|
2068 |
+
"legacy": true,
|
2069 |
+
"model_max_length": 16384,
|
2070 |
+
"pad_token": "<|end_of_text|>",
|
2071 |
+
"sp_model_kwargs": {},
|
2072 |
+
"tokenizer_class": "LlamaTokenizer",
|
2073 |
+
"unk_token": null,
|
2074 |
+
"use_default_system_prompt": false
|
2075 |
+
}
|
checkpoint-run1-124/trainer_state.json
ADDED
@@ -0,0 +1,1893 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 124,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.016260162601626018,
|
13 |
+
"grad_norm": 18.177886962890625,
|
14 |
+
"learning_rate": 2e-05,
|
15 |
+
"logits/chosen": -0.3472236394882202,
|
16 |
+
"logits/rejected": -0.13716036081314087,
|
17 |
+
"logps/chosen": -780.8181762695312,
|
18 |
+
"logps/rejected": -909.20263671875,
|
19 |
+
"loss": 0.6931,
|
20 |
+
"rewards/accuracies": 0.0,
|
21 |
+
"rewards/chosen": 0.0,
|
22 |
+
"rewards/margins": 0.0,
|
23 |
+
"rewards/rejected": 0.0,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.032520325203252036,
|
28 |
+
"grad_norm": 23.274246215820312,
|
29 |
+
"learning_rate": 4e-05,
|
30 |
+
"logits/chosen": -0.2127760350704193,
|
31 |
+
"logits/rejected": -0.08323362469673157,
|
32 |
+
"logps/chosen": -583.0169067382812,
|
33 |
+
"logps/rejected": -715.5615234375,
|
34 |
+
"loss": 0.6931,
|
35 |
+
"rewards/accuracies": 0.0,
|
36 |
+
"rewards/chosen": 0.0,
|
37 |
+
"rewards/margins": 0.0,
|
38 |
+
"rewards/rejected": 0.0,
|
39 |
+
"step": 2
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.04878048780487805,
|
43 |
+
"grad_norm": 20.149507522583008,
|
44 |
+
"learning_rate": 6e-05,
|
45 |
+
"logits/chosen": -0.18167662620544434,
|
46 |
+
"logits/rejected": -0.04478086531162262,
|
47 |
+
"logps/chosen": -941.0387573242188,
|
48 |
+
"logps/rejected": -825.662841796875,
|
49 |
+
"loss": 0.6976,
|
50 |
+
"rewards/accuracies": 0.5,
|
51 |
+
"rewards/chosen": 0.025517277419567108,
|
52 |
+
"rewards/margins": 0.022285467013716698,
|
53 |
+
"rewards/rejected": 0.0032318076118826866,
|
54 |
+
"step": 3
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.06504065040650407,
|
58 |
+
"grad_norm": 16.67251205444336,
|
59 |
+
"learning_rate": 8e-05,
|
60 |
+
"logits/chosen": 0.6866837739944458,
|
61 |
+
"logits/rejected": 0.971089243888855,
|
62 |
+
"logps/chosen": -999.306640625,
|
63 |
+
"logps/rejected": -386.5375671386719,
|
64 |
+
"loss": 0.563,
|
65 |
+
"rewards/accuracies": 1.0,
|
66 |
+
"rewards/chosen": 0.2688583433628082,
|
67 |
+
"rewards/margins": 0.3312031030654907,
|
68 |
+
"rewards/rejected": -0.062344741076231,
|
69 |
+
"step": 4
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.08130081300813008,
|
73 |
+
"grad_norm": 15.646084785461426,
|
74 |
+
"learning_rate": 0.0001,
|
75 |
+
"logits/chosen": 0.5107800364494324,
|
76 |
+
"logits/rejected": 0.5942208766937256,
|
77 |
+
"logps/chosen": -1051.1270751953125,
|
78 |
+
"logps/rejected": -745.8003540039062,
|
79 |
+
"loss": 0.647,
|
80 |
+
"rewards/accuracies": 0.5,
|
81 |
+
"rewards/chosen": 0.3622299134731293,
|
82 |
+
"rewards/margins": 0.34313660860061646,
|
83 |
+
"rewards/rejected": 0.01909332349896431,
|
84 |
+
"step": 5
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.0975609756097561,
|
88 |
+
"grad_norm": 38.70280456542969,
|
89 |
+
"learning_rate": 0.00012,
|
90 |
+
"logits/chosen": -0.31406939029693604,
|
91 |
+
"logits/rejected": -0.24293695390224457,
|
92 |
+
"logps/chosen": -845.9321899414062,
|
93 |
+
"logps/rejected": -932.499755859375,
|
94 |
+
"loss": 0.5175,
|
95 |
+
"rewards/accuracies": 0.75,
|
96 |
+
"rewards/chosen": 0.5435073971748352,
|
97 |
+
"rewards/margins": 0.47774890065193176,
|
98 |
+
"rewards/rejected": 0.06575851887464523,
|
99 |
+
"step": 6
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.11382113821138211,
|
103 |
+
"grad_norm": 23.665071487426758,
|
104 |
+
"learning_rate": 0.00014,
|
105 |
+
"logits/chosen": -0.2646118402481079,
|
106 |
+
"logits/rejected": -0.11520399153232574,
|
107 |
+
"logps/chosen": -866.503173828125,
|
108 |
+
"logps/rejected": -975.55126953125,
|
109 |
+
"loss": 0.5487,
|
110 |
+
"rewards/accuracies": 0.5,
|
111 |
+
"rewards/chosen": 0.6112838387489319,
|
112 |
+
"rewards/margins": 0.4790405333042145,
|
113 |
+
"rewards/rejected": 0.1322433352470398,
|
114 |
+
"step": 7
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.13008130081300814,
|
118 |
+
"grad_norm": 15.794047355651855,
|
119 |
+
"learning_rate": 0.00016,
|
120 |
+
"logits/chosen": -0.8256000876426697,
|
121 |
+
"logits/rejected": -0.8912097811698914,
|
122 |
+
"logps/chosen": -523.3858032226562,
|
123 |
+
"logps/rejected": -1084.9468994140625,
|
124 |
+
"loss": 0.4442,
|
125 |
+
"rewards/accuracies": 0.5,
|
126 |
+
"rewards/chosen": 0.5804435610771179,
|
127 |
+
"rewards/margins": 0.24081651866436005,
|
128 |
+
"rewards/rejected": 0.33962705731391907,
|
129 |
+
"step": 8
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.14634146341463414,
|
133 |
+
"grad_norm": 13.538564682006836,
|
134 |
+
"learning_rate": 0.00018,
|
135 |
+
"logits/chosen": -0.11683523654937744,
|
136 |
+
"logits/rejected": -0.0632472038269043,
|
137 |
+
"logps/chosen": -652.114501953125,
|
138 |
+
"logps/rejected": -551.6069946289062,
|
139 |
+
"loss": 0.1564,
|
140 |
+
"rewards/accuracies": 1.0,
|
141 |
+
"rewards/chosen": 1.6716469526290894,
|
142 |
+
"rewards/margins": 2.151698350906372,
|
143 |
+
"rewards/rejected": -0.4800514578819275,
|
144 |
+
"step": 9
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.16260162601626016,
|
148 |
+
"grad_norm": 3.9652626514434814,
|
149 |
+
"learning_rate": 0.0002,
|
150 |
+
"logits/chosen": 0.4062778949737549,
|
151 |
+
"logits/rejected": 0.5438919067382812,
|
152 |
+
"logps/chosen": -771.1934814453125,
|
153 |
+
"logps/rejected": -616.55908203125,
|
154 |
+
"loss": 0.0792,
|
155 |
+
"rewards/accuracies": 1.0,
|
156 |
+
"rewards/chosen": 3.8721909523010254,
|
157 |
+
"rewards/margins": 5.208758354187012,
|
158 |
+
"rewards/rejected": -1.3365669250488281,
|
159 |
+
"step": 10
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.17886178861788618,
|
163 |
+
"grad_norm": 0.18261243402957916,
|
164 |
+
"learning_rate": 0.0001999911398855782,
|
165 |
+
"logits/chosen": -0.7774271965026855,
|
166 |
+
"logits/rejected": -0.8629493117332458,
|
167 |
+
"logps/chosen": -601.1015014648438,
|
168 |
+
"logps/rejected": -1039.275146484375,
|
169 |
+
"loss": 0.0019,
|
170 |
+
"rewards/accuracies": 1.0,
|
171 |
+
"rewards/chosen": 1.0800025463104248,
|
172 |
+
"rewards/margins": 6.853862762451172,
|
173 |
+
"rewards/rejected": -5.773860454559326,
|
174 |
+
"step": 11
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.1951219512195122,
|
178 |
+
"grad_norm": 0.1421748697757721,
|
179 |
+
"learning_rate": 0.00019996456111234527,
|
180 |
+
"logits/chosen": 0.7899215817451477,
|
181 |
+
"logits/rejected": 1.119359016418457,
|
182 |
+
"logps/chosen": -1416.412353515625,
|
183 |
+
"logps/rejected": -827.2066650390625,
|
184 |
+
"loss": 0.0008,
|
185 |
+
"rewards/accuracies": 1.0,
|
186 |
+
"rewards/chosen": 3.7505874633789062,
|
187 |
+
"rewards/margins": 15.09115982055664,
|
188 |
+
"rewards/rejected": -11.340574264526367,
|
189 |
+
"step": 12
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.21138211382113822,
|
193 |
+
"grad_norm": 3.4406840801239014,
|
194 |
+
"learning_rate": 0.00019992026839012067,
|
195 |
+
"logits/chosen": -0.8033453226089478,
|
196 |
+
"logits/rejected": -0.877557098865509,
|
197 |
+
"logps/chosen": -514.6026611328125,
|
198 |
+
"logps/rejected": -1206.25537109375,
|
199 |
+
"loss": 0.0102,
|
200 |
+
"rewards/accuracies": 1.0,
|
201 |
+
"rewards/chosen": 1.7983558177947998,
|
202 |
+
"rewards/margins": 23.49526596069336,
|
203 |
+
"rewards/rejected": -21.696908950805664,
|
204 |
+
"step": 13
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.22764227642276422,
|
208 |
+
"grad_norm": 0.19398577511310577,
|
209 |
+
"learning_rate": 0.0001998582695676762,
|
210 |
+
"logits/chosen": 0.9254277944564819,
|
211 |
+
"logits/rejected": 1.1634798049926758,
|
212 |
+
"logps/chosen": -1028.993408203125,
|
213 |
+
"logps/rejected": -955.4432983398438,
|
214 |
+
"loss": 0.001,
|
215 |
+
"rewards/accuracies": 1.0,
|
216 |
+
"rewards/chosen": -0.5009795427322388,
|
217 |
+
"rewards/margins": 17.867931365966797,
|
218 |
+
"rewards/rejected": -18.368911743164062,
|
219 |
+
"step": 14
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.24390243902439024,
|
223 |
+
"grad_norm": 0.00010074722376884893,
|
224 |
+
"learning_rate": 0.000199778575631345,
|
225 |
+
"logits/chosen": 0.3904605507850647,
|
226 |
+
"logits/rejected": 0.3719422519207001,
|
227 |
+
"logps/chosen": -884.9620361328125,
|
228 |
+
"logps/rejected": -1075.615966796875,
|
229 |
+
"loss": 0.0,
|
230 |
+
"rewards/accuracies": 1.0,
|
231 |
+
"rewards/chosen": -2.482113838195801,
|
232 |
+
"rewards/margins": 21.95424461364746,
|
233 |
+
"rewards/rejected": -24.436357498168945,
|
234 |
+
"step": 15
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.2601626016260163,
|
238 |
+
"grad_norm": 3.7136353057576343e-05,
|
239 |
+
"learning_rate": 0.000199681200703075,
|
240 |
+
"logits/chosen": 0.2578551769256592,
|
241 |
+
"logits/rejected": 0.5335351824760437,
|
242 |
+
"logps/chosen": -1073.548828125,
|
243 |
+
"logps/rejected": -992.4033813476562,
|
244 |
+
"loss": 0.0,
|
245 |
+
"rewards/accuracies": 1.0,
|
246 |
+
"rewards/chosen": -2.9434356689453125,
|
247 |
+
"rewards/margins": 20.854663848876953,
|
248 |
+
"rewards/rejected": -23.798099517822266,
|
249 |
+
"step": 16
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.2764227642276423,
|
253 |
+
"grad_norm": 8.596338147981442e-07,
|
254 |
+
"learning_rate": 0.00019956616203792635,
|
255 |
+
"logits/chosen": 0.5267460346221924,
|
256 |
+
"logits/rejected": 0.4893237352371216,
|
257 |
+
"logps/chosen": -987.3567504882812,
|
258 |
+
"logps/rejected": -1127.171875,
|
259 |
+
"loss": 0.0,
|
260 |
+
"rewards/accuracies": 1.0,
|
261 |
+
"rewards/chosen": -1.0684036016464233,
|
262 |
+
"rewards/margins": 32.558319091796875,
|
263 |
+
"rewards/rejected": -33.62671661376953,
|
264 |
+
"step": 17
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.2926829268292683,
|
268 |
+
"grad_norm": 0.004051027819514275,
|
269 |
+
"learning_rate": 0.00019943348002101371,
|
270 |
+
"logits/chosen": 1.0484071969985962,
|
271 |
+
"logits/rejected": 1.1081664562225342,
|
272 |
+
"logps/chosen": -1105.1634521484375,
|
273 |
+
"logps/rejected": -898.9759521484375,
|
274 |
+
"loss": 0.0,
|
275 |
+
"rewards/accuracies": 1.0,
|
276 |
+
"rewards/chosen": -3.1622314453125,
|
277 |
+
"rewards/margins": 23.434669494628906,
|
278 |
+
"rewards/rejected": -26.596900939941406,
|
279 |
+
"step": 18
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.3089430894308943,
|
283 |
+
"grad_norm": 0.003306547412648797,
|
284 |
+
"learning_rate": 0.00019928317816389417,
|
285 |
+
"logits/chosen": 0.5566614866256714,
|
286 |
+
"logits/rejected": 0.6963181495666504,
|
287 |
+
"logps/chosen": -932.650390625,
|
288 |
+
"logps/rejected": -1061.4989013671875,
|
289 |
+
"loss": 0.0,
|
290 |
+
"rewards/accuracies": 1.0,
|
291 |
+
"rewards/chosen": -4.36033821105957,
|
292 |
+
"rewards/margins": 30.25779914855957,
|
293 |
+
"rewards/rejected": -34.61813735961914,
|
294 |
+
"step": 19
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.3252032520325203,
|
298 |
+
"grad_norm": 1.3893560968369911e-08,
|
299 |
+
"learning_rate": 0.00019911528310040074,
|
300 |
+
"logits/chosen": 1.239579200744629,
|
301 |
+
"logits/rejected": 1.046311855316162,
|
302 |
+
"logps/chosen": -1079.0159912109375,
|
303 |
+
"logps/rejected": -1033.2017822265625,
|
304 |
+
"loss": 0.0,
|
305 |
+
"rewards/accuracies": 1.0,
|
306 |
+
"rewards/chosen": 1.044548749923706,
|
307 |
+
"rewards/margins": 41.88936233520508,
|
308 |
+
"rewards/rejected": -40.844810485839844,
|
309 |
+
"step": 20
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.34146341463414637,
|
313 |
+
"grad_norm": 4.666223851756968e-09,
|
314 |
+
"learning_rate": 0.00019892982458192288,
|
315 |
+
"logits/chosen": 0.2726232409477234,
|
316 |
+
"logits/rejected": 0.14665402472019196,
|
317 |
+
"logps/chosen": -978.7222900390625,
|
318 |
+
"logps/rejected": -1133.2047119140625,
|
319 |
+
"loss": 0.0,
|
320 |
+
"rewards/accuracies": 1.0,
|
321 |
+
"rewards/chosen": 11.054238319396973,
|
322 |
+
"rewards/margins": 54.86410140991211,
|
323 |
+
"rewards/rejected": -43.80986404418945,
|
324 |
+
"step": 21
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.35772357723577236,
|
328 |
+
"grad_norm": 4.876813477494579e-07,
|
329 |
+
"learning_rate": 0.00019872683547213446,
|
330 |
+
"logits/chosen": -0.16925190389156342,
|
331 |
+
"logits/rejected": -0.19759103655815125,
|
332 |
+
"logps/chosen": -965.187255859375,
|
333 |
+
"logps/rejected": -1239.143798828125,
|
334 |
+
"loss": 0.0,
|
335 |
+
"rewards/accuracies": 1.0,
|
336 |
+
"rewards/chosen": -14.977485656738281,
|
337 |
+
"rewards/margins": 29.40732765197754,
|
338 |
+
"rewards/rejected": -44.38481140136719,
|
339 |
+
"step": 22
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.37398373983739835,
|
343 |
+
"grad_norm": 37.638973236083984,
|
344 |
+
"learning_rate": 0.00019850635174117033,
|
345 |
+
"logits/chosen": 0.437714159488678,
|
346 |
+
"logits/rejected": 0.4761970639228821,
|
347 |
+
"logps/chosen": -1137.6966552734375,
|
348 |
+
"logps/rejected": -1166.5640869140625,
|
349 |
+
"loss": 0.4393,
|
350 |
+
"rewards/accuracies": 1.0,
|
351 |
+
"rewards/chosen": -11.159793853759766,
|
352 |
+
"rewards/margins": 32.14189529418945,
|
353 |
+
"rewards/rejected": -43.301692962646484,
|
354 |
+
"step": 23
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.3902439024390244,
|
358 |
+
"grad_norm": 1.8173747229344173e-11,
|
359 |
+
"learning_rate": 0.00019826841245925212,
|
360 |
+
"logits/chosen": -0.7153763175010681,
|
361 |
+
"logits/rejected": -0.6940470933914185,
|
362 |
+
"logps/chosen": -938.263916015625,
|
363 |
+
"logps/rejected": -1608.4205322265625,
|
364 |
+
"loss": 0.0,
|
365 |
+
"rewards/accuracies": 1.0,
|
366 |
+
"rewards/chosen": -24.817350387573242,
|
367 |
+
"rewards/margins": 34.095001220703125,
|
368 |
+
"rewards/rejected": -58.912349700927734,
|
369 |
+
"step": 24
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.4065040650406504,
|
373 |
+
"grad_norm": 83.79772186279297,
|
374 |
+
"learning_rate": 0.0001980130597897651,
|
375 |
+
"logits/chosen": 1.1592888832092285,
|
376 |
+
"logits/rejected": 1.1738824844360352,
|
377 |
+
"logps/chosen": -948.4622802734375,
|
378 |
+
"logps/rejected": -865.396728515625,
|
379 |
+
"loss": 0.3825,
|
380 |
+
"rewards/accuracies": 1.0,
|
381 |
+
"rewards/chosen": -3.343675374984741,
|
382 |
+
"rewards/margins": 26.49417495727539,
|
383 |
+
"rewards/rejected": -29.837852478027344,
|
384 |
+
"step": 25
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.42276422764227645,
|
388 |
+
"grad_norm": 2.6143006834900007e-06,
|
389 |
+
"learning_rate": 0.00019774033898178667,
|
390 |
+
"logits/chosen": 0.5444796085357666,
|
391 |
+
"logits/rejected": 0.47586876153945923,
|
392 |
+
"logps/chosen": -932.6605834960938,
|
393 |
+
"logps/rejected": -1091.639892578125,
|
394 |
+
"loss": 0.0,
|
395 |
+
"rewards/accuracies": 1.0,
|
396 |
+
"rewards/chosen": -4.2753777503967285,
|
397 |
+
"rewards/margins": 34.133514404296875,
|
398 |
+
"rewards/rejected": -38.40888977050781,
|
399 |
+
"step": 26
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.43902439024390244,
|
403 |
+
"grad_norm": 0.0003061926399823278,
|
404 |
+
"learning_rate": 0.00019745029836206813,
|
405 |
+
"logits/chosen": -0.6794779896736145,
|
406 |
+
"logits/rejected": -0.8602011203765869,
|
407 |
+
"logps/chosen": -894.3270263671875,
|
408 |
+
"logps/rejected": -1067.5921630859375,
|
409 |
+
"loss": 0.0,
|
410 |
+
"rewards/accuracies": 1.0,
|
411 |
+
"rewards/chosen": -13.433198928833008,
|
412 |
+
"rewards/margins": 17.333955764770508,
|
413 |
+
"rewards/rejected": -30.767154693603516,
|
414 |
+
"step": 27
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.45528455284552843,
|
418 |
+
"grad_norm": 3.805017101399244e-08,
|
419 |
+
"learning_rate": 0.00019714298932647098,
|
420 |
+
"logits/chosen": 0.4980026185512543,
|
421 |
+
"logits/rejected": 0.6999194025993347,
|
422 |
+
"logps/chosen": -911.8473510742188,
|
423 |
+
"logps/rejected": -1126.07421875,
|
424 |
+
"loss": 0.0,
|
425 |
+
"rewards/accuracies": 1.0,
|
426 |
+
"rewards/chosen": -0.5412168502807617,
|
427 |
+
"rewards/margins": 29.520708084106445,
|
428 |
+
"rewards/rejected": -30.06192398071289,
|
429 |
+
"step": 28
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.4715447154471545,
|
433 |
+
"grad_norm": 5.17633900187775e-08,
|
434 |
+
"learning_rate": 0.00019681846633085967,
|
435 |
+
"logits/chosen": -0.5973828434944153,
|
436 |
+
"logits/rejected": -0.8376109600067139,
|
437 |
+
"logps/chosen": -711.66259765625,
|
438 |
+
"logps/rejected": -1186.1884765625,
|
439 |
+
"loss": 0.0,
|
440 |
+
"rewards/accuracies": 1.0,
|
441 |
+
"rewards/chosen": -2.467390537261963,
|
442 |
+
"rewards/margins": 25.050704956054688,
|
443 |
+
"rewards/rejected": -27.518096923828125,
|
444 |
+
"step": 29
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.4878048780487805,
|
448 |
+
"grad_norm": 0.00011633769463514909,
|
449 |
+
"learning_rate": 0.0001964767868814516,
|
450 |
+
"logits/chosen": 1.3797093629837036,
|
451 |
+
"logits/rejected": 1.5397391319274902,
|
452 |
+
"logps/chosen": -877.42333984375,
|
453 |
+
"logps/rejected": -1003.4732666015625,
|
454 |
+
"loss": 0.0,
|
455 |
+
"rewards/accuracies": 1.0,
|
456 |
+
"rewards/chosen": 4.624107360839844,
|
457 |
+
"rewards/margins": 29.784557342529297,
|
458 |
+
"rewards/rejected": -25.160449981689453,
|
459 |
+
"step": 30
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.5040650406504065,
|
463 |
+
"grad_norm": 6.257723228486611e-09,
|
464 |
+
"learning_rate": 0.00019611801152462715,
|
465 |
+
"logits/chosen": 1.2731826305389404,
|
466 |
+
"logits/rejected": 1.6379995346069336,
|
467 |
+
"logps/chosen": -1053.573486328125,
|
468 |
+
"logps/rejected": -1010.915283203125,
|
469 |
+
"loss": 0.0,
|
470 |
+
"rewards/accuracies": 1.0,
|
471 |
+
"rewards/chosen": 11.018058776855469,
|
472 |
+
"rewards/margins": 32.15219497680664,
|
473 |
+
"rewards/rejected": -21.13413429260254,
|
474 |
+
"step": 31
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.5203252032520326,
|
478 |
+
"grad_norm": 0.00035472630406729877,
|
479 |
+
"learning_rate": 0.00019574220383620055,
|
480 |
+
"logits/chosen": 0.6649560928344727,
|
481 |
+
"logits/rejected": 0.983564019203186,
|
482 |
+
"logps/chosen": -872.1873168945312,
|
483 |
+
"logps/rejected": -965.9480590820312,
|
484 |
+
"loss": 0.0,
|
485 |
+
"rewards/accuracies": 1.0,
|
486 |
+
"rewards/chosen": 5.504961967468262,
|
487 |
+
"rewards/margins": 23.669071197509766,
|
488 |
+
"rewards/rejected": -18.164108276367188,
|
489 |
+
"step": 32
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.5365853658536586,
|
493 |
+
"grad_norm": 3.0934195820009336e-05,
|
494 |
+
"learning_rate": 0.00019534943041015423,
|
495 |
+
"logits/chosen": 0.49574941396713257,
|
496 |
+
"logits/rejected": 0.5190873742103577,
|
497 |
+
"logps/chosen": -708.9269409179688,
|
498 |
+
"logps/rejected": -842.974365234375,
|
499 |
+
"loss": 0.0,
|
500 |
+
"rewards/accuracies": 1.0,
|
501 |
+
"rewards/chosen": 7.209194660186768,
|
502 |
+
"rewards/margins": 20.690357208251953,
|
503 |
+
"rewards/rejected": -13.48116397857666,
|
504 |
+
"step": 33
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.5528455284552846,
|
508 |
+
"grad_norm": 0.0006856573163531721,
|
509 |
+
"learning_rate": 0.00019493976084683813,
|
510 |
+
"logits/chosen": 0.992796778678894,
|
511 |
+
"logits/rejected": 1.1291236877441406,
|
512 |
+
"logps/chosen": -673.6188354492188,
|
513 |
+
"logps/rejected": -723.4482421875,
|
514 |
+
"loss": 0.0,
|
515 |
+
"rewards/accuracies": 1.0,
|
516 |
+
"rewards/chosen": 5.3715057373046875,
|
517 |
+
"rewards/margins": 19.963485717773438,
|
518 |
+
"rewards/rejected": -14.591980934143066,
|
519 |
+
"step": 34
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.5691056910569106,
|
523 |
+
"grad_norm": 5.983891969663091e-05,
|
524 |
+
"learning_rate": 0.00019451326774063636,
|
525 |
+
"logits/chosen": 0.7630600929260254,
|
526 |
+
"logits/rejected": 0.910960853099823,
|
527 |
+
"logps/chosen": -993.23828125,
|
528 |
+
"logps/rejected": -1011.3184204101562,
|
529 |
+
"loss": 0.0,
|
530 |
+
"rewards/accuracies": 1.0,
|
531 |
+
"rewards/chosen": 7.109509468078613,
|
532 |
+
"rewards/margins": 24.603878021240234,
|
533 |
+
"rewards/rejected": -17.494367599487305,
|
534 |
+
"step": 35
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.5853658536585366,
|
538 |
+
"grad_norm": 1.9749455532291904e-05,
|
539 |
+
"learning_rate": 0.00019407002666710336,
|
540 |
+
"logits/chosen": 1.8401339054107666,
|
541 |
+
"logits/rejected": 1.9955703020095825,
|
542 |
+
"logps/chosen": -1152.950927734375,
|
543 |
+
"logps/rejected": -827.0269775390625,
|
544 |
+
"loss": 0.0,
|
545 |
+
"rewards/accuracies": 1.0,
|
546 |
+
"rewards/chosen": 15.768245697021484,
|
547 |
+
"rewards/margins": 38.1776123046875,
|
548 |
+
"rewards/rejected": -22.40936851501465,
|
549 |
+
"step": 36
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.6016260162601627,
|
553 |
+
"grad_norm": 0.0017285533249378204,
|
554 |
+
"learning_rate": 0.00019361011616957164,
|
555 |
+
"logits/chosen": 2.153351306915283,
|
556 |
+
"logits/rejected": 2.235447883605957,
|
557 |
+
"logps/chosen": -1090.1943359375,
|
558 |
+
"logps/rejected": -682.7992553710938,
|
559 |
+
"loss": 0.0,
|
560 |
+
"rewards/accuracies": 1.0,
|
561 |
+
"rewards/chosen": 11.726329803466797,
|
562 |
+
"rewards/margins": 24.018630981445312,
|
563 |
+
"rewards/rejected": -12.292303085327148,
|
564 |
+
"step": 37
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.6178861788617886,
|
568 |
+
"grad_norm": 0.00919501855969429,
|
569 |
+
"learning_rate": 0.00019313361774523385,
|
570 |
+
"logits/chosen": 0.47314736247062683,
|
571 |
+
"logits/rejected": 0.557833731174469,
|
572 |
+
"logps/chosen": -691.4217529296875,
|
573 |
+
"logps/rejected": -673.1847534179688,
|
574 |
+
"loss": 0.0,
|
575 |
+
"rewards/accuracies": 1.0,
|
576 |
+
"rewards/chosen": 6.087795257568359,
|
577 |
+
"rewards/margins": 12.628225326538086,
|
578 |
+
"rewards/rejected": -6.540430068969727,
|
579 |
+
"step": 38
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.6341463414634146,
|
583 |
+
"grad_norm": 0.002680833451449871,
|
584 |
+
"learning_rate": 0.00019264061583070127,
|
585 |
+
"logits/chosen": 0.20066705346107483,
|
586 |
+
"logits/rejected": 0.2085224837064743,
|
587 |
+
"logps/chosen": -693.7376098632812,
|
588 |
+
"logps/rejected": -982.19091796875,
|
589 |
+
"loss": 0.0,
|
590 |
+
"rewards/accuracies": 1.0,
|
591 |
+
"rewards/chosen": 7.779763221740723,
|
592 |
+
"rewards/margins": 22.904094696044922,
|
593 |
+
"rewards/rejected": -15.124334335327148,
|
594 |
+
"step": 39
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.6504065040650406,
|
598 |
+
"grad_norm": 8.798202907200903e-05,
|
599 |
+
"learning_rate": 0.00019213119778704128,
|
600 |
+
"logits/chosen": 1.3898746967315674,
|
601 |
+
"logits/rejected": 1.5520107746124268,
|
602 |
+
"logps/chosen": -1247.770263671875,
|
603 |
+
"logps/rejected": -916.4830322265625,
|
604 |
+
"loss": 0.0,
|
605 |
+
"rewards/accuracies": 1.0,
|
606 |
+
"rewards/chosen": 15.276836395263672,
|
607 |
+
"rewards/margins": 34.69191360473633,
|
608 |
+
"rewards/rejected": -19.415077209472656,
|
609 |
+
"step": 40
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.6666666666666666,
|
613 |
+
"grad_norm": 0.0009758697124198079,
|
614 |
+
"learning_rate": 0.00019160545388429708,
|
615 |
+
"logits/chosen": 2.345059633255005,
|
616 |
+
"logits/rejected": 2.5746054649353027,
|
617 |
+
"logps/chosen": -1102.5548095703125,
|
618 |
+
"logps/rejected": -722.4332885742188,
|
619 |
+
"loss": 0.0,
|
620 |
+
"rewards/accuracies": 1.0,
|
621 |
+
"rewards/chosen": 13.800348281860352,
|
622 |
+
"rewards/margins": 32.747169494628906,
|
623 |
+
"rewards/rejected": -18.946823120117188,
|
624 |
+
"step": 41
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.6829268292682927,
|
628 |
+
"grad_norm": 0.0016077810432761908,
|
629 |
+
"learning_rate": 0.00019106347728549135,
|
630 |
+
"logits/chosen": 0.9104095697402954,
|
631 |
+
"logits/rejected": 0.9921329021453857,
|
632 |
+
"logps/chosen": -753.8040771484375,
|
633 |
+
"logps/rejected": -886.5813598632812,
|
634 |
+
"loss": 0.0,
|
635 |
+
"rewards/accuracies": 1.0,
|
636 |
+
"rewards/chosen": 11.367500305175781,
|
637 |
+
"rewards/margins": 27.856563568115234,
|
638 |
+
"rewards/rejected": -16.489063262939453,
|
639 |
+
"step": 42
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.6991869918699187,
|
643 |
+
"grad_norm": 0.0004074655589647591,
|
644 |
+
"learning_rate": 0.0001905053640301176,
|
645 |
+
"logits/chosen": 0.5256392955780029,
|
646 |
+
"logits/rejected": 0.4733426570892334,
|
647 |
+
"logps/chosen": -715.4669189453125,
|
648 |
+
"logps/rejected": -565.0441284179688,
|
649 |
+
"loss": 0.0,
|
650 |
+
"rewards/accuracies": 1.0,
|
651 |
+
"rewards/chosen": 6.25009822845459,
|
652 |
+
"rewards/margins": 21.391075134277344,
|
653 |
+
"rewards/rejected": -15.14097785949707,
|
654 |
+
"step": 43
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.7154471544715447,
|
658 |
+
"grad_norm": 0.013145952485501766,
|
659 |
+
"learning_rate": 0.00018993121301712193,
|
660 |
+
"logits/chosen": 0.9358551502227783,
|
661 |
+
"logits/rejected": 0.8306156992912292,
|
662 |
+
"logps/chosen": -867.1063232421875,
|
663 |
+
"logps/rejected": -973.7214965820312,
|
664 |
+
"loss": 0.0,
|
665 |
+
"rewards/accuracies": 1.0,
|
666 |
+
"rewards/chosen": 7.3925018310546875,
|
667 |
+
"rewards/margins": 21.35105323791504,
|
668 |
+
"rewards/rejected": -13.958552360534668,
|
669 |
+
"step": 44
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.7317073170731707,
|
673 |
+
"grad_norm": 8.829876605886966e-05,
|
674 |
+
"learning_rate": 0.00018934112598737777,
|
675 |
+
"logits/chosen": 2.2844998836517334,
|
676 |
+
"logits/rejected": 2.831254482269287,
|
677 |
+
"logps/chosen": -1142.8726806640625,
|
678 |
+
"logps/rejected": -776.1110229492188,
|
679 |
+
"loss": 0.0,
|
680 |
+
"rewards/accuracies": 1.0,
|
681 |
+
"rewards/chosen": 17.17538833618164,
|
682 |
+
"rewards/margins": 33.72625732421875,
|
683 |
+
"rewards/rejected": -16.550867080688477,
|
684 |
+
"step": 45
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.7479674796747967,
|
688 |
+
"grad_norm": 0.02624354511499405,
|
689 |
+
"learning_rate": 0.00018873520750565718,
|
690 |
+
"logits/chosen": 0.1806122362613678,
|
691 |
+
"logits/rejected": 0.31054702401161194,
|
692 |
+
"logps/chosen": -692.7060546875,
|
693 |
+
"logps/rejected": -1032.708740234375,
|
694 |
+
"loss": 0.0001,
|
695 |
+
"rewards/accuracies": 1.0,
|
696 |
+
"rewards/chosen": 6.434965133666992,
|
697 |
+
"rewards/margins": 16.74932098388672,
|
698 |
+
"rewards/rejected": -10.314356803894043,
|
699 |
+
"step": 46
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.7642276422764228,
|
703 |
+
"grad_norm": 4.268178963684477e-05,
|
704 |
+
"learning_rate": 0.00018811356494210165,
|
705 |
+
"logits/chosen": 1.1679103374481201,
|
706 |
+
"logits/rejected": 1.0418663024902344,
|
707 |
+
"logps/chosen": -720.220703125,
|
708 |
+
"logps/rejected": -911.58837890625,
|
709 |
+
"loss": 0.0,
|
710 |
+
"rewards/accuracies": 1.0,
|
711 |
+
"rewards/chosen": 7.991888523101807,
|
712 |
+
"rewards/margins": 21.064565658569336,
|
713 |
+
"rewards/rejected": -13.072675704956055,
|
714 |
+
"step": 47
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.7804878048780488,
|
718 |
+
"grad_norm": 0.0009461237932555377,
|
719 |
+
"learning_rate": 0.00018747630845319612,
|
720 |
+
"logits/chosen": 0.13339552283287048,
|
721 |
+
"logits/rejected": 0.3655449151992798,
|
722 |
+
"logps/chosen": -420.11431884765625,
|
723 |
+
"logps/rejected": -786.4783325195312,
|
724 |
+
"loss": 0.0,
|
725 |
+
"rewards/accuracies": 1.0,
|
726 |
+
"rewards/chosen": 11.16606330871582,
|
727 |
+
"rewards/margins": 30.41803741455078,
|
728 |
+
"rewards/rejected": -19.251976013183594,
|
729 |
+
"step": 48
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.7967479674796748,
|
733 |
+
"grad_norm": 0.0033115639816969633,
|
734 |
+
"learning_rate": 0.00018682355096224872,
|
735 |
+
"logits/chosen": 0.4472777247428894,
|
736 |
+
"logits/rejected": 0.3390260934829712,
|
737 |
+
"logps/chosen": -536.7960205078125,
|
738 |
+
"logps/rejected": -901.3749389648438,
|
739 |
+
"loss": 0.0,
|
740 |
+
"rewards/accuracies": 1.0,
|
741 |
+
"rewards/chosen": 10.887458801269531,
|
742 |
+
"rewards/margins": 27.701595306396484,
|
743 |
+
"rewards/rejected": -16.814136505126953,
|
744 |
+
"step": 49
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.8130081300813008,
|
748 |
+
"grad_norm": 0.01153454091399908,
|
749 |
+
"learning_rate": 0.0001861554081393806,
|
750 |
+
"logits/chosen": 0.6489148139953613,
|
751 |
+
"logits/rejected": 0.689254105091095,
|
752 |
+
"logps/chosen": -738.5593872070312,
|
753 |
+
"logps/rejected": -755.362060546875,
|
754 |
+
"loss": 0.0001,
|
755 |
+
"rewards/accuracies": 1.0,
|
756 |
+
"rewards/chosen": 10.205413818359375,
|
757 |
+
"rewards/margins": 16.344358444213867,
|
758 |
+
"rewards/rejected": -6.138944625854492,
|
759 |
+
"step": 50
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.8292682926829268,
|
763 |
+
"grad_norm": 0.001985176932066679,
|
764 |
+
"learning_rate": 0.00018547199838102904,
|
765 |
+
"logits/chosen": 0.144524484872818,
|
766 |
+
"logits/rejected": 0.26266002655029297,
|
767 |
+
"logps/chosen": -893.19482421875,
|
768 |
+
"logps/rejected": -1031.27294921875,
|
769 |
+
"loss": 0.0,
|
770 |
+
"rewards/accuracies": 1.0,
|
771 |
+
"rewards/chosen": 9.087849617004395,
|
772 |
+
"rewards/margins": 23.393884658813477,
|
773 |
+
"rewards/rejected": -14.306035041809082,
|
774 |
+
"step": 51
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.8455284552845529,
|
778 |
+
"grad_norm": 0.00042794409091584384,
|
779 |
+
"learning_rate": 0.0001847734427889671,
|
780 |
+
"logits/chosen": 0.5121033191680908,
|
781 |
+
"logits/rejected": 1.0676312446594238,
|
782 |
+
"logps/chosen": -987.8340454101562,
|
783 |
+
"logps/rejected": -830.7366943359375,
|
784 |
+
"loss": 0.0,
|
785 |
+
"rewards/accuracies": 1.0,
|
786 |
+
"rewards/chosen": 11.409669876098633,
|
787 |
+
"rewards/margins": 19.569660186767578,
|
788 |
+
"rewards/rejected": -8.159988403320312,
|
789 |
+
"step": 52
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.8617886178861789,
|
793 |
+
"grad_norm": 0.0011688657104969025,
|
794 |
+
"learning_rate": 0.00018405986514884434,
|
795 |
+
"logits/chosen": 1.793473243713379,
|
796 |
+
"logits/rejected": 1.9872632026672363,
|
797 |
+
"logps/chosen": -926.424560546875,
|
798 |
+
"logps/rejected": -618.4228515625,
|
799 |
+
"loss": 0.0,
|
800 |
+
"rewards/accuracies": 1.0,
|
801 |
+
"rewards/chosen": 11.011417388916016,
|
802 |
+
"rewards/margins": 22.01776123046875,
|
803 |
+
"rewards/rejected": -11.006343841552734,
|
804 |
+
"step": 53
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.8780487804878049,
|
808 |
+
"grad_norm": 0.005157554987818003,
|
809 |
+
"learning_rate": 0.0001833313919082515,
|
810 |
+
"logits/chosen": -0.02910199761390686,
|
811 |
+
"logits/rejected": 0.14243453741073608,
|
812 |
+
"logps/chosen": -725.36376953125,
|
813 |
+
"logps/rejected": -997.5311279296875,
|
814 |
+
"loss": 0.0,
|
815 |
+
"rewards/accuracies": 1.0,
|
816 |
+
"rewards/chosen": 5.557222366333008,
|
817 |
+
"rewards/margins": 15.359309196472168,
|
818 |
+
"rewards/rejected": -9.802087783813477,
|
819 |
+
"step": 54
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.8943089430894309,
|
823 |
+
"grad_norm": 0.005044507794082165,
|
824 |
+
"learning_rate": 0.00018258815215431396,
|
825 |
+
"logits/chosen": 0.17898443341255188,
|
826 |
+
"logits/rejected": 0.09989897906780243,
|
827 |
+
"logps/chosen": -803.9798583984375,
|
828 |
+
"logps/rejected": -925.3179321289062,
|
829 |
+
"loss": 0.0,
|
830 |
+
"rewards/accuracies": 1.0,
|
831 |
+
"rewards/chosen": 6.798739433288574,
|
832 |
+
"rewards/margins": 17.492319107055664,
|
833 |
+
"rewards/rejected": -10.69357967376709,
|
834 |
+
"step": 55
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.9105691056910569,
|
838 |
+
"grad_norm": 0.0031374047975987196,
|
839 |
+
"learning_rate": 0.0001818302775908169,
|
840 |
+
"logits/chosen": 1.017639398574829,
|
841 |
+
"logits/rejected": 1.2823631763458252,
|
842 |
+
"logps/chosen": -824.6445922851562,
|
843 |
+
"logps/rejected": -860.8942260742188,
|
844 |
+
"loss": 0.0,
|
845 |
+
"rewards/accuracies": 1.0,
|
846 |
+
"rewards/chosen": 6.019498825073242,
|
847 |
+
"rewards/margins": 16.16924285888672,
|
848 |
+
"rewards/rejected": -10.149742126464844,
|
849 |
+
"step": 56
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.926829268292683,
|
853 |
+
"grad_norm": 0.00014241511235013604,
|
854 |
+
"learning_rate": 0.0001810579025148674,
|
855 |
+
"logits/chosen": 1.0959478616714478,
|
856 |
+
"logits/rejected": 0.9008815288543701,
|
857 |
+
"logps/chosen": -782.0526123046875,
|
858 |
+
"logps/rejected": -916.8338623046875,
|
859 |
+
"loss": 0.0,
|
860 |
+
"rewards/accuracies": 1.0,
|
861 |
+
"rewards/chosen": 8.443077087402344,
|
862 |
+
"rewards/margins": 24.263744354248047,
|
863 |
+
"rewards/rejected": -15.820667266845703,
|
864 |
+
"step": 57
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.943089430894309,
|
868 |
+
"grad_norm": 5.913816494285129e-05,
|
869 |
+
"learning_rate": 0.00018027116379309638,
|
870 |
+
"logits/chosen": 0.2709883153438568,
|
871 |
+
"logits/rejected": 0.29769933223724365,
|
872 |
+
"logps/chosen": -735.5257568359375,
|
873 |
+
"logps/rejected": -1044.0601806640625,
|
874 |
+
"loss": 0.0,
|
875 |
+
"rewards/accuracies": 1.0,
|
876 |
+
"rewards/chosen": 8.65300178527832,
|
877 |
+
"rewards/margins": 18.755083084106445,
|
878 |
+
"rewards/rejected": -10.102080345153809,
|
879 |
+
"step": 58
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.959349593495935,
|
883 |
+
"grad_norm": 0.01578771322965622,
|
884 |
+
"learning_rate": 0.00017947020083740575,
|
885 |
+
"logits/chosen": 1.5522100925445557,
|
886 |
+
"logits/rejected": 1.7518442869186401,
|
887 |
+
"logps/chosen": -1019.1099853515625,
|
888 |
+
"logps/rejected": -624.6131591796875,
|
889 |
+
"loss": 0.0001,
|
890 |
+
"rewards/accuracies": 1.0,
|
891 |
+
"rewards/chosen": 10.32003402709961,
|
892 |
+
"rewards/margins": 23.75770378112793,
|
893 |
+
"rewards/rejected": -13.43766975402832,
|
894 |
+
"step": 59
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.975609756097561,
|
898 |
+
"grad_norm": 0.0010152229806408286,
|
899 |
+
"learning_rate": 0.00017865515558026428,
|
900 |
+
"logits/chosen": 0.8601479530334473,
|
901 |
+
"logits/rejected": 0.819040060043335,
|
902 |
+
"logps/chosen": -763.342041015625,
|
903 |
+
"logps/rejected": -817.870849609375,
|
904 |
+
"loss": 0.0,
|
905 |
+
"rewards/accuracies": 1.0,
|
906 |
+
"rewards/chosen": 8.2501859664917,
|
907 |
+
"rewards/margins": 16.491539001464844,
|
908 |
+
"rewards/rejected": -8.241353034973145,
|
909 |
+
"step": 60
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.991869918699187,
|
913 |
+
"grad_norm": 0.008696873672306538,
|
914 |
+
"learning_rate": 0.0001778261724495566,
|
915 |
+
"logits/chosen": 0.7409014701843262,
|
916 |
+
"logits/rejected": 0.9245580434799194,
|
917 |
+
"logps/chosen": -888.8350830078125,
|
918 |
+
"logps/rejected": -796.002685546875,
|
919 |
+
"loss": 0.0001,
|
920 |
+
"rewards/accuracies": 1.0,
|
921 |
+
"rewards/chosen": 11.07230281829834,
|
922 |
+
"rewards/margins": 22.53582000732422,
|
923 |
+
"rewards/rejected": -11.463518142700195,
|
924 |
+
"step": 61
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 1.0,
|
928 |
+
"grad_norm": 2.3132517526391894e-05,
|
929 |
+
"learning_rate": 0.00017698339834299061,
|
930 |
+
"logits/chosen": 0.962340772151947,
|
931 |
+
"logits/rejected": 1.369040608406067,
|
932 |
+
"logps/chosen": -843.8861083984375,
|
933 |
+
"logps/rejected": -833.0137329101562,
|
934 |
+
"loss": 0.0,
|
935 |
+
"rewards/accuracies": 1.0,
|
936 |
+
"rewards/chosen": 7.60971736907959,
|
937 |
+
"rewards/margins": 22.649456024169922,
|
938 |
+
"rewards/rejected": -15.039739608764648,
|
939 |
+
"step": 62
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 1.016260162601626,
|
943 |
+
"grad_norm": 3.0814584306426696e-07,
|
944 |
+
"learning_rate": 0.00017612698260206666,
|
945 |
+
"logits/chosen": 1.7351003885269165,
|
946 |
+
"logits/rejected": 2.39410400390625,
|
947 |
+
"logps/chosen": -1081.0841064453125,
|
948 |
+
"logps/rejected": -664.132080078125,
|
949 |
+
"loss": 0.0,
|
950 |
+
"rewards/accuracies": 1.0,
|
951 |
+
"rewards/chosen": 12.010480880737305,
|
952 |
+
"rewards/margins": 23.851722717285156,
|
953 |
+
"rewards/rejected": -11.841242790222168,
|
954 |
+
"step": 63
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 1.032520325203252,
|
958 |
+
"grad_norm": 0.0014821357326582074,
|
959 |
+
"learning_rate": 0.00017525707698561385,
|
960 |
+
"logits/chosen": 0.8669869899749756,
|
961 |
+
"logits/rejected": 1.2894644737243652,
|
962 |
+
"logps/chosen": -794.047607421875,
|
963 |
+
"logps/rejected": -812.5697631835938,
|
964 |
+
"loss": 0.0,
|
965 |
+
"rewards/accuracies": 1.0,
|
966 |
+
"rewards/chosen": 11.141783714294434,
|
967 |
+
"rewards/margins": 23.891061782836914,
|
968 |
+
"rewards/rejected": -12.749277114868164,
|
969 |
+
"step": 64
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 1.048780487804878,
|
973 |
+
"grad_norm": 0.002492019208148122,
|
974 |
+
"learning_rate": 0.00017437383564289816,
|
975 |
+
"logits/chosen": 1.1617192029953003,
|
976 |
+
"logits/rejected": 1.0443211793899536,
|
977 |
+
"logps/chosen": -706.7365112304688,
|
978 |
+
"logps/rejected": -834.9153442382812,
|
979 |
+
"loss": 0.0,
|
980 |
+
"rewards/accuracies": 1.0,
|
981 |
+
"rewards/chosen": 10.32893180847168,
|
982 |
+
"rewards/margins": 23.380508422851562,
|
983 |
+
"rewards/rejected": -13.0515775680542,
|
984 |
+
"step": 65
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 1.065040650406504,
|
988 |
+
"grad_norm": 0.10320430248975754,
|
989 |
+
"learning_rate": 0.00017347741508630672,
|
990 |
+
"logits/chosen": 1.5734750032424927,
|
991 |
+
"logits/rejected": 2.108652114868164,
|
992 |
+
"logps/chosen": -919.78125,
|
993 |
+
"logps/rejected": -843.049560546875,
|
994 |
+
"loss": 0.0005,
|
995 |
+
"rewards/accuracies": 1.0,
|
996 |
+
"rewards/chosen": 14.794572830200195,
|
997 |
+
"rewards/margins": 27.74661636352539,
|
998 |
+
"rewards/rejected": -12.952045440673828,
|
999 |
+
"step": 66
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 1.08130081300813,
|
1003 |
+
"grad_norm": 0.00033748566056601703,
|
1004 |
+
"learning_rate": 0.00017256797416361362,
|
1005 |
+
"logits/chosen": 0.10465478897094727,
|
1006 |
+
"logits/rejected": 0.11954197287559509,
|
1007 |
+
"logps/chosen": -770.0354614257812,
|
1008 |
+
"logps/rejected": -705.5811767578125,
|
1009 |
+
"loss": 0.0,
|
1010 |
+
"rewards/accuracies": 1.0,
|
1011 |
+
"rewards/chosen": 8.188321113586426,
|
1012 |
+
"rewards/margins": 18.007652282714844,
|
1013 |
+
"rewards/rejected": -9.819330215454102,
|
1014 |
+
"step": 67
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 1.0975609756097562,
|
1018 |
+
"grad_norm": 0.4934139549732208,
|
1019 |
+
"learning_rate": 0.00017164567402983152,
|
1020 |
+
"logits/chosen": 0.7908147573471069,
|
1021 |
+
"logits/rejected": 1.0772439241409302,
|
1022 |
+
"logps/chosen": -869.843017578125,
|
1023 |
+
"logps/rejected": -729.0626831054688,
|
1024 |
+
"loss": 0.0024,
|
1025 |
+
"rewards/accuracies": 1.0,
|
1026 |
+
"rewards/chosen": 8.537101745605469,
|
1027 |
+
"rewards/margins": 12.491724014282227,
|
1028 |
+
"rewards/rejected": -3.9546217918395996,
|
1029 |
+
"step": 68
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 1.113821138211382,
|
1033 |
+
"grad_norm": 2.1183014098369313e-07,
|
1034 |
+
"learning_rate": 0.00017071067811865476,
|
1035 |
+
"logits/chosen": 0.6217237710952759,
|
1036 |
+
"logits/rejected": 0.5386490225791931,
|
1037 |
+
"logps/chosen": -799.1664428710938,
|
1038 |
+
"logps/rejected": -820.0735473632812,
|
1039 |
+
"loss": 0.0,
|
1040 |
+
"rewards/accuracies": 1.0,
|
1041 |
+
"rewards/chosen": 12.295455932617188,
|
1042 |
+
"rewards/margins": 30.9702091217041,
|
1043 |
+
"rewards/rejected": -18.674753189086914,
|
1044 |
+
"step": 69
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 1.1300813008130082,
|
1048 |
+
"grad_norm": 7.591093162773177e-05,
|
1049 |
+
"learning_rate": 0.0001697631521134985,
|
1050 |
+
"logits/chosen": 1.664866328239441,
|
1051 |
+
"logits/rejected": 1.980355978012085,
|
1052 |
+
"logps/chosen": -1113.451416015625,
|
1053 |
+
"logps/rejected": -825.9473876953125,
|
1054 |
+
"loss": 0.0,
|
1055 |
+
"rewards/accuracies": 1.0,
|
1056 |
+
"rewards/chosen": 11.451591491699219,
|
1057 |
+
"rewards/margins": 29.68605613708496,
|
1058 |
+
"rewards/rejected": -18.23446273803711,
|
1059 |
+
"step": 70
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 1.146341463414634,
|
1063 |
+
"grad_norm": 4.4439241264626617e-07,
|
1064 |
+
"learning_rate": 0.00016880326391813916,
|
1065 |
+
"logits/chosen": -0.02196294069290161,
|
1066 |
+
"logits/rejected": 0.18253503739833832,
|
1067 |
+
"logps/chosen": -661.0505981445312,
|
1068 |
+
"logps/rejected": -834.158203125,
|
1069 |
+
"loss": 0.0,
|
1070 |
+
"rewards/accuracies": 1.0,
|
1071 |
+
"rewards/chosen": 9.791834831237793,
|
1072 |
+
"rewards/margins": 28.233205795288086,
|
1073 |
+
"rewards/rejected": -18.441370010375977,
|
1074 |
+
"step": 71
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 1.1626016260162602,
|
1078 |
+
"grad_norm": 8.045230060815811e-05,
|
1079 |
+
"learning_rate": 0.00016783118362696163,
|
1080 |
+
"logits/chosen": 0.24465110898017883,
|
1081 |
+
"logits/rejected": 0.2313007265329361,
|
1082 |
+
"logps/chosen": -715.2831420898438,
|
1083 |
+
"logps/rejected": -1050.01171875,
|
1084 |
+
"loss": 0.0,
|
1085 |
+
"rewards/accuracies": 1.0,
|
1086 |
+
"rewards/chosen": 4.176504611968994,
|
1087 |
+
"rewards/margins": 19.875812530517578,
|
1088 |
+
"rewards/rejected": -15.699307441711426,
|
1089 |
+
"step": 72
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 1.1788617886178863,
|
1093 |
+
"grad_norm": 5.927664005866973e-06,
|
1094 |
+
"learning_rate": 0.00016684708349481804,
|
1095 |
+
"logits/chosen": 1.5342342853546143,
|
1096 |
+
"logits/rejected": 2.0414443016052246,
|
1097 |
+
"logps/chosen": -1195.0989990234375,
|
1098 |
+
"logps/rejected": -652.9114990234375,
|
1099 |
+
"loss": 0.0,
|
1100 |
+
"rewards/accuracies": 1.0,
|
1101 |
+
"rewards/chosen": 8.883450508117676,
|
1102 |
+
"rewards/margins": 19.403560638427734,
|
1103 |
+
"rewards/rejected": -10.520109176635742,
|
1104 |
+
"step": 73
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 1.1951219512195121,
|
1108 |
+
"grad_norm": 1.7679340089671314e-05,
|
1109 |
+
"learning_rate": 0.00016585113790650388,
|
1110 |
+
"logits/chosen": 0.13918209075927734,
|
1111 |
+
"logits/rejected": 0.21283580362796783,
|
1112 |
+
"logps/chosen": -937.8267211914062,
|
1113 |
+
"logps/rejected": -958.693115234375,
|
1114 |
+
"loss": 0.0,
|
1115 |
+
"rewards/accuracies": 1.0,
|
1116 |
+
"rewards/chosen": 9.578910827636719,
|
1117 |
+
"rewards/margins": 31.493125915527344,
|
1118 |
+
"rewards/rejected": -21.914215087890625,
|
1119 |
+
"step": 74
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 1.2113821138211383,
|
1123 |
+
"grad_norm": 9.838218102231622e-05,
|
1124 |
+
"learning_rate": 0.00016484352334585653,
|
1125 |
+
"logits/chosen": 1.7902581691741943,
|
1126 |
+
"logits/rejected": 1.8008999824523926,
|
1127 |
+
"logps/chosen": -898.8333740234375,
|
1128 |
+
"logps/rejected": -869.8264770507812,
|
1129 |
+
"loss": 0.0,
|
1130 |
+
"rewards/accuracies": 1.0,
|
1131 |
+
"rewards/chosen": 8.36214828491211,
|
1132 |
+
"rewards/margins": 23.546051025390625,
|
1133 |
+
"rewards/rejected": -15.183902740478516,
|
1134 |
+
"step": 75
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 1.2276422764227641,
|
1138 |
+
"grad_norm": 0.00042859543464146554,
|
1139 |
+
"learning_rate": 0.00016382441836448202,
|
1140 |
+
"logits/chosen": 0.40593788027763367,
|
1141 |
+
"logits/rejected": 0.24162518978118896,
|
1142 |
+
"logps/chosen": -713.95263671875,
|
1143 |
+
"logps/rejected": -873.909423828125,
|
1144 |
+
"loss": 0.0,
|
1145 |
+
"rewards/accuracies": 1.0,
|
1146 |
+
"rewards/chosen": 3.870103359222412,
|
1147 |
+
"rewards/margins": 17.166872024536133,
|
1148 |
+
"rewards/rejected": -13.296768188476562,
|
1149 |
+
"step": 76
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 1.2439024390243902,
|
1153 |
+
"grad_norm": 0.0007489994168281555,
|
1154 |
+
"learning_rate": 0.0001627940035501152,
|
1155 |
+
"logits/chosen": 1.2316575050354004,
|
1156 |
+
"logits/rejected": 1.2072526216506958,
|
1157 |
+
"logps/chosen": -961.4344482421875,
|
1158 |
+
"logps/rejected": -1073.3685302734375,
|
1159 |
+
"loss": 0.0,
|
1160 |
+
"rewards/accuracies": 1.0,
|
1161 |
+
"rewards/chosen": 6.6541852951049805,
|
1162 |
+
"rewards/margins": 27.57451057434082,
|
1163 |
+
"rewards/rejected": -20.920326232910156,
|
1164 |
+
"step": 77
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 1.2601626016260163,
|
1168 |
+
"grad_norm": 3.269678200013004e-05,
|
1169 |
+
"learning_rate": 0.0001617524614946192,
|
1170 |
+
"logits/chosen": 0.06140974164009094,
|
1171 |
+
"logits/rejected": 0.11881747841835022,
|
1172 |
+
"logps/chosen": -900.48876953125,
|
1173 |
+
"logps/rejected": -1085.7061767578125,
|
1174 |
+
"loss": 0.0,
|
1175 |
+
"rewards/accuracies": 1.0,
|
1176 |
+
"rewards/chosen": 0.6411392688751221,
|
1177 |
+
"rewards/margins": 19.955745697021484,
|
1178 |
+
"rewards/rejected": -19.314605712890625,
|
1179 |
+
"step": 78
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 1.2764227642276422,
|
1183 |
+
"grad_norm": 3.813441480815527e-06,
|
1184 |
+
"learning_rate": 0.0001606999767616298,
|
1185 |
+
"logits/chosen": 1.1457127332687378,
|
1186 |
+
"logits/rejected": 0.8977339267730713,
|
1187 |
+
"logps/chosen": -757.8355712890625,
|
1188 |
+
"logps/rejected": -838.0936279296875,
|
1189 |
+
"loss": 0.0,
|
1190 |
+
"rewards/accuracies": 1.0,
|
1191 |
+
"rewards/chosen": 8.651698112487793,
|
1192 |
+
"rewards/margins": 31.715707778930664,
|
1193 |
+
"rewards/rejected": -23.064010620117188,
|
1194 |
+
"step": 79
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 1.2926829268292683,
|
1198 |
+
"grad_norm": 2.5300651032011956e-05,
|
1199 |
+
"learning_rate": 0.00015963673585385016,
|
1200 |
+
"logits/chosen": -0.5050560235977173,
|
1201 |
+
"logits/rejected": -0.5818659067153931,
|
1202 |
+
"logps/chosen": -833.4871826171875,
|
1203 |
+
"logps/rejected": -1177.144287109375,
|
1204 |
+
"loss": 0.0,
|
1205 |
+
"rewards/accuracies": 1.0,
|
1206 |
+
"rewards/chosen": 0.1878601312637329,
|
1207 |
+
"rewards/margins": 28.51848602294922,
|
1208 |
+
"rewards/rejected": -28.330625534057617,
|
1209 |
+
"step": 80
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 1.3089430894308944,
|
1213 |
+
"grad_norm": 6.81912133586593e-05,
|
1214 |
+
"learning_rate": 0.00015856292718000235,
|
1215 |
+
"logits/chosen": 1.6245973110198975,
|
1216 |
+
"logits/rejected": 1.942758560180664,
|
1217 |
+
"logps/chosen": -925.15966796875,
|
1218 |
+
"logps/rejected": -746.8193969726562,
|
1219 |
+
"loss": 0.0,
|
1220 |
+
"rewards/accuracies": 1.0,
|
1221 |
+
"rewards/chosen": 9.29654598236084,
|
1222 |
+
"rewards/margins": 26.77484893798828,
|
1223 |
+
"rewards/rejected": -17.478303909301758,
|
1224 |
+
"step": 81
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 1.3252032520325203,
|
1228 |
+
"grad_norm": 1.1350484783179127e-06,
|
1229 |
+
"learning_rate": 0.0001574787410214407,
|
1230 |
+
"logits/chosen": 0.8831353187561035,
|
1231 |
+
"logits/rejected": 1.1747808456420898,
|
1232 |
+
"logps/chosen": -812.7021484375,
|
1233 |
+
"logps/rejected": -1058.893310546875,
|
1234 |
+
"loss": 0.0,
|
1235 |
+
"rewards/accuracies": 1.0,
|
1236 |
+
"rewards/chosen": 3.832669258117676,
|
1237 |
+
"rewards/margins": 33.81871795654297,
|
1238 |
+
"rewards/rejected": -29.986047744750977,
|
1239 |
+
"step": 82
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 1.3414634146341464,
|
1243 |
+
"grad_norm": 7.43222301480273e-07,
|
1244 |
+
"learning_rate": 0.0001563843694984336,
|
1245 |
+
"logits/chosen": 1.199593424797058,
|
1246 |
+
"logits/rejected": 1.2259372472763062,
|
1247 |
+
"logps/chosen": -846.8779296875,
|
1248 |
+
"logps/rejected": -1035.00244140625,
|
1249 |
+
"loss": 0.0,
|
1250 |
+
"rewards/accuracies": 1.0,
|
1251 |
+
"rewards/chosen": 4.645470142364502,
|
1252 |
+
"rewards/margins": 35.18595886230469,
|
1253 |
+
"rewards/rejected": -30.540489196777344,
|
1254 |
+
"step": 83
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 1.3577235772357723,
|
1258 |
+
"grad_norm": 4.4819596951128915e-05,
|
1259 |
+
"learning_rate": 0.00015528000653611935,
|
1260 |
+
"logits/chosen": 1.7928721904754639,
|
1261 |
+
"logits/rejected": 2.1661128997802734,
|
1262 |
+
"logps/chosen": -932.3726806640625,
|
1263 |
+
"logps/rejected": -844.2169189453125,
|
1264 |
+
"loss": 0.0,
|
1265 |
+
"rewards/accuracies": 1.0,
|
1266 |
+
"rewards/chosen": 4.103044509887695,
|
1267 |
+
"rewards/margins": 21.569711685180664,
|
1268 |
+
"rewards/rejected": -17.4666690826416,
|
1269 |
+
"step": 84
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.3739837398373984,
|
1273 |
+
"grad_norm": 7.042069594120903e-09,
|
1274 |
+
"learning_rate": 0.0001541658478301421,
|
1275 |
+
"logits/chosen": 0.2531038522720337,
|
1276 |
+
"logits/rejected": 0.2639998197555542,
|
1277 |
+
"logps/chosen": -1010.8427734375,
|
1278 |
+
"logps/rejected": -1247.974609375,
|
1279 |
+
"loss": 0.0,
|
1280 |
+
"rewards/accuracies": 1.0,
|
1281 |
+
"rewards/chosen": 0.7464678287506104,
|
1282 |
+
"rewards/margins": 30.038406372070312,
|
1283 |
+
"rewards/rejected": -29.291942596435547,
|
1284 |
+
"step": 85
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 1.3902439024390243,
|
1288 |
+
"grad_norm": 2.4762075057083166e-08,
|
1289 |
+
"learning_rate": 0.00015304209081197425,
|
1290 |
+
"logits/chosen": 2.228158473968506,
|
1291 |
+
"logits/rejected": 2.7146129608154297,
|
1292 |
+
"logps/chosen": -1221.494384765625,
|
1293 |
+
"logps/rejected": -882.4944458007812,
|
1294 |
+
"loss": 0.0,
|
1295 |
+
"rewards/accuracies": 1.0,
|
1296 |
+
"rewards/chosen": 13.98241901397705,
|
1297 |
+
"rewards/margins": 33.62451171875,
|
1298 |
+
"rewards/rejected": -19.642091751098633,
|
1299 |
+
"step": 86
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 1.4065040650406504,
|
1303 |
+
"grad_norm": 3.7480401715583866e-06,
|
1304 |
+
"learning_rate": 0.00015190893461393108,
|
1305 |
+
"logits/chosen": 1.5811924934387207,
|
1306 |
+
"logits/rejected": 2.0754153728485107,
|
1307 |
+
"logps/chosen": -958.1056518554688,
|
1308 |
+
"logps/rejected": -741.9910278320312,
|
1309 |
+
"loss": 0.0,
|
1310 |
+
"rewards/accuracies": 1.0,
|
1311 |
+
"rewards/chosen": 14.536327362060547,
|
1312 |
+
"rewards/margins": 32.516456604003906,
|
1313 |
+
"rewards/rejected": -17.980131149291992,
|
1314 |
+
"step": 87
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 1.4227642276422765,
|
1318 |
+
"grad_norm": 1.9098067696177168e-06,
|
1319 |
+
"learning_rate": 0.000150766580033884,
|
1320 |
+
"logits/chosen": 1.6907765865325928,
|
1321 |
+
"logits/rejected": 1.9654494524002075,
|
1322 |
+
"logps/chosen": -1132.77978515625,
|
1323 |
+
"logps/rejected": -908.571044921875,
|
1324 |
+
"loss": 0.0,
|
1325 |
+
"rewards/accuracies": 1.0,
|
1326 |
+
"rewards/chosen": 5.22573709487915,
|
1327 |
+
"rewards/margins": 34.5124626159668,
|
1328 |
+
"rewards/rejected": -29.286724090576172,
|
1329 |
+
"step": 88
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 1.4390243902439024,
|
1333 |
+
"grad_norm": 1.1447126780694816e-05,
|
1334 |
+
"learning_rate": 0.00014961522949967886,
|
1335 |
+
"logits/chosen": 0.9937865734100342,
|
1336 |
+
"logits/rejected": 1.2049672603607178,
|
1337 |
+
"logps/chosen": -739.3209838867188,
|
1338 |
+
"logps/rejected": -1007.2611083984375,
|
1339 |
+
"loss": 0.0,
|
1340 |
+
"rewards/accuracies": 1.0,
|
1341 |
+
"rewards/chosen": 10.235821723937988,
|
1342 |
+
"rewards/margins": 34.75508499145508,
|
1343 |
+
"rewards/rejected": -24.51926040649414,
|
1344 |
+
"step": 89
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 1.4552845528455285,
|
1348 |
+
"grad_norm": 1.5996234026260936e-07,
|
1349 |
+
"learning_rate": 0.00014845508703326504,
|
1350 |
+
"logits/chosen": 1.005773663520813,
|
1351 |
+
"logits/rejected": 0.9975143671035767,
|
1352 |
+
"logps/chosen": -912.9910278320312,
|
1353 |
+
"logps/rejected": -1205.926513671875,
|
1354 |
+
"loss": 0.0,
|
1355 |
+
"rewards/accuracies": 1.0,
|
1356 |
+
"rewards/chosen": 2.948190212249756,
|
1357 |
+
"rewards/margins": 31.25839614868164,
|
1358 |
+
"rewards/rejected": -28.310203552246094,
|
1359 |
+
"step": 90
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 1.4715447154471546,
|
1363 |
+
"grad_norm": 1.9003784473170526e-05,
|
1364 |
+
"learning_rate": 0.00014728635821454255,
|
1365 |
+
"logits/chosen": 2.574889659881592,
|
1366 |
+
"logits/rejected": 2.5759711265563965,
|
1367 |
+
"logps/chosen": -915.0121459960938,
|
1368 |
+
"logps/rejected": -623.8654174804688,
|
1369 |
+
"loss": 0.0,
|
1370 |
+
"rewards/accuracies": 1.0,
|
1371 |
+
"rewards/chosen": 15.099142074584961,
|
1372 |
+
"rewards/margins": 31.881959915161133,
|
1373 |
+
"rewards/rejected": -16.782817840576172,
|
1374 |
+
"step": 91
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 1.4878048780487805,
|
1378 |
+
"grad_norm": 4.1650441318097364e-08,
|
1379 |
+
"learning_rate": 0.0001461092501449326,
|
1380 |
+
"logits/chosen": 1.0031987428665161,
|
1381 |
+
"logits/rejected": 1.2941582202911377,
|
1382 |
+
"logps/chosen": -823.1492309570312,
|
1383 |
+
"logps/rejected": -1055.567626953125,
|
1384 |
+
"loss": 0.0,
|
1385 |
+
"rewards/accuracies": 1.0,
|
1386 |
+
"rewards/chosen": 2.4376673698425293,
|
1387 |
+
"rewards/margins": 26.05483055114746,
|
1388 |
+
"rewards/rejected": -23.617162704467773,
|
1389 |
+
"step": 92
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.5040650406504064,
|
1393 |
+
"grad_norm": 4.165614697626552e-08,
|
1394 |
+
"learning_rate": 0.00014492397141067887,
|
1395 |
+
"logits/chosen": 0.8133536577224731,
|
1396 |
+
"logits/rejected": 1.0407506227493286,
|
1397 |
+
"logps/chosen": -961.2422485351562,
|
1398 |
+
"logps/rejected": -1156.6856689453125,
|
1399 |
+
"loss": 0.0,
|
1400 |
+
"rewards/accuracies": 1.0,
|
1401 |
+
"rewards/chosen": 1.8701601028442383,
|
1402 |
+
"rewards/margins": 33.655277252197266,
|
1403 |
+
"rewards/rejected": -31.785114288330078,
|
1404 |
+
"step": 93
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 1.5203252032520327,
|
1408 |
+
"grad_norm": 3.824939540209016e-06,
|
1409 |
+
"learning_rate": 0.00014373073204588556,
|
1410 |
+
"logits/chosen": 2.6779818534851074,
|
1411 |
+
"logits/rejected": 2.7686123847961426,
|
1412 |
+
"logps/chosen": -1121.3564453125,
|
1413 |
+
"logps/rejected": -698.586669921875,
|
1414 |
+
"loss": 0.0,
|
1415 |
+
"rewards/accuracies": 1.0,
|
1416 |
+
"rewards/chosen": 10.171032905578613,
|
1417 |
+
"rewards/margins": 27.788890838623047,
|
1418 |
+
"rewards/rejected": -17.617855072021484,
|
1419 |
+
"step": 94
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 1.5365853658536586,
|
1423 |
+
"grad_norm": 3.954168641939759e-05,
|
1424 |
+
"learning_rate": 0.0001425297434952987,
|
1425 |
+
"logits/chosen": 0.22321929037570953,
|
1426 |
+
"logits/rejected": 0.2271191030740738,
|
1427 |
+
"logps/chosen": -671.6175537109375,
|
1428 |
+
"logps/rejected": -1141.6953125,
|
1429 |
+
"loss": 0.0,
|
1430 |
+
"rewards/accuracies": 1.0,
|
1431 |
+
"rewards/chosen": -2.185655355453491,
|
1432 |
+
"rewards/margins": 26.3375301361084,
|
1433 |
+
"rewards/rejected": -28.52318572998047,
|
1434 |
+
"step": 95
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 1.5528455284552845,
|
1438 |
+
"grad_norm": 6.408844566152538e-10,
|
1439 |
+
"learning_rate": 0.00014132121857683783,
|
1440 |
+
"logits/chosen": 1.1100516319274902,
|
1441 |
+
"logits/rejected": 1.0310027599334717,
|
1442 |
+
"logps/chosen": -995.9828491210938,
|
1443 |
+
"logps/rejected": -1024.00244140625,
|
1444 |
+
"loss": 0.0,
|
1445 |
+
"rewards/accuracies": 1.0,
|
1446 |
+
"rewards/chosen": 8.543378829956055,
|
1447 |
+
"rewards/margins": 33.411643981933594,
|
1448 |
+
"rewards/rejected": -24.868263244628906,
|
1449 |
+
"step": 96
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 1.5691056910569106,
|
1453 |
+
"grad_norm": 6.710484399263805e-07,
|
1454 |
+
"learning_rate": 0.00014010537144388416,
|
1455 |
+
"logits/chosen": 0.19941049814224243,
|
1456 |
+
"logits/rejected": 0.2904074490070343,
|
1457 |
+
"logps/chosen": -580.1328125,
|
1458 |
+
"logps/rejected": -1122.187744140625,
|
1459 |
+
"loss": 0.0,
|
1460 |
+
"rewards/accuracies": 1.0,
|
1461 |
+
"rewards/chosen": -0.563772439956665,
|
1462 |
+
"rewards/margins": 23.33687400817871,
|
1463 |
+
"rewards/rejected": -23.900646209716797,
|
1464 |
+
"step": 97
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 1.5853658536585367,
|
1468 |
+
"grad_norm": 2.6136473252336145e-07,
|
1469 |
+
"learning_rate": 0.00013888241754733208,
|
1470 |
+
"logits/chosen": 0.8143081665039062,
|
1471 |
+
"logits/rejected": 1.183271050453186,
|
1472 |
+
"logps/chosen": -973.23583984375,
|
1473 |
+
"logps/rejected": -904.20556640625,
|
1474 |
+
"loss": 0.0,
|
1475 |
+
"rewards/accuracies": 1.0,
|
1476 |
+
"rewards/chosen": 3.3894622325897217,
|
1477 |
+
"rewards/margins": 23.915855407714844,
|
1478 |
+
"rewards/rejected": -20.526391983032227,
|
1479 |
+
"step": 98
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 1.6016260162601625,
|
1483 |
+
"grad_norm": 1.735031582938973e-05,
|
1484 |
+
"learning_rate": 0.00013765257359741063,
|
1485 |
+
"logits/chosen": 0.8897725343704224,
|
1486 |
+
"logits/rejected": 0.8052040338516235,
|
1487 |
+
"logps/chosen": -771.9832763671875,
|
1488 |
+
"logps/rejected": -874.3773193359375,
|
1489 |
+
"loss": 0.0,
|
1490 |
+
"rewards/accuracies": 1.0,
|
1491 |
+
"rewards/chosen": 6.943796157836914,
|
1492 |
+
"rewards/margins": 29.497058868408203,
|
1493 |
+
"rewards/rejected": -22.55326271057129,
|
1494 |
+
"step": 99
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 1.6178861788617886,
|
1498 |
+
"grad_norm": 1.2570103535836097e-07,
|
1499 |
+
"learning_rate": 0.00013641605752528224,
|
1500 |
+
"logits/chosen": 1.0415421724319458,
|
1501 |
+
"logits/rejected": 1.3014307022094727,
|
1502 |
+
"logps/chosen": -918.8525390625,
|
1503 |
+
"logps/rejected": -955.0538330078125,
|
1504 |
+
"loss": 0.0,
|
1505 |
+
"rewards/accuracies": 1.0,
|
1506 |
+
"rewards/chosen": 7.44915771484375,
|
1507 |
+
"rewards/margins": 33.4973258972168,
|
1508 |
+
"rewards/rejected": -26.04817008972168,
|
1509 |
+
"step": 100
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 1.6341463414634148,
|
1513 |
+
"grad_norm": 3.719053154327412e-07,
|
1514 |
+
"learning_rate": 0.0001351730884444245,
|
1515 |
+
"logits/chosen": 0.4167521595954895,
|
1516 |
+
"logits/rejected": 0.3483416438102722,
|
1517 |
+
"logps/chosen": -604.3650512695312,
|
1518 |
+
"logps/rejected": -1362.02587890625,
|
1519 |
+
"loss": 0.0,
|
1520 |
+
"rewards/accuracies": 1.0,
|
1521 |
+
"rewards/chosen": -2.4617691040039062,
|
1522 |
+
"rewards/margins": 44.77275466918945,
|
1523 |
+
"rewards/rejected": -47.23452377319336,
|
1524 |
+
"step": 101
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 1.6504065040650406,
|
1528 |
+
"grad_norm": 1.487089633656069e-07,
|
1529 |
+
"learning_rate": 0.00013392388661180303,
|
1530 |
+
"logits/chosen": 0.9698238968849182,
|
1531 |
+
"logits/rejected": 1.1324440240859985,
|
1532 |
+
"logps/chosen": -742.9386596679688,
|
1533 |
+
"logps/rejected": -905.581298828125,
|
1534 |
+
"loss": 0.0,
|
1535 |
+
"rewards/accuracies": 1.0,
|
1536 |
+
"rewards/chosen": 5.503021717071533,
|
1537 |
+
"rewards/margins": 32.864501953125,
|
1538 |
+
"rewards/rejected": -27.361482620239258,
|
1539 |
+
"step": 102
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 1.6666666666666665,
|
1543 |
+
"grad_norm": 0.00015168750542216003,
|
1544 |
+
"learning_rate": 0.0001326686733888413,
|
1545 |
+
"logits/chosen": 2.734503746032715,
|
1546 |
+
"logits/rejected": 2.7868616580963135,
|
1547 |
+
"logps/chosen": -845.9635009765625,
|
1548 |
+
"logps/rejected": -674.9261474609375,
|
1549 |
+
"loss": 0.0,
|
1550 |
+
"rewards/accuracies": 1.0,
|
1551 |
+
"rewards/chosen": 6.455021858215332,
|
1552 |
+
"rewards/margins": 21.768619537353516,
|
1553 |
+
"rewards/rejected": -15.3135986328125,
|
1554 |
+
"step": 103
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 1.6829268292682928,
|
1558 |
+
"grad_norm": 5.236762717686361e-06,
|
1559 |
+
"learning_rate": 0.0001314076712021949,
|
1560 |
+
"logits/chosen": 0.8474237322807312,
|
1561 |
+
"logits/rejected": 1.0795999765396118,
|
1562 |
+
"logps/chosen": -844.8881225585938,
|
1563 |
+
"logps/rejected": -1026.413818359375,
|
1564 |
+
"loss": 0.0,
|
1565 |
+
"rewards/accuracies": 1.0,
|
1566 |
+
"rewards/chosen": 9.01052474975586,
|
1567 |
+
"rewards/margins": 34.12953186035156,
|
1568 |
+
"rewards/rejected": -25.119007110595703,
|
1569 |
+
"step": 104
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 1.6991869918699187,
|
1573 |
+
"grad_norm": 4.3044991571150604e-08,
|
1574 |
+
"learning_rate": 0.000130141103504337,
|
1575 |
+
"logits/chosen": 1.0104427337646484,
|
1576 |
+
"logits/rejected": 0.809540867805481,
|
1577 |
+
"logps/chosen": -806.0650634765625,
|
1578 |
+
"logps/rejected": -1019.7612915039062,
|
1579 |
+
"loss": 0.0,
|
1580 |
+
"rewards/accuracies": 1.0,
|
1581 |
+
"rewards/chosen": 7.093156814575195,
|
1582 |
+
"rewards/margins": 29.144248962402344,
|
1583 |
+
"rewards/rejected": -22.051090240478516,
|
1584 |
+
"step": 105
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 1.7154471544715446,
|
1588 |
+
"grad_norm": 6.236035243745164e-09,
|
1589 |
+
"learning_rate": 0.0001288691947339621,
|
1590 |
+
"logits/chosen": 0.26283663511276245,
|
1591 |
+
"logits/rejected": 0.21620601415634155,
|
1592 |
+
"logps/chosen": -764.7117919921875,
|
1593 |
+
"logps/rejected": -1384.037353515625,
|
1594 |
+
"loss": 0.0,
|
1595 |
+
"rewards/accuracies": 1.0,
|
1596 |
+
"rewards/chosen": -0.5661294460296631,
|
1597 |
+
"rewards/margins": 35.904212951660156,
|
1598 |
+
"rewards/rejected": -36.470340728759766,
|
1599 |
+
"step": 106
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 1.7317073170731707,
|
1603 |
+
"grad_norm": 0.0002312189608346671,
|
1604 |
+
"learning_rate": 0.00012759217027621505,
|
1605 |
+
"logits/chosen": 0.8271576166152954,
|
1606 |
+
"logits/rejected": 0.8352835178375244,
|
1607 |
+
"logps/chosen": -639.9276123046875,
|
1608 |
+
"logps/rejected": -721.3944702148438,
|
1609 |
+
"loss": 0.0,
|
1610 |
+
"rewards/accuracies": 1.0,
|
1611 |
+
"rewards/chosen": 3.1902108192443848,
|
1612 |
+
"rewards/margins": 19.32707977294922,
|
1613 |
+
"rewards/rejected": -16.13686752319336,
|
1614 |
+
"step": 107
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 1.7479674796747968,
|
1618 |
+
"grad_norm": 5.53435963723814e-09,
|
1619 |
+
"learning_rate": 0.00012631025642275212,
|
1620 |
+
"logits/chosen": 0.9540997743606567,
|
1621 |
+
"logits/rejected": 1.0216646194458008,
|
1622 |
+
"logps/chosen": -920.1544189453125,
|
1623 |
+
"logps/rejected": -919.189453125,
|
1624 |
+
"loss": 0.0,
|
1625 |
+
"rewards/accuracies": 1.0,
|
1626 |
+
"rewards/chosen": 8.917628288269043,
|
1627 |
+
"rewards/margins": 31.62308692932129,
|
1628 |
+
"rewards/rejected": -22.705459594726562,
|
1629 |
+
"step": 108
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 1.7642276422764227,
|
1633 |
+
"grad_norm": 5.7604488290508016e-08,
|
1634 |
+
"learning_rate": 0.00012502368033164176,
|
1635 |
+
"logits/chosen": 1.9378834962844849,
|
1636 |
+
"logits/rejected": 2.0527262687683105,
|
1637 |
+
"logps/chosen": -616.1436767578125,
|
1638 |
+
"logps/rejected": -781.5704956054688,
|
1639 |
+
"loss": 0.0,
|
1640 |
+
"rewards/accuracies": 1.0,
|
1641 |
+
"rewards/chosen": 4.269429683685303,
|
1642 |
+
"rewards/margins": 27.761857986450195,
|
1643 |
+
"rewards/rejected": -23.492429733276367,
|
1644 |
+
"step": 109
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 1.7804878048780488,
|
1648 |
+
"grad_norm": 3.0333463740817024e-08,
|
1649 |
+
"learning_rate": 0.0001237326699871115,
|
1650 |
+
"logits/chosen": 0.784665584564209,
|
1651 |
+
"logits/rejected": 1.0081039667129517,
|
1652 |
+
"logps/chosen": -864.7948608398438,
|
1653 |
+
"logps/rejected": -946.906982421875,
|
1654 |
+
"loss": 0.0,
|
1655 |
+
"rewards/accuracies": 1.0,
|
1656 |
+
"rewards/chosen": 6.097116470336914,
|
1657 |
+
"rewards/margins": 30.87978172302246,
|
1658 |
+
"rewards/rejected": -24.78266716003418,
|
1659 |
+
"step": 110
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 1.796747967479675,
|
1663 |
+
"grad_norm": 3.1582476367475465e-07,
|
1664 |
+
"learning_rate": 0.00012243745415914883,
|
1665 |
+
"logits/chosen": -0.5353690385818481,
|
1666 |
+
"logits/rejected": -0.6592149138450623,
|
1667 |
+
"logps/chosen": -722.5419921875,
|
1668 |
+
"logps/rejected": -1070.7403564453125,
|
1669 |
+
"loss": 0.0,
|
1670 |
+
"rewards/accuracies": 1.0,
|
1671 |
+
"rewards/chosen": -1.3367981910705566,
|
1672 |
+
"rewards/margins": 27.85375213623047,
|
1673 |
+
"rewards/rejected": -29.190549850463867,
|
1674 |
+
"step": 111
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 1.8130081300813008,
|
1678 |
+
"grad_norm": 2.334864745989762e-07,
|
1679 |
+
"learning_rate": 0.00012113826236296244,
|
1680 |
+
"logits/chosen": 1.986028790473938,
|
1681 |
+
"logits/rejected": 2.0000312328338623,
|
1682 |
+
"logps/chosen": -1034.116455078125,
|
1683 |
+
"logps/rejected": -924.2823486328125,
|
1684 |
+
"loss": 0.0,
|
1685 |
+
"rewards/accuracies": 1.0,
|
1686 |
+
"rewards/chosen": 9.337306022644043,
|
1687 |
+
"rewards/margins": 34.88032531738281,
|
1688 |
+
"rewards/rejected": -25.54302215576172,
|
1689 |
+
"step": 112
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 1.8292682926829267,
|
1693 |
+
"grad_norm": 1.956110463652294e-05,
|
1694 |
+
"learning_rate": 0.0001198353248183118,
|
1695 |
+
"logits/chosen": 1.1676946878433228,
|
1696 |
+
"logits/rejected": 1.3392938375473022,
|
1697 |
+
"logps/chosen": -839.8267211914062,
|
1698 |
+
"logps/rejected": -966.1685180664062,
|
1699 |
+
"loss": 0.0,
|
1700 |
+
"rewards/accuracies": 1.0,
|
1701 |
+
"rewards/chosen": 4.940967082977295,
|
1702 |
+
"rewards/margins": 33.268653869628906,
|
1703 |
+
"rewards/rejected": -28.327686309814453,
|
1704 |
+
"step": 113
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 1.845528455284553,
|
1708 |
+
"grad_norm": 1.2582788144754886e-07,
|
1709 |
+
"learning_rate": 0.00011852887240871145,
|
1710 |
+
"logits/chosen": 1.7121946811676025,
|
1711 |
+
"logits/rejected": 1.834307074546814,
|
1712 |
+
"logps/chosen": -825.6591796875,
|
1713 |
+
"logps/rejected": -910.5638427734375,
|
1714 |
+
"loss": 0.0,
|
1715 |
+
"rewards/accuracies": 1.0,
|
1716 |
+
"rewards/chosen": 5.057826519012451,
|
1717 |
+
"rewards/margins": 26.722637176513672,
|
1718 |
+
"rewards/rejected": -21.664812088012695,
|
1719 |
+
"step": 114
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 1.8617886178861789,
|
1723 |
+
"grad_norm": 3.8171506275830325e-06,
|
1724 |
+
"learning_rate": 0.00011721913664051813,
|
1725 |
+
"logits/chosen": 0.09213051199913025,
|
1726 |
+
"logits/rejected": 0.2805327773094177,
|
1727 |
+
"logps/chosen": -785.7156982421875,
|
1728 |
+
"logps/rejected": -1021.4864501953125,
|
1729 |
+
"loss": 0.0,
|
1730 |
+
"rewards/accuracies": 1.0,
|
1731 |
+
"rewards/chosen": 0.823834240436554,
|
1732 |
+
"rewards/margins": 25.152664184570312,
|
1733 |
+
"rewards/rejected": -24.32883071899414,
|
1734 |
+
"step": 115
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 1.8780487804878048,
|
1738 |
+
"grad_norm": 2.6529932029006886e-08,
|
1739 |
+
"learning_rate": 0.00011590634960190721,
|
1740 |
+
"logits/chosen": -0.5069230198860168,
|
1741 |
+
"logits/rejected": -0.5888826847076416,
|
1742 |
+
"logps/chosen": -707.7698974609375,
|
1743 |
+
"logps/rejected": -1266.01904296875,
|
1744 |
+
"loss": 0.0,
|
1745 |
+
"rewards/accuracies": 1.0,
|
1746 |
+
"rewards/chosen": 0.027275919914245605,
|
1747 |
+
"rewards/margins": 27.478078842163086,
|
1748 |
+
"rewards/rejected": -27.450803756713867,
|
1749 |
+
"step": 116
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 1.8943089430894309,
|
1753 |
+
"grad_norm": 9.935014304573997e-07,
|
1754 |
+
"learning_rate": 0.00011459074392174618,
|
1755 |
+
"logits/chosen": 1.5636107921600342,
|
1756 |
+
"logits/rejected": 1.8575186729431152,
|
1757 |
+
"logps/chosen": -1191.93359375,
|
1758 |
+
"logps/rejected": -990.843505859375,
|
1759 |
+
"loss": 0.0,
|
1760 |
+
"rewards/accuracies": 1.0,
|
1761 |
+
"rewards/chosen": 12.92037582397461,
|
1762 |
+
"rewards/margins": 39.89407730102539,
|
1763 |
+
"rewards/rejected": -26.973697662353516,
|
1764 |
+
"step": 117
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 1.910569105691057,
|
1768 |
+
"grad_norm": 1.2037819942634087e-05,
|
1769 |
+
"learning_rate": 0.00011327255272837221,
|
1770 |
+
"logits/chosen": 1.0499224662780762,
|
1771 |
+
"logits/rejected": 0.9787989854812622,
|
1772 |
+
"logps/chosen": -971.0214233398438,
|
1773 |
+
"logps/rejected": -877.3848876953125,
|
1774 |
+
"loss": 0.0,
|
1775 |
+
"rewards/accuracies": 1.0,
|
1776 |
+
"rewards/chosen": 2.003582715988159,
|
1777 |
+
"rewards/margins": 20.236526489257812,
|
1778 |
+
"rewards/rejected": -18.23294448852539,
|
1779 |
+
"step": 118
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 1.9268292682926829,
|
1783 |
+
"grad_norm": 1.8166872450819938e-06,
|
1784 |
+
"learning_rate": 0.00011195200960828139,
|
1785 |
+
"logits/chosen": 1.6961169242858887,
|
1786 |
+
"logits/rejected": 2.2738733291625977,
|
1787 |
+
"logps/chosen": -1074.953369140625,
|
1788 |
+
"logps/rejected": -778.5762939453125,
|
1789 |
+
"loss": 0.0,
|
1790 |
+
"rewards/accuracies": 1.0,
|
1791 |
+
"rewards/chosen": 8.411404609680176,
|
1792 |
+
"rewards/margins": 25.984111785888672,
|
1793 |
+
"rewards/rejected": -17.57270622253418,
|
1794 |
+
"step": 119
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 1.943089430894309,
|
1798 |
+
"grad_norm": 0.002434302121400833,
|
1799 |
+
"learning_rate": 0.00011062934856473655,
|
1800 |
+
"logits/chosen": 0.24992449581623077,
|
1801 |
+
"logits/rejected": 0.18503600358963013,
|
1802 |
+
"logps/chosen": -811.4505615234375,
|
1803 |
+
"logps/rejected": -1088.271240234375,
|
1804 |
+
"loss": 0.0,
|
1805 |
+
"rewards/accuracies": 1.0,
|
1806 |
+
"rewards/chosen": 2.826874017715454,
|
1807 |
+
"rewards/margins": 32.1160888671875,
|
1808 |
+
"rewards/rejected": -29.289215087890625,
|
1809 |
+
"step": 120
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.959349593495935,
|
1813 |
+
"grad_norm": 3.818647797970698e-08,
|
1814 |
+
"learning_rate": 0.00010930480397630145,
|
1815 |
+
"logits/chosen": 1.889555811882019,
|
1816 |
+
"logits/rejected": 2.055070400238037,
|
1817 |
+
"logps/chosen": -1008.6806640625,
|
1818 |
+
"logps/rejected": -997.8306884765625,
|
1819 |
+
"loss": 0.0,
|
1820 |
+
"rewards/accuracies": 1.0,
|
1821 |
+
"rewards/chosen": 4.727387428283691,
|
1822 |
+
"rewards/margins": 32.15311813354492,
|
1823 |
+
"rewards/rejected": -27.42573356628418,
|
1824 |
+
"step": 121
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 1.975609756097561,
|
1828 |
+
"grad_norm": 4.203374359690315e-08,
|
1829 |
+
"learning_rate": 0.00010797861055530831,
|
1830 |
+
"logits/chosen": 0.33176711201667786,
|
1831 |
+
"logits/rejected": 0.2883341312408447,
|
1832 |
+
"logps/chosen": -764.9257202148438,
|
1833 |
+
"logps/rejected": -1157.33642578125,
|
1834 |
+
"loss": 0.0,
|
1835 |
+
"rewards/accuracies": 1.0,
|
1836 |
+
"rewards/chosen": -0.931965708732605,
|
1837 |
+
"rewards/margins": 29.445417404174805,
|
1838 |
+
"rewards/rejected": -30.377384185791016,
|
1839 |
+
"step": 122
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 1.9918699186991868,
|
1843 |
+
"grad_norm": 0.0003661888767965138,
|
1844 |
+
"learning_rate": 0.00010665100330626625,
|
1845 |
+
"logits/chosen": 2.023690700531006,
|
1846 |
+
"logits/rejected": 2.543468475341797,
|
1847 |
+
"logps/chosen": -1341.046875,
|
1848 |
+
"logps/rejected": -852.0292358398438,
|
1849 |
+
"loss": 0.0,
|
1850 |
+
"rewards/accuracies": 1.0,
|
1851 |
+
"rewards/chosen": 13.60735034942627,
|
1852 |
+
"rewards/margins": 33.2912483215332,
|
1853 |
+
"rewards/rejected": -19.68389892578125,
|
1854 |
+
"step": 123
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 2.0,
|
1858 |
+
"grad_norm": 1.4813576854066923e-07,
|
1859 |
+
"learning_rate": 0.00010532221748421787,
|
1860 |
+
"logits/chosen": 2.4457969665527344,
|
1861 |
+
"logits/rejected": 2.6656110286712646,
|
1862 |
+
"logps/chosen": -1094.49560546875,
|
1863 |
+
"logps/rejected": -546.4738159179688,
|
1864 |
+
"loss": 0.0,
|
1865 |
+
"rewards/accuracies": 1.0,
|
1866 |
+
"rewards/chosen": 12.480463027954102,
|
1867 |
+
"rewards/margins": 21.069480895996094,
|
1868 |
+
"rewards/rejected": -8.589018821716309,
|
1869 |
+
"step": 124
|
1870 |
+
}
|
1871 |
+
],
|
1872 |
+
"logging_steps": 1,
|
1873 |
+
"max_steps": 246,
|
1874 |
+
"num_input_tokens_seen": 0,
|
1875 |
+
"num_train_epochs": 5,
|
1876 |
+
"save_steps": 62,
|
1877 |
+
"stateful_callbacks": {
|
1878 |
+
"TrainerControl": {
|
1879 |
+
"args": {
|
1880 |
+
"should_epoch_stop": false,
|
1881 |
+
"should_evaluate": false,
|
1882 |
+
"should_log": false,
|
1883 |
+
"should_save": true,
|
1884 |
+
"should_training_stop": false
|
1885 |
+
},
|
1886 |
+
"attributes": {}
|
1887 |
+
}
|
1888 |
+
},
|
1889 |
+
"total_flos": 0.0,
|
1890 |
+
"train_batch_size": 1,
|
1891 |
+
"trial_name": null,
|
1892 |
+
"trial_params": null
|
1893 |
+
}
|
checkpoint-run1-124/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bfa7ff9d80b63c0ea349797dad26a60df3805ba7517614bd0d61390fa2637b7
|
3 |
+
size 7416
|
checkpoint-run1-186/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: /cpool/DeepSeek-R1-Distill-Llama-70B-Uncensored-v2
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.14.0
|
checkpoint-run1-186/adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "/cpool/DeepSeek-R1-Distill-Llama-70B-Uncensored-v2",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": null,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 32,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"v_proj",
|
27 |
+
"o_proj",
|
28 |
+
"q_proj",
|
29 |
+
"k_proj",
|
30 |
+
"gate_proj",
|
31 |
+
"down_proj",
|
32 |
+
"up_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
checkpoint-run1-186/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0997834bd7449a01249bfd08a722e673e4a8445665a4e0d2be31a39f7355bc4
|
3 |
+
size 1656902648
|
checkpoint-run1-186/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb3743621c41e3656d27fb5a3e6d586079c3526cf43db64425c01b7e9c009b00
|
3 |
+
size 3314505202
|
checkpoint-run1-186/pytorch_model_fsdp.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:908b0156a52dde4d052d15eb2b2afa95a6329389ff7348bf2ec543a3be3de696
|
3 |
+
size 1657168758
|
checkpoint-run1-186/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34bcae41c589c7e4cab7b2ef263b878c90c2741404a6af11994dc31537b2319b
|
3 |
+
size 14512
|
checkpoint-run1-186/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d05dc84075e8f7dd1191c36f3be9dda12073208e12f7d2cef433c38d6336774a
|
3 |
+
size 14512
|
checkpoint-run1-186/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ed52ba65a6629a293454dbe21c9f4b80cbe0997ed6d38be6388330a5d9db2f2
|
3 |
+
size 1064
|
checkpoint-run1-186/special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end_of_text|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
checkpoint-run1-186/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16f2ebc8d9a7de55360d83ea69f97916a1389f0a72264664d4d6c4db6da8d0b8
|
3 |
+
size 17209722
|
checkpoint-run1-186/tokenizer_config.json
ADDED
@@ -0,0 +1,2075 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"128000": {
|
7 |
+
"content": "<|begin▁of▁sentence|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"128001": {
|
15 |
+
"content": "<|end▁of▁sentence|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"128002": {
|
23 |
+
"content": "<|reserved_special_token_0|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"128003": {
|
31 |
+
"content": "<|reserved_special_token_1|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"128004": {
|
39 |
+
"content": "<|finetune_right_pad_id|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"128005": {
|
47 |
+
"content": "<|reserved_special_token_2|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"128006": {
|
55 |
+
"content": "<|start_header_id|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"128007": {
|
63 |
+
"content": "<|end_header_id|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"128008": {
|
71 |
+
"content": "<|eom_id|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"128009": {
|
79 |
+
"content": "<|eot_id|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"128010": {
|
87 |
+
"content": "<|python_tag|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"128011": {
|
95 |
+
"content": "<|User|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"128012": {
|
103 |
+
"content": "<|Assistant|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"128013": {
|
111 |
+
"content": "<think>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"128014": {
|
119 |
+
"content": "</think>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"128015": {
|
127 |
+
"content": "<|▁pad▁|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"128016": {
|
135 |
+
"content": "<|reserved_special_token_8|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"128017": {
|
143 |
+
"content": "<|reserved_special_token_9|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"128018": {
|
151 |
+
"content": "<|reserved_special_token_10|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"128019": {
|
159 |
+
"content": "<|reserved_special_token_11|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"128020": {
|
167 |
+
"content": "<|reserved_special_token_12|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"128021": {
|
175 |
+
"content": "<|reserved_special_token_13|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"128022": {
|
183 |
+
"content": "<|reserved_special_token_14|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"128023": {
|
191 |
+
"content": "<|reserved_special_token_15|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"128024": {
|
199 |
+
"content": "<|reserved_special_token_16|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"128025": {
|
207 |
+
"content": "<|reserved_special_token_17|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"128026": {
|
215 |
+
"content": "<|reserved_special_token_18|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"128027": {
|
223 |
+
"content": "<|reserved_special_token_19|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"128028": {
|
231 |
+
"content": "<|reserved_special_token_20|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"128029": {
|
239 |
+
"content": "<|reserved_special_token_21|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"128030": {
|
247 |
+
"content": "<|reserved_special_token_22|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"128031": {
|
255 |
+
"content": "<|reserved_special_token_23|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"128032": {
|
263 |
+
"content": "<|reserved_special_token_24|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"128033": {
|
271 |
+
"content": "<|reserved_special_token_25|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"128034": {
|
279 |
+
"content": "<|reserved_special_token_26|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"128035": {
|
287 |
+
"content": "<|reserved_special_token_27|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"128036": {
|
295 |
+
"content": "<|reserved_special_token_28|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"128037": {
|
303 |
+
"content": "<|reserved_special_token_29|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"128038": {
|
311 |
+
"content": "<|reserved_special_token_30|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"128039": {
|
319 |
+
"content": "<|reserved_special_token_31|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"128040": {
|
327 |
+
"content": "<|reserved_special_token_32|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"128041": {
|
335 |
+
"content": "<|reserved_special_token_33|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"128042": {
|
343 |
+
"content": "<|reserved_special_token_34|>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"128043": {
|
351 |
+
"content": "<|reserved_special_token_35|>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"128044": {
|
359 |
+
"content": "<|reserved_special_token_36|>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"128045": {
|
367 |
+
"content": "<|reserved_special_token_37|>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"128046": {
|
375 |
+
"content": "<|reserved_special_token_38|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"128047": {
|
383 |
+
"content": "<|reserved_special_token_39|>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"128048": {
|
391 |
+
"content": "<|reserved_special_token_40|>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"128049": {
|
399 |
+
"content": "<|reserved_special_token_41|>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"128050": {
|
407 |
+
"content": "<|reserved_special_token_42|>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"128051": {
|
415 |
+
"content": "<|reserved_special_token_43|>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"128052": {
|
423 |
+
"content": "<|reserved_special_token_44|>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"128053": {
|
431 |
+
"content": "<|reserved_special_token_45|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"128054": {
|
439 |
+
"content": "<|reserved_special_token_46|>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"128055": {
|
447 |
+
"content": "<|reserved_special_token_47|>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"128056": {
|
455 |
+
"content": "<|reserved_special_token_48|>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"128057": {
|
463 |
+
"content": "<|reserved_special_token_49|>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"128058": {
|
471 |
+
"content": "<|reserved_special_token_50|>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"128059": {
|
479 |
+
"content": "<|reserved_special_token_51|>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"128060": {
|
487 |
+
"content": "<|reserved_special_token_52|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"128061": {
|
495 |
+
"content": "<|reserved_special_token_53|>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"128062": {
|
503 |
+
"content": "<|reserved_special_token_54|>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"128063": {
|
511 |
+
"content": "<|reserved_special_token_55|>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"128064": {
|
519 |
+
"content": "<|reserved_special_token_56|>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"128065": {
|
527 |
+
"content": "<|reserved_special_token_57|>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"128066": {
|
535 |
+
"content": "<|reserved_special_token_58|>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
},
|
542 |
+
"128067": {
|
543 |
+
"content": "<|reserved_special_token_59|>",
|
544 |
+
"lstrip": false,
|
545 |
+
"normalized": false,
|
546 |
+
"rstrip": false,
|
547 |
+
"single_word": false,
|
548 |
+
"special": true
|
549 |
+
},
|
550 |
+
"128068": {
|
551 |
+
"content": "<|reserved_special_token_60|>",
|
552 |
+
"lstrip": false,
|
553 |
+
"normalized": false,
|
554 |
+
"rstrip": false,
|
555 |
+
"single_word": false,
|
556 |
+
"special": true
|
557 |
+
},
|
558 |
+
"128069": {
|
559 |
+
"content": "<|reserved_special_token_61|>",
|
560 |
+
"lstrip": false,
|
561 |
+
"normalized": false,
|
562 |
+
"rstrip": false,
|
563 |
+
"single_word": false,
|
564 |
+
"special": true
|
565 |
+
},
|
566 |
+
"128070": {
|
567 |
+
"content": "<|reserved_special_token_62|>",
|
568 |
+
"lstrip": false,
|
569 |
+
"normalized": false,
|
570 |
+
"rstrip": false,
|
571 |
+
"single_word": false,
|
572 |
+
"special": true
|
573 |
+
},
|
574 |
+
"128071": {
|
575 |
+
"content": "<|reserved_special_token_63|>",
|
576 |
+
"lstrip": false,
|
577 |
+
"normalized": false,
|
578 |
+
"rstrip": false,
|
579 |
+
"single_word": false,
|
580 |
+
"special": true
|
581 |
+
},
|
582 |
+
"128072": {
|
583 |
+
"content": "<|reserved_special_token_64|>",
|
584 |
+
"lstrip": false,
|
585 |
+
"normalized": false,
|
586 |
+
"rstrip": false,
|
587 |
+
"single_word": false,
|
588 |
+
"special": true
|
589 |
+
},
|
590 |
+
"128073": {
|
591 |
+
"content": "<|reserved_special_token_65|>",
|
592 |
+
"lstrip": false,
|
593 |
+
"normalized": false,
|
594 |
+
"rstrip": false,
|
595 |
+
"single_word": false,
|
596 |
+
"special": true
|
597 |
+
},
|
598 |
+
"128074": {
|
599 |
+
"content": "<|reserved_special_token_66|>",
|
600 |
+
"lstrip": false,
|
601 |
+
"normalized": false,
|
602 |
+
"rstrip": false,
|
603 |
+
"single_word": false,
|
604 |
+
"special": true
|
605 |
+
},
|
606 |
+
"128075": {
|
607 |
+
"content": "<|reserved_special_token_67|>",
|
608 |
+
"lstrip": false,
|
609 |
+
"normalized": false,
|
610 |
+
"rstrip": false,
|
611 |
+
"single_word": false,
|
612 |
+
"special": true
|
613 |
+
},
|
614 |
+
"128076": {
|
615 |
+
"content": "<|reserved_special_token_68|>",
|
616 |
+
"lstrip": false,
|
617 |
+
"normalized": false,
|
618 |
+
"rstrip": false,
|
619 |
+
"single_word": false,
|
620 |
+
"special": true
|
621 |
+
},
|
622 |
+
"128077": {
|
623 |
+
"content": "<|reserved_special_token_69|>",
|
624 |
+
"lstrip": false,
|
625 |
+
"normalized": false,
|
626 |
+
"rstrip": false,
|
627 |
+
"single_word": false,
|
628 |
+
"special": true
|
629 |
+
},
|
630 |
+
"128078": {
|
631 |
+
"content": "<|reserved_special_token_70|>",
|
632 |
+
"lstrip": false,
|
633 |
+
"normalized": false,
|
634 |
+
"rstrip": false,
|
635 |
+
"single_word": false,
|
636 |
+
"special": true
|
637 |
+
},
|
638 |
+
"128079": {
|
639 |
+
"content": "<|reserved_special_token_71|>",
|
640 |
+
"lstrip": false,
|
641 |
+
"normalized": false,
|
642 |
+
"rstrip": false,
|
643 |
+
"single_word": false,
|
644 |
+
"special": true
|
645 |
+
},
|
646 |
+
"128080": {
|
647 |
+
"content": "<|reserved_special_token_72|>",
|
648 |
+
"lstrip": false,
|
649 |
+
"normalized": false,
|
650 |
+
"rstrip": false,
|
651 |
+
"single_word": false,
|
652 |
+
"special": true
|
653 |
+
},
|
654 |
+
"128081": {
|
655 |
+
"content": "<|reserved_special_token_73|>",
|
656 |
+
"lstrip": false,
|
657 |
+
"normalized": false,
|
658 |
+
"rstrip": false,
|
659 |
+
"single_word": false,
|
660 |
+
"special": true
|
661 |
+
},
|
662 |
+
"128082": {
|
663 |
+
"content": "<|reserved_special_token_74|>",
|
664 |
+
"lstrip": false,
|
665 |
+
"normalized": false,
|
666 |
+
"rstrip": false,
|
667 |
+
"single_word": false,
|
668 |
+
"special": true
|
669 |
+
},
|
670 |
+
"128083": {
|
671 |
+
"content": "<|reserved_special_token_75|>",
|
672 |
+
"lstrip": false,
|
673 |
+
"normalized": false,
|
674 |
+
"rstrip": false,
|
675 |
+
"single_word": false,
|
676 |
+
"special": true
|
677 |
+
},
|
678 |
+
"128084": {
|
679 |
+
"content": "<|reserved_special_token_76|>",
|
680 |
+
"lstrip": false,
|
681 |
+
"normalized": false,
|
682 |
+
"rstrip": false,
|
683 |
+
"single_word": false,
|
684 |
+
"special": true
|
685 |
+
},
|
686 |
+
"128085": {
|
687 |
+
"content": "<|reserved_special_token_77|>",
|
688 |
+
"lstrip": false,
|
689 |
+
"normalized": false,
|
690 |
+
"rstrip": false,
|
691 |
+
"single_word": false,
|
692 |
+
"special": true
|
693 |
+
},
|
694 |
+
"128086": {
|
695 |
+
"content": "<|reserved_special_token_78|>",
|
696 |
+
"lstrip": false,
|
697 |
+
"normalized": false,
|
698 |
+
"rstrip": false,
|
699 |
+
"single_word": false,
|
700 |
+
"special": true
|
701 |
+
},
|
702 |
+
"128087": {
|
703 |
+
"content": "<|reserved_special_token_79|>",
|
704 |
+
"lstrip": false,
|
705 |
+
"normalized": false,
|
706 |
+
"rstrip": false,
|
707 |
+
"single_word": false,
|
708 |
+
"special": true
|
709 |
+
},
|
710 |
+
"128088": {
|
711 |
+
"content": "<|reserved_special_token_80|>",
|
712 |
+
"lstrip": false,
|
713 |
+
"normalized": false,
|
714 |
+
"rstrip": false,
|
715 |
+
"single_word": false,
|
716 |
+
"special": true
|
717 |
+
},
|
718 |
+
"128089": {
|
719 |
+
"content": "<|reserved_special_token_81|>",
|
720 |
+
"lstrip": false,
|
721 |
+
"normalized": false,
|
722 |
+
"rstrip": false,
|
723 |
+
"single_word": false,
|
724 |
+
"special": true
|
725 |
+
},
|
726 |
+
"128090": {
|
727 |
+
"content": "<|reserved_special_token_82|>",
|
728 |
+
"lstrip": false,
|
729 |
+
"normalized": false,
|
730 |
+
"rstrip": false,
|
731 |
+
"single_word": false,
|
732 |
+
"special": true
|
733 |
+
},
|
734 |
+
"128091": {
|
735 |
+
"content": "<|reserved_special_token_83|>",
|
736 |
+
"lstrip": false,
|
737 |
+
"normalized": false,
|
738 |
+
"rstrip": false,
|
739 |
+
"single_word": false,
|
740 |
+
"special": true
|
741 |
+
},
|
742 |
+
"128092": {
|
743 |
+
"content": "<|reserved_special_token_84|>",
|
744 |
+
"lstrip": false,
|
745 |
+
"normalized": false,
|
746 |
+
"rstrip": false,
|
747 |
+
"single_word": false,
|
748 |
+
"special": true
|
749 |
+
},
|
750 |
+
"128093": {
|
751 |
+
"content": "<|reserved_special_token_85|>",
|
752 |
+
"lstrip": false,
|
753 |
+
"normalized": false,
|
754 |
+
"rstrip": false,
|
755 |
+
"single_word": false,
|
756 |
+
"special": true
|
757 |
+
},
|
758 |
+
"128094": {
|
759 |
+
"content": "<|reserved_special_token_86|>",
|
760 |
+
"lstrip": false,
|
761 |
+
"normalized": false,
|
762 |
+
"rstrip": false,
|
763 |
+
"single_word": false,
|
764 |
+
"special": true
|
765 |
+
},
|
766 |
+
"128095": {
|
767 |
+
"content": "<|reserved_special_token_87|>",
|
768 |
+
"lstrip": false,
|
769 |
+
"normalized": false,
|
770 |
+
"rstrip": false,
|
771 |
+
"single_word": false,
|
772 |
+
"special": true
|
773 |
+
},
|
774 |
+
"128096": {
|
775 |
+
"content": "<|reserved_special_token_88|>",
|
776 |
+
"lstrip": false,
|
777 |
+
"normalized": false,
|
778 |
+
"rstrip": false,
|
779 |
+
"single_word": false,
|
780 |
+
"special": true
|
781 |
+
},
|
782 |
+
"128097": {
|
783 |
+
"content": "<|reserved_special_token_89|>",
|
784 |
+
"lstrip": false,
|
785 |
+
"normalized": false,
|
786 |
+
"rstrip": false,
|
787 |
+
"single_word": false,
|
788 |
+
"special": true
|
789 |
+
},
|
790 |
+
"128098": {
|
791 |
+
"content": "<|reserved_special_token_90|>",
|
792 |
+
"lstrip": false,
|
793 |
+
"normalized": false,
|
794 |
+
"rstrip": false,
|
795 |
+
"single_word": false,
|
796 |
+
"special": true
|
797 |
+
},
|
798 |
+
"128099": {
|
799 |
+
"content": "<|reserved_special_token_91|>",
|
800 |
+
"lstrip": false,
|
801 |
+
"normalized": false,
|
802 |
+
"rstrip": false,
|
803 |
+
"single_word": false,
|
804 |
+
"special": true
|
805 |
+
},
|
806 |
+
"128100": {
|
807 |
+
"content": "<|reserved_special_token_92|>",
|
808 |
+
"lstrip": false,
|
809 |
+
"normalized": false,
|
810 |
+
"rstrip": false,
|
811 |
+
"single_word": false,
|
812 |
+
"special": true
|
813 |
+
},
|
814 |
+
"128101": {
|
815 |
+
"content": "<|reserved_special_token_93|>",
|
816 |
+
"lstrip": false,
|
817 |
+
"normalized": false,
|
818 |
+
"rstrip": false,
|
819 |
+
"single_word": false,
|
820 |
+
"special": true
|
821 |
+
},
|
822 |
+
"128102": {
|
823 |
+
"content": "<|reserved_special_token_94|>",
|
824 |
+
"lstrip": false,
|
825 |
+
"normalized": false,
|
826 |
+
"rstrip": false,
|
827 |
+
"single_word": false,
|
828 |
+
"special": true
|
829 |
+
},
|
830 |
+
"128103": {
|
831 |
+
"content": "<|reserved_special_token_95|>",
|
832 |
+
"lstrip": false,
|
833 |
+
"normalized": false,
|
834 |
+
"rstrip": false,
|
835 |
+
"single_word": false,
|
836 |
+
"special": true
|
837 |
+
},
|
838 |
+
"128104": {
|
839 |
+
"content": "<|reserved_special_token_96|>",
|
840 |
+
"lstrip": false,
|
841 |
+
"normalized": false,
|
842 |
+
"rstrip": false,
|
843 |
+
"single_word": false,
|
844 |
+
"special": true
|
845 |
+
},
|
846 |
+
"128105": {
|
847 |
+
"content": "<|reserved_special_token_97|>",
|
848 |
+
"lstrip": false,
|
849 |
+
"normalized": false,
|
850 |
+
"rstrip": false,
|
851 |
+
"single_word": false,
|
852 |
+
"special": true
|
853 |
+
},
|
854 |
+
"128106": {
|
855 |
+
"content": "<|reserved_special_token_98|>",
|
856 |
+
"lstrip": false,
|
857 |
+
"normalized": false,
|
858 |
+
"rstrip": false,
|
859 |
+
"single_word": false,
|
860 |
+
"special": true
|
861 |
+
},
|
862 |
+
"128107": {
|
863 |
+
"content": "<|reserved_special_token_99|>",
|
864 |
+
"lstrip": false,
|
865 |
+
"normalized": false,
|
866 |
+
"rstrip": false,
|
867 |
+
"single_word": false,
|
868 |
+
"special": true
|
869 |
+
},
|
870 |
+
"128108": {
|
871 |
+
"content": "<|reserved_special_token_100|>",
|
872 |
+
"lstrip": false,
|
873 |
+
"normalized": false,
|
874 |
+
"rstrip": false,
|
875 |
+
"single_word": false,
|
876 |
+
"special": true
|
877 |
+
},
|
878 |
+
"128109": {
|
879 |
+
"content": "<|reserved_special_token_101|>",
|
880 |
+
"lstrip": false,
|
881 |
+
"normalized": false,
|
882 |
+
"rstrip": false,
|
883 |
+
"single_word": false,
|
884 |
+
"special": true
|
885 |
+
},
|
886 |
+
"128110": {
|
887 |
+
"content": "<|reserved_special_token_102|>",
|
888 |
+
"lstrip": false,
|
889 |
+
"normalized": false,
|
890 |
+
"rstrip": false,
|
891 |
+
"single_word": false,
|
892 |
+
"special": true
|
893 |
+
},
|
894 |
+
"128111": {
|
895 |
+
"content": "<|reserved_special_token_103|>",
|
896 |
+
"lstrip": false,
|
897 |
+
"normalized": false,
|
898 |
+
"rstrip": false,
|
899 |
+
"single_word": false,
|
900 |
+
"special": true
|
901 |
+
},
|
902 |
+
"128112": {
|
903 |
+
"content": "<|reserved_special_token_104|>",
|
904 |
+
"lstrip": false,
|
905 |
+
"normalized": false,
|
906 |
+
"rstrip": false,
|
907 |
+
"single_word": false,
|
908 |
+
"special": true
|
909 |
+
},
|
910 |
+
"128113": {
|
911 |
+
"content": "<|reserved_special_token_105|>",
|
912 |
+
"lstrip": false,
|
913 |
+
"normalized": false,
|
914 |
+
"rstrip": false,
|
915 |
+
"single_word": false,
|
916 |
+
"special": true
|
917 |
+
},
|
918 |
+
"128114": {
|
919 |
+
"content": "<|reserved_special_token_106|>",
|
920 |
+
"lstrip": false,
|
921 |
+
"normalized": false,
|
922 |
+
"rstrip": false,
|
923 |
+
"single_word": false,
|
924 |
+
"special": true
|
925 |
+
},
|
926 |
+
"128115": {
|
927 |
+
"content": "<|reserved_special_token_107|>",
|
928 |
+
"lstrip": false,
|
929 |
+
"normalized": false,
|
930 |
+
"rstrip": false,
|
931 |
+
"single_word": false,
|
932 |
+
"special": true
|
933 |
+
},
|
934 |
+
"128116": {
|
935 |
+
"content": "<|reserved_special_token_108|>",
|
936 |
+
"lstrip": false,
|
937 |
+
"normalized": false,
|
938 |
+
"rstrip": false,
|
939 |
+
"single_word": false,
|
940 |
+
"special": true
|
941 |
+
},
|
942 |
+
"128117": {
|
943 |
+
"content": "<|reserved_special_token_109|>",
|
944 |
+
"lstrip": false,
|
945 |
+
"normalized": false,
|
946 |
+
"rstrip": false,
|
947 |
+
"single_word": false,
|
948 |
+
"special": true
|
949 |
+
},
|
950 |
+
"128118": {
|
951 |
+
"content": "<|reserved_special_token_110|>",
|
952 |
+
"lstrip": false,
|
953 |
+
"normalized": false,
|
954 |
+
"rstrip": false,
|
955 |
+
"single_word": false,
|
956 |
+
"special": true
|
957 |
+
},
|
958 |
+
"128119": {
|
959 |
+
"content": "<|reserved_special_token_111|>",
|
960 |
+
"lstrip": false,
|
961 |
+
"normalized": false,
|
962 |
+
"rstrip": false,
|
963 |
+
"single_word": false,
|
964 |
+
"special": true
|
965 |
+
},
|
966 |
+
"128120": {
|
967 |
+
"content": "<|reserved_special_token_112|>",
|
968 |
+
"lstrip": false,
|
969 |
+
"normalized": false,
|
970 |
+
"rstrip": false,
|
971 |
+
"single_word": false,
|
972 |
+
"special": true
|
973 |
+
},
|
974 |
+
"128121": {
|
975 |
+
"content": "<|reserved_special_token_113|>",
|
976 |
+
"lstrip": false,
|
977 |
+
"normalized": false,
|
978 |
+
"rstrip": false,
|
979 |
+
"single_word": false,
|
980 |
+
"special": true
|
981 |
+
},
|
982 |
+
"128122": {
|
983 |
+
"content": "<|reserved_special_token_114|>",
|
984 |
+
"lstrip": false,
|
985 |
+
"normalized": false,
|
986 |
+
"rstrip": false,
|
987 |
+
"single_word": false,
|
988 |
+
"special": true
|
989 |
+
},
|
990 |
+
"128123": {
|
991 |
+
"content": "<|reserved_special_token_115|>",
|
992 |
+
"lstrip": false,
|
993 |
+
"normalized": false,
|
994 |
+
"rstrip": false,
|
995 |
+
"single_word": false,
|
996 |
+
"special": true
|
997 |
+
},
|
998 |
+
"128124": {
|
999 |
+
"content": "<|reserved_special_token_116|>",
|
1000 |
+
"lstrip": false,
|
1001 |
+
"normalized": false,
|
1002 |
+
"rstrip": false,
|
1003 |
+
"single_word": false,
|
1004 |
+
"special": true
|
1005 |
+
},
|
1006 |
+
"128125": {
|
1007 |
+
"content": "<|reserved_special_token_117|>",
|
1008 |
+
"lstrip": false,
|
1009 |
+
"normalized": false,
|
1010 |
+
"rstrip": false,
|
1011 |
+
"single_word": false,
|
1012 |
+
"special": true
|
1013 |
+
},
|
1014 |
+
"128126": {
|
1015 |
+
"content": "<|reserved_special_token_118|>",
|
1016 |
+
"lstrip": false,
|
1017 |
+
"normalized": false,
|
1018 |
+
"rstrip": false,
|
1019 |
+
"single_word": false,
|
1020 |
+
"special": true
|
1021 |
+
},
|
1022 |
+
"128127": {
|
1023 |
+
"content": "<|reserved_special_token_119|>",
|
1024 |
+
"lstrip": false,
|
1025 |
+
"normalized": false,
|
1026 |
+
"rstrip": false,
|
1027 |
+
"single_word": false,
|
1028 |
+
"special": true
|
1029 |
+
},
|
1030 |
+
"128128": {
|
1031 |
+
"content": "<|reserved_special_token_120|>",
|
1032 |
+
"lstrip": false,
|
1033 |
+
"normalized": false,
|
1034 |
+
"rstrip": false,
|
1035 |
+
"single_word": false,
|
1036 |
+
"special": true
|
1037 |
+
},
|
1038 |
+
"128129": {
|
1039 |
+
"content": "<|reserved_special_token_121|>",
|
1040 |
+
"lstrip": false,
|
1041 |
+
"normalized": false,
|
1042 |
+
"rstrip": false,
|
1043 |
+
"single_word": false,
|
1044 |
+
"special": true
|
1045 |
+
},
|
1046 |
+
"128130": {
|
1047 |
+
"content": "<|reserved_special_token_122|>",
|
1048 |
+
"lstrip": false,
|
1049 |
+
"normalized": false,
|
1050 |
+
"rstrip": false,
|
1051 |
+
"single_word": false,
|
1052 |
+
"special": true
|
1053 |
+
},
|
1054 |
+
"128131": {
|
1055 |
+
"content": "<|reserved_special_token_123|>",
|
1056 |
+
"lstrip": false,
|
1057 |
+
"normalized": false,
|
1058 |
+
"rstrip": false,
|
1059 |
+
"single_word": false,
|
1060 |
+
"special": true
|
1061 |
+
},
|
1062 |
+
"128132": {
|
1063 |
+
"content": "<|reserved_special_token_124|>",
|
1064 |
+
"lstrip": false,
|
1065 |
+
"normalized": false,
|
1066 |
+
"rstrip": false,
|
1067 |
+
"single_word": false,
|
1068 |
+
"special": true
|
1069 |
+
},
|
1070 |
+
"128133": {
|
1071 |
+
"content": "<|reserved_special_token_125|>",
|
1072 |
+
"lstrip": false,
|
1073 |
+
"normalized": false,
|
1074 |
+
"rstrip": false,
|
1075 |
+
"single_word": false,
|
1076 |
+
"special": true
|
1077 |
+
},
|
1078 |
+
"128134": {
|
1079 |
+
"content": "<|reserved_special_token_126|>",
|
1080 |
+
"lstrip": false,
|
1081 |
+
"normalized": false,
|
1082 |
+
"rstrip": false,
|
1083 |
+
"single_word": false,
|
1084 |
+
"special": true
|
1085 |
+
},
|
1086 |
+
"128135": {
|
1087 |
+
"content": "<|reserved_special_token_127|>",
|
1088 |
+
"lstrip": false,
|
1089 |
+
"normalized": false,
|
1090 |
+
"rstrip": false,
|
1091 |
+
"single_word": false,
|
1092 |
+
"special": true
|
1093 |
+
},
|
1094 |
+
"128136": {
|
1095 |
+
"content": "<|reserved_special_token_128|>",
|
1096 |
+
"lstrip": false,
|
1097 |
+
"normalized": false,
|
1098 |
+
"rstrip": false,
|
1099 |
+
"single_word": false,
|
1100 |
+
"special": true
|
1101 |
+
},
|
1102 |
+
"128137": {
|
1103 |
+
"content": "<|reserved_special_token_129|>",
|
1104 |
+
"lstrip": false,
|
1105 |
+
"normalized": false,
|
1106 |
+
"rstrip": false,
|
1107 |
+
"single_word": false,
|
1108 |
+
"special": true
|
1109 |
+
},
|
1110 |
+
"128138": {
|
1111 |
+
"content": "<|reserved_special_token_130|>",
|
1112 |
+
"lstrip": false,
|
1113 |
+
"normalized": false,
|
1114 |
+
"rstrip": false,
|
1115 |
+
"single_word": false,
|
1116 |
+
"special": true
|
1117 |
+
},
|
1118 |
+
"128139": {
|
1119 |
+
"content": "<|reserved_special_token_131|>",
|
1120 |
+
"lstrip": false,
|
1121 |
+
"normalized": false,
|
1122 |
+
"rstrip": false,
|
1123 |
+
"single_word": false,
|
1124 |
+
"special": true
|
1125 |
+
},
|
1126 |
+
"128140": {
|
1127 |
+
"content": "<|reserved_special_token_132|>",
|
1128 |
+
"lstrip": false,
|
1129 |
+
"normalized": false,
|
1130 |
+
"rstrip": false,
|
1131 |
+
"single_word": false,
|
1132 |
+
"special": true
|
1133 |
+
},
|
1134 |
+
"128141": {
|
1135 |
+
"content": "<|reserved_special_token_133|>",
|
1136 |
+
"lstrip": false,
|
1137 |
+
"normalized": false,
|
1138 |
+
"rstrip": false,
|
1139 |
+
"single_word": false,
|
1140 |
+
"special": true
|
1141 |
+
},
|
1142 |
+
"128142": {
|
1143 |
+
"content": "<|reserved_special_token_134|>",
|
1144 |
+
"lstrip": false,
|
1145 |
+
"normalized": false,
|
1146 |
+
"rstrip": false,
|
1147 |
+
"single_word": false,
|
1148 |
+
"special": true
|
1149 |
+
},
|
1150 |
+
"128143": {
|
1151 |
+
"content": "<|reserved_special_token_135|>",
|
1152 |
+
"lstrip": false,
|
1153 |
+
"normalized": false,
|
1154 |
+
"rstrip": false,
|
1155 |
+
"single_word": false,
|
1156 |
+
"special": true
|
1157 |
+
},
|
1158 |
+
"128144": {
|
1159 |
+
"content": "<|reserved_special_token_136|>",
|
1160 |
+
"lstrip": false,
|
1161 |
+
"normalized": false,
|
1162 |
+
"rstrip": false,
|
1163 |
+
"single_word": false,
|
1164 |
+
"special": true
|
1165 |
+
},
|
1166 |
+
"128145": {
|
1167 |
+
"content": "<|reserved_special_token_137|>",
|
1168 |
+
"lstrip": false,
|
1169 |
+
"normalized": false,
|
1170 |
+
"rstrip": false,
|
1171 |
+
"single_word": false,
|
1172 |
+
"special": true
|
1173 |
+
},
|
1174 |
+
"128146": {
|
1175 |
+
"content": "<|reserved_special_token_138|>",
|
1176 |
+
"lstrip": false,
|
1177 |
+
"normalized": false,
|
1178 |
+
"rstrip": false,
|
1179 |
+
"single_word": false,
|
1180 |
+
"special": true
|
1181 |
+
},
|
1182 |
+
"128147": {
|
1183 |
+
"content": "<|reserved_special_token_139|>",
|
1184 |
+
"lstrip": false,
|
1185 |
+
"normalized": false,
|
1186 |
+
"rstrip": false,
|
1187 |
+
"single_word": false,
|
1188 |
+
"special": true
|
1189 |
+
},
|
1190 |
+
"128148": {
|
1191 |
+
"content": "<|reserved_special_token_140|>",
|
1192 |
+
"lstrip": false,
|
1193 |
+
"normalized": false,
|
1194 |
+
"rstrip": false,
|
1195 |
+
"single_word": false,
|
1196 |
+
"special": true
|
1197 |
+
},
|
1198 |
+
"128149": {
|
1199 |
+
"content": "<|reserved_special_token_141|>",
|
1200 |
+
"lstrip": false,
|
1201 |
+
"normalized": false,
|
1202 |
+
"rstrip": false,
|
1203 |
+
"single_word": false,
|
1204 |
+
"special": true
|
1205 |
+
},
|
1206 |
+
"128150": {
|
1207 |
+
"content": "<|reserved_special_token_142|>",
|
1208 |
+
"lstrip": false,
|
1209 |
+
"normalized": false,
|
1210 |
+
"rstrip": false,
|
1211 |
+
"single_word": false,
|
1212 |
+
"special": true
|
1213 |
+
},
|
1214 |
+
"128151": {
|
1215 |
+
"content": "<|reserved_special_token_143|>",
|
1216 |
+
"lstrip": false,
|
1217 |
+
"normalized": false,
|
1218 |
+
"rstrip": false,
|
1219 |
+
"single_word": false,
|
1220 |
+
"special": true
|
1221 |
+
},
|
1222 |
+
"128152": {
|
1223 |
+
"content": "<|reserved_special_token_144|>",
|
1224 |
+
"lstrip": false,
|
1225 |
+
"normalized": false,
|
1226 |
+
"rstrip": false,
|
1227 |
+
"single_word": false,
|
1228 |
+
"special": true
|
1229 |
+
},
|
1230 |
+
"128153": {
|
1231 |
+
"content": "<|reserved_special_token_145|>",
|
1232 |
+
"lstrip": false,
|
1233 |
+
"normalized": false,
|
1234 |
+
"rstrip": false,
|
1235 |
+
"single_word": false,
|
1236 |
+
"special": true
|
1237 |
+
},
|
1238 |
+
"128154": {
|
1239 |
+
"content": "<|reserved_special_token_146|>",
|
1240 |
+
"lstrip": false,
|
1241 |
+
"normalized": false,
|
1242 |
+
"rstrip": false,
|
1243 |
+
"single_word": false,
|
1244 |
+
"special": true
|
1245 |
+
},
|
1246 |
+
"128155": {
|
1247 |
+
"content": "<|reserved_special_token_147|>",
|
1248 |
+
"lstrip": false,
|
1249 |
+
"normalized": false,
|
1250 |
+
"rstrip": false,
|
1251 |
+
"single_word": false,
|
1252 |
+
"special": true
|
1253 |
+
},
|
1254 |
+
"128156": {
|
1255 |
+
"content": "<|reserved_special_token_148|>",
|
1256 |
+
"lstrip": false,
|
1257 |
+
"normalized": false,
|
1258 |
+
"rstrip": false,
|
1259 |
+
"single_word": false,
|
1260 |
+
"special": true
|
1261 |
+
},
|
1262 |
+
"128157": {
|
1263 |
+
"content": "<|reserved_special_token_149|>",
|
1264 |
+
"lstrip": false,
|
1265 |
+
"normalized": false,
|
1266 |
+
"rstrip": false,
|
1267 |
+
"single_word": false,
|
1268 |
+
"special": true
|
1269 |
+
},
|
1270 |
+
"128158": {
|
1271 |
+
"content": "<|reserved_special_token_150|>",
|
1272 |
+
"lstrip": false,
|
1273 |
+
"normalized": false,
|
1274 |
+
"rstrip": false,
|
1275 |
+
"single_word": false,
|
1276 |
+
"special": true
|
1277 |
+
},
|
1278 |
+
"128159": {
|
1279 |
+
"content": "<|reserved_special_token_151|>",
|
1280 |
+
"lstrip": false,
|
1281 |
+
"normalized": false,
|
1282 |
+
"rstrip": false,
|
1283 |
+
"single_word": false,
|
1284 |
+
"special": true
|
1285 |
+
},
|
1286 |
+
"128160": {
|
1287 |
+
"content": "<|reserved_special_token_152|>",
|
1288 |
+
"lstrip": false,
|
1289 |
+
"normalized": false,
|
1290 |
+
"rstrip": false,
|
1291 |
+
"single_word": false,
|
1292 |
+
"special": true
|
1293 |
+
},
|
1294 |
+
"128161": {
|
1295 |
+
"content": "<|reserved_special_token_153|>",
|
1296 |
+
"lstrip": false,
|
1297 |
+
"normalized": false,
|
1298 |
+
"rstrip": false,
|
1299 |
+
"single_word": false,
|
1300 |
+
"special": true
|
1301 |
+
},
|
1302 |
+
"128162": {
|
1303 |
+
"content": "<|reserved_special_token_154|>",
|
1304 |
+
"lstrip": false,
|
1305 |
+
"normalized": false,
|
1306 |
+
"rstrip": false,
|
1307 |
+
"single_word": false,
|
1308 |
+
"special": true
|
1309 |
+
},
|
1310 |
+
"128163": {
|
1311 |
+
"content": "<|reserved_special_token_155|>",
|
1312 |
+
"lstrip": false,
|
1313 |
+
"normalized": false,
|
1314 |
+
"rstrip": false,
|
1315 |
+
"single_word": false,
|
1316 |
+
"special": true
|
1317 |
+
},
|
1318 |
+
"128164": {
|
1319 |
+
"content": "<|reserved_special_token_156|>",
|
1320 |
+
"lstrip": false,
|
1321 |
+
"normalized": false,
|
1322 |
+
"rstrip": false,
|
1323 |
+
"single_word": false,
|
1324 |
+
"special": true
|
1325 |
+
},
|
1326 |
+
"128165": {
|
1327 |
+
"content": "<|reserved_special_token_157|>",
|
1328 |
+
"lstrip": false,
|
1329 |
+
"normalized": false,
|
1330 |
+
"rstrip": false,
|
1331 |
+
"single_word": false,
|
1332 |
+
"special": true
|
1333 |
+
},
|
1334 |
+
"128166": {
|
1335 |
+
"content": "<|reserved_special_token_158|>",
|
1336 |
+
"lstrip": false,
|
1337 |
+
"normalized": false,
|
1338 |
+
"rstrip": false,
|
1339 |
+
"single_word": false,
|
1340 |
+
"special": true
|
1341 |
+
},
|
1342 |
+
"128167": {
|
1343 |
+
"content": "<|reserved_special_token_159|>",
|
1344 |
+
"lstrip": false,
|
1345 |
+
"normalized": false,
|
1346 |
+
"rstrip": false,
|
1347 |
+
"single_word": false,
|
1348 |
+
"special": true
|
1349 |
+
},
|
1350 |
+
"128168": {
|
1351 |
+
"content": "<|reserved_special_token_160|>",
|
1352 |
+
"lstrip": false,
|
1353 |
+
"normalized": false,
|
1354 |
+
"rstrip": false,
|
1355 |
+
"single_word": false,
|
1356 |
+
"special": true
|
1357 |
+
},
|
1358 |
+
"128169": {
|
1359 |
+
"content": "<|reserved_special_token_161|>",
|
1360 |
+
"lstrip": false,
|
1361 |
+
"normalized": false,
|
1362 |
+
"rstrip": false,
|
1363 |
+
"single_word": false,
|
1364 |
+
"special": true
|
1365 |
+
},
|
1366 |
+
"128170": {
|
1367 |
+
"content": "<|reserved_special_token_162|>",
|
1368 |
+
"lstrip": false,
|
1369 |
+
"normalized": false,
|
1370 |
+
"rstrip": false,
|
1371 |
+
"single_word": false,
|
1372 |
+
"special": true
|
1373 |
+
},
|
1374 |
+
"128171": {
|
1375 |
+
"content": "<|reserved_special_token_163|>",
|
1376 |
+
"lstrip": false,
|
1377 |
+
"normalized": false,
|
1378 |
+
"rstrip": false,
|
1379 |
+
"single_word": false,
|
1380 |
+
"special": true
|
1381 |
+
},
|
1382 |
+
"128172": {
|
1383 |
+
"content": "<|reserved_special_token_164|>",
|
1384 |
+
"lstrip": false,
|
1385 |
+
"normalized": false,
|
1386 |
+
"rstrip": false,
|
1387 |
+
"single_word": false,
|
1388 |
+
"special": true
|
1389 |
+
},
|
1390 |
+
"128173": {
|
1391 |
+
"content": "<|reserved_special_token_165|>",
|
1392 |
+
"lstrip": false,
|
1393 |
+
"normalized": false,
|
1394 |
+
"rstrip": false,
|
1395 |
+
"single_word": false,
|
1396 |
+
"special": true
|
1397 |
+
},
|
1398 |
+
"128174": {
|
1399 |
+
"content": "<|reserved_special_token_166|>",
|
1400 |
+
"lstrip": false,
|
1401 |
+
"normalized": false,
|
1402 |
+
"rstrip": false,
|
1403 |
+
"single_word": false,
|
1404 |
+
"special": true
|
1405 |
+
},
|
1406 |
+
"128175": {
|
1407 |
+
"content": "<|reserved_special_token_167|>",
|
1408 |
+
"lstrip": false,
|
1409 |
+
"normalized": false,
|
1410 |
+
"rstrip": false,
|
1411 |
+
"single_word": false,
|
1412 |
+
"special": true
|
1413 |
+
},
|
1414 |
+
"128176": {
|
1415 |
+
"content": "<|reserved_special_token_168|>",
|
1416 |
+
"lstrip": false,
|
1417 |
+
"normalized": false,
|
1418 |
+
"rstrip": false,
|
1419 |
+
"single_word": false,
|
1420 |
+
"special": true
|
1421 |
+
},
|
1422 |
+
"128177": {
|
1423 |
+
"content": "<|reserved_special_token_169|>",
|
1424 |
+
"lstrip": false,
|
1425 |
+
"normalized": false,
|
1426 |
+
"rstrip": false,
|
1427 |
+
"single_word": false,
|
1428 |
+
"special": true
|
1429 |
+
},
|
1430 |
+
"128178": {
|
1431 |
+
"content": "<|reserved_special_token_170|>",
|
1432 |
+
"lstrip": false,
|
1433 |
+
"normalized": false,
|
1434 |
+
"rstrip": false,
|
1435 |
+
"single_word": false,
|
1436 |
+
"special": true
|
1437 |
+
},
|
1438 |
+
"128179": {
|
1439 |
+
"content": "<|reserved_special_token_171|>",
|
1440 |
+
"lstrip": false,
|
1441 |
+
"normalized": false,
|
1442 |
+
"rstrip": false,
|
1443 |
+
"single_word": false,
|
1444 |
+
"special": true
|
1445 |
+
},
|
1446 |
+
"128180": {
|
1447 |
+
"content": "<|reserved_special_token_172|>",
|
1448 |
+
"lstrip": false,
|
1449 |
+
"normalized": false,
|
1450 |
+
"rstrip": false,
|
1451 |
+
"single_word": false,
|
1452 |
+
"special": true
|
1453 |
+
},
|
1454 |
+
"128181": {
|
1455 |
+
"content": "<|reserved_special_token_173|>",
|
1456 |
+
"lstrip": false,
|
1457 |
+
"normalized": false,
|
1458 |
+
"rstrip": false,
|
1459 |
+
"single_word": false,
|
1460 |
+
"special": true
|
1461 |
+
},
|
1462 |
+
"128182": {
|
1463 |
+
"content": "<|reserved_special_token_174|>",
|
1464 |
+
"lstrip": false,
|
1465 |
+
"normalized": false,
|
1466 |
+
"rstrip": false,
|
1467 |
+
"single_word": false,
|
1468 |
+
"special": true
|
1469 |
+
},
|
1470 |
+
"128183": {
|
1471 |
+
"content": "<|reserved_special_token_175|>",
|
1472 |
+
"lstrip": false,
|
1473 |
+
"normalized": false,
|
1474 |
+
"rstrip": false,
|
1475 |
+
"single_word": false,
|
1476 |
+
"special": true
|
1477 |
+
},
|
1478 |
+
"128184": {
|
1479 |
+
"content": "<|reserved_special_token_176|>",
|
1480 |
+
"lstrip": false,
|
1481 |
+
"normalized": false,
|
1482 |
+
"rstrip": false,
|
1483 |
+
"single_word": false,
|
1484 |
+
"special": true
|
1485 |
+
},
|
1486 |
+
"128185": {
|
1487 |
+
"content": "<|reserved_special_token_177|>",
|
1488 |
+
"lstrip": false,
|
1489 |
+
"normalized": false,
|
1490 |
+
"rstrip": false,
|
1491 |
+
"single_word": false,
|
1492 |
+
"special": true
|
1493 |
+
},
|
1494 |
+
"128186": {
|
1495 |
+
"content": "<|reserved_special_token_178|>",
|
1496 |
+
"lstrip": false,
|
1497 |
+
"normalized": false,
|
1498 |
+
"rstrip": false,
|
1499 |
+
"single_word": false,
|
1500 |
+
"special": true
|
1501 |
+
},
|
1502 |
+
"128187": {
|
1503 |
+
"content": "<|reserved_special_token_179|>",
|
1504 |
+
"lstrip": false,
|
1505 |
+
"normalized": false,
|
1506 |
+
"rstrip": false,
|
1507 |
+
"single_word": false,
|
1508 |
+
"special": true
|
1509 |
+
},
|
1510 |
+
"128188": {
|
1511 |
+
"content": "<|reserved_special_token_180|>",
|
1512 |
+
"lstrip": false,
|
1513 |
+
"normalized": false,
|
1514 |
+
"rstrip": false,
|
1515 |
+
"single_word": false,
|
1516 |
+
"special": true
|
1517 |
+
},
|
1518 |
+
"128189": {
|
1519 |
+
"content": "<|reserved_special_token_181|>",
|
1520 |
+
"lstrip": false,
|
1521 |
+
"normalized": false,
|
1522 |
+
"rstrip": false,
|
1523 |
+
"single_word": false,
|
1524 |
+
"special": true
|
1525 |
+
},
|
1526 |
+
"128190": {
|
1527 |
+
"content": "<|reserved_special_token_182|>",
|
1528 |
+
"lstrip": false,
|
1529 |
+
"normalized": false,
|
1530 |
+
"rstrip": false,
|
1531 |
+
"single_word": false,
|
1532 |
+
"special": true
|
1533 |
+
},
|
1534 |
+
"128191": {
|
1535 |
+
"content": "<|reserved_special_token_183|>",
|
1536 |
+
"lstrip": false,
|
1537 |
+
"normalized": false,
|
1538 |
+
"rstrip": false,
|
1539 |
+
"single_word": false,
|
1540 |
+
"special": true
|
1541 |
+
},
|
1542 |
+
"128192": {
|
1543 |
+
"content": "<|reserved_special_token_184|>",
|
1544 |
+
"lstrip": false,
|
1545 |
+
"normalized": false,
|
1546 |
+
"rstrip": false,
|
1547 |
+
"single_word": false,
|
1548 |
+
"special": true
|
1549 |
+
},
|
1550 |
+
"128193": {
|
1551 |
+
"content": "<|reserved_special_token_185|>",
|
1552 |
+
"lstrip": false,
|
1553 |
+
"normalized": false,
|
1554 |
+
"rstrip": false,
|
1555 |
+
"single_word": false,
|
1556 |
+
"special": true
|
1557 |
+
},
|
1558 |
+
"128194": {
|
1559 |
+
"content": "<|reserved_special_token_186|>",
|
1560 |
+
"lstrip": false,
|
1561 |
+
"normalized": false,
|
1562 |
+
"rstrip": false,
|
1563 |
+
"single_word": false,
|
1564 |
+
"special": true
|
1565 |
+
},
|
1566 |
+
"128195": {
|
1567 |
+
"content": "<|reserved_special_token_187|>",
|
1568 |
+
"lstrip": false,
|
1569 |
+
"normalized": false,
|
1570 |
+
"rstrip": false,
|
1571 |
+
"single_word": false,
|
1572 |
+
"special": true
|
1573 |
+
},
|
1574 |
+
"128196": {
|
1575 |
+
"content": "<|reserved_special_token_188|>",
|
1576 |
+
"lstrip": false,
|
1577 |
+
"normalized": false,
|
1578 |
+
"rstrip": false,
|
1579 |
+
"single_word": false,
|
1580 |
+
"special": true
|
1581 |
+
},
|
1582 |
+
"128197": {
|
1583 |
+
"content": "<|reserved_special_token_189|>",
|
1584 |
+
"lstrip": false,
|
1585 |
+
"normalized": false,
|
1586 |
+
"rstrip": false,
|
1587 |
+
"single_word": false,
|
1588 |
+
"special": true
|
1589 |
+
},
|
1590 |
+
"128198": {
|
1591 |
+
"content": "<|reserved_special_token_190|>",
|
1592 |
+
"lstrip": false,
|
1593 |
+
"normalized": false,
|
1594 |
+
"rstrip": false,
|
1595 |
+
"single_word": false,
|
1596 |
+
"special": true
|
1597 |
+
},
|
1598 |
+
"128199": {
|
1599 |
+
"content": "<|reserved_special_token_191|>",
|
1600 |
+
"lstrip": false,
|
1601 |
+
"normalized": false,
|
1602 |
+
"rstrip": false,
|
1603 |
+
"single_word": false,
|
1604 |
+
"special": true
|
1605 |
+
},
|
1606 |
+
"128200": {
|
1607 |
+
"content": "<|reserved_special_token_192|>",
|
1608 |
+
"lstrip": false,
|
1609 |
+
"normalized": false,
|
1610 |
+
"rstrip": false,
|
1611 |
+
"single_word": false,
|
1612 |
+
"special": true
|
1613 |
+
},
|
1614 |
+
"128201": {
|
1615 |
+
"content": "<|reserved_special_token_193|>",
|
1616 |
+
"lstrip": false,
|
1617 |
+
"normalized": false,
|
1618 |
+
"rstrip": false,
|
1619 |
+
"single_word": false,
|
1620 |
+
"special": true
|
1621 |
+
},
|
1622 |
+
"128202": {
|
1623 |
+
"content": "<|reserved_special_token_194|>",
|
1624 |
+
"lstrip": false,
|
1625 |
+
"normalized": false,
|
1626 |
+
"rstrip": false,
|
1627 |
+
"single_word": false,
|
1628 |
+
"special": true
|
1629 |
+
},
|
1630 |
+
"128203": {
|
1631 |
+
"content": "<|reserved_special_token_195|>",
|
1632 |
+
"lstrip": false,
|
1633 |
+
"normalized": false,
|
1634 |
+
"rstrip": false,
|
1635 |
+
"single_word": false,
|
1636 |
+
"special": true
|
1637 |
+
},
|
1638 |
+
"128204": {
|
1639 |
+
"content": "<|reserved_special_token_196|>",
|
1640 |
+
"lstrip": false,
|
1641 |
+
"normalized": false,
|
1642 |
+
"rstrip": false,
|
1643 |
+
"single_word": false,
|
1644 |
+
"special": true
|
1645 |
+
},
|
1646 |
+
"128205": {
|
1647 |
+
"content": "<|reserved_special_token_197|>",
|
1648 |
+
"lstrip": false,
|
1649 |
+
"normalized": false,
|
1650 |
+
"rstrip": false,
|
1651 |
+
"single_word": false,
|
1652 |
+
"special": true
|
1653 |
+
},
|
1654 |
+
"128206": {
|
1655 |
+
"content": "<|reserved_special_token_198|>",
|
1656 |
+
"lstrip": false,
|
1657 |
+
"normalized": false,
|
1658 |
+
"rstrip": false,
|
1659 |
+
"single_word": false,
|
1660 |
+
"special": true
|
1661 |
+
},
|
1662 |
+
"128207": {
|
1663 |
+
"content": "<|reserved_special_token_199|>",
|
1664 |
+
"lstrip": false,
|
1665 |
+
"normalized": false,
|
1666 |
+
"rstrip": false,
|
1667 |
+
"single_word": false,
|
1668 |
+
"special": true
|
1669 |
+
},
|
1670 |
+
"128208": {
|
1671 |
+
"content": "<|reserved_special_token_200|>",
|
1672 |
+
"lstrip": false,
|
1673 |
+
"normalized": false,
|
1674 |
+
"rstrip": false,
|
1675 |
+
"single_word": false,
|
1676 |
+
"special": true
|
1677 |
+
},
|
1678 |
+
"128209": {
|
1679 |
+
"content": "<|reserved_special_token_201|>",
|
1680 |
+
"lstrip": false,
|
1681 |
+
"normalized": false,
|
1682 |
+
"rstrip": false,
|
1683 |
+
"single_word": false,
|
1684 |
+
"special": true
|
1685 |
+
},
|
1686 |
+
"128210": {
|
1687 |
+
"content": "<|reserved_special_token_202|>",
|
1688 |
+
"lstrip": false,
|
1689 |
+
"normalized": false,
|
1690 |
+
"rstrip": false,
|
1691 |
+
"single_word": false,
|
1692 |
+
"special": true
|
1693 |
+
},
|
1694 |
+
"128211": {
|
1695 |
+
"content": "<|reserved_special_token_203|>",
|
1696 |
+
"lstrip": false,
|
1697 |
+
"normalized": false,
|
1698 |
+
"rstrip": false,
|
1699 |
+
"single_word": false,
|
1700 |
+
"special": true
|
1701 |
+
},
|
1702 |
+
"128212": {
|
1703 |
+
"content": "<|reserved_special_token_204|>",
|
1704 |
+
"lstrip": false,
|
1705 |
+
"normalized": false,
|
1706 |
+
"rstrip": false,
|
1707 |
+
"single_word": false,
|
1708 |
+
"special": true
|
1709 |
+
},
|
1710 |
+
"128213": {
|
1711 |
+
"content": "<|reserved_special_token_205|>",
|
1712 |
+
"lstrip": false,
|
1713 |
+
"normalized": false,
|
1714 |
+
"rstrip": false,
|
1715 |
+
"single_word": false,
|
1716 |
+
"special": true
|
1717 |
+
},
|
1718 |
+
"128214": {
|
1719 |
+
"content": "<|reserved_special_token_206|>",
|
1720 |
+
"lstrip": false,
|
1721 |
+
"normalized": false,
|
1722 |
+
"rstrip": false,
|
1723 |
+
"single_word": false,
|
1724 |
+
"special": true
|
1725 |
+
},
|
1726 |
+
"128215": {
|
1727 |
+
"content": "<|reserved_special_token_207|>",
|
1728 |
+
"lstrip": false,
|
1729 |
+
"normalized": false,
|
1730 |
+
"rstrip": false,
|
1731 |
+
"single_word": false,
|
1732 |
+
"special": true
|
1733 |
+
},
|
1734 |
+
"128216": {
|
1735 |
+
"content": "<|reserved_special_token_208|>",
|
1736 |
+
"lstrip": false,
|
1737 |
+
"normalized": false,
|
1738 |
+
"rstrip": false,
|
1739 |
+
"single_word": false,
|
1740 |
+
"special": true
|
1741 |
+
},
|
1742 |
+
"128217": {
|
1743 |
+
"content": "<|reserved_special_token_209|>",
|
1744 |
+
"lstrip": false,
|
1745 |
+
"normalized": false,
|
1746 |
+
"rstrip": false,
|
1747 |
+
"single_word": false,
|
1748 |
+
"special": true
|
1749 |
+
},
|
1750 |
+
"128218": {
|
1751 |
+
"content": "<|reserved_special_token_210|>",
|
1752 |
+
"lstrip": false,
|
1753 |
+
"normalized": false,
|
1754 |
+
"rstrip": false,
|
1755 |
+
"single_word": false,
|
1756 |
+
"special": true
|
1757 |
+
},
|
1758 |
+
"128219": {
|
1759 |
+
"content": "<|reserved_special_token_211|>",
|
1760 |
+
"lstrip": false,
|
1761 |
+
"normalized": false,
|
1762 |
+
"rstrip": false,
|
1763 |
+
"single_word": false,
|
1764 |
+
"special": true
|
1765 |
+
},
|
1766 |
+
"128220": {
|
1767 |
+
"content": "<|reserved_special_token_212|>",
|
1768 |
+
"lstrip": false,
|
1769 |
+
"normalized": false,
|
1770 |
+
"rstrip": false,
|
1771 |
+
"single_word": false,
|
1772 |
+
"special": true
|
1773 |
+
},
|
1774 |
+
"128221": {
|
1775 |
+
"content": "<|reserved_special_token_213|>",
|
1776 |
+
"lstrip": false,
|
1777 |
+
"normalized": false,
|
1778 |
+
"rstrip": false,
|
1779 |
+
"single_word": false,
|
1780 |
+
"special": true
|
1781 |
+
},
|
1782 |
+
"128222": {
|
1783 |
+
"content": "<|reserved_special_token_214|>",
|
1784 |
+
"lstrip": false,
|
1785 |
+
"normalized": false,
|
1786 |
+
"rstrip": false,
|
1787 |
+
"single_word": false,
|
1788 |
+
"special": true
|
1789 |
+
},
|
1790 |
+
"128223": {
|
1791 |
+
"content": "<|reserved_special_token_215|>",
|
1792 |
+
"lstrip": false,
|
1793 |
+
"normalized": false,
|
1794 |
+
"rstrip": false,
|
1795 |
+
"single_word": false,
|
1796 |
+
"special": true
|
1797 |
+
},
|
1798 |
+
"128224": {
|
1799 |
+
"content": "<|reserved_special_token_216|>",
|
1800 |
+
"lstrip": false,
|
1801 |
+
"normalized": false,
|
1802 |
+
"rstrip": false,
|
1803 |
+
"single_word": false,
|
1804 |
+
"special": true
|
1805 |
+
},
|
1806 |
+
"128225": {
|
1807 |
+
"content": "<|reserved_special_token_217|>",
|
1808 |
+
"lstrip": false,
|
1809 |
+
"normalized": false,
|
1810 |
+
"rstrip": false,
|
1811 |
+
"single_word": false,
|
1812 |
+
"special": true
|
1813 |
+
},
|
1814 |
+
"128226": {
|
1815 |
+
"content": "<|reserved_special_token_218|>",
|
1816 |
+
"lstrip": false,
|
1817 |
+
"normalized": false,
|
1818 |
+
"rstrip": false,
|
1819 |
+
"single_word": false,
|
1820 |
+
"special": true
|
1821 |
+
},
|
1822 |
+
"128227": {
|
1823 |
+
"content": "<|reserved_special_token_219|>",
|
1824 |
+
"lstrip": false,
|
1825 |
+
"normalized": false,
|
1826 |
+
"rstrip": false,
|
1827 |
+
"single_word": false,
|
1828 |
+
"special": true
|
1829 |
+
},
|
1830 |
+
"128228": {
|
1831 |
+
"content": "<|reserved_special_token_220|>",
|
1832 |
+
"lstrip": false,
|
1833 |
+
"normalized": false,
|
1834 |
+
"rstrip": false,
|
1835 |
+
"single_word": false,
|
1836 |
+
"special": true
|
1837 |
+
},
|
1838 |
+
"128229": {
|
1839 |
+
"content": "<|reserved_special_token_221|>",
|
1840 |
+
"lstrip": false,
|
1841 |
+
"normalized": false,
|
1842 |
+
"rstrip": false,
|
1843 |
+
"single_word": false,
|
1844 |
+
"special": true
|
1845 |
+
},
|
1846 |
+
"128230": {
|
1847 |
+
"content": "<|reserved_special_token_222|>",
|
1848 |
+
"lstrip": false,
|
1849 |
+
"normalized": false,
|
1850 |
+
"rstrip": false,
|
1851 |
+
"single_word": false,
|
1852 |
+
"special": true
|
1853 |
+
},
|
1854 |
+
"128231": {
|
1855 |
+
"content": "<|reserved_special_token_223|>",
|
1856 |
+
"lstrip": false,
|
1857 |
+
"normalized": false,
|
1858 |
+
"rstrip": false,
|
1859 |
+
"single_word": false,
|
1860 |
+
"special": true
|
1861 |
+
},
|
1862 |
+
"128232": {
|
1863 |
+
"content": "<|reserved_special_token_224|>",
|
1864 |
+
"lstrip": false,
|
1865 |
+
"normalized": false,
|
1866 |
+
"rstrip": false,
|
1867 |
+
"single_word": false,
|
1868 |
+
"special": true
|
1869 |
+
},
|
1870 |
+
"128233": {
|
1871 |
+
"content": "<|reserved_special_token_225|>",
|
1872 |
+
"lstrip": false,
|
1873 |
+
"normalized": false,
|
1874 |
+
"rstrip": false,
|
1875 |
+
"single_word": false,
|
1876 |
+
"special": true
|
1877 |
+
},
|
1878 |
+
"128234": {
|
1879 |
+
"content": "<|reserved_special_token_226|>",
|
1880 |
+
"lstrip": false,
|
1881 |
+
"normalized": false,
|
1882 |
+
"rstrip": false,
|
1883 |
+
"single_word": false,
|
1884 |
+
"special": true
|
1885 |
+
},
|
1886 |
+
"128235": {
|
1887 |
+
"content": "<|reserved_special_token_227|>",
|
1888 |
+
"lstrip": false,
|
1889 |
+
"normalized": false,
|
1890 |
+
"rstrip": false,
|
1891 |
+
"single_word": false,
|
1892 |
+
"special": true
|
1893 |
+
},
|
1894 |
+
"128236": {
|
1895 |
+
"content": "<|reserved_special_token_228|>",
|
1896 |
+
"lstrip": false,
|
1897 |
+
"normalized": false,
|
1898 |
+
"rstrip": false,
|
1899 |
+
"single_word": false,
|
1900 |
+
"special": true
|
1901 |
+
},
|
1902 |
+
"128237": {
|
1903 |
+
"content": "<|reserved_special_token_229|>",
|
1904 |
+
"lstrip": false,
|
1905 |
+
"normalized": false,
|
1906 |
+
"rstrip": false,
|
1907 |
+
"single_word": false,
|
1908 |
+
"special": true
|
1909 |
+
},
|
1910 |
+
"128238": {
|
1911 |
+
"content": "<|reserved_special_token_230|>",
|
1912 |
+
"lstrip": false,
|
1913 |
+
"normalized": false,
|
1914 |
+
"rstrip": false,
|
1915 |
+
"single_word": false,
|
1916 |
+
"special": true
|
1917 |
+
},
|
1918 |
+
"128239": {
|
1919 |
+
"content": "<|reserved_special_token_231|>",
|
1920 |
+
"lstrip": false,
|
1921 |
+
"normalized": false,
|
1922 |
+
"rstrip": false,
|
1923 |
+
"single_word": false,
|
1924 |
+
"special": true
|
1925 |
+
},
|
1926 |
+
"128240": {
|
1927 |
+
"content": "<|reserved_special_token_232|>",
|
1928 |
+
"lstrip": false,
|
1929 |
+
"normalized": false,
|
1930 |
+
"rstrip": false,
|
1931 |
+
"single_word": false,
|
1932 |
+
"special": true
|
1933 |
+
},
|
1934 |
+
"128241": {
|
1935 |
+
"content": "<|reserved_special_token_233|>",
|
1936 |
+
"lstrip": false,
|
1937 |
+
"normalized": false,
|
1938 |
+
"rstrip": false,
|
1939 |
+
"single_word": false,
|
1940 |
+
"special": true
|
1941 |
+
},
|
1942 |
+
"128242": {
|
1943 |
+
"content": "<|reserved_special_token_234|>",
|
1944 |
+
"lstrip": false,
|
1945 |
+
"normalized": false,
|
1946 |
+
"rstrip": false,
|
1947 |
+
"single_word": false,
|
1948 |
+
"special": true
|
1949 |
+
},
|
1950 |
+
"128243": {
|
1951 |
+
"content": "<|reserved_special_token_235|>",
|
1952 |
+
"lstrip": false,
|
1953 |
+
"normalized": false,
|
1954 |
+
"rstrip": false,
|
1955 |
+
"single_word": false,
|
1956 |
+
"special": true
|
1957 |
+
},
|
1958 |
+
"128244": {
|
1959 |
+
"content": "<|reserved_special_token_236|>",
|
1960 |
+
"lstrip": false,
|
1961 |
+
"normalized": false,
|
1962 |
+
"rstrip": false,
|
1963 |
+
"single_word": false,
|
1964 |
+
"special": true
|
1965 |
+
},
|
1966 |
+
"128245": {
|
1967 |
+
"content": "<|reserved_special_token_237|>",
|
1968 |
+
"lstrip": false,
|
1969 |
+
"normalized": false,
|
1970 |
+
"rstrip": false,
|
1971 |
+
"single_word": false,
|
1972 |
+
"special": true
|
1973 |
+
},
|
1974 |
+
"128246": {
|
1975 |
+
"content": "<|reserved_special_token_238|>",
|
1976 |
+
"lstrip": false,
|
1977 |
+
"normalized": false,
|
1978 |
+
"rstrip": false,
|
1979 |
+
"single_word": false,
|
1980 |
+
"special": true
|
1981 |
+
},
|
1982 |
+
"128247": {
|
1983 |
+
"content": "<|reserved_special_token_239|>",
|
1984 |
+
"lstrip": false,
|
1985 |
+
"normalized": false,
|
1986 |
+
"rstrip": false,
|
1987 |
+
"single_word": false,
|
1988 |
+
"special": true
|
1989 |
+
},
|
1990 |
+
"128248": {
|
1991 |
+
"content": "<|reserved_special_token_240|>",
|
1992 |
+
"lstrip": false,
|
1993 |
+
"normalized": false,
|
1994 |
+
"rstrip": false,
|
1995 |
+
"single_word": false,
|
1996 |
+
"special": true
|
1997 |
+
},
|
1998 |
+
"128249": {
|
1999 |
+
"content": "<|reserved_special_token_241|>",
|
2000 |
+
"lstrip": false,
|
2001 |
+
"normalized": false,
|
2002 |
+
"rstrip": false,
|
2003 |
+
"single_word": false,
|
2004 |
+
"special": true
|
2005 |
+
},
|
2006 |
+
"128250": {
|
2007 |
+
"content": "<|reserved_special_token_242|>",
|
2008 |
+
"lstrip": false,
|
2009 |
+
"normalized": false,
|
2010 |
+
"rstrip": false,
|
2011 |
+
"single_word": false,
|
2012 |
+
"special": true
|
2013 |
+
},
|
2014 |
+
"128251": {
|
2015 |
+
"content": "<|reserved_special_token_243|>",
|
2016 |
+
"lstrip": false,
|
2017 |
+
"normalized": false,
|
2018 |
+
"rstrip": false,
|
2019 |
+
"single_word": false,
|
2020 |
+
"special": true
|
2021 |
+
},
|
2022 |
+
"128252": {
|
2023 |
+
"content": "<|reserved_special_token_244|>",
|
2024 |
+
"lstrip": false,
|
2025 |
+
"normalized": false,
|
2026 |
+
"rstrip": false,
|
2027 |
+
"single_word": false,
|
2028 |
+
"special": true
|
2029 |
+
},
|
2030 |
+
"128253": {
|
2031 |
+
"content": "<|reserved_special_token_245|>",
|
2032 |
+
"lstrip": false,
|
2033 |
+
"normalized": false,
|
2034 |
+
"rstrip": false,
|
2035 |
+
"single_word": false,
|
2036 |
+
"special": true
|
2037 |
+
},
|
2038 |
+
"128254": {
|
2039 |
+
"content": "<|reserved_special_token_246|>",
|
2040 |
+
"lstrip": false,
|
2041 |
+
"normalized": false,
|
2042 |
+
"rstrip": false,
|
2043 |
+
"single_word": false,
|
2044 |
+
"special": true
|
2045 |
+
},
|
2046 |
+
"128255": {
|
2047 |
+
"content": "<|reserved_special_token_247|>",
|
2048 |
+
"lstrip": false,
|
2049 |
+
"normalized": false,
|
2050 |
+
"rstrip": false,
|
2051 |
+
"single_word": false,
|
2052 |
+
"special": true
|
2053 |
+
},
|
2054 |
+
"128256": {
|
2055 |
+
"content": "<|end_of_text|>",
|
2056 |
+
"lstrip": false,
|
2057 |
+
"normalized": false,
|
2058 |
+
"rstrip": false,
|
2059 |
+
"single_word": false,
|
2060 |
+
"special": true
|
2061 |
+
}
|
2062 |
+
},
|
2063 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
2064 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2065 |
+
"clean_up_tokenization_spaces": false,
|
2066 |
+
"eos_token": "<|end▁of▁sentence|>",
|
2067 |
+
"extra_special_tokens": {},
|
2068 |
+
"legacy": true,
|
2069 |
+
"model_max_length": 16384,
|
2070 |
+
"pad_token": "<|end_of_text|>",
|
2071 |
+
"sp_model_kwargs": {},
|
2072 |
+
"tokenizer_class": "LlamaTokenizer",
|
2073 |
+
"unk_token": null,
|
2074 |
+
"use_default_system_prompt": false
|
2075 |
+
}
|
checkpoint-run1-186/trainer_state.json
ADDED
@@ -0,0 +1,2823 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 186,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.016260162601626018,
|
13 |
+
"grad_norm": 18.177886962890625,
|
14 |
+
"learning_rate": 2e-05,
|
15 |
+
"logits/chosen": -0.3472236394882202,
|
16 |
+
"logits/rejected": -0.13716036081314087,
|
17 |
+
"logps/chosen": -780.8181762695312,
|
18 |
+
"logps/rejected": -909.20263671875,
|
19 |
+
"loss": 0.6931,
|
20 |
+
"rewards/accuracies": 0.0,
|
21 |
+
"rewards/chosen": 0.0,
|
22 |
+
"rewards/margins": 0.0,
|
23 |
+
"rewards/rejected": 0.0,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.032520325203252036,
|
28 |
+
"grad_norm": 23.274246215820312,
|
29 |
+
"learning_rate": 4e-05,
|
30 |
+
"logits/chosen": -0.2127760350704193,
|
31 |
+
"logits/rejected": -0.08323362469673157,
|
32 |
+
"logps/chosen": -583.0169067382812,
|
33 |
+
"logps/rejected": -715.5615234375,
|
34 |
+
"loss": 0.6931,
|
35 |
+
"rewards/accuracies": 0.0,
|
36 |
+
"rewards/chosen": 0.0,
|
37 |
+
"rewards/margins": 0.0,
|
38 |
+
"rewards/rejected": 0.0,
|
39 |
+
"step": 2
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.04878048780487805,
|
43 |
+
"grad_norm": 20.149507522583008,
|
44 |
+
"learning_rate": 6e-05,
|
45 |
+
"logits/chosen": -0.18167662620544434,
|
46 |
+
"logits/rejected": -0.04478086531162262,
|
47 |
+
"logps/chosen": -941.0387573242188,
|
48 |
+
"logps/rejected": -825.662841796875,
|
49 |
+
"loss": 0.6976,
|
50 |
+
"rewards/accuracies": 0.5,
|
51 |
+
"rewards/chosen": 0.025517277419567108,
|
52 |
+
"rewards/margins": 0.022285467013716698,
|
53 |
+
"rewards/rejected": 0.0032318076118826866,
|
54 |
+
"step": 3
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.06504065040650407,
|
58 |
+
"grad_norm": 16.67251205444336,
|
59 |
+
"learning_rate": 8e-05,
|
60 |
+
"logits/chosen": 0.6866837739944458,
|
61 |
+
"logits/rejected": 0.971089243888855,
|
62 |
+
"logps/chosen": -999.306640625,
|
63 |
+
"logps/rejected": -386.5375671386719,
|
64 |
+
"loss": 0.563,
|
65 |
+
"rewards/accuracies": 1.0,
|
66 |
+
"rewards/chosen": 0.2688583433628082,
|
67 |
+
"rewards/margins": 0.3312031030654907,
|
68 |
+
"rewards/rejected": -0.062344741076231,
|
69 |
+
"step": 4
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.08130081300813008,
|
73 |
+
"grad_norm": 15.646084785461426,
|
74 |
+
"learning_rate": 0.0001,
|
75 |
+
"logits/chosen": 0.5107800364494324,
|
76 |
+
"logits/rejected": 0.5942208766937256,
|
77 |
+
"logps/chosen": -1051.1270751953125,
|
78 |
+
"logps/rejected": -745.8003540039062,
|
79 |
+
"loss": 0.647,
|
80 |
+
"rewards/accuracies": 0.5,
|
81 |
+
"rewards/chosen": 0.3622299134731293,
|
82 |
+
"rewards/margins": 0.34313660860061646,
|
83 |
+
"rewards/rejected": 0.01909332349896431,
|
84 |
+
"step": 5
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.0975609756097561,
|
88 |
+
"grad_norm": 38.70280456542969,
|
89 |
+
"learning_rate": 0.00012,
|
90 |
+
"logits/chosen": -0.31406939029693604,
|
91 |
+
"logits/rejected": -0.24293695390224457,
|
92 |
+
"logps/chosen": -845.9321899414062,
|
93 |
+
"logps/rejected": -932.499755859375,
|
94 |
+
"loss": 0.5175,
|
95 |
+
"rewards/accuracies": 0.75,
|
96 |
+
"rewards/chosen": 0.5435073971748352,
|
97 |
+
"rewards/margins": 0.47774890065193176,
|
98 |
+
"rewards/rejected": 0.06575851887464523,
|
99 |
+
"step": 6
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.11382113821138211,
|
103 |
+
"grad_norm": 23.665071487426758,
|
104 |
+
"learning_rate": 0.00014,
|
105 |
+
"logits/chosen": -0.2646118402481079,
|
106 |
+
"logits/rejected": -0.11520399153232574,
|
107 |
+
"logps/chosen": -866.503173828125,
|
108 |
+
"logps/rejected": -975.55126953125,
|
109 |
+
"loss": 0.5487,
|
110 |
+
"rewards/accuracies": 0.5,
|
111 |
+
"rewards/chosen": 0.6112838387489319,
|
112 |
+
"rewards/margins": 0.4790405333042145,
|
113 |
+
"rewards/rejected": 0.1322433352470398,
|
114 |
+
"step": 7
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.13008130081300814,
|
118 |
+
"grad_norm": 15.794047355651855,
|
119 |
+
"learning_rate": 0.00016,
|
120 |
+
"logits/chosen": -0.8256000876426697,
|
121 |
+
"logits/rejected": -0.8912097811698914,
|
122 |
+
"logps/chosen": -523.3858032226562,
|
123 |
+
"logps/rejected": -1084.9468994140625,
|
124 |
+
"loss": 0.4442,
|
125 |
+
"rewards/accuracies": 0.5,
|
126 |
+
"rewards/chosen": 0.5804435610771179,
|
127 |
+
"rewards/margins": 0.24081651866436005,
|
128 |
+
"rewards/rejected": 0.33962705731391907,
|
129 |
+
"step": 8
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.14634146341463414,
|
133 |
+
"grad_norm": 13.538564682006836,
|
134 |
+
"learning_rate": 0.00018,
|
135 |
+
"logits/chosen": -0.11683523654937744,
|
136 |
+
"logits/rejected": -0.0632472038269043,
|
137 |
+
"logps/chosen": -652.114501953125,
|
138 |
+
"logps/rejected": -551.6069946289062,
|
139 |
+
"loss": 0.1564,
|
140 |
+
"rewards/accuracies": 1.0,
|
141 |
+
"rewards/chosen": 1.6716469526290894,
|
142 |
+
"rewards/margins": 2.151698350906372,
|
143 |
+
"rewards/rejected": -0.4800514578819275,
|
144 |
+
"step": 9
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.16260162601626016,
|
148 |
+
"grad_norm": 3.9652626514434814,
|
149 |
+
"learning_rate": 0.0002,
|
150 |
+
"logits/chosen": 0.4062778949737549,
|
151 |
+
"logits/rejected": 0.5438919067382812,
|
152 |
+
"logps/chosen": -771.1934814453125,
|
153 |
+
"logps/rejected": -616.55908203125,
|
154 |
+
"loss": 0.0792,
|
155 |
+
"rewards/accuracies": 1.0,
|
156 |
+
"rewards/chosen": 3.8721909523010254,
|
157 |
+
"rewards/margins": 5.208758354187012,
|
158 |
+
"rewards/rejected": -1.3365669250488281,
|
159 |
+
"step": 10
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.17886178861788618,
|
163 |
+
"grad_norm": 0.18261243402957916,
|
164 |
+
"learning_rate": 0.0001999911398855782,
|
165 |
+
"logits/chosen": -0.7774271965026855,
|
166 |
+
"logits/rejected": -0.8629493117332458,
|
167 |
+
"logps/chosen": -601.1015014648438,
|
168 |
+
"logps/rejected": -1039.275146484375,
|
169 |
+
"loss": 0.0019,
|
170 |
+
"rewards/accuracies": 1.0,
|
171 |
+
"rewards/chosen": 1.0800025463104248,
|
172 |
+
"rewards/margins": 6.853862762451172,
|
173 |
+
"rewards/rejected": -5.773860454559326,
|
174 |
+
"step": 11
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.1951219512195122,
|
178 |
+
"grad_norm": 0.1421748697757721,
|
179 |
+
"learning_rate": 0.00019996456111234527,
|
180 |
+
"logits/chosen": 0.7899215817451477,
|
181 |
+
"logits/rejected": 1.119359016418457,
|
182 |
+
"logps/chosen": -1416.412353515625,
|
183 |
+
"logps/rejected": -827.2066650390625,
|
184 |
+
"loss": 0.0008,
|
185 |
+
"rewards/accuracies": 1.0,
|
186 |
+
"rewards/chosen": 3.7505874633789062,
|
187 |
+
"rewards/margins": 15.09115982055664,
|
188 |
+
"rewards/rejected": -11.340574264526367,
|
189 |
+
"step": 12
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.21138211382113822,
|
193 |
+
"grad_norm": 3.4406840801239014,
|
194 |
+
"learning_rate": 0.00019992026839012067,
|
195 |
+
"logits/chosen": -0.8033453226089478,
|
196 |
+
"logits/rejected": -0.877557098865509,
|
197 |
+
"logps/chosen": -514.6026611328125,
|
198 |
+
"logps/rejected": -1206.25537109375,
|
199 |
+
"loss": 0.0102,
|
200 |
+
"rewards/accuracies": 1.0,
|
201 |
+
"rewards/chosen": 1.7983558177947998,
|
202 |
+
"rewards/margins": 23.49526596069336,
|
203 |
+
"rewards/rejected": -21.696908950805664,
|
204 |
+
"step": 13
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.22764227642276422,
|
208 |
+
"grad_norm": 0.19398577511310577,
|
209 |
+
"learning_rate": 0.0001998582695676762,
|
210 |
+
"logits/chosen": 0.9254277944564819,
|
211 |
+
"logits/rejected": 1.1634798049926758,
|
212 |
+
"logps/chosen": -1028.993408203125,
|
213 |
+
"logps/rejected": -955.4432983398438,
|
214 |
+
"loss": 0.001,
|
215 |
+
"rewards/accuracies": 1.0,
|
216 |
+
"rewards/chosen": -0.5009795427322388,
|
217 |
+
"rewards/margins": 17.867931365966797,
|
218 |
+
"rewards/rejected": -18.368911743164062,
|
219 |
+
"step": 14
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.24390243902439024,
|
223 |
+
"grad_norm": 0.00010074722376884893,
|
224 |
+
"learning_rate": 0.000199778575631345,
|
225 |
+
"logits/chosen": 0.3904605507850647,
|
226 |
+
"logits/rejected": 0.3719422519207001,
|
227 |
+
"logps/chosen": -884.9620361328125,
|
228 |
+
"logps/rejected": -1075.615966796875,
|
229 |
+
"loss": 0.0,
|
230 |
+
"rewards/accuracies": 1.0,
|
231 |
+
"rewards/chosen": -2.482113838195801,
|
232 |
+
"rewards/margins": 21.95424461364746,
|
233 |
+
"rewards/rejected": -24.436357498168945,
|
234 |
+
"step": 15
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.2601626016260163,
|
238 |
+
"grad_norm": 3.7136353057576343e-05,
|
239 |
+
"learning_rate": 0.000199681200703075,
|
240 |
+
"logits/chosen": 0.2578551769256592,
|
241 |
+
"logits/rejected": 0.5335351824760437,
|
242 |
+
"logps/chosen": -1073.548828125,
|
243 |
+
"logps/rejected": -992.4033813476562,
|
244 |
+
"loss": 0.0,
|
245 |
+
"rewards/accuracies": 1.0,
|
246 |
+
"rewards/chosen": -2.9434356689453125,
|
247 |
+
"rewards/margins": 20.854663848876953,
|
248 |
+
"rewards/rejected": -23.798099517822266,
|
249 |
+
"step": 16
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.2764227642276423,
|
253 |
+
"grad_norm": 8.596338147981442e-07,
|
254 |
+
"learning_rate": 0.00019956616203792635,
|
255 |
+
"logits/chosen": 0.5267460346221924,
|
256 |
+
"logits/rejected": 0.4893237352371216,
|
257 |
+
"logps/chosen": -987.3567504882812,
|
258 |
+
"logps/rejected": -1127.171875,
|
259 |
+
"loss": 0.0,
|
260 |
+
"rewards/accuracies": 1.0,
|
261 |
+
"rewards/chosen": -1.0684036016464233,
|
262 |
+
"rewards/margins": 32.558319091796875,
|
263 |
+
"rewards/rejected": -33.62671661376953,
|
264 |
+
"step": 17
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.2926829268292683,
|
268 |
+
"grad_norm": 0.004051027819514275,
|
269 |
+
"learning_rate": 0.00019943348002101371,
|
270 |
+
"logits/chosen": 1.0484071969985962,
|
271 |
+
"logits/rejected": 1.1081664562225342,
|
272 |
+
"logps/chosen": -1105.1634521484375,
|
273 |
+
"logps/rejected": -898.9759521484375,
|
274 |
+
"loss": 0.0,
|
275 |
+
"rewards/accuracies": 1.0,
|
276 |
+
"rewards/chosen": -3.1622314453125,
|
277 |
+
"rewards/margins": 23.434669494628906,
|
278 |
+
"rewards/rejected": -26.596900939941406,
|
279 |
+
"step": 18
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.3089430894308943,
|
283 |
+
"grad_norm": 0.003306547412648797,
|
284 |
+
"learning_rate": 0.00019928317816389417,
|
285 |
+
"logits/chosen": 0.5566614866256714,
|
286 |
+
"logits/rejected": 0.6963181495666504,
|
287 |
+
"logps/chosen": -932.650390625,
|
288 |
+
"logps/rejected": -1061.4989013671875,
|
289 |
+
"loss": 0.0,
|
290 |
+
"rewards/accuracies": 1.0,
|
291 |
+
"rewards/chosen": -4.36033821105957,
|
292 |
+
"rewards/margins": 30.25779914855957,
|
293 |
+
"rewards/rejected": -34.61813735961914,
|
294 |
+
"step": 19
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.3252032520325203,
|
298 |
+
"grad_norm": 1.3893560968369911e-08,
|
299 |
+
"learning_rate": 0.00019911528310040074,
|
300 |
+
"logits/chosen": 1.239579200744629,
|
301 |
+
"logits/rejected": 1.046311855316162,
|
302 |
+
"logps/chosen": -1079.0159912109375,
|
303 |
+
"logps/rejected": -1033.2017822265625,
|
304 |
+
"loss": 0.0,
|
305 |
+
"rewards/accuracies": 1.0,
|
306 |
+
"rewards/chosen": 1.044548749923706,
|
307 |
+
"rewards/margins": 41.88936233520508,
|
308 |
+
"rewards/rejected": -40.844810485839844,
|
309 |
+
"step": 20
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.34146341463414637,
|
313 |
+
"grad_norm": 4.666223851756968e-09,
|
314 |
+
"learning_rate": 0.00019892982458192288,
|
315 |
+
"logits/chosen": 0.2726232409477234,
|
316 |
+
"logits/rejected": 0.14665402472019196,
|
317 |
+
"logps/chosen": -978.7222900390625,
|
318 |
+
"logps/rejected": -1133.2047119140625,
|
319 |
+
"loss": 0.0,
|
320 |
+
"rewards/accuracies": 1.0,
|
321 |
+
"rewards/chosen": 11.054238319396973,
|
322 |
+
"rewards/margins": 54.86410140991211,
|
323 |
+
"rewards/rejected": -43.80986404418945,
|
324 |
+
"step": 21
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.35772357723577236,
|
328 |
+
"grad_norm": 4.876813477494579e-07,
|
329 |
+
"learning_rate": 0.00019872683547213446,
|
330 |
+
"logits/chosen": -0.16925190389156342,
|
331 |
+
"logits/rejected": -0.19759103655815125,
|
332 |
+
"logps/chosen": -965.187255859375,
|
333 |
+
"logps/rejected": -1239.143798828125,
|
334 |
+
"loss": 0.0,
|
335 |
+
"rewards/accuracies": 1.0,
|
336 |
+
"rewards/chosen": -14.977485656738281,
|
337 |
+
"rewards/margins": 29.40732765197754,
|
338 |
+
"rewards/rejected": -44.38481140136719,
|
339 |
+
"step": 22
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.37398373983739835,
|
343 |
+
"grad_norm": 37.638973236083984,
|
344 |
+
"learning_rate": 0.00019850635174117033,
|
345 |
+
"logits/chosen": 0.437714159488678,
|
346 |
+
"logits/rejected": 0.4761970639228821,
|
347 |
+
"logps/chosen": -1137.6966552734375,
|
348 |
+
"logps/rejected": -1166.5640869140625,
|
349 |
+
"loss": 0.4393,
|
350 |
+
"rewards/accuracies": 1.0,
|
351 |
+
"rewards/chosen": -11.159793853759766,
|
352 |
+
"rewards/margins": 32.14189529418945,
|
353 |
+
"rewards/rejected": -43.301692962646484,
|
354 |
+
"step": 23
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.3902439024390244,
|
358 |
+
"grad_norm": 1.8173747229344173e-11,
|
359 |
+
"learning_rate": 0.00019826841245925212,
|
360 |
+
"logits/chosen": -0.7153763175010681,
|
361 |
+
"logits/rejected": -0.6940470933914185,
|
362 |
+
"logps/chosen": -938.263916015625,
|
363 |
+
"logps/rejected": -1608.4205322265625,
|
364 |
+
"loss": 0.0,
|
365 |
+
"rewards/accuracies": 1.0,
|
366 |
+
"rewards/chosen": -24.817350387573242,
|
367 |
+
"rewards/margins": 34.095001220703125,
|
368 |
+
"rewards/rejected": -58.912349700927734,
|
369 |
+
"step": 24
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.4065040650406504,
|
373 |
+
"grad_norm": 83.79772186279297,
|
374 |
+
"learning_rate": 0.0001980130597897651,
|
375 |
+
"logits/chosen": 1.1592888832092285,
|
376 |
+
"logits/rejected": 1.1738824844360352,
|
377 |
+
"logps/chosen": -948.4622802734375,
|
378 |
+
"logps/rejected": -865.396728515625,
|
379 |
+
"loss": 0.3825,
|
380 |
+
"rewards/accuracies": 1.0,
|
381 |
+
"rewards/chosen": -3.343675374984741,
|
382 |
+
"rewards/margins": 26.49417495727539,
|
383 |
+
"rewards/rejected": -29.837852478027344,
|
384 |
+
"step": 25
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.42276422764227645,
|
388 |
+
"grad_norm": 2.6143006834900007e-06,
|
389 |
+
"learning_rate": 0.00019774033898178667,
|
390 |
+
"logits/chosen": 0.5444796085357666,
|
391 |
+
"logits/rejected": 0.47586876153945923,
|
392 |
+
"logps/chosen": -932.6605834960938,
|
393 |
+
"logps/rejected": -1091.639892578125,
|
394 |
+
"loss": 0.0,
|
395 |
+
"rewards/accuracies": 1.0,
|
396 |
+
"rewards/chosen": -4.2753777503967285,
|
397 |
+
"rewards/margins": 34.133514404296875,
|
398 |
+
"rewards/rejected": -38.40888977050781,
|
399 |
+
"step": 26
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.43902439024390244,
|
403 |
+
"grad_norm": 0.0003061926399823278,
|
404 |
+
"learning_rate": 0.00019745029836206813,
|
405 |
+
"logits/chosen": -0.6794779896736145,
|
406 |
+
"logits/rejected": -0.8602011203765869,
|
407 |
+
"logps/chosen": -894.3270263671875,
|
408 |
+
"logps/rejected": -1067.5921630859375,
|
409 |
+
"loss": 0.0,
|
410 |
+
"rewards/accuracies": 1.0,
|
411 |
+
"rewards/chosen": -13.433198928833008,
|
412 |
+
"rewards/margins": 17.333955764770508,
|
413 |
+
"rewards/rejected": -30.767154693603516,
|
414 |
+
"step": 27
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.45528455284552843,
|
418 |
+
"grad_norm": 3.805017101399244e-08,
|
419 |
+
"learning_rate": 0.00019714298932647098,
|
420 |
+
"logits/chosen": 0.4980026185512543,
|
421 |
+
"logits/rejected": 0.6999194025993347,
|
422 |
+
"logps/chosen": -911.8473510742188,
|
423 |
+
"logps/rejected": -1126.07421875,
|
424 |
+
"loss": 0.0,
|
425 |
+
"rewards/accuracies": 1.0,
|
426 |
+
"rewards/chosen": -0.5412168502807617,
|
427 |
+
"rewards/margins": 29.520708084106445,
|
428 |
+
"rewards/rejected": -30.06192398071289,
|
429 |
+
"step": 28
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.4715447154471545,
|
433 |
+
"grad_norm": 5.17633900187775e-08,
|
434 |
+
"learning_rate": 0.00019681846633085967,
|
435 |
+
"logits/chosen": -0.5973828434944153,
|
436 |
+
"logits/rejected": -0.8376109600067139,
|
437 |
+
"logps/chosen": -711.66259765625,
|
438 |
+
"logps/rejected": -1186.1884765625,
|
439 |
+
"loss": 0.0,
|
440 |
+
"rewards/accuracies": 1.0,
|
441 |
+
"rewards/chosen": -2.467390537261963,
|
442 |
+
"rewards/margins": 25.050704956054688,
|
443 |
+
"rewards/rejected": -27.518096923828125,
|
444 |
+
"step": 29
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.4878048780487805,
|
448 |
+
"grad_norm": 0.00011633769463514909,
|
449 |
+
"learning_rate": 0.0001964767868814516,
|
450 |
+
"logits/chosen": 1.3797093629837036,
|
451 |
+
"logits/rejected": 1.5397391319274902,
|
452 |
+
"logps/chosen": -877.42333984375,
|
453 |
+
"logps/rejected": -1003.4732666015625,
|
454 |
+
"loss": 0.0,
|
455 |
+
"rewards/accuracies": 1.0,
|
456 |
+
"rewards/chosen": 4.624107360839844,
|
457 |
+
"rewards/margins": 29.784557342529297,
|
458 |
+
"rewards/rejected": -25.160449981689453,
|
459 |
+
"step": 30
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.5040650406504065,
|
463 |
+
"grad_norm": 6.257723228486611e-09,
|
464 |
+
"learning_rate": 0.00019611801152462715,
|
465 |
+
"logits/chosen": 1.2731826305389404,
|
466 |
+
"logits/rejected": 1.6379995346069336,
|
467 |
+
"logps/chosen": -1053.573486328125,
|
468 |
+
"logps/rejected": -1010.915283203125,
|
469 |
+
"loss": 0.0,
|
470 |
+
"rewards/accuracies": 1.0,
|
471 |
+
"rewards/chosen": 11.018058776855469,
|
472 |
+
"rewards/margins": 32.15219497680664,
|
473 |
+
"rewards/rejected": -21.13413429260254,
|
474 |
+
"step": 31
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.5203252032520326,
|
478 |
+
"grad_norm": 0.00035472630406729877,
|
479 |
+
"learning_rate": 0.00019574220383620055,
|
480 |
+
"logits/chosen": 0.6649560928344727,
|
481 |
+
"logits/rejected": 0.983564019203186,
|
482 |
+
"logps/chosen": -872.1873168945312,
|
483 |
+
"logps/rejected": -965.9480590820312,
|
484 |
+
"loss": 0.0,
|
485 |
+
"rewards/accuracies": 1.0,
|
486 |
+
"rewards/chosen": 5.504961967468262,
|
487 |
+
"rewards/margins": 23.669071197509766,
|
488 |
+
"rewards/rejected": -18.164108276367188,
|
489 |
+
"step": 32
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.5365853658536586,
|
493 |
+
"grad_norm": 3.0934195820009336e-05,
|
494 |
+
"learning_rate": 0.00019534943041015423,
|
495 |
+
"logits/chosen": 0.49574941396713257,
|
496 |
+
"logits/rejected": 0.5190873742103577,
|
497 |
+
"logps/chosen": -708.9269409179688,
|
498 |
+
"logps/rejected": -842.974365234375,
|
499 |
+
"loss": 0.0,
|
500 |
+
"rewards/accuracies": 1.0,
|
501 |
+
"rewards/chosen": 7.209194660186768,
|
502 |
+
"rewards/margins": 20.690357208251953,
|
503 |
+
"rewards/rejected": -13.48116397857666,
|
504 |
+
"step": 33
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.5528455284552846,
|
508 |
+
"grad_norm": 0.0006856573163531721,
|
509 |
+
"learning_rate": 0.00019493976084683813,
|
510 |
+
"logits/chosen": 0.992796778678894,
|
511 |
+
"logits/rejected": 1.1291236877441406,
|
512 |
+
"logps/chosen": -673.6188354492188,
|
513 |
+
"logps/rejected": -723.4482421875,
|
514 |
+
"loss": 0.0,
|
515 |
+
"rewards/accuracies": 1.0,
|
516 |
+
"rewards/chosen": 5.3715057373046875,
|
517 |
+
"rewards/margins": 19.963485717773438,
|
518 |
+
"rewards/rejected": -14.591980934143066,
|
519 |
+
"step": 34
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.5691056910569106,
|
523 |
+
"grad_norm": 5.983891969663091e-05,
|
524 |
+
"learning_rate": 0.00019451326774063636,
|
525 |
+
"logits/chosen": 0.7630600929260254,
|
526 |
+
"logits/rejected": 0.910960853099823,
|
527 |
+
"logps/chosen": -993.23828125,
|
528 |
+
"logps/rejected": -1011.3184204101562,
|
529 |
+
"loss": 0.0,
|
530 |
+
"rewards/accuracies": 1.0,
|
531 |
+
"rewards/chosen": 7.109509468078613,
|
532 |
+
"rewards/margins": 24.603878021240234,
|
533 |
+
"rewards/rejected": -17.494367599487305,
|
534 |
+
"step": 35
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.5853658536585366,
|
538 |
+
"grad_norm": 1.9749455532291904e-05,
|
539 |
+
"learning_rate": 0.00019407002666710336,
|
540 |
+
"logits/chosen": 1.8401339054107666,
|
541 |
+
"logits/rejected": 1.9955703020095825,
|
542 |
+
"logps/chosen": -1152.950927734375,
|
543 |
+
"logps/rejected": -827.0269775390625,
|
544 |
+
"loss": 0.0,
|
545 |
+
"rewards/accuracies": 1.0,
|
546 |
+
"rewards/chosen": 15.768245697021484,
|
547 |
+
"rewards/margins": 38.1776123046875,
|
548 |
+
"rewards/rejected": -22.40936851501465,
|
549 |
+
"step": 36
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.6016260162601627,
|
553 |
+
"grad_norm": 0.0017285533249378204,
|
554 |
+
"learning_rate": 0.00019361011616957164,
|
555 |
+
"logits/chosen": 2.153351306915283,
|
556 |
+
"logits/rejected": 2.235447883605957,
|
557 |
+
"logps/chosen": -1090.1943359375,
|
558 |
+
"logps/rejected": -682.7992553710938,
|
559 |
+
"loss": 0.0,
|
560 |
+
"rewards/accuracies": 1.0,
|
561 |
+
"rewards/chosen": 11.726329803466797,
|
562 |
+
"rewards/margins": 24.018630981445312,
|
563 |
+
"rewards/rejected": -12.292303085327148,
|
564 |
+
"step": 37
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.6178861788617886,
|
568 |
+
"grad_norm": 0.00919501855969429,
|
569 |
+
"learning_rate": 0.00019313361774523385,
|
570 |
+
"logits/chosen": 0.47314736247062683,
|
571 |
+
"logits/rejected": 0.557833731174469,
|
572 |
+
"logps/chosen": -691.4217529296875,
|
573 |
+
"logps/rejected": -673.1847534179688,
|
574 |
+
"loss": 0.0,
|
575 |
+
"rewards/accuracies": 1.0,
|
576 |
+
"rewards/chosen": 6.087795257568359,
|
577 |
+
"rewards/margins": 12.628225326538086,
|
578 |
+
"rewards/rejected": -6.540430068969727,
|
579 |
+
"step": 38
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.6341463414634146,
|
583 |
+
"grad_norm": 0.002680833451449871,
|
584 |
+
"learning_rate": 0.00019264061583070127,
|
585 |
+
"logits/chosen": 0.20066705346107483,
|
586 |
+
"logits/rejected": 0.2085224837064743,
|
587 |
+
"logps/chosen": -693.7376098632812,
|
588 |
+
"logps/rejected": -982.19091796875,
|
589 |
+
"loss": 0.0,
|
590 |
+
"rewards/accuracies": 1.0,
|
591 |
+
"rewards/chosen": 7.779763221740723,
|
592 |
+
"rewards/margins": 22.904094696044922,
|
593 |
+
"rewards/rejected": -15.124334335327148,
|
594 |
+
"step": 39
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.6504065040650406,
|
598 |
+
"grad_norm": 8.798202907200903e-05,
|
599 |
+
"learning_rate": 0.00019213119778704128,
|
600 |
+
"logits/chosen": 1.3898746967315674,
|
601 |
+
"logits/rejected": 1.5520107746124268,
|
602 |
+
"logps/chosen": -1247.770263671875,
|
603 |
+
"logps/rejected": -916.4830322265625,
|
604 |
+
"loss": 0.0,
|
605 |
+
"rewards/accuracies": 1.0,
|
606 |
+
"rewards/chosen": 15.276836395263672,
|
607 |
+
"rewards/margins": 34.69191360473633,
|
608 |
+
"rewards/rejected": -19.415077209472656,
|
609 |
+
"step": 40
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.6666666666666666,
|
613 |
+
"grad_norm": 0.0009758697124198079,
|
614 |
+
"learning_rate": 0.00019160545388429708,
|
615 |
+
"logits/chosen": 2.345059633255005,
|
616 |
+
"logits/rejected": 2.5746054649353027,
|
617 |
+
"logps/chosen": -1102.5548095703125,
|
618 |
+
"logps/rejected": -722.4332885742188,
|
619 |
+
"loss": 0.0,
|
620 |
+
"rewards/accuracies": 1.0,
|
621 |
+
"rewards/chosen": 13.800348281860352,
|
622 |
+
"rewards/margins": 32.747169494628906,
|
623 |
+
"rewards/rejected": -18.946823120117188,
|
624 |
+
"step": 41
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.6829268292682927,
|
628 |
+
"grad_norm": 0.0016077810432761908,
|
629 |
+
"learning_rate": 0.00019106347728549135,
|
630 |
+
"logits/chosen": 0.9104095697402954,
|
631 |
+
"logits/rejected": 0.9921329021453857,
|
632 |
+
"logps/chosen": -753.8040771484375,
|
633 |
+
"logps/rejected": -886.5813598632812,
|
634 |
+
"loss": 0.0,
|
635 |
+
"rewards/accuracies": 1.0,
|
636 |
+
"rewards/chosen": 11.367500305175781,
|
637 |
+
"rewards/margins": 27.856563568115234,
|
638 |
+
"rewards/rejected": -16.489063262939453,
|
639 |
+
"step": 42
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.6991869918699187,
|
643 |
+
"grad_norm": 0.0004074655589647591,
|
644 |
+
"learning_rate": 0.0001905053640301176,
|
645 |
+
"logits/chosen": 0.5256392955780029,
|
646 |
+
"logits/rejected": 0.4733426570892334,
|
647 |
+
"logps/chosen": -715.4669189453125,
|
648 |
+
"logps/rejected": -565.0441284179688,
|
649 |
+
"loss": 0.0,
|
650 |
+
"rewards/accuracies": 1.0,
|
651 |
+
"rewards/chosen": 6.25009822845459,
|
652 |
+
"rewards/margins": 21.391075134277344,
|
653 |
+
"rewards/rejected": -15.14097785949707,
|
654 |
+
"step": 43
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.7154471544715447,
|
658 |
+
"grad_norm": 0.013145952485501766,
|
659 |
+
"learning_rate": 0.00018993121301712193,
|
660 |
+
"logits/chosen": 0.9358551502227783,
|
661 |
+
"logits/rejected": 0.8306156992912292,
|
662 |
+
"logps/chosen": -867.1063232421875,
|
663 |
+
"logps/rejected": -973.7214965820312,
|
664 |
+
"loss": 0.0,
|
665 |
+
"rewards/accuracies": 1.0,
|
666 |
+
"rewards/chosen": 7.3925018310546875,
|
667 |
+
"rewards/margins": 21.35105323791504,
|
668 |
+
"rewards/rejected": -13.958552360534668,
|
669 |
+
"step": 44
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.7317073170731707,
|
673 |
+
"grad_norm": 8.829876605886966e-05,
|
674 |
+
"learning_rate": 0.00018934112598737777,
|
675 |
+
"logits/chosen": 2.2844998836517334,
|
676 |
+
"logits/rejected": 2.831254482269287,
|
677 |
+
"logps/chosen": -1142.8726806640625,
|
678 |
+
"logps/rejected": -776.1110229492188,
|
679 |
+
"loss": 0.0,
|
680 |
+
"rewards/accuracies": 1.0,
|
681 |
+
"rewards/chosen": 17.17538833618164,
|
682 |
+
"rewards/margins": 33.72625732421875,
|
683 |
+
"rewards/rejected": -16.550867080688477,
|
684 |
+
"step": 45
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.7479674796747967,
|
688 |
+
"grad_norm": 0.02624354511499405,
|
689 |
+
"learning_rate": 0.00018873520750565718,
|
690 |
+
"logits/chosen": 0.1806122362613678,
|
691 |
+
"logits/rejected": 0.31054702401161194,
|
692 |
+
"logps/chosen": -692.7060546875,
|
693 |
+
"logps/rejected": -1032.708740234375,
|
694 |
+
"loss": 0.0001,
|
695 |
+
"rewards/accuracies": 1.0,
|
696 |
+
"rewards/chosen": 6.434965133666992,
|
697 |
+
"rewards/margins": 16.74932098388672,
|
698 |
+
"rewards/rejected": -10.314356803894043,
|
699 |
+
"step": 46
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.7642276422764228,
|
703 |
+
"grad_norm": 4.268178963684477e-05,
|
704 |
+
"learning_rate": 0.00018811356494210165,
|
705 |
+
"logits/chosen": 1.1679103374481201,
|
706 |
+
"logits/rejected": 1.0418663024902344,
|
707 |
+
"logps/chosen": -720.220703125,
|
708 |
+
"logps/rejected": -911.58837890625,
|
709 |
+
"loss": 0.0,
|
710 |
+
"rewards/accuracies": 1.0,
|
711 |
+
"rewards/chosen": 7.991888523101807,
|
712 |
+
"rewards/margins": 21.064565658569336,
|
713 |
+
"rewards/rejected": -13.072675704956055,
|
714 |
+
"step": 47
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.7804878048780488,
|
718 |
+
"grad_norm": 0.0009461237932555377,
|
719 |
+
"learning_rate": 0.00018747630845319612,
|
720 |
+
"logits/chosen": 0.13339552283287048,
|
721 |
+
"logits/rejected": 0.3655449151992798,
|
722 |
+
"logps/chosen": -420.11431884765625,
|
723 |
+
"logps/rejected": -786.4783325195312,
|
724 |
+
"loss": 0.0,
|
725 |
+
"rewards/accuracies": 1.0,
|
726 |
+
"rewards/chosen": 11.16606330871582,
|
727 |
+
"rewards/margins": 30.41803741455078,
|
728 |
+
"rewards/rejected": -19.251976013183594,
|
729 |
+
"step": 48
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.7967479674796748,
|
733 |
+
"grad_norm": 0.0033115639816969633,
|
734 |
+
"learning_rate": 0.00018682355096224872,
|
735 |
+
"logits/chosen": 0.4472777247428894,
|
736 |
+
"logits/rejected": 0.3390260934829712,
|
737 |
+
"logps/chosen": -536.7960205078125,
|
738 |
+
"logps/rejected": -901.3749389648438,
|
739 |
+
"loss": 0.0,
|
740 |
+
"rewards/accuracies": 1.0,
|
741 |
+
"rewards/chosen": 10.887458801269531,
|
742 |
+
"rewards/margins": 27.701595306396484,
|
743 |
+
"rewards/rejected": -16.814136505126953,
|
744 |
+
"step": 49
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.8130081300813008,
|
748 |
+
"grad_norm": 0.01153454091399908,
|
749 |
+
"learning_rate": 0.0001861554081393806,
|
750 |
+
"logits/chosen": 0.6489148139953613,
|
751 |
+
"logits/rejected": 0.689254105091095,
|
752 |
+
"logps/chosen": -738.5593872070312,
|
753 |
+
"logps/rejected": -755.362060546875,
|
754 |
+
"loss": 0.0001,
|
755 |
+
"rewards/accuracies": 1.0,
|
756 |
+
"rewards/chosen": 10.205413818359375,
|
757 |
+
"rewards/margins": 16.344358444213867,
|
758 |
+
"rewards/rejected": -6.138944625854492,
|
759 |
+
"step": 50
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.8292682926829268,
|
763 |
+
"grad_norm": 0.001985176932066679,
|
764 |
+
"learning_rate": 0.00018547199838102904,
|
765 |
+
"logits/chosen": 0.144524484872818,
|
766 |
+
"logits/rejected": 0.26266002655029297,
|
767 |
+
"logps/chosen": -893.19482421875,
|
768 |
+
"logps/rejected": -1031.27294921875,
|
769 |
+
"loss": 0.0,
|
770 |
+
"rewards/accuracies": 1.0,
|
771 |
+
"rewards/chosen": 9.087849617004395,
|
772 |
+
"rewards/margins": 23.393884658813477,
|
773 |
+
"rewards/rejected": -14.306035041809082,
|
774 |
+
"step": 51
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.8455284552845529,
|
778 |
+
"grad_norm": 0.00042794409091584384,
|
779 |
+
"learning_rate": 0.0001847734427889671,
|
780 |
+
"logits/chosen": 0.5121033191680908,
|
781 |
+
"logits/rejected": 1.0676312446594238,
|
782 |
+
"logps/chosen": -987.8340454101562,
|
783 |
+
"logps/rejected": -830.7366943359375,
|
784 |
+
"loss": 0.0,
|
785 |
+
"rewards/accuracies": 1.0,
|
786 |
+
"rewards/chosen": 11.409669876098633,
|
787 |
+
"rewards/margins": 19.569660186767578,
|
788 |
+
"rewards/rejected": -8.159988403320312,
|
789 |
+
"step": 52
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.8617886178861789,
|
793 |
+
"grad_norm": 0.0011688657104969025,
|
794 |
+
"learning_rate": 0.00018405986514884434,
|
795 |
+
"logits/chosen": 1.793473243713379,
|
796 |
+
"logits/rejected": 1.9872632026672363,
|
797 |
+
"logps/chosen": -926.424560546875,
|
798 |
+
"logps/rejected": -618.4228515625,
|
799 |
+
"loss": 0.0,
|
800 |
+
"rewards/accuracies": 1.0,
|
801 |
+
"rewards/chosen": 11.011417388916016,
|
802 |
+
"rewards/margins": 22.01776123046875,
|
803 |
+
"rewards/rejected": -11.006343841552734,
|
804 |
+
"step": 53
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.8780487804878049,
|
808 |
+
"grad_norm": 0.005157554987818003,
|
809 |
+
"learning_rate": 0.0001833313919082515,
|
810 |
+
"logits/chosen": -0.02910199761390686,
|
811 |
+
"logits/rejected": 0.14243453741073608,
|
812 |
+
"logps/chosen": -725.36376953125,
|
813 |
+
"logps/rejected": -997.5311279296875,
|
814 |
+
"loss": 0.0,
|
815 |
+
"rewards/accuracies": 1.0,
|
816 |
+
"rewards/chosen": 5.557222366333008,
|
817 |
+
"rewards/margins": 15.359309196472168,
|
818 |
+
"rewards/rejected": -9.802087783813477,
|
819 |
+
"step": 54
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.8943089430894309,
|
823 |
+
"grad_norm": 0.005044507794082165,
|
824 |
+
"learning_rate": 0.00018258815215431396,
|
825 |
+
"logits/chosen": 0.17898443341255188,
|
826 |
+
"logits/rejected": 0.09989897906780243,
|
827 |
+
"logps/chosen": -803.9798583984375,
|
828 |
+
"logps/rejected": -925.3179321289062,
|
829 |
+
"loss": 0.0,
|
830 |
+
"rewards/accuracies": 1.0,
|
831 |
+
"rewards/chosen": 6.798739433288574,
|
832 |
+
"rewards/margins": 17.492319107055664,
|
833 |
+
"rewards/rejected": -10.69357967376709,
|
834 |
+
"step": 55
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.9105691056910569,
|
838 |
+
"grad_norm": 0.0031374047975987196,
|
839 |
+
"learning_rate": 0.0001818302775908169,
|
840 |
+
"logits/chosen": 1.017639398574829,
|
841 |
+
"logits/rejected": 1.2823631763458252,
|
842 |
+
"logps/chosen": -824.6445922851562,
|
843 |
+
"logps/rejected": -860.8942260742188,
|
844 |
+
"loss": 0.0,
|
845 |
+
"rewards/accuracies": 1.0,
|
846 |
+
"rewards/chosen": 6.019498825073242,
|
847 |
+
"rewards/margins": 16.16924285888672,
|
848 |
+
"rewards/rejected": -10.149742126464844,
|
849 |
+
"step": 56
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.926829268292683,
|
853 |
+
"grad_norm": 0.00014241511235013604,
|
854 |
+
"learning_rate": 0.0001810579025148674,
|
855 |
+
"logits/chosen": 1.0959478616714478,
|
856 |
+
"logits/rejected": 0.9008815288543701,
|
857 |
+
"logps/chosen": -782.0526123046875,
|
858 |
+
"logps/rejected": -916.8338623046875,
|
859 |
+
"loss": 0.0,
|
860 |
+
"rewards/accuracies": 1.0,
|
861 |
+
"rewards/chosen": 8.443077087402344,
|
862 |
+
"rewards/margins": 24.263744354248047,
|
863 |
+
"rewards/rejected": -15.820667266845703,
|
864 |
+
"step": 57
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.943089430894309,
|
868 |
+
"grad_norm": 5.913816494285129e-05,
|
869 |
+
"learning_rate": 0.00018027116379309638,
|
870 |
+
"logits/chosen": 0.2709883153438568,
|
871 |
+
"logits/rejected": 0.29769933223724365,
|
872 |
+
"logps/chosen": -735.5257568359375,
|
873 |
+
"logps/rejected": -1044.0601806640625,
|
874 |
+
"loss": 0.0,
|
875 |
+
"rewards/accuracies": 1.0,
|
876 |
+
"rewards/chosen": 8.65300178527832,
|
877 |
+
"rewards/margins": 18.755083084106445,
|
878 |
+
"rewards/rejected": -10.102080345153809,
|
879 |
+
"step": 58
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.959349593495935,
|
883 |
+
"grad_norm": 0.01578771322965622,
|
884 |
+
"learning_rate": 0.00017947020083740575,
|
885 |
+
"logits/chosen": 1.5522100925445557,
|
886 |
+
"logits/rejected": 1.7518442869186401,
|
887 |
+
"logps/chosen": -1019.1099853515625,
|
888 |
+
"logps/rejected": -624.6131591796875,
|
889 |
+
"loss": 0.0001,
|
890 |
+
"rewards/accuracies": 1.0,
|
891 |
+
"rewards/chosen": 10.32003402709961,
|
892 |
+
"rewards/margins": 23.75770378112793,
|
893 |
+
"rewards/rejected": -13.43766975402832,
|
894 |
+
"step": 59
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.975609756097561,
|
898 |
+
"grad_norm": 0.0010152229806408286,
|
899 |
+
"learning_rate": 0.00017865515558026428,
|
900 |
+
"logits/chosen": 0.8601479530334473,
|
901 |
+
"logits/rejected": 0.819040060043335,
|
902 |
+
"logps/chosen": -763.342041015625,
|
903 |
+
"logps/rejected": -817.870849609375,
|
904 |
+
"loss": 0.0,
|
905 |
+
"rewards/accuracies": 1.0,
|
906 |
+
"rewards/chosen": 8.2501859664917,
|
907 |
+
"rewards/margins": 16.491539001464844,
|
908 |
+
"rewards/rejected": -8.241353034973145,
|
909 |
+
"step": 60
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.991869918699187,
|
913 |
+
"grad_norm": 0.008696873672306538,
|
914 |
+
"learning_rate": 0.0001778261724495566,
|
915 |
+
"logits/chosen": 0.7409014701843262,
|
916 |
+
"logits/rejected": 0.9245580434799194,
|
917 |
+
"logps/chosen": -888.8350830078125,
|
918 |
+
"logps/rejected": -796.002685546875,
|
919 |
+
"loss": 0.0001,
|
920 |
+
"rewards/accuracies": 1.0,
|
921 |
+
"rewards/chosen": 11.07230281829834,
|
922 |
+
"rewards/margins": 22.53582000732422,
|
923 |
+
"rewards/rejected": -11.463518142700195,
|
924 |
+
"step": 61
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 1.0,
|
928 |
+
"grad_norm": 2.3132517526391894e-05,
|
929 |
+
"learning_rate": 0.00017698339834299061,
|
930 |
+
"logits/chosen": 0.962340772151947,
|
931 |
+
"logits/rejected": 1.369040608406067,
|
932 |
+
"logps/chosen": -843.8861083984375,
|
933 |
+
"logps/rejected": -833.0137329101562,
|
934 |
+
"loss": 0.0,
|
935 |
+
"rewards/accuracies": 1.0,
|
936 |
+
"rewards/chosen": 7.60971736907959,
|
937 |
+
"rewards/margins": 22.649456024169922,
|
938 |
+
"rewards/rejected": -15.039739608764648,
|
939 |
+
"step": 62
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 1.016260162601626,
|
943 |
+
"grad_norm": 3.0814584306426696e-07,
|
944 |
+
"learning_rate": 0.00017612698260206666,
|
945 |
+
"logits/chosen": 1.7351003885269165,
|
946 |
+
"logits/rejected": 2.39410400390625,
|
947 |
+
"logps/chosen": -1081.0841064453125,
|
948 |
+
"logps/rejected": -664.132080078125,
|
949 |
+
"loss": 0.0,
|
950 |
+
"rewards/accuracies": 1.0,
|
951 |
+
"rewards/chosen": 12.010480880737305,
|
952 |
+
"rewards/margins": 23.851722717285156,
|
953 |
+
"rewards/rejected": -11.841242790222168,
|
954 |
+
"step": 63
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 1.032520325203252,
|
958 |
+
"grad_norm": 0.0014821357326582074,
|
959 |
+
"learning_rate": 0.00017525707698561385,
|
960 |
+
"logits/chosen": 0.8669869899749756,
|
961 |
+
"logits/rejected": 1.2894644737243652,
|
962 |
+
"logps/chosen": -794.047607421875,
|
963 |
+
"logps/rejected": -812.5697631835938,
|
964 |
+
"loss": 0.0,
|
965 |
+
"rewards/accuracies": 1.0,
|
966 |
+
"rewards/chosen": 11.141783714294434,
|
967 |
+
"rewards/margins": 23.891061782836914,
|
968 |
+
"rewards/rejected": -12.749277114868164,
|
969 |
+
"step": 64
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 1.048780487804878,
|
973 |
+
"grad_norm": 0.002492019208148122,
|
974 |
+
"learning_rate": 0.00017437383564289816,
|
975 |
+
"logits/chosen": 1.1617192029953003,
|
976 |
+
"logits/rejected": 1.0443211793899536,
|
977 |
+
"logps/chosen": -706.7365112304688,
|
978 |
+
"logps/rejected": -834.9153442382812,
|
979 |
+
"loss": 0.0,
|
980 |
+
"rewards/accuracies": 1.0,
|
981 |
+
"rewards/chosen": 10.32893180847168,
|
982 |
+
"rewards/margins": 23.380508422851562,
|
983 |
+
"rewards/rejected": -13.0515775680542,
|
984 |
+
"step": 65
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 1.065040650406504,
|
988 |
+
"grad_norm": 0.10320430248975754,
|
989 |
+
"learning_rate": 0.00017347741508630672,
|
990 |
+
"logits/chosen": 1.5734750032424927,
|
991 |
+
"logits/rejected": 2.108652114868164,
|
992 |
+
"logps/chosen": -919.78125,
|
993 |
+
"logps/rejected": -843.049560546875,
|
994 |
+
"loss": 0.0005,
|
995 |
+
"rewards/accuracies": 1.0,
|
996 |
+
"rewards/chosen": 14.794572830200195,
|
997 |
+
"rewards/margins": 27.74661636352539,
|
998 |
+
"rewards/rejected": -12.952045440673828,
|
999 |
+
"step": 66
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 1.08130081300813,
|
1003 |
+
"grad_norm": 0.00033748566056601703,
|
1004 |
+
"learning_rate": 0.00017256797416361362,
|
1005 |
+
"logits/chosen": 0.10465478897094727,
|
1006 |
+
"logits/rejected": 0.11954197287559509,
|
1007 |
+
"logps/chosen": -770.0354614257812,
|
1008 |
+
"logps/rejected": -705.5811767578125,
|
1009 |
+
"loss": 0.0,
|
1010 |
+
"rewards/accuracies": 1.0,
|
1011 |
+
"rewards/chosen": 8.188321113586426,
|
1012 |
+
"rewards/margins": 18.007652282714844,
|
1013 |
+
"rewards/rejected": -9.819330215454102,
|
1014 |
+
"step": 67
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 1.0975609756097562,
|
1018 |
+
"grad_norm": 0.4934139549732208,
|
1019 |
+
"learning_rate": 0.00017164567402983152,
|
1020 |
+
"logits/chosen": 0.7908147573471069,
|
1021 |
+
"logits/rejected": 1.0772439241409302,
|
1022 |
+
"logps/chosen": -869.843017578125,
|
1023 |
+
"logps/rejected": -729.0626831054688,
|
1024 |
+
"loss": 0.0024,
|
1025 |
+
"rewards/accuracies": 1.0,
|
1026 |
+
"rewards/chosen": 8.537101745605469,
|
1027 |
+
"rewards/margins": 12.491724014282227,
|
1028 |
+
"rewards/rejected": -3.9546217918395996,
|
1029 |
+
"step": 68
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 1.113821138211382,
|
1033 |
+
"grad_norm": 2.1183014098369313e-07,
|
1034 |
+
"learning_rate": 0.00017071067811865476,
|
1035 |
+
"logits/chosen": 0.6217237710952759,
|
1036 |
+
"logits/rejected": 0.5386490225791931,
|
1037 |
+
"logps/chosen": -799.1664428710938,
|
1038 |
+
"logps/rejected": -820.0735473632812,
|
1039 |
+
"loss": 0.0,
|
1040 |
+
"rewards/accuracies": 1.0,
|
1041 |
+
"rewards/chosen": 12.295455932617188,
|
1042 |
+
"rewards/margins": 30.9702091217041,
|
1043 |
+
"rewards/rejected": -18.674753189086914,
|
1044 |
+
"step": 69
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 1.1300813008130082,
|
1048 |
+
"grad_norm": 7.591093162773177e-05,
|
1049 |
+
"learning_rate": 0.0001697631521134985,
|
1050 |
+
"logits/chosen": 1.664866328239441,
|
1051 |
+
"logits/rejected": 1.980355978012085,
|
1052 |
+
"logps/chosen": -1113.451416015625,
|
1053 |
+
"logps/rejected": -825.9473876953125,
|
1054 |
+
"loss": 0.0,
|
1055 |
+
"rewards/accuracies": 1.0,
|
1056 |
+
"rewards/chosen": 11.451591491699219,
|
1057 |
+
"rewards/margins": 29.68605613708496,
|
1058 |
+
"rewards/rejected": -18.23446273803711,
|
1059 |
+
"step": 70
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 1.146341463414634,
|
1063 |
+
"grad_norm": 4.4439241264626617e-07,
|
1064 |
+
"learning_rate": 0.00016880326391813916,
|
1065 |
+
"logits/chosen": -0.02196294069290161,
|
1066 |
+
"logits/rejected": 0.18253503739833832,
|
1067 |
+
"logps/chosen": -661.0505981445312,
|
1068 |
+
"logps/rejected": -834.158203125,
|
1069 |
+
"loss": 0.0,
|
1070 |
+
"rewards/accuracies": 1.0,
|
1071 |
+
"rewards/chosen": 9.791834831237793,
|
1072 |
+
"rewards/margins": 28.233205795288086,
|
1073 |
+
"rewards/rejected": -18.441370010375977,
|
1074 |
+
"step": 71
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 1.1626016260162602,
|
1078 |
+
"grad_norm": 8.045230060815811e-05,
|
1079 |
+
"learning_rate": 0.00016783118362696163,
|
1080 |
+
"logits/chosen": 0.24465110898017883,
|
1081 |
+
"logits/rejected": 0.2313007265329361,
|
1082 |
+
"logps/chosen": -715.2831420898438,
|
1083 |
+
"logps/rejected": -1050.01171875,
|
1084 |
+
"loss": 0.0,
|
1085 |
+
"rewards/accuracies": 1.0,
|
1086 |
+
"rewards/chosen": 4.176504611968994,
|
1087 |
+
"rewards/margins": 19.875812530517578,
|
1088 |
+
"rewards/rejected": -15.699307441711426,
|
1089 |
+
"step": 72
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 1.1788617886178863,
|
1093 |
+
"grad_norm": 5.927664005866973e-06,
|
1094 |
+
"learning_rate": 0.00016684708349481804,
|
1095 |
+
"logits/chosen": 1.5342342853546143,
|
1096 |
+
"logits/rejected": 2.0414443016052246,
|
1097 |
+
"logps/chosen": -1195.0989990234375,
|
1098 |
+
"logps/rejected": -652.9114990234375,
|
1099 |
+
"loss": 0.0,
|
1100 |
+
"rewards/accuracies": 1.0,
|
1101 |
+
"rewards/chosen": 8.883450508117676,
|
1102 |
+
"rewards/margins": 19.403560638427734,
|
1103 |
+
"rewards/rejected": -10.520109176635742,
|
1104 |
+
"step": 73
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 1.1951219512195121,
|
1108 |
+
"grad_norm": 1.7679340089671314e-05,
|
1109 |
+
"learning_rate": 0.00016585113790650388,
|
1110 |
+
"logits/chosen": 0.13918209075927734,
|
1111 |
+
"logits/rejected": 0.21283580362796783,
|
1112 |
+
"logps/chosen": -937.8267211914062,
|
1113 |
+
"logps/rejected": -958.693115234375,
|
1114 |
+
"loss": 0.0,
|
1115 |
+
"rewards/accuracies": 1.0,
|
1116 |
+
"rewards/chosen": 9.578910827636719,
|
1117 |
+
"rewards/margins": 31.493125915527344,
|
1118 |
+
"rewards/rejected": -21.914215087890625,
|
1119 |
+
"step": 74
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 1.2113821138211383,
|
1123 |
+
"grad_norm": 9.838218102231622e-05,
|
1124 |
+
"learning_rate": 0.00016484352334585653,
|
1125 |
+
"logits/chosen": 1.7902581691741943,
|
1126 |
+
"logits/rejected": 1.8008999824523926,
|
1127 |
+
"logps/chosen": -898.8333740234375,
|
1128 |
+
"logps/rejected": -869.8264770507812,
|
1129 |
+
"loss": 0.0,
|
1130 |
+
"rewards/accuracies": 1.0,
|
1131 |
+
"rewards/chosen": 8.36214828491211,
|
1132 |
+
"rewards/margins": 23.546051025390625,
|
1133 |
+
"rewards/rejected": -15.183902740478516,
|
1134 |
+
"step": 75
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 1.2276422764227641,
|
1138 |
+
"grad_norm": 0.00042859543464146554,
|
1139 |
+
"learning_rate": 0.00016382441836448202,
|
1140 |
+
"logits/chosen": 0.40593788027763367,
|
1141 |
+
"logits/rejected": 0.24162518978118896,
|
1142 |
+
"logps/chosen": -713.95263671875,
|
1143 |
+
"logps/rejected": -873.909423828125,
|
1144 |
+
"loss": 0.0,
|
1145 |
+
"rewards/accuracies": 1.0,
|
1146 |
+
"rewards/chosen": 3.870103359222412,
|
1147 |
+
"rewards/margins": 17.166872024536133,
|
1148 |
+
"rewards/rejected": -13.296768188476562,
|
1149 |
+
"step": 76
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 1.2439024390243902,
|
1153 |
+
"grad_norm": 0.0007489994168281555,
|
1154 |
+
"learning_rate": 0.0001627940035501152,
|
1155 |
+
"logits/chosen": 1.2316575050354004,
|
1156 |
+
"logits/rejected": 1.2072526216506958,
|
1157 |
+
"logps/chosen": -961.4344482421875,
|
1158 |
+
"logps/rejected": -1073.3685302734375,
|
1159 |
+
"loss": 0.0,
|
1160 |
+
"rewards/accuracies": 1.0,
|
1161 |
+
"rewards/chosen": 6.6541852951049805,
|
1162 |
+
"rewards/margins": 27.57451057434082,
|
1163 |
+
"rewards/rejected": -20.920326232910156,
|
1164 |
+
"step": 77
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 1.2601626016260163,
|
1168 |
+
"grad_norm": 3.269678200013004e-05,
|
1169 |
+
"learning_rate": 0.0001617524614946192,
|
1170 |
+
"logits/chosen": 0.06140974164009094,
|
1171 |
+
"logits/rejected": 0.11881747841835022,
|
1172 |
+
"logps/chosen": -900.48876953125,
|
1173 |
+
"logps/rejected": -1085.7061767578125,
|
1174 |
+
"loss": 0.0,
|
1175 |
+
"rewards/accuracies": 1.0,
|
1176 |
+
"rewards/chosen": 0.6411392688751221,
|
1177 |
+
"rewards/margins": 19.955745697021484,
|
1178 |
+
"rewards/rejected": -19.314605712890625,
|
1179 |
+
"step": 78
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 1.2764227642276422,
|
1183 |
+
"grad_norm": 3.813441480815527e-06,
|
1184 |
+
"learning_rate": 0.0001606999767616298,
|
1185 |
+
"logits/chosen": 1.1457127332687378,
|
1186 |
+
"logits/rejected": 0.8977339267730713,
|
1187 |
+
"logps/chosen": -757.8355712890625,
|
1188 |
+
"logps/rejected": -838.0936279296875,
|
1189 |
+
"loss": 0.0,
|
1190 |
+
"rewards/accuracies": 1.0,
|
1191 |
+
"rewards/chosen": 8.651698112487793,
|
1192 |
+
"rewards/margins": 31.715707778930664,
|
1193 |
+
"rewards/rejected": -23.064010620117188,
|
1194 |
+
"step": 79
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 1.2926829268292683,
|
1198 |
+
"grad_norm": 2.5300651032011956e-05,
|
1199 |
+
"learning_rate": 0.00015963673585385016,
|
1200 |
+
"logits/chosen": -0.5050560235977173,
|
1201 |
+
"logits/rejected": -0.5818659067153931,
|
1202 |
+
"logps/chosen": -833.4871826171875,
|
1203 |
+
"logps/rejected": -1177.144287109375,
|
1204 |
+
"loss": 0.0,
|
1205 |
+
"rewards/accuracies": 1.0,
|
1206 |
+
"rewards/chosen": 0.1878601312637329,
|
1207 |
+
"rewards/margins": 28.51848602294922,
|
1208 |
+
"rewards/rejected": -28.330625534057617,
|
1209 |
+
"step": 80
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 1.3089430894308944,
|
1213 |
+
"grad_norm": 6.81912133586593e-05,
|
1214 |
+
"learning_rate": 0.00015856292718000235,
|
1215 |
+
"logits/chosen": 1.6245973110198975,
|
1216 |
+
"logits/rejected": 1.942758560180664,
|
1217 |
+
"logps/chosen": -925.15966796875,
|
1218 |
+
"logps/rejected": -746.8193969726562,
|
1219 |
+
"loss": 0.0,
|
1220 |
+
"rewards/accuracies": 1.0,
|
1221 |
+
"rewards/chosen": 9.29654598236084,
|
1222 |
+
"rewards/margins": 26.77484893798828,
|
1223 |
+
"rewards/rejected": -17.478303909301758,
|
1224 |
+
"step": 81
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 1.3252032520325203,
|
1228 |
+
"grad_norm": 1.1350484783179127e-06,
|
1229 |
+
"learning_rate": 0.0001574787410214407,
|
1230 |
+
"logits/chosen": 0.8831353187561035,
|
1231 |
+
"logits/rejected": 1.1747808456420898,
|
1232 |
+
"logps/chosen": -812.7021484375,
|
1233 |
+
"logps/rejected": -1058.893310546875,
|
1234 |
+
"loss": 0.0,
|
1235 |
+
"rewards/accuracies": 1.0,
|
1236 |
+
"rewards/chosen": 3.832669258117676,
|
1237 |
+
"rewards/margins": 33.81871795654297,
|
1238 |
+
"rewards/rejected": -29.986047744750977,
|
1239 |
+
"step": 82
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 1.3414634146341464,
|
1243 |
+
"grad_norm": 7.43222301480273e-07,
|
1244 |
+
"learning_rate": 0.0001563843694984336,
|
1245 |
+
"logits/chosen": 1.199593424797058,
|
1246 |
+
"logits/rejected": 1.2259372472763062,
|
1247 |
+
"logps/chosen": -846.8779296875,
|
1248 |
+
"logps/rejected": -1035.00244140625,
|
1249 |
+
"loss": 0.0,
|
1250 |
+
"rewards/accuracies": 1.0,
|
1251 |
+
"rewards/chosen": 4.645470142364502,
|
1252 |
+
"rewards/margins": 35.18595886230469,
|
1253 |
+
"rewards/rejected": -30.540489196777344,
|
1254 |
+
"step": 83
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 1.3577235772357723,
|
1258 |
+
"grad_norm": 4.4819596951128915e-05,
|
1259 |
+
"learning_rate": 0.00015528000653611935,
|
1260 |
+
"logits/chosen": 1.7928721904754639,
|
1261 |
+
"logits/rejected": 2.1661128997802734,
|
1262 |
+
"logps/chosen": -932.3726806640625,
|
1263 |
+
"logps/rejected": -844.2169189453125,
|
1264 |
+
"loss": 0.0,
|
1265 |
+
"rewards/accuracies": 1.0,
|
1266 |
+
"rewards/chosen": 4.103044509887695,
|
1267 |
+
"rewards/margins": 21.569711685180664,
|
1268 |
+
"rewards/rejected": -17.4666690826416,
|
1269 |
+
"step": 84
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.3739837398373984,
|
1273 |
+
"grad_norm": 7.042069594120903e-09,
|
1274 |
+
"learning_rate": 0.0001541658478301421,
|
1275 |
+
"logits/chosen": 0.2531038522720337,
|
1276 |
+
"logits/rejected": 0.2639998197555542,
|
1277 |
+
"logps/chosen": -1010.8427734375,
|
1278 |
+
"logps/rejected": -1247.974609375,
|
1279 |
+
"loss": 0.0,
|
1280 |
+
"rewards/accuracies": 1.0,
|
1281 |
+
"rewards/chosen": 0.7464678287506104,
|
1282 |
+
"rewards/margins": 30.038406372070312,
|
1283 |
+
"rewards/rejected": -29.291942596435547,
|
1284 |
+
"step": 85
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 1.3902439024390243,
|
1288 |
+
"grad_norm": 2.4762075057083166e-08,
|
1289 |
+
"learning_rate": 0.00015304209081197425,
|
1290 |
+
"logits/chosen": 2.228158473968506,
|
1291 |
+
"logits/rejected": 2.7146129608154297,
|
1292 |
+
"logps/chosen": -1221.494384765625,
|
1293 |
+
"logps/rejected": -882.4944458007812,
|
1294 |
+
"loss": 0.0,
|
1295 |
+
"rewards/accuracies": 1.0,
|
1296 |
+
"rewards/chosen": 13.98241901397705,
|
1297 |
+
"rewards/margins": 33.62451171875,
|
1298 |
+
"rewards/rejected": -19.642091751098633,
|
1299 |
+
"step": 86
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 1.4065040650406504,
|
1303 |
+
"grad_norm": 3.7480401715583866e-06,
|
1304 |
+
"learning_rate": 0.00015190893461393108,
|
1305 |
+
"logits/chosen": 1.5811924934387207,
|
1306 |
+
"logits/rejected": 2.0754153728485107,
|
1307 |
+
"logps/chosen": -958.1056518554688,
|
1308 |
+
"logps/rejected": -741.9910278320312,
|
1309 |
+
"loss": 0.0,
|
1310 |
+
"rewards/accuracies": 1.0,
|
1311 |
+
"rewards/chosen": 14.536327362060547,
|
1312 |
+
"rewards/margins": 32.516456604003906,
|
1313 |
+
"rewards/rejected": -17.980131149291992,
|
1314 |
+
"step": 87
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 1.4227642276422765,
|
1318 |
+
"grad_norm": 1.9098067696177168e-06,
|
1319 |
+
"learning_rate": 0.000150766580033884,
|
1320 |
+
"logits/chosen": 1.6907765865325928,
|
1321 |
+
"logits/rejected": 1.9654494524002075,
|
1322 |
+
"logps/chosen": -1132.77978515625,
|
1323 |
+
"logps/rejected": -908.571044921875,
|
1324 |
+
"loss": 0.0,
|
1325 |
+
"rewards/accuracies": 1.0,
|
1326 |
+
"rewards/chosen": 5.22573709487915,
|
1327 |
+
"rewards/margins": 34.5124626159668,
|
1328 |
+
"rewards/rejected": -29.286724090576172,
|
1329 |
+
"step": 88
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 1.4390243902439024,
|
1333 |
+
"grad_norm": 1.1447126780694816e-05,
|
1334 |
+
"learning_rate": 0.00014961522949967886,
|
1335 |
+
"logits/chosen": 0.9937865734100342,
|
1336 |
+
"logits/rejected": 1.2049672603607178,
|
1337 |
+
"logps/chosen": -739.3209838867188,
|
1338 |
+
"logps/rejected": -1007.2611083984375,
|
1339 |
+
"loss": 0.0,
|
1340 |
+
"rewards/accuracies": 1.0,
|
1341 |
+
"rewards/chosen": 10.235821723937988,
|
1342 |
+
"rewards/margins": 34.75508499145508,
|
1343 |
+
"rewards/rejected": -24.51926040649414,
|
1344 |
+
"step": 89
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 1.4552845528455285,
|
1348 |
+
"grad_norm": 1.5996234026260936e-07,
|
1349 |
+
"learning_rate": 0.00014845508703326504,
|
1350 |
+
"logits/chosen": 1.005773663520813,
|
1351 |
+
"logits/rejected": 0.9975143671035767,
|
1352 |
+
"logps/chosen": -912.9910278320312,
|
1353 |
+
"logps/rejected": -1205.926513671875,
|
1354 |
+
"loss": 0.0,
|
1355 |
+
"rewards/accuracies": 1.0,
|
1356 |
+
"rewards/chosen": 2.948190212249756,
|
1357 |
+
"rewards/margins": 31.25839614868164,
|
1358 |
+
"rewards/rejected": -28.310203552246094,
|
1359 |
+
"step": 90
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 1.4715447154471546,
|
1363 |
+
"grad_norm": 1.9003784473170526e-05,
|
1364 |
+
"learning_rate": 0.00014728635821454255,
|
1365 |
+
"logits/chosen": 2.574889659881592,
|
1366 |
+
"logits/rejected": 2.5759711265563965,
|
1367 |
+
"logps/chosen": -915.0121459960938,
|
1368 |
+
"logps/rejected": -623.8654174804688,
|
1369 |
+
"loss": 0.0,
|
1370 |
+
"rewards/accuracies": 1.0,
|
1371 |
+
"rewards/chosen": 15.099142074584961,
|
1372 |
+
"rewards/margins": 31.881959915161133,
|
1373 |
+
"rewards/rejected": -16.782817840576172,
|
1374 |
+
"step": 91
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 1.4878048780487805,
|
1378 |
+
"grad_norm": 4.1650441318097364e-08,
|
1379 |
+
"learning_rate": 0.0001461092501449326,
|
1380 |
+
"logits/chosen": 1.0031987428665161,
|
1381 |
+
"logits/rejected": 1.2941582202911377,
|
1382 |
+
"logps/chosen": -823.1492309570312,
|
1383 |
+
"logps/rejected": -1055.567626953125,
|
1384 |
+
"loss": 0.0,
|
1385 |
+
"rewards/accuracies": 1.0,
|
1386 |
+
"rewards/chosen": 2.4376673698425293,
|
1387 |
+
"rewards/margins": 26.05483055114746,
|
1388 |
+
"rewards/rejected": -23.617162704467773,
|
1389 |
+
"step": 92
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.5040650406504064,
|
1393 |
+
"grad_norm": 4.165614697626552e-08,
|
1394 |
+
"learning_rate": 0.00014492397141067887,
|
1395 |
+
"logits/chosen": 0.8133536577224731,
|
1396 |
+
"logits/rejected": 1.0407506227493286,
|
1397 |
+
"logps/chosen": -961.2422485351562,
|
1398 |
+
"logps/rejected": -1156.6856689453125,
|
1399 |
+
"loss": 0.0,
|
1400 |
+
"rewards/accuracies": 1.0,
|
1401 |
+
"rewards/chosen": 1.8701601028442383,
|
1402 |
+
"rewards/margins": 33.655277252197266,
|
1403 |
+
"rewards/rejected": -31.785114288330078,
|
1404 |
+
"step": 93
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 1.5203252032520327,
|
1408 |
+
"grad_norm": 3.824939540209016e-06,
|
1409 |
+
"learning_rate": 0.00014373073204588556,
|
1410 |
+
"logits/chosen": 2.6779818534851074,
|
1411 |
+
"logits/rejected": 2.7686123847961426,
|
1412 |
+
"logps/chosen": -1121.3564453125,
|
1413 |
+
"logps/rejected": -698.586669921875,
|
1414 |
+
"loss": 0.0,
|
1415 |
+
"rewards/accuracies": 1.0,
|
1416 |
+
"rewards/chosen": 10.171032905578613,
|
1417 |
+
"rewards/margins": 27.788890838623047,
|
1418 |
+
"rewards/rejected": -17.617855072021484,
|
1419 |
+
"step": 94
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 1.5365853658536586,
|
1423 |
+
"grad_norm": 3.954168641939759e-05,
|
1424 |
+
"learning_rate": 0.0001425297434952987,
|
1425 |
+
"logits/chosen": 0.22321929037570953,
|
1426 |
+
"logits/rejected": 0.2271191030740738,
|
1427 |
+
"logps/chosen": -671.6175537109375,
|
1428 |
+
"logps/rejected": -1141.6953125,
|
1429 |
+
"loss": 0.0,
|
1430 |
+
"rewards/accuracies": 1.0,
|
1431 |
+
"rewards/chosen": -2.185655355453491,
|
1432 |
+
"rewards/margins": 26.3375301361084,
|
1433 |
+
"rewards/rejected": -28.52318572998047,
|
1434 |
+
"step": 95
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 1.5528455284552845,
|
1438 |
+
"grad_norm": 6.408844566152538e-10,
|
1439 |
+
"learning_rate": 0.00014132121857683783,
|
1440 |
+
"logits/chosen": 1.1100516319274902,
|
1441 |
+
"logits/rejected": 1.0310027599334717,
|
1442 |
+
"logps/chosen": -995.9828491210938,
|
1443 |
+
"logps/rejected": -1024.00244140625,
|
1444 |
+
"loss": 0.0,
|
1445 |
+
"rewards/accuracies": 1.0,
|
1446 |
+
"rewards/chosen": 8.543378829956055,
|
1447 |
+
"rewards/margins": 33.411643981933594,
|
1448 |
+
"rewards/rejected": -24.868263244628906,
|
1449 |
+
"step": 96
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 1.5691056910569106,
|
1453 |
+
"grad_norm": 6.710484399263805e-07,
|
1454 |
+
"learning_rate": 0.00014010537144388416,
|
1455 |
+
"logits/chosen": 0.19941049814224243,
|
1456 |
+
"logits/rejected": 0.2904074490070343,
|
1457 |
+
"logps/chosen": -580.1328125,
|
1458 |
+
"logps/rejected": -1122.187744140625,
|
1459 |
+
"loss": 0.0,
|
1460 |
+
"rewards/accuracies": 1.0,
|
1461 |
+
"rewards/chosen": -0.563772439956665,
|
1462 |
+
"rewards/margins": 23.33687400817871,
|
1463 |
+
"rewards/rejected": -23.900646209716797,
|
1464 |
+
"step": 97
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 1.5853658536585367,
|
1468 |
+
"grad_norm": 2.6136473252336145e-07,
|
1469 |
+
"learning_rate": 0.00013888241754733208,
|
1470 |
+
"logits/chosen": 0.8143081665039062,
|
1471 |
+
"logits/rejected": 1.183271050453186,
|
1472 |
+
"logps/chosen": -973.23583984375,
|
1473 |
+
"logps/rejected": -904.20556640625,
|
1474 |
+
"loss": 0.0,
|
1475 |
+
"rewards/accuracies": 1.0,
|
1476 |
+
"rewards/chosen": 3.3894622325897217,
|
1477 |
+
"rewards/margins": 23.915855407714844,
|
1478 |
+
"rewards/rejected": -20.526391983032227,
|
1479 |
+
"step": 98
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 1.6016260162601625,
|
1483 |
+
"grad_norm": 1.735031582938973e-05,
|
1484 |
+
"learning_rate": 0.00013765257359741063,
|
1485 |
+
"logits/chosen": 0.8897725343704224,
|
1486 |
+
"logits/rejected": 0.8052040338516235,
|
1487 |
+
"logps/chosen": -771.9832763671875,
|
1488 |
+
"logps/rejected": -874.3773193359375,
|
1489 |
+
"loss": 0.0,
|
1490 |
+
"rewards/accuracies": 1.0,
|
1491 |
+
"rewards/chosen": 6.943796157836914,
|
1492 |
+
"rewards/margins": 29.497058868408203,
|
1493 |
+
"rewards/rejected": -22.55326271057129,
|
1494 |
+
"step": 99
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 1.6178861788617886,
|
1498 |
+
"grad_norm": 1.2570103535836097e-07,
|
1499 |
+
"learning_rate": 0.00013641605752528224,
|
1500 |
+
"logits/chosen": 1.0415421724319458,
|
1501 |
+
"logits/rejected": 1.3014307022094727,
|
1502 |
+
"logps/chosen": -918.8525390625,
|
1503 |
+
"logps/rejected": -955.0538330078125,
|
1504 |
+
"loss": 0.0,
|
1505 |
+
"rewards/accuracies": 1.0,
|
1506 |
+
"rewards/chosen": 7.44915771484375,
|
1507 |
+
"rewards/margins": 33.4973258972168,
|
1508 |
+
"rewards/rejected": -26.04817008972168,
|
1509 |
+
"step": 100
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 1.6341463414634148,
|
1513 |
+
"grad_norm": 3.719053154327412e-07,
|
1514 |
+
"learning_rate": 0.0001351730884444245,
|
1515 |
+
"logits/chosen": 0.4167521595954895,
|
1516 |
+
"logits/rejected": 0.3483416438102722,
|
1517 |
+
"logps/chosen": -604.3650512695312,
|
1518 |
+
"logps/rejected": -1362.02587890625,
|
1519 |
+
"loss": 0.0,
|
1520 |
+
"rewards/accuracies": 1.0,
|
1521 |
+
"rewards/chosen": -2.4617691040039062,
|
1522 |
+
"rewards/margins": 44.77275466918945,
|
1523 |
+
"rewards/rejected": -47.23452377319336,
|
1524 |
+
"step": 101
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 1.6504065040650406,
|
1528 |
+
"grad_norm": 1.487089633656069e-07,
|
1529 |
+
"learning_rate": 0.00013392388661180303,
|
1530 |
+
"logits/chosen": 0.9698238968849182,
|
1531 |
+
"logits/rejected": 1.1324440240859985,
|
1532 |
+
"logps/chosen": -742.9386596679688,
|
1533 |
+
"logps/rejected": -905.581298828125,
|
1534 |
+
"loss": 0.0,
|
1535 |
+
"rewards/accuracies": 1.0,
|
1536 |
+
"rewards/chosen": 5.503021717071533,
|
1537 |
+
"rewards/margins": 32.864501953125,
|
1538 |
+
"rewards/rejected": -27.361482620239258,
|
1539 |
+
"step": 102
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 1.6666666666666665,
|
1543 |
+
"grad_norm": 0.00015168750542216003,
|
1544 |
+
"learning_rate": 0.0001326686733888413,
|
1545 |
+
"logits/chosen": 2.734503746032715,
|
1546 |
+
"logits/rejected": 2.7868616580963135,
|
1547 |
+
"logps/chosen": -845.9635009765625,
|
1548 |
+
"logps/rejected": -674.9261474609375,
|
1549 |
+
"loss": 0.0,
|
1550 |
+
"rewards/accuracies": 1.0,
|
1551 |
+
"rewards/chosen": 6.455021858215332,
|
1552 |
+
"rewards/margins": 21.768619537353516,
|
1553 |
+
"rewards/rejected": -15.3135986328125,
|
1554 |
+
"step": 103
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 1.6829268292682928,
|
1558 |
+
"grad_norm": 5.236762717686361e-06,
|
1559 |
+
"learning_rate": 0.0001314076712021949,
|
1560 |
+
"logits/chosen": 0.8474237322807312,
|
1561 |
+
"logits/rejected": 1.0795999765396118,
|
1562 |
+
"logps/chosen": -844.8881225585938,
|
1563 |
+
"logps/rejected": -1026.413818359375,
|
1564 |
+
"loss": 0.0,
|
1565 |
+
"rewards/accuracies": 1.0,
|
1566 |
+
"rewards/chosen": 9.01052474975586,
|
1567 |
+
"rewards/margins": 34.12953186035156,
|
1568 |
+
"rewards/rejected": -25.119007110595703,
|
1569 |
+
"step": 104
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 1.6991869918699187,
|
1573 |
+
"grad_norm": 4.3044991571150604e-08,
|
1574 |
+
"learning_rate": 0.000130141103504337,
|
1575 |
+
"logits/chosen": 1.0104427337646484,
|
1576 |
+
"logits/rejected": 0.809540867805481,
|
1577 |
+
"logps/chosen": -806.0650634765625,
|
1578 |
+
"logps/rejected": -1019.7612915039062,
|
1579 |
+
"loss": 0.0,
|
1580 |
+
"rewards/accuracies": 1.0,
|
1581 |
+
"rewards/chosen": 7.093156814575195,
|
1582 |
+
"rewards/margins": 29.144248962402344,
|
1583 |
+
"rewards/rejected": -22.051090240478516,
|
1584 |
+
"step": 105
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 1.7154471544715446,
|
1588 |
+
"grad_norm": 6.236035243745164e-09,
|
1589 |
+
"learning_rate": 0.0001288691947339621,
|
1590 |
+
"logits/chosen": 0.26283663511276245,
|
1591 |
+
"logits/rejected": 0.21620601415634155,
|
1592 |
+
"logps/chosen": -764.7117919921875,
|
1593 |
+
"logps/rejected": -1384.037353515625,
|
1594 |
+
"loss": 0.0,
|
1595 |
+
"rewards/accuracies": 1.0,
|
1596 |
+
"rewards/chosen": -0.5661294460296631,
|
1597 |
+
"rewards/margins": 35.904212951660156,
|
1598 |
+
"rewards/rejected": -36.470340728759766,
|
1599 |
+
"step": 106
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 1.7317073170731707,
|
1603 |
+
"grad_norm": 0.0002312189608346671,
|
1604 |
+
"learning_rate": 0.00012759217027621505,
|
1605 |
+
"logits/chosen": 0.8271576166152954,
|
1606 |
+
"logits/rejected": 0.8352835178375244,
|
1607 |
+
"logps/chosen": -639.9276123046875,
|
1608 |
+
"logps/rejected": -721.3944702148438,
|
1609 |
+
"loss": 0.0,
|
1610 |
+
"rewards/accuracies": 1.0,
|
1611 |
+
"rewards/chosen": 3.1902108192443848,
|
1612 |
+
"rewards/margins": 19.32707977294922,
|
1613 |
+
"rewards/rejected": -16.13686752319336,
|
1614 |
+
"step": 107
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 1.7479674796747968,
|
1618 |
+
"grad_norm": 5.53435963723814e-09,
|
1619 |
+
"learning_rate": 0.00012631025642275212,
|
1620 |
+
"logits/chosen": 0.9540997743606567,
|
1621 |
+
"logits/rejected": 1.0216646194458008,
|
1622 |
+
"logps/chosen": -920.1544189453125,
|
1623 |
+
"logps/rejected": -919.189453125,
|
1624 |
+
"loss": 0.0,
|
1625 |
+
"rewards/accuracies": 1.0,
|
1626 |
+
"rewards/chosen": 8.917628288269043,
|
1627 |
+
"rewards/margins": 31.62308692932129,
|
1628 |
+
"rewards/rejected": -22.705459594726562,
|
1629 |
+
"step": 108
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 1.7642276422764227,
|
1633 |
+
"grad_norm": 5.7604488290508016e-08,
|
1634 |
+
"learning_rate": 0.00012502368033164176,
|
1635 |
+
"logits/chosen": 1.9378834962844849,
|
1636 |
+
"logits/rejected": 2.0527262687683105,
|
1637 |
+
"logps/chosen": -616.1436767578125,
|
1638 |
+
"logps/rejected": -781.5704956054688,
|
1639 |
+
"loss": 0.0,
|
1640 |
+
"rewards/accuracies": 1.0,
|
1641 |
+
"rewards/chosen": 4.269429683685303,
|
1642 |
+
"rewards/margins": 27.761857986450195,
|
1643 |
+
"rewards/rejected": -23.492429733276367,
|
1644 |
+
"step": 109
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 1.7804878048780488,
|
1648 |
+
"grad_norm": 3.0333463740817024e-08,
|
1649 |
+
"learning_rate": 0.0001237326699871115,
|
1650 |
+
"logits/chosen": 0.784665584564209,
|
1651 |
+
"logits/rejected": 1.0081039667129517,
|
1652 |
+
"logps/chosen": -864.7948608398438,
|
1653 |
+
"logps/rejected": -946.906982421875,
|
1654 |
+
"loss": 0.0,
|
1655 |
+
"rewards/accuracies": 1.0,
|
1656 |
+
"rewards/chosen": 6.097116470336914,
|
1657 |
+
"rewards/margins": 30.87978172302246,
|
1658 |
+
"rewards/rejected": -24.78266716003418,
|
1659 |
+
"step": 110
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 1.796747967479675,
|
1663 |
+
"grad_norm": 3.1582476367475465e-07,
|
1664 |
+
"learning_rate": 0.00012243745415914883,
|
1665 |
+
"logits/chosen": -0.5353690385818481,
|
1666 |
+
"logits/rejected": -0.6592149138450623,
|
1667 |
+
"logps/chosen": -722.5419921875,
|
1668 |
+
"logps/rejected": -1070.7403564453125,
|
1669 |
+
"loss": 0.0,
|
1670 |
+
"rewards/accuracies": 1.0,
|
1671 |
+
"rewards/chosen": -1.3367981910705566,
|
1672 |
+
"rewards/margins": 27.85375213623047,
|
1673 |
+
"rewards/rejected": -29.190549850463867,
|
1674 |
+
"step": 111
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 1.8130081300813008,
|
1678 |
+
"grad_norm": 2.334864745989762e-07,
|
1679 |
+
"learning_rate": 0.00012113826236296244,
|
1680 |
+
"logits/chosen": 1.986028790473938,
|
1681 |
+
"logits/rejected": 2.0000312328338623,
|
1682 |
+
"logps/chosen": -1034.116455078125,
|
1683 |
+
"logps/rejected": -924.2823486328125,
|
1684 |
+
"loss": 0.0,
|
1685 |
+
"rewards/accuracies": 1.0,
|
1686 |
+
"rewards/chosen": 9.337306022644043,
|
1687 |
+
"rewards/margins": 34.88032531738281,
|
1688 |
+
"rewards/rejected": -25.54302215576172,
|
1689 |
+
"step": 112
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 1.8292682926829267,
|
1693 |
+
"grad_norm": 1.956110463652294e-05,
|
1694 |
+
"learning_rate": 0.0001198353248183118,
|
1695 |
+
"logits/chosen": 1.1676946878433228,
|
1696 |
+
"logits/rejected": 1.3392938375473022,
|
1697 |
+
"logps/chosen": -839.8267211914062,
|
1698 |
+
"logps/rejected": -966.1685180664062,
|
1699 |
+
"loss": 0.0,
|
1700 |
+
"rewards/accuracies": 1.0,
|
1701 |
+
"rewards/chosen": 4.940967082977295,
|
1702 |
+
"rewards/margins": 33.268653869628906,
|
1703 |
+
"rewards/rejected": -28.327686309814453,
|
1704 |
+
"step": 113
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 1.845528455284553,
|
1708 |
+
"grad_norm": 1.2582788144754886e-07,
|
1709 |
+
"learning_rate": 0.00011852887240871145,
|
1710 |
+
"logits/chosen": 1.7121946811676025,
|
1711 |
+
"logits/rejected": 1.834307074546814,
|
1712 |
+
"logps/chosen": -825.6591796875,
|
1713 |
+
"logps/rejected": -910.5638427734375,
|
1714 |
+
"loss": 0.0,
|
1715 |
+
"rewards/accuracies": 1.0,
|
1716 |
+
"rewards/chosen": 5.057826519012451,
|
1717 |
+
"rewards/margins": 26.722637176513672,
|
1718 |
+
"rewards/rejected": -21.664812088012695,
|
1719 |
+
"step": 114
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 1.8617886178861789,
|
1723 |
+
"grad_norm": 3.8171506275830325e-06,
|
1724 |
+
"learning_rate": 0.00011721913664051813,
|
1725 |
+
"logits/chosen": 0.09213051199913025,
|
1726 |
+
"logits/rejected": 0.2805327773094177,
|
1727 |
+
"logps/chosen": -785.7156982421875,
|
1728 |
+
"logps/rejected": -1021.4864501953125,
|
1729 |
+
"loss": 0.0,
|
1730 |
+
"rewards/accuracies": 1.0,
|
1731 |
+
"rewards/chosen": 0.823834240436554,
|
1732 |
+
"rewards/margins": 25.152664184570312,
|
1733 |
+
"rewards/rejected": -24.32883071899414,
|
1734 |
+
"step": 115
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 1.8780487804878048,
|
1738 |
+
"grad_norm": 2.6529932029006886e-08,
|
1739 |
+
"learning_rate": 0.00011590634960190721,
|
1740 |
+
"logits/chosen": -0.5069230198860168,
|
1741 |
+
"logits/rejected": -0.5888826847076416,
|
1742 |
+
"logps/chosen": -707.7698974609375,
|
1743 |
+
"logps/rejected": -1266.01904296875,
|
1744 |
+
"loss": 0.0,
|
1745 |
+
"rewards/accuracies": 1.0,
|
1746 |
+
"rewards/chosen": 0.027275919914245605,
|
1747 |
+
"rewards/margins": 27.478078842163086,
|
1748 |
+
"rewards/rejected": -27.450803756713867,
|
1749 |
+
"step": 116
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 1.8943089430894309,
|
1753 |
+
"grad_norm": 9.935014304573997e-07,
|
1754 |
+
"learning_rate": 0.00011459074392174618,
|
1755 |
+
"logits/chosen": 1.5636107921600342,
|
1756 |
+
"logits/rejected": 1.8575186729431152,
|
1757 |
+
"logps/chosen": -1191.93359375,
|
1758 |
+
"logps/rejected": -990.843505859375,
|
1759 |
+
"loss": 0.0,
|
1760 |
+
"rewards/accuracies": 1.0,
|
1761 |
+
"rewards/chosen": 12.92037582397461,
|
1762 |
+
"rewards/margins": 39.89407730102539,
|
1763 |
+
"rewards/rejected": -26.973697662353516,
|
1764 |
+
"step": 117
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 1.910569105691057,
|
1768 |
+
"grad_norm": 1.2037819942634087e-05,
|
1769 |
+
"learning_rate": 0.00011327255272837221,
|
1770 |
+
"logits/chosen": 1.0499224662780762,
|
1771 |
+
"logits/rejected": 0.9787989854812622,
|
1772 |
+
"logps/chosen": -971.0214233398438,
|
1773 |
+
"logps/rejected": -877.3848876953125,
|
1774 |
+
"loss": 0.0,
|
1775 |
+
"rewards/accuracies": 1.0,
|
1776 |
+
"rewards/chosen": 2.003582715988159,
|
1777 |
+
"rewards/margins": 20.236526489257812,
|
1778 |
+
"rewards/rejected": -18.23294448852539,
|
1779 |
+
"step": 118
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 1.9268292682926829,
|
1783 |
+
"grad_norm": 1.8166872450819938e-06,
|
1784 |
+
"learning_rate": 0.00011195200960828139,
|
1785 |
+
"logits/chosen": 1.6961169242858887,
|
1786 |
+
"logits/rejected": 2.2738733291625977,
|
1787 |
+
"logps/chosen": -1074.953369140625,
|
1788 |
+
"logps/rejected": -778.5762939453125,
|
1789 |
+
"loss": 0.0,
|
1790 |
+
"rewards/accuracies": 1.0,
|
1791 |
+
"rewards/chosen": 8.411404609680176,
|
1792 |
+
"rewards/margins": 25.984111785888672,
|
1793 |
+
"rewards/rejected": -17.57270622253418,
|
1794 |
+
"step": 119
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 1.943089430894309,
|
1798 |
+
"grad_norm": 0.002434302121400833,
|
1799 |
+
"learning_rate": 0.00011062934856473655,
|
1800 |
+
"logits/chosen": 0.24992449581623077,
|
1801 |
+
"logits/rejected": 0.18503600358963013,
|
1802 |
+
"logps/chosen": -811.4505615234375,
|
1803 |
+
"logps/rejected": -1088.271240234375,
|
1804 |
+
"loss": 0.0,
|
1805 |
+
"rewards/accuracies": 1.0,
|
1806 |
+
"rewards/chosen": 2.826874017715454,
|
1807 |
+
"rewards/margins": 32.1160888671875,
|
1808 |
+
"rewards/rejected": -29.289215087890625,
|
1809 |
+
"step": 120
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.959349593495935,
|
1813 |
+
"grad_norm": 3.818647797970698e-08,
|
1814 |
+
"learning_rate": 0.00010930480397630145,
|
1815 |
+
"logits/chosen": 1.889555811882019,
|
1816 |
+
"logits/rejected": 2.055070400238037,
|
1817 |
+
"logps/chosen": -1008.6806640625,
|
1818 |
+
"logps/rejected": -997.8306884765625,
|
1819 |
+
"loss": 0.0,
|
1820 |
+
"rewards/accuracies": 1.0,
|
1821 |
+
"rewards/chosen": 4.727387428283691,
|
1822 |
+
"rewards/margins": 32.15311813354492,
|
1823 |
+
"rewards/rejected": -27.42573356628418,
|
1824 |
+
"step": 121
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 1.975609756097561,
|
1828 |
+
"grad_norm": 4.203374359690315e-08,
|
1829 |
+
"learning_rate": 0.00010797861055530831,
|
1830 |
+
"logits/chosen": 0.33176711201667786,
|
1831 |
+
"logits/rejected": 0.2883341312408447,
|
1832 |
+
"logps/chosen": -764.9257202148438,
|
1833 |
+
"logps/rejected": -1157.33642578125,
|
1834 |
+
"loss": 0.0,
|
1835 |
+
"rewards/accuracies": 1.0,
|
1836 |
+
"rewards/chosen": -0.931965708732605,
|
1837 |
+
"rewards/margins": 29.445417404174805,
|
1838 |
+
"rewards/rejected": -30.377384185791016,
|
1839 |
+
"step": 122
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 1.9918699186991868,
|
1843 |
+
"grad_norm": 0.0003661888767965138,
|
1844 |
+
"learning_rate": 0.00010665100330626625,
|
1845 |
+
"logits/chosen": 2.023690700531006,
|
1846 |
+
"logits/rejected": 2.543468475341797,
|
1847 |
+
"logps/chosen": -1341.046875,
|
1848 |
+
"logps/rejected": -852.0292358398438,
|
1849 |
+
"loss": 0.0,
|
1850 |
+
"rewards/accuracies": 1.0,
|
1851 |
+
"rewards/chosen": 13.60735034942627,
|
1852 |
+
"rewards/margins": 33.2912483215332,
|
1853 |
+
"rewards/rejected": -19.68389892578125,
|
1854 |
+
"step": 123
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 2.0,
|
1858 |
+
"grad_norm": 1.4813576854066923e-07,
|
1859 |
+
"learning_rate": 0.00010532221748421787,
|
1860 |
+
"logits/chosen": 2.4457969665527344,
|
1861 |
+
"logits/rejected": 2.6656110286712646,
|
1862 |
+
"logps/chosen": -1094.49560546875,
|
1863 |
+
"logps/rejected": -546.4738159179688,
|
1864 |
+
"loss": 0.0,
|
1865 |
+
"rewards/accuracies": 1.0,
|
1866 |
+
"rewards/chosen": 12.480463027954102,
|
1867 |
+
"rewards/margins": 21.069480895996094,
|
1868 |
+
"rewards/rejected": -8.589018821716309,
|
1869 |
+
"step": 124
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 2.016260162601626,
|
1873 |
+
"grad_norm": 1.126546635532577e-06,
|
1874 |
+
"learning_rate": 0.00010399248855305176,
|
1875 |
+
"logits/chosen": 2.4012436866760254,
|
1876 |
+
"logits/rejected": 2.676316022872925,
|
1877 |
+
"logps/chosen": -1016.7650756835938,
|
1878 |
+
"logps/rejected": -629.0308227539062,
|
1879 |
+
"loss": 0.0,
|
1880 |
+
"rewards/accuracies": 1.0,
|
1881 |
+
"rewards/chosen": 10.325331687927246,
|
1882 |
+
"rewards/margins": 25.8978214263916,
|
1883 |
+
"rewards/rejected": -15.572492599487305,
|
1884 |
+
"step": 125
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 2.032520325203252,
|
1888 |
+
"grad_norm": 3.7227684401841543e-07,
|
1889 |
+
"learning_rate": 0.00010266205214377748,
|
1890 |
+
"logits/chosen": 0.39638862013816833,
|
1891 |
+
"logits/rejected": 0.4992075562477112,
|
1892 |
+
"logps/chosen": -648.75,
|
1893 |
+
"logps/rejected": -1030.2962646484375,
|
1894 |
+
"loss": 0.0,
|
1895 |
+
"rewards/accuracies": 1.0,
|
1896 |
+
"rewards/chosen": -1.0494887828826904,
|
1897 |
+
"rewards/margins": 27.84441566467285,
|
1898 |
+
"rewards/rejected": -28.893905639648438,
|
1899 |
+
"step": 126
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 2.048780487804878,
|
1903 |
+
"grad_norm": 8.69819905346958e-06,
|
1904 |
+
"learning_rate": 0.00010133114401277139,
|
1905 |
+
"logits/chosen": 1.1746121644973755,
|
1906 |
+
"logits/rejected": 1.2504253387451172,
|
1907 |
+
"logps/chosen": -591.2756958007812,
|
1908 |
+
"logps/rejected": -956.6802978515625,
|
1909 |
+
"loss": 0.0,
|
1910 |
+
"rewards/accuracies": 1.0,
|
1911 |
+
"rewards/chosen": 6.541916370391846,
|
1912 |
+
"rewards/margins": 27.245861053466797,
|
1913 |
+
"rewards/rejected": -20.70394515991211,
|
1914 |
+
"step": 127
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 2.065040650406504,
|
1918 |
+
"grad_norm": 8.625072211998486e-08,
|
1919 |
+
"learning_rate": 0.0001,
|
1920 |
+
"logits/chosen": 0.2615965008735657,
|
1921 |
+
"logits/rejected": 0.2532449960708618,
|
1922 |
+
"logps/chosen": -716.9295654296875,
|
1923 |
+
"logps/rejected": -1199.100830078125,
|
1924 |
+
"loss": 0.0,
|
1925 |
+
"rewards/accuracies": 1.0,
|
1926 |
+
"rewards/chosen": 2.7087082862854004,
|
1927 |
+
"rewards/margins": 39.123931884765625,
|
1928 |
+
"rewards/rejected": -36.415225982666016,
|
1929 |
+
"step": 128
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 2.08130081300813,
|
1933 |
+
"grad_norm": 1.545291006266325e-08,
|
1934 |
+
"learning_rate": 9.866885598722863e-05,
|
1935 |
+
"logits/chosen": 0.8479726314544678,
|
1936 |
+
"logits/rejected": 0.9798691272735596,
|
1937 |
+
"logps/chosen": -1156.03271484375,
|
1938 |
+
"logps/rejected": -1160.611572265625,
|
1939 |
+
"loss": 0.0,
|
1940 |
+
"rewards/accuracies": 1.0,
|
1941 |
+
"rewards/chosen": 5.804194450378418,
|
1942 |
+
"rewards/margins": 37.919864654541016,
|
1943 |
+
"rewards/rejected": -32.11566925048828,
|
1944 |
+
"step": 129
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"epoch": 2.097560975609756,
|
1948 |
+
"grad_norm": 2.0759840481332503e-05,
|
1949 |
+
"learning_rate": 9.733794785622253e-05,
|
1950 |
+
"logits/chosen": 1.8465713262557983,
|
1951 |
+
"logits/rejected": 1.999639868736267,
|
1952 |
+
"logps/chosen": -1016.758056640625,
|
1953 |
+
"logps/rejected": -908.3006591796875,
|
1954 |
+
"loss": 0.0,
|
1955 |
+
"rewards/accuracies": 1.0,
|
1956 |
+
"rewards/chosen": 13.583747863769531,
|
1957 |
+
"rewards/margins": 40.76252746582031,
|
1958 |
+
"rewards/rejected": -27.178781509399414,
|
1959 |
+
"step": 130
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 2.113821138211382,
|
1963 |
+
"grad_norm": 9.728922805152251e-07,
|
1964 |
+
"learning_rate": 9.600751144694827e-05,
|
1965 |
+
"logits/chosen": 0.35091227293014526,
|
1966 |
+
"logits/rejected": 0.1413639485836029,
|
1967 |
+
"logps/chosen": -736.62158203125,
|
1968 |
+
"logps/rejected": -1333.1005859375,
|
1969 |
+
"loss": 0.0,
|
1970 |
+
"rewards/accuracies": 1.0,
|
1971 |
+
"rewards/chosen": -0.6688979268074036,
|
1972 |
+
"rewards/margins": 32.4841423034668,
|
1973 |
+
"rewards/rejected": -33.153038024902344,
|
1974 |
+
"step": 131
|
1975 |
+
},
|
1976 |
+
{
|
1977 |
+
"epoch": 2.130081300813008,
|
1978 |
+
"grad_norm": 8.801747242159763e-08,
|
1979 |
+
"learning_rate": 9.467778251578217e-05,
|
1980 |
+
"logits/chosen": 0.14253884553909302,
|
1981 |
+
"logits/rejected": 0.12810415029525757,
|
1982 |
+
"logps/chosen": -657.0384521484375,
|
1983 |
+
"logps/rejected": -1078.23388671875,
|
1984 |
+
"loss": 0.0,
|
1985 |
+
"rewards/accuracies": 1.0,
|
1986 |
+
"rewards/chosen": 2.2970056533813477,
|
1987 |
+
"rewards/margins": 37.40379333496094,
|
1988 |
+
"rewards/rejected": -35.106788635253906,
|
1989 |
+
"step": 132
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 2.1463414634146343,
|
1993 |
+
"grad_norm": 1.7610488067809627e-10,
|
1994 |
+
"learning_rate": 9.334899669373379e-05,
|
1995 |
+
"logits/chosen": 1.6143238544464111,
|
1996 |
+
"logits/rejected": 1.877280354499817,
|
1997 |
+
"logps/chosen": -1136.3955078125,
|
1998 |
+
"logps/rejected": -927.5528564453125,
|
1999 |
+
"loss": 0.0,
|
2000 |
+
"rewards/accuracies": 1.0,
|
2001 |
+
"rewards/chosen": 7.586950302124023,
|
2002 |
+
"rewards/margins": 33.43904113769531,
|
2003 |
+
"rewards/rejected": -25.852088928222656,
|
2004 |
+
"step": 133
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 2.16260162601626,
|
2008 |
+
"grad_norm": 1.4042621288012924e-08,
|
2009 |
+
"learning_rate": 9.202138944469168e-05,
|
2010 |
+
"logits/chosen": 0.2330748736858368,
|
2011 |
+
"logits/rejected": 0.10119885206222534,
|
2012 |
+
"logps/chosen": -655.632568359375,
|
2013 |
+
"logps/rejected": -1187.6663818359375,
|
2014 |
+
"loss": 0.0,
|
2015 |
+
"rewards/accuracies": 1.0,
|
2016 |
+
"rewards/chosen": 4.547595024108887,
|
2017 |
+
"rewards/margins": 44.532859802246094,
|
2018 |
+
"rewards/rejected": -39.985267639160156,
|
2019 |
+
"step": 134
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 2.178861788617886,
|
2023 |
+
"grad_norm": 5.396844926508493e-07,
|
2024 |
+
"learning_rate": 9.069519602369856e-05,
|
2025 |
+
"logits/chosen": 0.9299556016921997,
|
2026 |
+
"logits/rejected": 1.2056376934051514,
|
2027 |
+
"logps/chosen": -1106.3253173828125,
|
2028 |
+
"logps/rejected": -1032.9913330078125,
|
2029 |
+
"loss": 0.0,
|
2030 |
+
"rewards/accuracies": 1.0,
|
2031 |
+
"rewards/chosen": 7.694305419921875,
|
2032 |
+
"rewards/margins": 29.57136344909668,
|
2033 |
+
"rewards/rejected": -21.877056121826172,
|
2034 |
+
"step": 135
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 2.1951219512195124,
|
2038 |
+
"grad_norm": 4.877493847743608e-05,
|
2039 |
+
"learning_rate": 8.937065143526347e-05,
|
2040 |
+
"logits/chosen": 0.9594597816467285,
|
2041 |
+
"logits/rejected": 1.179040551185608,
|
2042 |
+
"logps/chosen": -1040.9154052734375,
|
2043 |
+
"logps/rejected": -1039.5325927734375,
|
2044 |
+
"loss": 0.0,
|
2045 |
+
"rewards/accuracies": 1.0,
|
2046 |
+
"rewards/chosen": 9.09385871887207,
|
2047 |
+
"rewards/margins": 31.479862213134766,
|
2048 |
+
"rewards/rejected": -22.386003494262695,
|
2049 |
+
"step": 136
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 2.2113821138211383,
|
2053 |
+
"grad_norm": 2.6771798111724365e-09,
|
2054 |
+
"learning_rate": 8.804799039171863e-05,
|
2055 |
+
"logits/chosen": 1.9819426536560059,
|
2056 |
+
"logits/rejected": 2.158479690551758,
|
2057 |
+
"logps/chosen": -1134.637451171875,
|
2058 |
+
"logps/rejected": -965.3215942382812,
|
2059 |
+
"loss": 0.0,
|
2060 |
+
"rewards/accuracies": 1.0,
|
2061 |
+
"rewards/chosen": 6.446025371551514,
|
2062 |
+
"rewards/margins": 35.7391357421875,
|
2063 |
+
"rewards/rejected": -29.293109893798828,
|
2064 |
+
"step": 137
|
2065 |
+
},
|
2066 |
+
{
|
2067 |
+
"epoch": 2.227642276422764,
|
2068 |
+
"grad_norm": 1.1452775652287528e-06,
|
2069 |
+
"learning_rate": 8.672744727162781e-05,
|
2070 |
+
"logits/chosen": 0.8104963302612305,
|
2071 |
+
"logits/rejected": 0.8570412993431091,
|
2072 |
+
"logps/chosen": -1031.75634765625,
|
2073 |
+
"logps/rejected": -923.9554443359375,
|
2074 |
+
"loss": 0.0,
|
2075 |
+
"rewards/accuracies": 1.0,
|
2076 |
+
"rewards/chosen": 12.884162902832031,
|
2077 |
+
"rewards/margins": 38.34416198730469,
|
2078 |
+
"rewards/rejected": -25.459999084472656,
|
2079 |
+
"step": 138
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 2.2439024390243905,
|
2083 |
+
"grad_norm": 6.028212928832488e-10,
|
2084 |
+
"learning_rate": 8.540925607825384e-05,
|
2085 |
+
"logits/chosen": 0.17743420600891113,
|
2086 |
+
"logits/rejected": 0.07549530267715454,
|
2087 |
+
"logps/chosen": -991.336669921875,
|
2088 |
+
"logps/rejected": -1199.3358154296875,
|
2089 |
+
"loss": 0.0,
|
2090 |
+
"rewards/accuracies": 1.0,
|
2091 |
+
"rewards/chosen": 6.6160173416137695,
|
2092 |
+
"rewards/margins": 32.7667236328125,
|
2093 |
+
"rewards/rejected": -26.150705337524414,
|
2094 |
+
"step": 139
|
2095 |
+
},
|
2096 |
+
{
|
2097 |
+
"epoch": 2.2601626016260163,
|
2098 |
+
"grad_norm": 2.8898223263240652e-06,
|
2099 |
+
"learning_rate": 8.409365039809281e-05,
|
2100 |
+
"logits/chosen": 0.33150625228881836,
|
2101 |
+
"logits/rejected": 0.3002138137817383,
|
2102 |
+
"logps/chosen": -775.9059448242188,
|
2103 |
+
"logps/rejected": -1114.199462890625,
|
2104 |
+
"loss": 0.0,
|
2105 |
+
"rewards/accuracies": 1.0,
|
2106 |
+
"rewards/chosen": 3.3382678031921387,
|
2107 |
+
"rewards/margins": 34.20747375488281,
|
2108 |
+
"rewards/rejected": -30.86920738220215,
|
2109 |
+
"step": 140
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 2.2764227642276422,
|
2113 |
+
"grad_norm": 4.3099689719383605e-06,
|
2114 |
+
"learning_rate": 8.27808633594819e-05,
|
2115 |
+
"logits/chosen": 0.7698372602462769,
|
2116 |
+
"logits/rejected": 1.1860891580581665,
|
2117 |
+
"logps/chosen": -843.12646484375,
|
2118 |
+
"logps/rejected": -918.1942749023438,
|
2119 |
+
"loss": 0.0,
|
2120 |
+
"rewards/accuracies": 1.0,
|
2121 |
+
"rewards/chosen": 4.282138347625732,
|
2122 |
+
"rewards/margins": 23.585163116455078,
|
2123 |
+
"rewards/rejected": -19.303022384643555,
|
2124 |
+
"step": 141
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 2.292682926829268,
|
2128 |
+
"grad_norm": 3.220544385840185e-06,
|
2129 |
+
"learning_rate": 8.147112759128859e-05,
|
2130 |
+
"logits/chosen": 0.8874784708023071,
|
2131 |
+
"logits/rejected": 0.9459190368652344,
|
2132 |
+
"logps/chosen": -1038.4764404296875,
|
2133 |
+
"logps/rejected": -1069.7886962890625,
|
2134 |
+
"loss": 0.0,
|
2135 |
+
"rewards/accuracies": 1.0,
|
2136 |
+
"rewards/chosen": 3.8034682273864746,
|
2137 |
+
"rewards/margins": 26.194406509399414,
|
2138 |
+
"rewards/rejected": -22.390939712524414,
|
2139 |
+
"step": 142
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 2.3089430894308944,
|
2143 |
+
"grad_norm": 0.00022328611521515995,
|
2144 |
+
"learning_rate": 8.016467518168821e-05,
|
2145 |
+
"logits/chosen": 2.493546724319458,
|
2146 |
+
"logits/rejected": 2.539395332336426,
|
2147 |
+
"logps/chosen": -893.9352416992188,
|
2148 |
+
"logps/rejected": -696.1506958007812,
|
2149 |
+
"loss": 0.0,
|
2150 |
+
"rewards/accuracies": 1.0,
|
2151 |
+
"rewards/chosen": 8.509476661682129,
|
2152 |
+
"rewards/margins": 21.499731063842773,
|
2153 |
+
"rewards/rejected": -12.990255355834961,
|
2154 |
+
"step": 143
|
2155 |
+
},
|
2156 |
+
{
|
2157 |
+
"epoch": 2.3252032520325203,
|
2158 |
+
"grad_norm": 0.00013990582374390215,
|
2159 |
+
"learning_rate": 7.886173763703757e-05,
|
2160 |
+
"logits/chosen": 0.21920743584632874,
|
2161 |
+
"logits/rejected": 0.28335481882095337,
|
2162 |
+
"logps/chosen": -728.2202758789062,
|
2163 |
+
"logps/rejected": -1100.657958984375,
|
2164 |
+
"loss": 0.0,
|
2165 |
+
"rewards/accuracies": 1.0,
|
2166 |
+
"rewards/chosen": 5.098618507385254,
|
2167 |
+
"rewards/margins": 33.223487854003906,
|
2168 |
+
"rewards/rejected": -28.124868392944336,
|
2169 |
+
"step": 144
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 2.341463414634146,
|
2173 |
+
"grad_norm": 2.5570125217200257e-05,
|
2174 |
+
"learning_rate": 7.756254584085121e-05,
|
2175 |
+
"logits/chosen": 1.576183557510376,
|
2176 |
+
"logits/rejected": 2.116095542907715,
|
2177 |
+
"logps/chosen": -1211.36767578125,
|
2178 |
+
"logps/rejected": -841.2113037109375,
|
2179 |
+
"loss": 0.0,
|
2180 |
+
"rewards/accuracies": 1.0,
|
2181 |
+
"rewards/chosen": 8.20867919921875,
|
2182 |
+
"rewards/margins": 23.45158576965332,
|
2183 |
+
"rewards/rejected": -15.242904663085938,
|
2184 |
+
"step": 145
|
2185 |
+
},
|
2186 |
+
{
|
2187 |
+
"epoch": 2.3577235772357725,
|
2188 |
+
"grad_norm": 1.5557947818933826e-08,
|
2189 |
+
"learning_rate": 7.626733001288851e-05,
|
2190 |
+
"logits/chosen": 1.017463207244873,
|
2191 |
+
"logits/rejected": 1.2662559747695923,
|
2192 |
+
"logps/chosen": -1075.69677734375,
|
2193 |
+
"logps/rejected": -1051.0823974609375,
|
2194 |
+
"loss": 0.0,
|
2195 |
+
"rewards/accuracies": 1.0,
|
2196 |
+
"rewards/chosen": 2.859679937362671,
|
2197 |
+
"rewards/margins": 33.41606521606445,
|
2198 |
+
"rewards/rejected": -30.556386947631836,
|
2199 |
+
"step": 146
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 2.3739837398373984,
|
2203 |
+
"grad_norm": 1.1387073506341494e-08,
|
2204 |
+
"learning_rate": 7.497631966835828e-05,
|
2205 |
+
"logits/chosen": 1.214647889137268,
|
2206 |
+
"logits/rejected": 0.9382815957069397,
|
2207 |
+
"logps/chosen": -861.36181640625,
|
2208 |
+
"logps/rejected": -860.1260375976562,
|
2209 |
+
"loss": 0.0,
|
2210 |
+
"rewards/accuracies": 1.0,
|
2211 |
+
"rewards/chosen": 7.3777055740356445,
|
2212 |
+
"rewards/margins": 31.344114303588867,
|
2213 |
+
"rewards/rejected": -23.966407775878906,
|
2214 |
+
"step": 147
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 2.3902439024390243,
|
2218 |
+
"grad_norm": 1.4444401131186169e-05,
|
2219 |
+
"learning_rate": 7.368974357724789e-05,
|
2220 |
+
"logits/chosen": 1.4694726467132568,
|
2221 |
+
"logits/rejected": 1.837304711341858,
|
2222 |
+
"logps/chosen": -828.1371459960938,
|
2223 |
+
"logps/rejected": -890.37548828125,
|
2224 |
+
"loss": 0.0,
|
2225 |
+
"rewards/accuracies": 1.0,
|
2226 |
+
"rewards/chosen": 0.28642868995666504,
|
2227 |
+
"rewards/margins": 23.24945068359375,
|
2228 |
+
"rewards/rejected": -22.963022232055664,
|
2229 |
+
"step": 148
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 2.40650406504065,
|
2233 |
+
"grad_norm": 8.854440380900996e-08,
|
2234 |
+
"learning_rate": 7.240782972378496e-05,
|
2235 |
+
"logits/chosen": 0.38753101229667664,
|
2236 |
+
"logits/rejected": 0.24646523594856262,
|
2237 |
+
"logps/chosen": -710.2447509765625,
|
2238 |
+
"logps/rejected": -1220.842041015625,
|
2239 |
+
"loss": 0.0,
|
2240 |
+
"rewards/accuracies": 1.0,
|
2241 |
+
"rewards/chosen": -0.22469329833984375,
|
2242 |
+
"rewards/margins": 27.240110397338867,
|
2243 |
+
"rewards/rejected": -27.464805603027344,
|
2244 |
+
"step": 149
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 2.4227642276422765,
|
2248 |
+
"grad_norm": 0.0004863929934799671,
|
2249 |
+
"learning_rate": 7.113080526603792e-05,
|
2250 |
+
"logits/chosen": 0.851685106754303,
|
2251 |
+
"logits/rejected": 0.6417226195335388,
|
2252 |
+
"logps/chosen": -741.8690795898438,
|
2253 |
+
"logps/rejected": -1010.4365234375,
|
2254 |
+
"loss": 0.0,
|
2255 |
+
"rewards/accuracies": 1.0,
|
2256 |
+
"rewards/chosen": 6.342030048370361,
|
2257 |
+
"rewards/margins": 33.09426498413086,
|
2258 |
+
"rewards/rejected": -26.752235412597656,
|
2259 |
+
"step": 150
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 2.4390243902439024,
|
2263 |
+
"grad_norm": 5.4216638091020286e-05,
|
2264 |
+
"learning_rate": 6.985889649566305e-05,
|
2265 |
+
"logits/chosen": 1.0506223440170288,
|
2266 |
+
"logits/rejected": 0.997691810131073,
|
2267 |
+
"logps/chosen": -695.2083740234375,
|
2268 |
+
"logps/rejected": -622.5052490234375,
|
2269 |
+
"loss": 0.0,
|
2270 |
+
"rewards/accuracies": 1.0,
|
2271 |
+
"rewards/chosen": 3.0346758365631104,
|
2272 |
+
"rewards/margins": 23.93063735961914,
|
2273 |
+
"rewards/rejected": -20.89596176147461,
|
2274 |
+
"step": 151
|
2275 |
+
},
|
2276 |
+
{
|
2277 |
+
"epoch": 2.4552845528455283,
|
2278 |
+
"grad_norm": 1.0896185813180637e-05,
|
2279 |
+
"learning_rate": 6.859232879780515e-05,
|
2280 |
+
"logits/chosen": 0.6958073377609253,
|
2281 |
+
"logits/rejected": 0.7431595325469971,
|
2282 |
+
"logps/chosen": -946.8716430664062,
|
2283 |
+
"logps/rejected": -869.7786865234375,
|
2284 |
+
"loss": 0.0,
|
2285 |
+
"rewards/accuracies": 1.0,
|
2286 |
+
"rewards/chosen": 2.730717420578003,
|
2287 |
+
"rewards/margins": 25.248491287231445,
|
2288 |
+
"rewards/rejected": -22.517772674560547,
|
2289 |
+
"step": 152
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 2.4715447154471546,
|
2293 |
+
"grad_norm": 7.235275489847481e-08,
|
2294 |
+
"learning_rate": 6.73313266111587e-05,
|
2295 |
+
"logits/chosen": 1.8724164962768555,
|
2296 |
+
"logits/rejected": 2.186227560043335,
|
2297 |
+
"logps/chosen": -961.348876953125,
|
2298 |
+
"logps/rejected": -889.3941040039062,
|
2299 |
+
"loss": 0.0,
|
2300 |
+
"rewards/accuracies": 1.0,
|
2301 |
+
"rewards/chosen": 8.482477188110352,
|
2302 |
+
"rewards/margins": 33.20310974121094,
|
2303 |
+
"rewards/rejected": -24.720630645751953,
|
2304 |
+
"step": 153
|
2305 |
+
},
|
2306 |
+
{
|
2307 |
+
"epoch": 2.4878048780487805,
|
2308 |
+
"grad_norm": 5.680619324266445e-06,
|
2309 |
+
"learning_rate": 6.607611338819697e-05,
|
2310 |
+
"logits/chosen": 0.2374384105205536,
|
2311 |
+
"logits/rejected": 0.2661726474761963,
|
2312 |
+
"logps/chosen": -884.477783203125,
|
2313 |
+
"logps/rejected": -1196.705810546875,
|
2314 |
+
"loss": 0.0,
|
2315 |
+
"rewards/accuracies": 1.0,
|
2316 |
+
"rewards/chosen": 2.1550889015197754,
|
2317 |
+
"rewards/margins": 33.60582733154297,
|
2318 |
+
"rewards/rejected": -31.450740814208984,
|
2319 |
+
"step": 154
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 2.5040650406504064,
|
2323 |
+
"grad_norm": 0.00021473168453667313,
|
2324 |
+
"learning_rate": 6.48269115555755e-05,
|
2325 |
+
"logits/chosen": 1.6578993797302246,
|
2326 |
+
"logits/rejected": 1.9648597240447998,
|
2327 |
+
"logps/chosen": -1154.904541015625,
|
2328 |
+
"logps/rejected": -830.4815673828125,
|
2329 |
+
"loss": 0.0,
|
2330 |
+
"rewards/accuracies": 1.0,
|
2331 |
+
"rewards/chosen": 9.426295280456543,
|
2332 |
+
"rewards/margins": 29.979768753051758,
|
2333 |
+
"rewards/rejected": -20.5534725189209,
|
2334 |
+
"step": 155
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 2.5203252032520327,
|
2338 |
+
"grad_norm": 1.3903934359404957e-06,
|
2339 |
+
"learning_rate": 6.358394247471778e-05,
|
2340 |
+
"logits/chosen": 1.9553877115249634,
|
2341 |
+
"logits/rejected": 1.973337173461914,
|
2342 |
+
"logps/chosen": -982.8421630859375,
|
2343 |
+
"logps/rejected": -899.3438110351562,
|
2344 |
+
"loss": 0.0,
|
2345 |
+
"rewards/accuracies": 1.0,
|
2346 |
+
"rewards/chosen": 4.616971969604492,
|
2347 |
+
"rewards/margins": 27.25063133239746,
|
2348 |
+
"rewards/rejected": -22.6336612701416,
|
2349 |
+
"step": 156
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 2.5365853658536586,
|
2353 |
+
"grad_norm": 4.822657047043322e-06,
|
2354 |
+
"learning_rate": 6.234742640258938e-05,
|
2355 |
+
"logits/chosen": 0.8568439483642578,
|
2356 |
+
"logits/rejected": 0.8998463749885559,
|
2357 |
+
"logps/chosen": -699.6088256835938,
|
2358 |
+
"logps/rejected": -1193.45751953125,
|
2359 |
+
"loss": 0.0,
|
2360 |
+
"rewards/accuracies": 1.0,
|
2361 |
+
"rewards/chosen": 7.211078643798828,
|
2362 |
+
"rewards/margins": 35.346927642822266,
|
2363 |
+
"rewards/rejected": -28.135848999023438,
|
2364 |
+
"step": 157
|
2365 |
+
},
|
2366 |
+
{
|
2367 |
+
"epoch": 2.5528455284552845,
|
2368 |
+
"grad_norm": 1.5767127881094467e-10,
|
2369 |
+
"learning_rate": 6.111758245266794e-05,
|
2370 |
+
"logits/chosen": 0.2673335671424866,
|
2371 |
+
"logits/rejected": 0.40638232231140137,
|
2372 |
+
"logps/chosen": -872.9669189453125,
|
2373 |
+
"logps/rejected": -1310.6427001953125,
|
2374 |
+
"loss": 0.0,
|
2375 |
+
"rewards/accuracies": 1.0,
|
2376 |
+
"rewards/chosen": 17.302719116210938,
|
2377 |
+
"rewards/margins": 70.62458801269531,
|
2378 |
+
"rewards/rejected": -53.321868896484375,
|
2379 |
+
"step": 158
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 2.569105691056911,
|
2383 |
+
"grad_norm": 0.00041443470399826765,
|
2384 |
+
"learning_rate": 5.9894628556115854e-05,
|
2385 |
+
"logits/chosen": 0.14544445276260376,
|
2386 |
+
"logits/rejected": 0.3626626133918762,
|
2387 |
+
"logps/chosen": -622.1597900390625,
|
2388 |
+
"logps/rejected": -962.1544799804688,
|
2389 |
+
"loss": 0.0,
|
2390 |
+
"rewards/accuracies": 1.0,
|
2391 |
+
"rewards/chosen": -0.17218637466430664,
|
2392 |
+
"rewards/margins": 21.543460845947266,
|
2393 |
+
"rewards/rejected": -21.715648651123047,
|
2394 |
+
"step": 159
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 2.5853658536585367,
|
2398 |
+
"grad_norm": 2.103996763480609e-07,
|
2399 |
+
"learning_rate": 5.867878142316221e-05,
|
2400 |
+
"logits/chosen": 1.6551589965820312,
|
2401 |
+
"logits/rejected": 1.5491437911987305,
|
2402 |
+
"logps/chosen": -1024.2724609375,
|
2403 |
+
"logps/rejected": -868.7474975585938,
|
2404 |
+
"loss": 0.0,
|
2405 |
+
"rewards/accuracies": 1.0,
|
2406 |
+
"rewards/chosen": 8.687625885009766,
|
2407 |
+
"rewards/margins": 29.73490333557129,
|
2408 |
+
"rewards/rejected": -21.047279357910156,
|
2409 |
+
"step": 160
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 2.6016260162601625,
|
2413 |
+
"grad_norm": 4.0969604242491187e-07,
|
2414 |
+
"learning_rate": 5.7470256504701347e-05,
|
2415 |
+
"logits/chosen": 1.521755576133728,
|
2416 |
+
"logits/rejected": 1.847412109375,
|
2417 |
+
"logps/chosen": -1056.821533203125,
|
2418 |
+
"logps/rejected": -826.6946411132812,
|
2419 |
+
"loss": 0.0,
|
2420 |
+
"rewards/accuracies": 1.0,
|
2421 |
+
"rewards/chosen": 9.350458145141602,
|
2422 |
+
"rewards/margins": 27.10157012939453,
|
2423 |
+
"rewards/rejected": -17.751113891601562,
|
2424 |
+
"step": 161
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 2.617886178861789,
|
2428 |
+
"grad_norm": 5.504219870999805e-07,
|
2429 |
+
"learning_rate": 5.626926795411447e-05,
|
2430 |
+
"logits/chosen": 0.2913011908531189,
|
2431 |
+
"logits/rejected": 0.4079492688179016,
|
2432 |
+
"logps/chosen": -718.0723876953125,
|
2433 |
+
"logps/rejected": -1118.736083984375,
|
2434 |
+
"loss": 0.0,
|
2435 |
+
"rewards/accuracies": 1.0,
|
2436 |
+
"rewards/chosen": 3.049485206604004,
|
2437 |
+
"rewards/margins": 43.513614654541016,
|
2438 |
+
"rewards/rejected": -40.46412658691406,
|
2439 |
+
"step": 162
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 2.6341463414634148,
|
2443 |
+
"grad_norm": 7.391007805779282e-10,
|
2444 |
+
"learning_rate": 5.507602858932113e-05,
|
2445 |
+
"logits/chosen": 0.13623125851154327,
|
2446 |
+
"logits/rejected": 0.14287753403186798,
|
2447 |
+
"logps/chosen": -709.7506103515625,
|
2448 |
+
"logps/rejected": -943.9478759765625,
|
2449 |
+
"loss": 0.0,
|
2450 |
+
"rewards/accuracies": 1.0,
|
2451 |
+
"rewards/chosen": 3.784420967102051,
|
2452 |
+
"rewards/margins": 28.368255615234375,
|
2453 |
+
"rewards/rejected": -24.583837509155273,
|
2454 |
+
"step": 163
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"epoch": 2.6504065040650406,
|
2458 |
+
"grad_norm": 2.608588545172097e-07,
|
2459 |
+
"learning_rate": 5.38907498550674e-05,
|
2460 |
+
"logits/chosen": 0.3549523949623108,
|
2461 |
+
"logits/rejected": 0.2945078909397125,
|
2462 |
+
"logps/chosen": -627.5148315429688,
|
2463 |
+
"logps/rejected": -970.0422973632812,
|
2464 |
+
"loss": 0.0,
|
2465 |
+
"rewards/accuracies": 1.0,
|
2466 |
+
"rewards/chosen": 4.014554023742676,
|
2467 |
+
"rewards/margins": 28.548900604248047,
|
2468 |
+
"rewards/rejected": -24.534347534179688,
|
2469 |
+
"step": 164
|
2470 |
+
},
|
2471 |
+
{
|
2472 |
+
"epoch": 2.6666666666666665,
|
2473 |
+
"grad_norm": 2.4691764188844445e-09,
|
2474 |
+
"learning_rate": 5.27136417854575e-05,
|
2475 |
+
"logits/chosen": 0.393886923789978,
|
2476 |
+
"logits/rejected": 0.25684821605682373,
|
2477 |
+
"logps/chosen": -773.8262329101562,
|
2478 |
+
"logps/rejected": -1119.12060546875,
|
2479 |
+
"loss": 0.0,
|
2480 |
+
"rewards/accuracies": 1.0,
|
2481 |
+
"rewards/chosen": 0.5616737008094788,
|
2482 |
+
"rewards/margins": 27.010391235351562,
|
2483 |
+
"rewards/rejected": -26.448719024658203,
|
2484 |
+
"step": 165
|
2485 |
+
},
|
2486 |
+
{
|
2487 |
+
"epoch": 2.682926829268293,
|
2488 |
+
"grad_norm": 1.6074091035989113e-05,
|
2489 |
+
"learning_rate": 5.1544912966734994e-05,
|
2490 |
+
"logits/chosen": 1.0595850944519043,
|
2491 |
+
"logits/rejected": 1.1324055194854736,
|
2492 |
+
"logps/chosen": -1086.4296875,
|
2493 |
+
"logps/rejected": -1205.9815673828125,
|
2494 |
+
"loss": 0.0,
|
2495 |
+
"rewards/accuracies": 1.0,
|
2496 |
+
"rewards/chosen": 0.2086625099182129,
|
2497 |
+
"rewards/margins": 30.370914459228516,
|
2498 |
+
"rewards/rejected": -30.16225242614746,
|
2499 |
+
"step": 166
|
2500 |
+
},
|
2501 |
+
{
|
2502 |
+
"epoch": 2.6991869918699187,
|
2503 |
+
"grad_norm": 4.716870535048656e-06,
|
2504 |
+
"learning_rate": 5.0384770500321176e-05,
|
2505 |
+
"logits/chosen": 0.7150585651397705,
|
2506 |
+
"logits/rejected": 1.0305664539337158,
|
2507 |
+
"logps/chosen": -949.9681396484375,
|
2508 |
+
"logps/rejected": -1113.91015625,
|
2509 |
+
"loss": 0.0,
|
2510 |
+
"rewards/accuracies": 1.0,
|
2511 |
+
"rewards/chosen": 6.314611911773682,
|
2512 |
+
"rewards/margins": 30.07944107055664,
|
2513 |
+
"rewards/rejected": -23.764827728271484,
|
2514 |
+
"step": 167
|
2515 |
+
},
|
2516 |
+
{
|
2517 |
+
"epoch": 2.7154471544715446,
|
2518 |
+
"grad_norm": 3.2816437851579394e-06,
|
2519 |
+
"learning_rate": 4.9233419966116036e-05,
|
2520 |
+
"logits/chosen": 1.9386444091796875,
|
2521 |
+
"logits/rejected": 2.0223605632781982,
|
2522 |
+
"logps/chosen": -868.1651000976562,
|
2523 |
+
"logps/rejected": -765.9869995117188,
|
2524 |
+
"loss": 0.0,
|
2525 |
+
"rewards/accuracies": 1.0,
|
2526 |
+
"rewards/chosen": 9.12423038482666,
|
2527 |
+
"rewards/margins": 30.5165958404541,
|
2528 |
+
"rewards/rejected": -21.392364501953125,
|
2529 |
+
"step": 168
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 2.7317073170731705,
|
2533 |
+
"grad_norm": 2.4390756152570248e-05,
|
2534 |
+
"learning_rate": 4.809106538606896e-05,
|
2535 |
+
"logits/chosen": 0.955643355846405,
|
2536 |
+
"logits/rejected": 1.1507562398910522,
|
2537 |
+
"logps/chosen": -1002.4882202148438,
|
2538 |
+
"logps/rejected": -1020.2136840820312,
|
2539 |
+
"loss": 0.0,
|
2540 |
+
"rewards/accuracies": 1.0,
|
2541 |
+
"rewards/chosen": 1.6517884731292725,
|
2542 |
+
"rewards/margins": 26.767532348632812,
|
2543 |
+
"rewards/rejected": -25.115745544433594,
|
2544 |
+
"step": 169
|
2545 |
+
},
|
2546 |
+
{
|
2547 |
+
"epoch": 2.747967479674797,
|
2548 |
+
"grad_norm": 0.00012876000255346298,
|
2549 |
+
"learning_rate": 4.695790918802576e-05,
|
2550 |
+
"logits/chosen": 2.1373488903045654,
|
2551 |
+
"logits/rejected": 1.845626950263977,
|
2552 |
+
"logps/chosen": -643.7026977539062,
|
2553 |
+
"logps/rejected": -862.6270751953125,
|
2554 |
+
"loss": 0.0,
|
2555 |
+
"rewards/accuracies": 1.0,
|
2556 |
+
"rewards/chosen": 2.4644973278045654,
|
2557 |
+
"rewards/margins": 26.4927978515625,
|
2558 |
+
"rewards/rejected": -24.028301239013672,
|
2559 |
+
"step": 170
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 2.7642276422764227,
|
2563 |
+
"grad_norm": 8.289234392577782e-05,
|
2564 |
+
"learning_rate": 4.58341521698579e-05,
|
2565 |
+
"logits/chosen": 0.25596243143081665,
|
2566 |
+
"logits/rejected": -0.03055526316165924,
|
2567 |
+
"logps/chosen": -614.50244140625,
|
2568 |
+
"logps/rejected": -1223.715576171875,
|
2569 |
+
"loss": 0.0,
|
2570 |
+
"rewards/accuracies": 1.0,
|
2571 |
+
"rewards/chosen": 4.4099273681640625,
|
2572 |
+
"rewards/margins": 31.352651596069336,
|
2573 |
+
"rewards/rejected": -26.942724227905273,
|
2574 |
+
"step": 171
|
2575 |
+
},
|
2576 |
+
{
|
2577 |
+
"epoch": 2.7804878048780486,
|
2578 |
+
"grad_norm": 3.854520969071018e-08,
|
2579 |
+
"learning_rate": 4.47199934638807e-05,
|
2580 |
+
"logits/chosen": 0.8832861185073853,
|
2581 |
+
"logits/rejected": 0.8490067720413208,
|
2582 |
+
"logps/chosen": -775.900634765625,
|
2583 |
+
"logps/rejected": -1054.091796875,
|
2584 |
+
"loss": 0.0,
|
2585 |
+
"rewards/accuracies": 1.0,
|
2586 |
+
"rewards/chosen": 6.442215442657471,
|
2587 |
+
"rewards/margins": 29.371417999267578,
|
2588 |
+
"rewards/rejected": -22.929203033447266,
|
2589 |
+
"step": 172
|
2590 |
+
},
|
2591 |
+
{
|
2592 |
+
"epoch": 2.796747967479675,
|
2593 |
+
"grad_norm": 3.370180934325617e-08,
|
2594 |
+
"learning_rate": 4.3615630501566384e-05,
|
2595 |
+
"logits/chosen": 1.1688926219940186,
|
2596 |
+
"logits/rejected": 1.1840847730636597,
|
2597 |
+
"logps/chosen": -789.5611572265625,
|
2598 |
+
"logps/rejected": -892.3736572265625,
|
2599 |
+
"loss": 0.0,
|
2600 |
+
"rewards/accuracies": 1.0,
|
2601 |
+
"rewards/chosen": 4.048530578613281,
|
2602 |
+
"rewards/margins": 35.47740173339844,
|
2603 |
+
"rewards/rejected": -31.428869247436523,
|
2604 |
+
"step": 173
|
2605 |
+
},
|
2606 |
+
{
|
2607 |
+
"epoch": 2.813008130081301,
|
2608 |
+
"grad_norm": 6.220017439773073e-06,
|
2609 |
+
"learning_rate": 4.252125897855932e-05,
|
2610 |
+
"logits/chosen": 0.24903741478919983,
|
2611 |
+
"logits/rejected": 0.07388614118099213,
|
2612 |
+
"logps/chosen": -845.9579467773438,
|
2613 |
+
"logps/rejected": -1296.85400390625,
|
2614 |
+
"loss": 0.0,
|
2615 |
+
"rewards/accuracies": 1.0,
|
2616 |
+
"rewards/chosen": -2.9718475341796875,
|
2617 |
+
"rewards/margins": 31.60814094543457,
|
2618 |
+
"rewards/rejected": -34.57999038696289,
|
2619 |
+
"step": 174
|
2620 |
+
},
|
2621 |
+
{
|
2622 |
+
"epoch": 2.8292682926829267,
|
2623 |
+
"grad_norm": 4.538567566214624e-07,
|
2624 |
+
"learning_rate": 4.143707281999767e-05,
|
2625 |
+
"logits/chosen": 1.117840051651001,
|
2626 |
+
"logits/rejected": 1.1794054508209229,
|
2627 |
+
"logps/chosen": -692.6531372070312,
|
2628 |
+
"logps/rejected": -1131.69970703125,
|
2629 |
+
"loss": 0.0,
|
2630 |
+
"rewards/accuracies": 1.0,
|
2631 |
+
"rewards/chosen": 7.421784400939941,
|
2632 |
+
"rewards/margins": 30.24844741821289,
|
2633 |
+
"rewards/rejected": -22.826662063598633,
|
2634 |
+
"step": 175
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 2.845528455284553,
|
2638 |
+
"grad_norm": 1.9607491594797466e-06,
|
2639 |
+
"learning_rate": 4.036326414614985e-05,
|
2640 |
+
"logits/chosen": 1.117968201637268,
|
2641 |
+
"logits/rejected": 1.3285045623779297,
|
2642 |
+
"logps/chosen": -915.8657836914062,
|
2643 |
+
"logps/rejected": -880.1917724609375,
|
2644 |
+
"loss": 0.0,
|
2645 |
+
"rewards/accuracies": 1.0,
|
2646 |
+
"rewards/chosen": 5.270617485046387,
|
2647 |
+
"rewards/margins": 27.518800735473633,
|
2648 |
+
"rewards/rejected": -22.248184204101562,
|
2649 |
+
"step": 176
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 2.861788617886179,
|
2653 |
+
"grad_norm": 2.6408181952319865e-07,
|
2654 |
+
"learning_rate": 3.930002323837025e-05,
|
2655 |
+
"logits/chosen": 0.2848118543624878,
|
2656 |
+
"logits/rejected": 0.30847471952438354,
|
2657 |
+
"logps/chosen": -777.3819580078125,
|
2658 |
+
"logps/rejected": -1265.9404296875,
|
2659 |
+
"loss": 0.0,
|
2660 |
+
"rewards/accuracies": 1.0,
|
2661 |
+
"rewards/chosen": -4.468026161193848,
|
2662 |
+
"rewards/margins": 30.405376434326172,
|
2663 |
+
"rewards/rejected": -34.8734016418457,
|
2664 |
+
"step": 177
|
2665 |
+
},
|
2666 |
+
{
|
2667 |
+
"epoch": 2.8780487804878048,
|
2668 |
+
"grad_norm": 5.149066055309959e-06,
|
2669 |
+
"learning_rate": 3.824753850538082e-05,
|
2670 |
+
"logits/chosen": -0.513633131980896,
|
2671 |
+
"logits/rejected": -0.5264861583709717,
|
2672 |
+
"logps/chosen": -658.2607421875,
|
2673 |
+
"logps/rejected": -1306.8682861328125,
|
2674 |
+
"loss": 0.0,
|
2675 |
+
"rewards/accuracies": 1.0,
|
2676 |
+
"rewards/chosen": 4.874265670776367,
|
2677 |
+
"rewards/margins": 48.48944091796875,
|
2678 |
+
"rewards/rejected": -43.615177154541016,
|
2679 |
+
"step": 178
|
2680 |
+
},
|
2681 |
+
{
|
2682 |
+
"epoch": 2.894308943089431,
|
2683 |
+
"grad_norm": 0.0007087494013831019,
|
2684 |
+
"learning_rate": 3.720599644988482e-05,
|
2685 |
+
"logits/chosen": 0.9137465357780457,
|
2686 |
+
"logits/rejected": 1.133833885192871,
|
2687 |
+
"logps/chosen": -883.857177734375,
|
2688 |
+
"logps/rejected": -836.129638671875,
|
2689 |
+
"loss": 0.0,
|
2690 |
+
"rewards/accuracies": 1.0,
|
2691 |
+
"rewards/chosen": 3.139035224914551,
|
2692 |
+
"rewards/margins": 25.803987503051758,
|
2693 |
+
"rewards/rejected": -22.664953231811523,
|
2694 |
+
"step": 179
|
2695 |
+
},
|
2696 |
+
{
|
2697 |
+
"epoch": 2.910569105691057,
|
2698 |
+
"grad_norm": 3.135071528959088e-05,
|
2699 |
+
"learning_rate": 3.617558163551802e-05,
|
2700 |
+
"logits/chosen": 0.9635988473892212,
|
2701 |
+
"logits/rejected": 1.133531093597412,
|
2702 |
+
"logps/chosen": -889.0616455078125,
|
2703 |
+
"logps/rejected": -834.8280029296875,
|
2704 |
+
"loss": 0.0,
|
2705 |
+
"rewards/accuracies": 1.0,
|
2706 |
+
"rewards/chosen": 1.593743920326233,
|
2707 |
+
"rewards/margins": 22.950916290283203,
|
2708 |
+
"rewards/rejected": -21.3571720123291,
|
2709 |
+
"step": 180
|
2710 |
+
},
|
2711 |
+
{
|
2712 |
+
"epoch": 2.926829268292683,
|
2713 |
+
"grad_norm": 9.376124580739997e-06,
|
2714 |
+
"learning_rate": 3.5156476654143497e-05,
|
2715 |
+
"logits/chosen": 0.21040788292884827,
|
2716 |
+
"logits/rejected": 0.14262419939041138,
|
2717 |
+
"logps/chosen": -848.9990844726562,
|
2718 |
+
"logps/rejected": -1117.9007568359375,
|
2719 |
+
"loss": 0.0,
|
2720 |
+
"rewards/accuracies": 1.0,
|
2721 |
+
"rewards/chosen": 0.15429675579071045,
|
2722 |
+
"rewards/margins": 29.727014541625977,
|
2723 |
+
"rewards/rejected": -29.57271957397461,
|
2724 |
+
"step": 181
|
2725 |
+
},
|
2726 |
+
{
|
2727 |
+
"epoch": 2.943089430894309,
|
2728 |
+
"grad_norm": 5.8795808399736416e-06,
|
2729 |
+
"learning_rate": 3.414886209349615e-05,
|
2730 |
+
"logits/chosen": 1.1507726907730103,
|
2731 |
+
"logits/rejected": 0.9590345025062561,
|
2732 |
+
"logps/chosen": -977.4312744140625,
|
2733 |
+
"logps/rejected": -943.8434448242188,
|
2734 |
+
"loss": 0.0,
|
2735 |
+
"rewards/accuracies": 1.0,
|
2736 |
+
"rewards/chosen": 2.495950222015381,
|
2737 |
+
"rewards/margins": 23.74968719482422,
|
2738 |
+
"rewards/rejected": -21.253738403320312,
|
2739 |
+
"step": 182
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 2.959349593495935,
|
2743 |
+
"grad_norm": 3.5330920411524858e-09,
|
2744 |
+
"learning_rate": 3.315291650518197e-05,
|
2745 |
+
"logits/chosen": 1.0992462635040283,
|
2746 |
+
"logits/rejected": 1.1924934387207031,
|
2747 |
+
"logps/chosen": -962.3739624023438,
|
2748 |
+
"logps/rejected": -1141.202880859375,
|
2749 |
+
"loss": 0.0,
|
2750 |
+
"rewards/accuracies": 1.0,
|
2751 |
+
"rewards/chosen": 3.505153179168701,
|
2752 |
+
"rewards/margins": 32.49464416503906,
|
2753 |
+
"rewards/rejected": -28.989490509033203,
|
2754 |
+
"step": 183
|
2755 |
+
},
|
2756 |
+
{
|
2757 |
+
"epoch": 2.975609756097561,
|
2758 |
+
"grad_norm": 0.00035440587089397013,
|
2759 |
+
"learning_rate": 3.216881637303839e-05,
|
2760 |
+
"logits/chosen": 0.8002848625183105,
|
2761 |
+
"logits/rejected": 1.1536259651184082,
|
2762 |
+
"logps/chosen": -1330.277099609375,
|
2763 |
+
"logps/rejected": -1155.875,
|
2764 |
+
"loss": 0.0,
|
2765 |
+
"rewards/accuracies": 1.0,
|
2766 |
+
"rewards/chosen": 1.3375800848007202,
|
2767 |
+
"rewards/margins": 29.2307186126709,
|
2768 |
+
"rewards/rejected": -27.893136978149414,
|
2769 |
+
"step": 184
|
2770 |
+
},
|
2771 |
+
{
|
2772 |
+
"epoch": 2.991869918699187,
|
2773 |
+
"grad_norm": 4.985774285160005e-05,
|
2774 |
+
"learning_rate": 3.119673608186085e-05,
|
2775 |
+
"logits/chosen": 1.2516355514526367,
|
2776 |
+
"logits/rejected": 1.7440040111541748,
|
2777 |
+
"logps/chosen": -1085.0638427734375,
|
2778 |
+
"logps/rejected": -953.7195434570312,
|
2779 |
+
"loss": 0.0,
|
2780 |
+
"rewards/accuracies": 1.0,
|
2781 |
+
"rewards/chosen": 12.24714183807373,
|
2782 |
+
"rewards/margins": 41.917320251464844,
|
2783 |
+
"rewards/rejected": -29.67017936706543,
|
2784 |
+
"step": 185
|
2785 |
+
},
|
2786 |
+
{
|
2787 |
+
"epoch": 3.0,
|
2788 |
+
"grad_norm": 5.4140009808634204e-08,
|
2789 |
+
"learning_rate": 3.0236847886501542e-05,
|
2790 |
+
"logits/chosen": 2.206167697906494,
|
2791 |
+
"logits/rejected": 2.992643117904663,
|
2792 |
+
"logps/chosen": -1038.874267578125,
|
2793 |
+
"logps/rejected": -695.817626953125,
|
2794 |
+
"loss": 0.0,
|
2795 |
+
"rewards/accuracies": 1.0,
|
2796 |
+
"rewards/chosen": 8.593250274658203,
|
2797 |
+
"rewards/margins": 23.8295841217041,
|
2798 |
+
"rewards/rejected": -15.236334800720215,
|
2799 |
+
"step": 186
|
2800 |
+
}
|
2801 |
+
],
|
2802 |
+
"logging_steps": 1,
|
2803 |
+
"max_steps": 246,
|
2804 |
+
"num_input_tokens_seen": 0,
|
2805 |
+
"num_train_epochs": 5,
|
2806 |
+
"save_steps": 62,
|
2807 |
+
"stateful_callbacks": {
|
2808 |
+
"TrainerControl": {
|
2809 |
+
"args": {
|
2810 |
+
"should_epoch_stop": false,
|
2811 |
+
"should_evaluate": false,
|
2812 |
+
"should_log": false,
|
2813 |
+
"should_save": true,
|
2814 |
+
"should_training_stop": false
|
2815 |
+
},
|
2816 |
+
"attributes": {}
|
2817 |
+
}
|
2818 |
+
},
|
2819 |
+
"total_flos": 0.0,
|
2820 |
+
"train_batch_size": 1,
|
2821 |
+
"trial_name": null,
|
2822 |
+
"trial_params": null
|
2823 |
+
}
|
checkpoint-run1-186/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bfa7ff9d80b63c0ea349797dad26a60df3805ba7517614bd0d61390fa2637b7
|
3 |
+
size 7416
|
checkpoint-run1-246/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: /cpool/DeepSeek-R1-Distill-Llama-70B-Uncensored-v2
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.14.0
|
checkpoint-run1-246/adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "/cpool/DeepSeek-R1-Distill-Llama-70B-Uncensored-v2",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": null,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 32,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"v_proj",
|
27 |
+
"o_proj",
|
28 |
+
"q_proj",
|
29 |
+
"k_proj",
|
30 |
+
"gate_proj",
|
31 |
+
"down_proj",
|
32 |
+
"up_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
checkpoint-run1-246/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:973a76907849a8c19a5591bcf6259148974a06fa4c8874cf8b23c825f5694d47
|
3 |
+
size 1656902648
|
checkpoint-run1-246/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:563c435a4ba977ce6d9a541c019a69a44dc6e0a4992b5f8f26ebf0052bda726b
|
3 |
+
size 3314505202
|
checkpoint-run1-246/pytorch_model_fsdp.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d720deaac80f43e3138f265e563d8738db6a37d2b932fdfbc9ef00d3a3848756
|
3 |
+
size 1657168758
|
checkpoint-run1-246/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9affc1541e7e94c18354d5173bc55400c5f07faf3d080c6d453d48e7a8d6ac3
|
3 |
+
size 14512
|
checkpoint-run1-246/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4748c3ebf0e4c051c58b92e4a8c5b87cdb39d55cfdc2aec81a1baef0f02fc113
|
3 |
+
size 14512
|
checkpoint-run1-246/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b3154f604c355b4c2a690337308ab3c82a9c84454f48e161a6c7b113ec8d355
|
3 |
+
size 1064
|
checkpoint-run1-246/special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end_of_text|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
checkpoint-run1-246/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16f2ebc8d9a7de55360d83ea69f97916a1389f0a72264664d4d6c4db6da8d0b8
|
3 |
+
size 17209722
|
checkpoint-run1-246/tokenizer_config.json
ADDED
@@ -0,0 +1,2075 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"128000": {
|
7 |
+
"content": "<|begin▁of▁sentence|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"128001": {
|
15 |
+
"content": "<|end▁of▁sentence|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"128002": {
|
23 |
+
"content": "<|reserved_special_token_0|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"128003": {
|
31 |
+
"content": "<|reserved_special_token_1|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"128004": {
|
39 |
+
"content": "<|finetune_right_pad_id|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"128005": {
|
47 |
+
"content": "<|reserved_special_token_2|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"128006": {
|
55 |
+
"content": "<|start_header_id|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"128007": {
|
63 |
+
"content": "<|end_header_id|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"128008": {
|
71 |
+
"content": "<|eom_id|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"128009": {
|
79 |
+
"content": "<|eot_id|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"128010": {
|
87 |
+
"content": "<|python_tag|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"128011": {
|
95 |
+
"content": "<|User|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"128012": {
|
103 |
+
"content": "<|Assistant|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"128013": {
|
111 |
+
"content": "<think>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"128014": {
|
119 |
+
"content": "</think>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"128015": {
|
127 |
+
"content": "<|▁pad▁|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"128016": {
|
135 |
+
"content": "<|reserved_special_token_8|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"128017": {
|
143 |
+
"content": "<|reserved_special_token_9|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"128018": {
|
151 |
+
"content": "<|reserved_special_token_10|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"128019": {
|
159 |
+
"content": "<|reserved_special_token_11|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"128020": {
|
167 |
+
"content": "<|reserved_special_token_12|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"128021": {
|
175 |
+
"content": "<|reserved_special_token_13|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"128022": {
|
183 |
+
"content": "<|reserved_special_token_14|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"128023": {
|
191 |
+
"content": "<|reserved_special_token_15|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"128024": {
|
199 |
+
"content": "<|reserved_special_token_16|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"128025": {
|
207 |
+
"content": "<|reserved_special_token_17|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"128026": {
|
215 |
+
"content": "<|reserved_special_token_18|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"128027": {
|
223 |
+
"content": "<|reserved_special_token_19|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"128028": {
|
231 |
+
"content": "<|reserved_special_token_20|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"128029": {
|
239 |
+
"content": "<|reserved_special_token_21|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"128030": {
|
247 |
+
"content": "<|reserved_special_token_22|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"128031": {
|
255 |
+
"content": "<|reserved_special_token_23|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"128032": {
|
263 |
+
"content": "<|reserved_special_token_24|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"128033": {
|
271 |
+
"content": "<|reserved_special_token_25|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"128034": {
|
279 |
+
"content": "<|reserved_special_token_26|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"128035": {
|
287 |
+
"content": "<|reserved_special_token_27|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"128036": {
|
295 |
+
"content": "<|reserved_special_token_28|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"128037": {
|
303 |
+
"content": "<|reserved_special_token_29|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"128038": {
|
311 |
+
"content": "<|reserved_special_token_30|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"128039": {
|
319 |
+
"content": "<|reserved_special_token_31|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"128040": {
|
327 |
+
"content": "<|reserved_special_token_32|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"128041": {
|
335 |
+
"content": "<|reserved_special_token_33|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"128042": {
|
343 |
+
"content": "<|reserved_special_token_34|>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"128043": {
|
351 |
+
"content": "<|reserved_special_token_35|>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"128044": {
|
359 |
+
"content": "<|reserved_special_token_36|>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"128045": {
|
367 |
+
"content": "<|reserved_special_token_37|>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"128046": {
|
375 |
+
"content": "<|reserved_special_token_38|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"128047": {
|
383 |
+
"content": "<|reserved_special_token_39|>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"128048": {
|
391 |
+
"content": "<|reserved_special_token_40|>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"128049": {
|
399 |
+
"content": "<|reserved_special_token_41|>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"128050": {
|
407 |
+
"content": "<|reserved_special_token_42|>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"128051": {
|
415 |
+
"content": "<|reserved_special_token_43|>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"128052": {
|
423 |
+
"content": "<|reserved_special_token_44|>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"128053": {
|
431 |
+
"content": "<|reserved_special_token_45|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"128054": {
|
439 |
+
"content": "<|reserved_special_token_46|>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"128055": {
|
447 |
+
"content": "<|reserved_special_token_47|>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"128056": {
|
455 |
+
"content": "<|reserved_special_token_48|>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"128057": {
|
463 |
+
"content": "<|reserved_special_token_49|>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"128058": {
|
471 |
+
"content": "<|reserved_special_token_50|>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"128059": {
|
479 |
+
"content": "<|reserved_special_token_51|>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"128060": {
|
487 |
+
"content": "<|reserved_special_token_52|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"128061": {
|
495 |
+
"content": "<|reserved_special_token_53|>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"128062": {
|
503 |
+
"content": "<|reserved_special_token_54|>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"128063": {
|
511 |
+
"content": "<|reserved_special_token_55|>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"128064": {
|
519 |
+
"content": "<|reserved_special_token_56|>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"128065": {
|
527 |
+
"content": "<|reserved_special_token_57|>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"128066": {
|
535 |
+
"content": "<|reserved_special_token_58|>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
},
|
542 |
+
"128067": {
|
543 |
+
"content": "<|reserved_special_token_59|>",
|
544 |
+
"lstrip": false,
|
545 |
+
"normalized": false,
|
546 |
+
"rstrip": false,
|
547 |
+
"single_word": false,
|
548 |
+
"special": true
|
549 |
+
},
|
550 |
+
"128068": {
|
551 |
+
"content": "<|reserved_special_token_60|>",
|
552 |
+
"lstrip": false,
|
553 |
+
"normalized": false,
|
554 |
+
"rstrip": false,
|
555 |
+
"single_word": false,
|
556 |
+
"special": true
|
557 |
+
},
|
558 |
+
"128069": {
|
559 |
+
"content": "<|reserved_special_token_61|>",
|
560 |
+
"lstrip": false,
|
561 |
+
"normalized": false,
|
562 |
+
"rstrip": false,
|
563 |
+
"single_word": false,
|
564 |
+
"special": true
|
565 |
+
},
|
566 |
+
"128070": {
|
567 |
+
"content": "<|reserved_special_token_62|>",
|
568 |
+
"lstrip": false,
|
569 |
+
"normalized": false,
|
570 |
+
"rstrip": false,
|
571 |
+
"single_word": false,
|
572 |
+
"special": true
|
573 |
+
},
|
574 |
+
"128071": {
|
575 |
+
"content": "<|reserved_special_token_63|>",
|
576 |
+
"lstrip": false,
|
577 |
+
"normalized": false,
|
578 |
+
"rstrip": false,
|
579 |
+
"single_word": false,
|
580 |
+
"special": true
|
581 |
+
},
|
582 |
+
"128072": {
|
583 |
+
"content": "<|reserved_special_token_64|>",
|
584 |
+
"lstrip": false,
|
585 |
+
"normalized": false,
|
586 |
+
"rstrip": false,
|
587 |
+
"single_word": false,
|
588 |
+
"special": true
|
589 |
+
},
|
590 |
+
"128073": {
|
591 |
+
"content": "<|reserved_special_token_65|>",
|
592 |
+
"lstrip": false,
|
593 |
+
"normalized": false,
|
594 |
+
"rstrip": false,
|
595 |
+
"single_word": false,
|
596 |
+
"special": true
|
597 |
+
},
|
598 |
+
"128074": {
|
599 |
+
"content": "<|reserved_special_token_66|>",
|
600 |
+
"lstrip": false,
|
601 |
+
"normalized": false,
|
602 |
+
"rstrip": false,
|
603 |
+
"single_word": false,
|
604 |
+
"special": true
|
605 |
+
},
|
606 |
+
"128075": {
|
607 |
+
"content": "<|reserved_special_token_67|>",
|
608 |
+
"lstrip": false,
|
609 |
+
"normalized": false,
|
610 |
+
"rstrip": false,
|
611 |
+
"single_word": false,
|
612 |
+
"special": true
|
613 |
+
},
|
614 |
+
"128076": {
|
615 |
+
"content": "<|reserved_special_token_68|>",
|
616 |
+
"lstrip": false,
|
617 |
+
"normalized": false,
|
618 |
+
"rstrip": false,
|
619 |
+
"single_word": false,
|
620 |
+
"special": true
|
621 |
+
},
|
622 |
+
"128077": {
|
623 |
+
"content": "<|reserved_special_token_69|>",
|
624 |
+
"lstrip": false,
|
625 |
+
"normalized": false,
|
626 |
+
"rstrip": false,
|
627 |
+
"single_word": false,
|
628 |
+
"special": true
|
629 |
+
},
|
630 |
+
"128078": {
|
631 |
+
"content": "<|reserved_special_token_70|>",
|
632 |
+
"lstrip": false,
|
633 |
+
"normalized": false,
|
634 |
+
"rstrip": false,
|
635 |
+
"single_word": false,
|
636 |
+
"special": true
|
637 |
+
},
|
638 |
+
"128079": {
|
639 |
+
"content": "<|reserved_special_token_71|>",
|
640 |
+
"lstrip": false,
|
641 |
+
"normalized": false,
|
642 |
+
"rstrip": false,
|
643 |
+
"single_word": false,
|
644 |
+
"special": true
|
645 |
+
},
|
646 |
+
"128080": {
|
647 |
+
"content": "<|reserved_special_token_72|>",
|
648 |
+
"lstrip": false,
|
649 |
+
"normalized": false,
|
650 |
+
"rstrip": false,
|
651 |
+
"single_word": false,
|
652 |
+
"special": true
|
653 |
+
},
|
654 |
+
"128081": {
|
655 |
+
"content": "<|reserved_special_token_73|>",
|
656 |
+
"lstrip": false,
|
657 |
+
"normalized": false,
|
658 |
+
"rstrip": false,
|
659 |
+
"single_word": false,
|
660 |
+
"special": true
|
661 |
+
},
|
662 |
+
"128082": {
|
663 |
+
"content": "<|reserved_special_token_74|>",
|
664 |
+
"lstrip": false,
|
665 |
+
"normalized": false,
|
666 |
+
"rstrip": false,
|
667 |
+
"single_word": false,
|
668 |
+
"special": true
|
669 |
+
},
|
670 |
+
"128083": {
|
671 |
+
"content": "<|reserved_special_token_75|>",
|
672 |
+
"lstrip": false,
|
673 |
+
"normalized": false,
|
674 |
+
"rstrip": false,
|
675 |
+
"single_word": false,
|
676 |
+
"special": true
|
677 |
+
},
|
678 |
+
"128084": {
|
679 |
+
"content": "<|reserved_special_token_76|>",
|
680 |
+
"lstrip": false,
|
681 |
+
"normalized": false,
|
682 |
+
"rstrip": false,
|
683 |
+
"single_word": false,
|
684 |
+
"special": true
|
685 |
+
},
|
686 |
+
"128085": {
|
687 |
+
"content": "<|reserved_special_token_77|>",
|
688 |
+
"lstrip": false,
|
689 |
+
"normalized": false,
|
690 |
+
"rstrip": false,
|
691 |
+
"single_word": false,
|
692 |
+
"special": true
|
693 |
+
},
|
694 |
+
"128086": {
|
695 |
+
"content": "<|reserved_special_token_78|>",
|
696 |
+
"lstrip": false,
|
697 |
+
"normalized": false,
|
698 |
+
"rstrip": false,
|
699 |
+
"single_word": false,
|
700 |
+
"special": true
|
701 |
+
},
|
702 |
+
"128087": {
|
703 |
+
"content": "<|reserved_special_token_79|>",
|
704 |
+
"lstrip": false,
|
705 |
+
"normalized": false,
|
706 |
+
"rstrip": false,
|
707 |
+
"single_word": false,
|
708 |
+
"special": true
|
709 |
+
},
|
710 |
+
"128088": {
|
711 |
+
"content": "<|reserved_special_token_80|>",
|
712 |
+
"lstrip": false,
|
713 |
+
"normalized": false,
|
714 |
+
"rstrip": false,
|
715 |
+
"single_word": false,
|
716 |
+
"special": true
|
717 |
+
},
|
718 |
+
"128089": {
|
719 |
+
"content": "<|reserved_special_token_81|>",
|
720 |
+
"lstrip": false,
|
721 |
+
"normalized": false,
|
722 |
+
"rstrip": false,
|
723 |
+
"single_word": false,
|
724 |
+
"special": true
|
725 |
+
},
|
726 |
+
"128090": {
|
727 |
+
"content": "<|reserved_special_token_82|>",
|
728 |
+
"lstrip": false,
|
729 |
+
"normalized": false,
|
730 |
+
"rstrip": false,
|
731 |
+
"single_word": false,
|
732 |
+
"special": true
|
733 |
+
},
|
734 |
+
"128091": {
|
735 |
+
"content": "<|reserved_special_token_83|>",
|
736 |
+
"lstrip": false,
|
737 |
+
"normalized": false,
|
738 |
+
"rstrip": false,
|
739 |
+
"single_word": false,
|
740 |
+
"special": true
|
741 |
+
},
|
742 |
+
"128092": {
|
743 |
+
"content": "<|reserved_special_token_84|>",
|
744 |
+
"lstrip": false,
|
745 |
+
"normalized": false,
|
746 |
+
"rstrip": false,
|
747 |
+
"single_word": false,
|
748 |
+
"special": true
|
749 |
+
},
|
750 |
+
"128093": {
|
751 |
+
"content": "<|reserved_special_token_85|>",
|
752 |
+
"lstrip": false,
|
753 |
+
"normalized": false,
|
754 |
+
"rstrip": false,
|
755 |
+
"single_word": false,
|
756 |
+
"special": true
|
757 |
+
},
|
758 |
+
"128094": {
|
759 |
+
"content": "<|reserved_special_token_86|>",
|
760 |
+
"lstrip": false,
|
761 |
+
"normalized": false,
|
762 |
+
"rstrip": false,
|
763 |
+
"single_word": false,
|
764 |
+
"special": true
|
765 |
+
},
|
766 |
+
"128095": {
|
767 |
+
"content": "<|reserved_special_token_87|>",
|
768 |
+
"lstrip": false,
|
769 |
+
"normalized": false,
|
770 |
+
"rstrip": false,
|
771 |
+
"single_word": false,
|
772 |
+
"special": true
|
773 |
+
},
|
774 |
+
"128096": {
|
775 |
+
"content": "<|reserved_special_token_88|>",
|
776 |
+
"lstrip": false,
|
777 |
+
"normalized": false,
|
778 |
+
"rstrip": false,
|
779 |
+
"single_word": false,
|
780 |
+
"special": true
|
781 |
+
},
|
782 |
+
"128097": {
|
783 |
+
"content": "<|reserved_special_token_89|>",
|
784 |
+
"lstrip": false,
|
785 |
+
"normalized": false,
|
786 |
+
"rstrip": false,
|
787 |
+
"single_word": false,
|
788 |
+
"special": true
|
789 |
+
},
|
790 |
+
"128098": {
|
791 |
+
"content": "<|reserved_special_token_90|>",
|
792 |
+
"lstrip": false,
|
793 |
+
"normalized": false,
|
794 |
+
"rstrip": false,
|
795 |
+
"single_word": false,
|
796 |
+
"special": true
|
797 |
+
},
|
798 |
+
"128099": {
|
799 |
+
"content": "<|reserved_special_token_91|>",
|
800 |
+
"lstrip": false,
|
801 |
+
"normalized": false,
|
802 |
+
"rstrip": false,
|
803 |
+
"single_word": false,
|
804 |
+
"special": true
|
805 |
+
},
|
806 |
+
"128100": {
|
807 |
+
"content": "<|reserved_special_token_92|>",
|
808 |
+
"lstrip": false,
|
809 |
+
"normalized": false,
|
810 |
+
"rstrip": false,
|
811 |
+
"single_word": false,
|
812 |
+
"special": true
|
813 |
+
},
|
814 |
+
"128101": {
|
815 |
+
"content": "<|reserved_special_token_93|>",
|
816 |
+
"lstrip": false,
|
817 |
+
"normalized": false,
|
818 |
+
"rstrip": false,
|
819 |
+
"single_word": false,
|
820 |
+
"special": true
|
821 |
+
},
|
822 |
+
"128102": {
|
823 |
+
"content": "<|reserved_special_token_94|>",
|
824 |
+
"lstrip": false,
|
825 |
+
"normalized": false,
|
826 |
+
"rstrip": false,
|
827 |
+
"single_word": false,
|
828 |
+
"special": true
|
829 |
+
},
|
830 |
+
"128103": {
|
831 |
+
"content": "<|reserved_special_token_95|>",
|
832 |
+
"lstrip": false,
|
833 |
+
"normalized": false,
|
834 |
+
"rstrip": false,
|
835 |
+
"single_word": false,
|
836 |
+
"special": true
|
837 |
+
},
|
838 |
+
"128104": {
|
839 |
+
"content": "<|reserved_special_token_96|>",
|
840 |
+
"lstrip": false,
|
841 |
+
"normalized": false,
|
842 |
+
"rstrip": false,
|
843 |
+
"single_word": false,
|
844 |
+
"special": true
|
845 |
+
},
|
846 |
+
"128105": {
|
847 |
+
"content": "<|reserved_special_token_97|>",
|
848 |
+
"lstrip": false,
|
849 |
+
"normalized": false,
|
850 |
+
"rstrip": false,
|
851 |
+
"single_word": false,
|
852 |
+
"special": true
|
853 |
+
},
|
854 |
+
"128106": {
|
855 |
+
"content": "<|reserved_special_token_98|>",
|
856 |
+
"lstrip": false,
|
857 |
+
"normalized": false,
|
858 |
+
"rstrip": false,
|
859 |
+
"single_word": false,
|
860 |
+
"special": true
|
861 |
+
},
|
862 |
+
"128107": {
|
863 |
+
"content": "<|reserved_special_token_99|>",
|
864 |
+
"lstrip": false,
|
865 |
+
"normalized": false,
|
866 |
+
"rstrip": false,
|
867 |
+
"single_word": false,
|
868 |
+
"special": true
|
869 |
+
},
|
870 |
+
"128108": {
|
871 |
+
"content": "<|reserved_special_token_100|>",
|
872 |
+
"lstrip": false,
|
873 |
+
"normalized": false,
|
874 |
+
"rstrip": false,
|
875 |
+
"single_word": false,
|
876 |
+
"special": true
|
877 |
+
},
|
878 |
+
"128109": {
|
879 |
+
"content": "<|reserved_special_token_101|>",
|
880 |
+
"lstrip": false,
|
881 |
+
"normalized": false,
|
882 |
+
"rstrip": false,
|
883 |
+
"single_word": false,
|
884 |
+
"special": true
|
885 |
+
},
|
886 |
+
"128110": {
|
887 |
+
"content": "<|reserved_special_token_102|>",
|
888 |
+
"lstrip": false,
|
889 |
+
"normalized": false,
|
890 |
+
"rstrip": false,
|
891 |
+
"single_word": false,
|
892 |
+
"special": true
|
893 |
+
},
|
894 |
+
"128111": {
|
895 |
+
"content": "<|reserved_special_token_103|>",
|
896 |
+
"lstrip": false,
|
897 |
+
"normalized": false,
|
898 |
+
"rstrip": false,
|
899 |
+
"single_word": false,
|
900 |
+
"special": true
|
901 |
+
},
|
902 |
+
"128112": {
|
903 |
+
"content": "<|reserved_special_token_104|>",
|
904 |
+
"lstrip": false,
|
905 |
+
"normalized": false,
|
906 |
+
"rstrip": false,
|
907 |
+
"single_word": false,
|
908 |
+
"special": true
|
909 |
+
},
|
910 |
+
"128113": {
|
911 |
+
"content": "<|reserved_special_token_105|>",
|
912 |
+
"lstrip": false,
|
913 |
+
"normalized": false,
|
914 |
+
"rstrip": false,
|
915 |
+
"single_word": false,
|
916 |
+
"special": true
|
917 |
+
},
|
918 |
+
"128114": {
|
919 |
+
"content": "<|reserved_special_token_106|>",
|
920 |
+
"lstrip": false,
|
921 |
+
"normalized": false,
|
922 |
+
"rstrip": false,
|
923 |
+
"single_word": false,
|
924 |
+
"special": true
|
925 |
+
},
|
926 |
+
"128115": {
|
927 |
+
"content": "<|reserved_special_token_107|>",
|
928 |
+
"lstrip": false,
|
929 |
+
"normalized": false,
|
930 |
+
"rstrip": false,
|
931 |
+
"single_word": false,
|
932 |
+
"special": true
|
933 |
+
},
|
934 |
+
"128116": {
|
935 |
+
"content": "<|reserved_special_token_108|>",
|
936 |
+
"lstrip": false,
|
937 |
+
"normalized": false,
|
938 |
+
"rstrip": false,
|
939 |
+
"single_word": false,
|
940 |
+
"special": true
|
941 |
+
},
|
942 |
+
"128117": {
|
943 |
+
"content": "<|reserved_special_token_109|>",
|
944 |
+
"lstrip": false,
|
945 |
+
"normalized": false,
|
946 |
+
"rstrip": false,
|
947 |
+
"single_word": false,
|
948 |
+
"special": true
|
949 |
+
},
|
950 |
+
"128118": {
|
951 |
+
"content": "<|reserved_special_token_110|>",
|
952 |
+
"lstrip": false,
|
953 |
+
"normalized": false,
|
954 |
+
"rstrip": false,
|
955 |
+
"single_word": false,
|
956 |
+
"special": true
|
957 |
+
},
|
958 |
+
"128119": {
|
959 |
+
"content": "<|reserved_special_token_111|>",
|
960 |
+
"lstrip": false,
|
961 |
+
"normalized": false,
|
962 |
+
"rstrip": false,
|
963 |
+
"single_word": false,
|
964 |
+
"special": true
|
965 |
+
},
|
966 |
+
"128120": {
|
967 |
+
"content": "<|reserved_special_token_112|>",
|
968 |
+
"lstrip": false,
|
969 |
+
"normalized": false,
|
970 |
+
"rstrip": false,
|
971 |
+
"single_word": false,
|
972 |
+
"special": true
|
973 |
+
},
|
974 |
+
"128121": {
|
975 |
+
"content": "<|reserved_special_token_113|>",
|
976 |
+
"lstrip": false,
|
977 |
+
"normalized": false,
|
978 |
+
"rstrip": false,
|
979 |
+
"single_word": false,
|
980 |
+
"special": true
|
981 |
+
},
|
982 |
+
"128122": {
|
983 |
+
"content": "<|reserved_special_token_114|>",
|
984 |
+
"lstrip": false,
|
985 |
+
"normalized": false,
|
986 |
+
"rstrip": false,
|
987 |
+
"single_word": false,
|
988 |
+
"special": true
|
989 |
+
},
|
990 |
+
"128123": {
|
991 |
+
"content": "<|reserved_special_token_115|>",
|
992 |
+
"lstrip": false,
|
993 |
+
"normalized": false,
|
994 |
+
"rstrip": false,
|
995 |
+
"single_word": false,
|
996 |
+
"special": true
|
997 |
+
},
|
998 |
+
"128124": {
|
999 |
+
"content": "<|reserved_special_token_116|>",
|
1000 |
+
"lstrip": false,
|
1001 |
+
"normalized": false,
|
1002 |
+
"rstrip": false,
|
1003 |
+
"single_word": false,
|
1004 |
+
"special": true
|
1005 |
+
},
|
1006 |
+
"128125": {
|
1007 |
+
"content": "<|reserved_special_token_117|>",
|
1008 |
+
"lstrip": false,
|
1009 |
+
"normalized": false,
|
1010 |
+
"rstrip": false,
|
1011 |
+
"single_word": false,
|
1012 |
+
"special": true
|
1013 |
+
},
|
1014 |
+
"128126": {
|
1015 |
+
"content": "<|reserved_special_token_118|>",
|
1016 |
+
"lstrip": false,
|
1017 |
+
"normalized": false,
|
1018 |
+
"rstrip": false,
|
1019 |
+
"single_word": false,
|
1020 |
+
"special": true
|
1021 |
+
},
|
1022 |
+
"128127": {
|
1023 |
+
"content": "<|reserved_special_token_119|>",
|
1024 |
+
"lstrip": false,
|
1025 |
+
"normalized": false,
|
1026 |
+
"rstrip": false,
|
1027 |
+
"single_word": false,
|
1028 |
+
"special": true
|
1029 |
+
},
|
1030 |
+
"128128": {
|
1031 |
+
"content": "<|reserved_special_token_120|>",
|
1032 |
+
"lstrip": false,
|
1033 |
+
"normalized": false,
|
1034 |
+
"rstrip": false,
|
1035 |
+
"single_word": false,
|
1036 |
+
"special": true
|
1037 |
+
},
|
1038 |
+
"128129": {
|
1039 |
+
"content": "<|reserved_special_token_121|>",
|
1040 |
+
"lstrip": false,
|
1041 |
+
"normalized": false,
|
1042 |
+
"rstrip": false,
|
1043 |
+
"single_word": false,
|
1044 |
+
"special": true
|
1045 |
+
},
|
1046 |
+
"128130": {
|
1047 |
+
"content": "<|reserved_special_token_122|>",
|
1048 |
+
"lstrip": false,
|
1049 |
+
"normalized": false,
|
1050 |
+
"rstrip": false,
|
1051 |
+
"single_word": false,
|
1052 |
+
"special": true
|
1053 |
+
},
|
1054 |
+
"128131": {
|
1055 |
+
"content": "<|reserved_special_token_123|>",
|
1056 |
+
"lstrip": false,
|
1057 |
+
"normalized": false,
|
1058 |
+
"rstrip": false,
|
1059 |
+
"single_word": false,
|
1060 |
+
"special": true
|
1061 |
+
},
|
1062 |
+
"128132": {
|
1063 |
+
"content": "<|reserved_special_token_124|>",
|
1064 |
+
"lstrip": false,
|
1065 |
+
"normalized": false,
|
1066 |
+
"rstrip": false,
|
1067 |
+
"single_word": false,
|
1068 |
+
"special": true
|
1069 |
+
},
|
1070 |
+
"128133": {
|
1071 |
+
"content": "<|reserved_special_token_125|>",
|
1072 |
+
"lstrip": false,
|
1073 |
+
"normalized": false,
|
1074 |
+
"rstrip": false,
|
1075 |
+
"single_word": false,
|
1076 |
+
"special": true
|
1077 |
+
},
|
1078 |
+
"128134": {
|
1079 |
+
"content": "<|reserved_special_token_126|>",
|
1080 |
+
"lstrip": false,
|
1081 |
+
"normalized": false,
|
1082 |
+
"rstrip": false,
|
1083 |
+
"single_word": false,
|
1084 |
+
"special": true
|
1085 |
+
},
|
1086 |
+
"128135": {
|
1087 |
+
"content": "<|reserved_special_token_127|>",
|
1088 |
+
"lstrip": false,
|
1089 |
+
"normalized": false,
|
1090 |
+
"rstrip": false,
|
1091 |
+
"single_word": false,
|
1092 |
+
"special": true
|
1093 |
+
},
|
1094 |
+
"128136": {
|
1095 |
+
"content": "<|reserved_special_token_128|>",
|
1096 |
+
"lstrip": false,
|
1097 |
+
"normalized": false,
|
1098 |
+
"rstrip": false,
|
1099 |
+
"single_word": false,
|
1100 |
+
"special": true
|
1101 |
+
},
|
1102 |
+
"128137": {
|
1103 |
+
"content": "<|reserved_special_token_129|>",
|
1104 |
+
"lstrip": false,
|
1105 |
+
"normalized": false,
|
1106 |
+
"rstrip": false,
|
1107 |
+
"single_word": false,
|
1108 |
+
"special": true
|
1109 |
+
},
|
1110 |
+
"128138": {
|
1111 |
+
"content": "<|reserved_special_token_130|>",
|
1112 |
+
"lstrip": false,
|
1113 |
+
"normalized": false,
|
1114 |
+
"rstrip": false,
|
1115 |
+
"single_word": false,
|
1116 |
+
"special": true
|
1117 |
+
},
|
1118 |
+
"128139": {
|
1119 |
+
"content": "<|reserved_special_token_131|>",
|
1120 |
+
"lstrip": false,
|
1121 |
+
"normalized": false,
|
1122 |
+
"rstrip": false,
|
1123 |
+
"single_word": false,
|
1124 |
+
"special": true
|
1125 |
+
},
|
1126 |
+
"128140": {
|
1127 |
+
"content": "<|reserved_special_token_132|>",
|
1128 |
+
"lstrip": false,
|
1129 |
+
"normalized": false,
|
1130 |
+
"rstrip": false,
|
1131 |
+
"single_word": false,
|
1132 |
+
"special": true
|
1133 |
+
},
|
1134 |
+
"128141": {
|
1135 |
+
"content": "<|reserved_special_token_133|>",
|
1136 |
+
"lstrip": false,
|
1137 |
+
"normalized": false,
|
1138 |
+
"rstrip": false,
|
1139 |
+
"single_word": false,
|
1140 |
+
"special": true
|
1141 |
+
},
|
1142 |
+
"128142": {
|
1143 |
+
"content": "<|reserved_special_token_134|>",
|
1144 |
+
"lstrip": false,
|
1145 |
+
"normalized": false,
|
1146 |
+
"rstrip": false,
|
1147 |
+
"single_word": false,
|
1148 |
+
"special": true
|
1149 |
+
},
|
1150 |
+
"128143": {
|
1151 |
+
"content": "<|reserved_special_token_135|>",
|
1152 |
+
"lstrip": false,
|
1153 |
+
"normalized": false,
|
1154 |
+
"rstrip": false,
|
1155 |
+
"single_word": false,
|
1156 |
+
"special": true
|
1157 |
+
},
|
1158 |
+
"128144": {
|
1159 |
+
"content": "<|reserved_special_token_136|>",
|
1160 |
+
"lstrip": false,
|
1161 |
+
"normalized": false,
|
1162 |
+
"rstrip": false,
|
1163 |
+
"single_word": false,
|
1164 |
+
"special": true
|
1165 |
+
},
|
1166 |
+
"128145": {
|
1167 |
+
"content": "<|reserved_special_token_137|>",
|
1168 |
+
"lstrip": false,
|
1169 |
+
"normalized": false,
|
1170 |
+
"rstrip": false,
|
1171 |
+
"single_word": false,
|
1172 |
+
"special": true
|
1173 |
+
},
|
1174 |
+
"128146": {
|
1175 |
+
"content": "<|reserved_special_token_138|>",
|
1176 |
+
"lstrip": false,
|
1177 |
+
"normalized": false,
|
1178 |
+
"rstrip": false,
|
1179 |
+
"single_word": false,
|
1180 |
+
"special": true
|
1181 |
+
},
|
1182 |
+
"128147": {
|
1183 |
+
"content": "<|reserved_special_token_139|>",
|
1184 |
+
"lstrip": false,
|
1185 |
+
"normalized": false,
|
1186 |
+
"rstrip": false,
|
1187 |
+
"single_word": false,
|
1188 |
+
"special": true
|
1189 |
+
},
|
1190 |
+
"128148": {
|
1191 |
+
"content": "<|reserved_special_token_140|>",
|
1192 |
+
"lstrip": false,
|
1193 |
+
"normalized": false,
|
1194 |
+
"rstrip": false,
|
1195 |
+
"single_word": false,
|
1196 |
+
"special": true
|
1197 |
+
},
|
1198 |
+
"128149": {
|
1199 |
+
"content": "<|reserved_special_token_141|>",
|
1200 |
+
"lstrip": false,
|
1201 |
+
"normalized": false,
|
1202 |
+
"rstrip": false,
|
1203 |
+
"single_word": false,
|
1204 |
+
"special": true
|
1205 |
+
},
|
1206 |
+
"128150": {
|
1207 |
+
"content": "<|reserved_special_token_142|>",
|
1208 |
+
"lstrip": false,
|
1209 |
+
"normalized": false,
|
1210 |
+
"rstrip": false,
|
1211 |
+
"single_word": false,
|
1212 |
+
"special": true
|
1213 |
+
},
|
1214 |
+
"128151": {
|
1215 |
+
"content": "<|reserved_special_token_143|>",
|
1216 |
+
"lstrip": false,
|
1217 |
+
"normalized": false,
|
1218 |
+
"rstrip": false,
|
1219 |
+
"single_word": false,
|
1220 |
+
"special": true
|
1221 |
+
},
|
1222 |
+
"128152": {
|
1223 |
+
"content": "<|reserved_special_token_144|>",
|
1224 |
+
"lstrip": false,
|
1225 |
+
"normalized": false,
|
1226 |
+
"rstrip": false,
|
1227 |
+
"single_word": false,
|
1228 |
+
"special": true
|
1229 |
+
},
|
1230 |
+
"128153": {
|
1231 |
+
"content": "<|reserved_special_token_145|>",
|
1232 |
+
"lstrip": false,
|
1233 |
+
"normalized": false,
|
1234 |
+
"rstrip": false,
|
1235 |
+
"single_word": false,
|
1236 |
+
"special": true
|
1237 |
+
},
|
1238 |
+
"128154": {
|
1239 |
+
"content": "<|reserved_special_token_146|>",
|
1240 |
+
"lstrip": false,
|
1241 |
+
"normalized": false,
|
1242 |
+
"rstrip": false,
|
1243 |
+
"single_word": false,
|
1244 |
+
"special": true
|
1245 |
+
},
|
1246 |
+
"128155": {
|
1247 |
+
"content": "<|reserved_special_token_147|>",
|
1248 |
+
"lstrip": false,
|
1249 |
+
"normalized": false,
|
1250 |
+
"rstrip": false,
|
1251 |
+
"single_word": false,
|
1252 |
+
"special": true
|
1253 |
+
},
|
1254 |
+
"128156": {
|
1255 |
+
"content": "<|reserved_special_token_148|>",
|
1256 |
+
"lstrip": false,
|
1257 |
+
"normalized": false,
|
1258 |
+
"rstrip": false,
|
1259 |
+
"single_word": false,
|
1260 |
+
"special": true
|
1261 |
+
},
|
1262 |
+
"128157": {
|
1263 |
+
"content": "<|reserved_special_token_149|>",
|
1264 |
+
"lstrip": false,
|
1265 |
+
"normalized": false,
|
1266 |
+
"rstrip": false,
|
1267 |
+
"single_word": false,
|
1268 |
+
"special": true
|
1269 |
+
},
|
1270 |
+
"128158": {
|
1271 |
+
"content": "<|reserved_special_token_150|>",
|
1272 |
+
"lstrip": false,
|
1273 |
+
"normalized": false,
|
1274 |
+
"rstrip": false,
|
1275 |
+
"single_word": false,
|
1276 |
+
"special": true
|
1277 |
+
},
|
1278 |
+
"128159": {
|
1279 |
+
"content": "<|reserved_special_token_151|>",
|
1280 |
+
"lstrip": false,
|
1281 |
+
"normalized": false,
|
1282 |
+
"rstrip": false,
|
1283 |
+
"single_word": false,
|
1284 |
+
"special": true
|
1285 |
+
},
|
1286 |
+
"128160": {
|
1287 |
+
"content": "<|reserved_special_token_152|>",
|
1288 |
+
"lstrip": false,
|
1289 |
+
"normalized": false,
|
1290 |
+
"rstrip": false,
|
1291 |
+
"single_word": false,
|
1292 |
+
"special": true
|
1293 |
+
},
|
1294 |
+
"128161": {
|
1295 |
+
"content": "<|reserved_special_token_153|>",
|
1296 |
+
"lstrip": false,
|
1297 |
+
"normalized": false,
|
1298 |
+
"rstrip": false,
|
1299 |
+
"single_word": false,
|
1300 |
+
"special": true
|
1301 |
+
},
|
1302 |
+
"128162": {
|
1303 |
+
"content": "<|reserved_special_token_154|>",
|
1304 |
+
"lstrip": false,
|
1305 |
+
"normalized": false,
|
1306 |
+
"rstrip": false,
|
1307 |
+
"single_word": false,
|
1308 |
+
"special": true
|
1309 |
+
},
|
1310 |
+
"128163": {
|
1311 |
+
"content": "<|reserved_special_token_155|>",
|
1312 |
+
"lstrip": false,
|
1313 |
+
"normalized": false,
|
1314 |
+
"rstrip": false,
|
1315 |
+
"single_word": false,
|
1316 |
+
"special": true
|
1317 |
+
},
|
1318 |
+
"128164": {
|
1319 |
+
"content": "<|reserved_special_token_156|>",
|
1320 |
+
"lstrip": false,
|
1321 |
+
"normalized": false,
|
1322 |
+
"rstrip": false,
|
1323 |
+
"single_word": false,
|
1324 |
+
"special": true
|
1325 |
+
},
|
1326 |
+
"128165": {
|
1327 |
+
"content": "<|reserved_special_token_157|>",
|
1328 |
+
"lstrip": false,
|
1329 |
+
"normalized": false,
|
1330 |
+
"rstrip": false,
|
1331 |
+
"single_word": false,
|
1332 |
+
"special": true
|
1333 |
+
},
|
1334 |
+
"128166": {
|
1335 |
+
"content": "<|reserved_special_token_158|>",
|
1336 |
+
"lstrip": false,
|
1337 |
+
"normalized": false,
|
1338 |
+
"rstrip": false,
|
1339 |
+
"single_word": false,
|
1340 |
+
"special": true
|
1341 |
+
},
|
1342 |
+
"128167": {
|
1343 |
+
"content": "<|reserved_special_token_159|>",
|
1344 |
+
"lstrip": false,
|
1345 |
+
"normalized": false,
|
1346 |
+
"rstrip": false,
|
1347 |
+
"single_word": false,
|
1348 |
+
"special": true
|
1349 |
+
},
|
1350 |
+
"128168": {
|
1351 |
+
"content": "<|reserved_special_token_160|>",
|
1352 |
+
"lstrip": false,
|
1353 |
+
"normalized": false,
|
1354 |
+
"rstrip": false,
|
1355 |
+
"single_word": false,
|
1356 |
+
"special": true
|
1357 |
+
},
|
1358 |
+
"128169": {
|
1359 |
+
"content": "<|reserved_special_token_161|>",
|
1360 |
+
"lstrip": false,
|
1361 |
+
"normalized": false,
|
1362 |
+
"rstrip": false,
|
1363 |
+
"single_word": false,
|
1364 |
+
"special": true
|
1365 |
+
},
|
1366 |
+
"128170": {
|
1367 |
+
"content": "<|reserved_special_token_162|>",
|
1368 |
+
"lstrip": false,
|
1369 |
+
"normalized": false,
|
1370 |
+
"rstrip": false,
|
1371 |
+
"single_word": false,
|
1372 |
+
"special": true
|
1373 |
+
},
|
1374 |
+
"128171": {
|
1375 |
+
"content": "<|reserved_special_token_163|>",
|
1376 |
+
"lstrip": false,
|
1377 |
+
"normalized": false,
|
1378 |
+
"rstrip": false,
|
1379 |
+
"single_word": false,
|
1380 |
+
"special": true
|
1381 |
+
},
|
1382 |
+
"128172": {
|
1383 |
+
"content": "<|reserved_special_token_164|>",
|
1384 |
+
"lstrip": false,
|
1385 |
+
"normalized": false,
|
1386 |
+
"rstrip": false,
|
1387 |
+
"single_word": false,
|
1388 |
+
"special": true
|
1389 |
+
},
|
1390 |
+
"128173": {
|
1391 |
+
"content": "<|reserved_special_token_165|>",
|
1392 |
+
"lstrip": false,
|
1393 |
+
"normalized": false,
|
1394 |
+
"rstrip": false,
|
1395 |
+
"single_word": false,
|
1396 |
+
"special": true
|
1397 |
+
},
|
1398 |
+
"128174": {
|
1399 |
+
"content": "<|reserved_special_token_166|>",
|
1400 |
+
"lstrip": false,
|
1401 |
+
"normalized": false,
|
1402 |
+
"rstrip": false,
|
1403 |
+
"single_word": false,
|
1404 |
+
"special": true
|
1405 |
+
},
|
1406 |
+
"128175": {
|
1407 |
+
"content": "<|reserved_special_token_167|>",
|
1408 |
+
"lstrip": false,
|
1409 |
+
"normalized": false,
|
1410 |
+
"rstrip": false,
|
1411 |
+
"single_word": false,
|
1412 |
+
"special": true
|
1413 |
+
},
|
1414 |
+
"128176": {
|
1415 |
+
"content": "<|reserved_special_token_168|>",
|
1416 |
+
"lstrip": false,
|
1417 |
+
"normalized": false,
|
1418 |
+
"rstrip": false,
|
1419 |
+
"single_word": false,
|
1420 |
+
"special": true
|
1421 |
+
},
|
1422 |
+
"128177": {
|
1423 |
+
"content": "<|reserved_special_token_169|>",
|
1424 |
+
"lstrip": false,
|
1425 |
+
"normalized": false,
|
1426 |
+
"rstrip": false,
|
1427 |
+
"single_word": false,
|
1428 |
+
"special": true
|
1429 |
+
},
|
1430 |
+
"128178": {
|
1431 |
+
"content": "<|reserved_special_token_170|>",
|
1432 |
+
"lstrip": false,
|
1433 |
+
"normalized": false,
|
1434 |
+
"rstrip": false,
|
1435 |
+
"single_word": false,
|
1436 |
+
"special": true
|
1437 |
+
},
|
1438 |
+
"128179": {
|
1439 |
+
"content": "<|reserved_special_token_171|>",
|
1440 |
+
"lstrip": false,
|
1441 |
+
"normalized": false,
|
1442 |
+
"rstrip": false,
|
1443 |
+
"single_word": false,
|
1444 |
+
"special": true
|
1445 |
+
},
|
1446 |
+
"128180": {
|
1447 |
+
"content": "<|reserved_special_token_172|>",
|
1448 |
+
"lstrip": false,
|
1449 |
+
"normalized": false,
|
1450 |
+
"rstrip": false,
|
1451 |
+
"single_word": false,
|
1452 |
+
"special": true
|
1453 |
+
},
|
1454 |
+
"128181": {
|
1455 |
+
"content": "<|reserved_special_token_173|>",
|
1456 |
+
"lstrip": false,
|
1457 |
+
"normalized": false,
|
1458 |
+
"rstrip": false,
|
1459 |
+
"single_word": false,
|
1460 |
+
"special": true
|
1461 |
+
},
|
1462 |
+
"128182": {
|
1463 |
+
"content": "<|reserved_special_token_174|>",
|
1464 |
+
"lstrip": false,
|
1465 |
+
"normalized": false,
|
1466 |
+
"rstrip": false,
|
1467 |
+
"single_word": false,
|
1468 |
+
"special": true
|
1469 |
+
},
|
1470 |
+
"128183": {
|
1471 |
+
"content": "<|reserved_special_token_175|>",
|
1472 |
+
"lstrip": false,
|
1473 |
+
"normalized": false,
|
1474 |
+
"rstrip": false,
|
1475 |
+
"single_word": false,
|
1476 |
+
"special": true
|
1477 |
+
},
|
1478 |
+
"128184": {
|
1479 |
+
"content": "<|reserved_special_token_176|>",
|
1480 |
+
"lstrip": false,
|
1481 |
+
"normalized": false,
|
1482 |
+
"rstrip": false,
|
1483 |
+
"single_word": false,
|
1484 |
+
"special": true
|
1485 |
+
},
|
1486 |
+
"128185": {
|
1487 |
+
"content": "<|reserved_special_token_177|>",
|
1488 |
+
"lstrip": false,
|
1489 |
+
"normalized": false,
|
1490 |
+
"rstrip": false,
|
1491 |
+
"single_word": false,
|
1492 |
+
"special": true
|
1493 |
+
},
|
1494 |
+
"128186": {
|
1495 |
+
"content": "<|reserved_special_token_178|>",
|
1496 |
+
"lstrip": false,
|
1497 |
+
"normalized": false,
|
1498 |
+
"rstrip": false,
|
1499 |
+
"single_word": false,
|
1500 |
+
"special": true
|
1501 |
+
},
|
1502 |
+
"128187": {
|
1503 |
+
"content": "<|reserved_special_token_179|>",
|
1504 |
+
"lstrip": false,
|
1505 |
+
"normalized": false,
|
1506 |
+
"rstrip": false,
|
1507 |
+
"single_word": false,
|
1508 |
+
"special": true
|
1509 |
+
},
|
1510 |
+
"128188": {
|
1511 |
+
"content": "<|reserved_special_token_180|>",
|
1512 |
+
"lstrip": false,
|
1513 |
+
"normalized": false,
|
1514 |
+
"rstrip": false,
|
1515 |
+
"single_word": false,
|
1516 |
+
"special": true
|
1517 |
+
},
|
1518 |
+
"128189": {
|
1519 |
+
"content": "<|reserved_special_token_181|>",
|
1520 |
+
"lstrip": false,
|
1521 |
+
"normalized": false,
|
1522 |
+
"rstrip": false,
|
1523 |
+
"single_word": false,
|
1524 |
+
"special": true
|
1525 |
+
},
|
1526 |
+
"128190": {
|
1527 |
+
"content": "<|reserved_special_token_182|>",
|
1528 |
+
"lstrip": false,
|
1529 |
+
"normalized": false,
|
1530 |
+
"rstrip": false,
|
1531 |
+
"single_word": false,
|
1532 |
+
"special": true
|
1533 |
+
},
|
1534 |
+
"128191": {
|
1535 |
+
"content": "<|reserved_special_token_183|>",
|
1536 |
+
"lstrip": false,
|
1537 |
+
"normalized": false,
|
1538 |
+
"rstrip": false,
|
1539 |
+
"single_word": false,
|
1540 |
+
"special": true
|
1541 |
+
},
|
1542 |
+
"128192": {
|
1543 |
+
"content": "<|reserved_special_token_184|>",
|
1544 |
+
"lstrip": false,
|
1545 |
+
"normalized": false,
|
1546 |
+
"rstrip": false,
|
1547 |
+
"single_word": false,
|
1548 |
+
"special": true
|
1549 |
+
},
|
1550 |
+
"128193": {
|
1551 |
+
"content": "<|reserved_special_token_185|>",
|
1552 |
+
"lstrip": false,
|
1553 |
+
"normalized": false,
|
1554 |
+
"rstrip": false,
|
1555 |
+
"single_word": false,
|
1556 |
+
"special": true
|
1557 |
+
},
|
1558 |
+
"128194": {
|
1559 |
+
"content": "<|reserved_special_token_186|>",
|
1560 |
+
"lstrip": false,
|
1561 |
+
"normalized": false,
|
1562 |
+
"rstrip": false,
|
1563 |
+
"single_word": false,
|
1564 |
+
"special": true
|
1565 |
+
},
|
1566 |
+
"128195": {
|
1567 |
+
"content": "<|reserved_special_token_187|>",
|
1568 |
+
"lstrip": false,
|
1569 |
+
"normalized": false,
|
1570 |
+
"rstrip": false,
|
1571 |
+
"single_word": false,
|
1572 |
+
"special": true
|
1573 |
+
},
|
1574 |
+
"128196": {
|
1575 |
+
"content": "<|reserved_special_token_188|>",
|
1576 |
+
"lstrip": false,
|
1577 |
+
"normalized": false,
|
1578 |
+
"rstrip": false,
|
1579 |
+
"single_word": false,
|
1580 |
+
"special": true
|
1581 |
+
},
|
1582 |
+
"128197": {
|
1583 |
+
"content": "<|reserved_special_token_189|>",
|
1584 |
+
"lstrip": false,
|
1585 |
+
"normalized": false,
|
1586 |
+
"rstrip": false,
|
1587 |
+
"single_word": false,
|
1588 |
+
"special": true
|
1589 |
+
},
|
1590 |
+
"128198": {
|
1591 |
+
"content": "<|reserved_special_token_190|>",
|
1592 |
+
"lstrip": false,
|
1593 |
+
"normalized": false,
|
1594 |
+
"rstrip": false,
|
1595 |
+
"single_word": false,
|
1596 |
+
"special": true
|
1597 |
+
},
|
1598 |
+
"128199": {
|
1599 |
+
"content": "<|reserved_special_token_191|>",
|
1600 |
+
"lstrip": false,
|
1601 |
+
"normalized": false,
|
1602 |
+
"rstrip": false,
|
1603 |
+
"single_word": false,
|
1604 |
+
"special": true
|
1605 |
+
},
|
1606 |
+
"128200": {
|
1607 |
+
"content": "<|reserved_special_token_192|>",
|
1608 |
+
"lstrip": false,
|
1609 |
+
"normalized": false,
|
1610 |
+
"rstrip": false,
|
1611 |
+
"single_word": false,
|
1612 |
+
"special": true
|
1613 |
+
},
|
1614 |
+
"128201": {
|
1615 |
+
"content": "<|reserved_special_token_193|>",
|
1616 |
+
"lstrip": false,
|
1617 |
+
"normalized": false,
|
1618 |
+
"rstrip": false,
|
1619 |
+
"single_word": false,
|
1620 |
+
"special": true
|
1621 |
+
},
|
1622 |
+
"128202": {
|
1623 |
+
"content": "<|reserved_special_token_194|>",
|
1624 |
+
"lstrip": false,
|
1625 |
+
"normalized": false,
|
1626 |
+
"rstrip": false,
|
1627 |
+
"single_word": false,
|
1628 |
+
"special": true
|
1629 |
+
},
|
1630 |
+
"128203": {
|
1631 |
+
"content": "<|reserved_special_token_195|>",
|
1632 |
+
"lstrip": false,
|
1633 |
+
"normalized": false,
|
1634 |
+
"rstrip": false,
|
1635 |
+
"single_word": false,
|
1636 |
+
"special": true
|
1637 |
+
},
|
1638 |
+
"128204": {
|
1639 |
+
"content": "<|reserved_special_token_196|>",
|
1640 |
+
"lstrip": false,
|
1641 |
+
"normalized": false,
|
1642 |
+
"rstrip": false,
|
1643 |
+
"single_word": false,
|
1644 |
+
"special": true
|
1645 |
+
},
|
1646 |
+
"128205": {
|
1647 |
+
"content": "<|reserved_special_token_197|>",
|
1648 |
+
"lstrip": false,
|
1649 |
+
"normalized": false,
|
1650 |
+
"rstrip": false,
|
1651 |
+
"single_word": false,
|
1652 |
+
"special": true
|
1653 |
+
},
|
1654 |
+
"128206": {
|
1655 |
+
"content": "<|reserved_special_token_198|>",
|
1656 |
+
"lstrip": false,
|
1657 |
+
"normalized": false,
|
1658 |
+
"rstrip": false,
|
1659 |
+
"single_word": false,
|
1660 |
+
"special": true
|
1661 |
+
},
|
1662 |
+
"128207": {
|
1663 |
+
"content": "<|reserved_special_token_199|>",
|
1664 |
+
"lstrip": false,
|
1665 |
+
"normalized": false,
|
1666 |
+
"rstrip": false,
|
1667 |
+
"single_word": false,
|
1668 |
+
"special": true
|
1669 |
+
},
|
1670 |
+
"128208": {
|
1671 |
+
"content": "<|reserved_special_token_200|>",
|
1672 |
+
"lstrip": false,
|
1673 |
+
"normalized": false,
|
1674 |
+
"rstrip": false,
|
1675 |
+
"single_word": false,
|
1676 |
+
"special": true
|
1677 |
+
},
|
1678 |
+
"128209": {
|
1679 |
+
"content": "<|reserved_special_token_201|>",
|
1680 |
+
"lstrip": false,
|
1681 |
+
"normalized": false,
|
1682 |
+
"rstrip": false,
|
1683 |
+
"single_word": false,
|
1684 |
+
"special": true
|
1685 |
+
},
|
1686 |
+
"128210": {
|
1687 |
+
"content": "<|reserved_special_token_202|>",
|
1688 |
+
"lstrip": false,
|
1689 |
+
"normalized": false,
|
1690 |
+
"rstrip": false,
|
1691 |
+
"single_word": false,
|
1692 |
+
"special": true
|
1693 |
+
},
|
1694 |
+
"128211": {
|
1695 |
+
"content": "<|reserved_special_token_203|>",
|
1696 |
+
"lstrip": false,
|
1697 |
+
"normalized": false,
|
1698 |
+
"rstrip": false,
|
1699 |
+
"single_word": false,
|
1700 |
+
"special": true
|
1701 |
+
},
|
1702 |
+
"128212": {
|
1703 |
+
"content": "<|reserved_special_token_204|>",
|
1704 |
+
"lstrip": false,
|
1705 |
+
"normalized": false,
|
1706 |
+
"rstrip": false,
|
1707 |
+
"single_word": false,
|
1708 |
+
"special": true
|
1709 |
+
},
|
1710 |
+
"128213": {
|
1711 |
+
"content": "<|reserved_special_token_205|>",
|
1712 |
+
"lstrip": false,
|
1713 |
+
"normalized": false,
|
1714 |
+
"rstrip": false,
|
1715 |
+
"single_word": false,
|
1716 |
+
"special": true
|
1717 |
+
},
|
1718 |
+
"128214": {
|
1719 |
+
"content": "<|reserved_special_token_206|>",
|
1720 |
+
"lstrip": false,
|
1721 |
+
"normalized": false,
|
1722 |
+
"rstrip": false,
|
1723 |
+
"single_word": false,
|
1724 |
+
"special": true
|
1725 |
+
},
|
1726 |
+
"128215": {
|
1727 |
+
"content": "<|reserved_special_token_207|>",
|
1728 |
+
"lstrip": false,
|
1729 |
+
"normalized": false,
|
1730 |
+
"rstrip": false,
|
1731 |
+
"single_word": false,
|
1732 |
+
"special": true
|
1733 |
+
},
|
1734 |
+
"128216": {
|
1735 |
+
"content": "<|reserved_special_token_208|>",
|
1736 |
+
"lstrip": false,
|
1737 |
+
"normalized": false,
|
1738 |
+
"rstrip": false,
|
1739 |
+
"single_word": false,
|
1740 |
+
"special": true
|
1741 |
+
},
|
1742 |
+
"128217": {
|
1743 |
+
"content": "<|reserved_special_token_209|>",
|
1744 |
+
"lstrip": false,
|
1745 |
+
"normalized": false,
|
1746 |
+
"rstrip": false,
|
1747 |
+
"single_word": false,
|
1748 |
+
"special": true
|
1749 |
+
},
|
1750 |
+
"128218": {
|
1751 |
+
"content": "<|reserved_special_token_210|>",
|
1752 |
+
"lstrip": false,
|
1753 |
+
"normalized": false,
|
1754 |
+
"rstrip": false,
|
1755 |
+
"single_word": false,
|
1756 |
+
"special": true
|
1757 |
+
},
|
1758 |
+
"128219": {
|
1759 |
+
"content": "<|reserved_special_token_211|>",
|
1760 |
+
"lstrip": false,
|
1761 |
+
"normalized": false,
|
1762 |
+
"rstrip": false,
|
1763 |
+
"single_word": false,
|
1764 |
+
"special": true
|
1765 |
+
},
|
1766 |
+
"128220": {
|
1767 |
+
"content": "<|reserved_special_token_212|>",
|
1768 |
+
"lstrip": false,
|
1769 |
+
"normalized": false,
|
1770 |
+
"rstrip": false,
|
1771 |
+
"single_word": false,
|
1772 |
+
"special": true
|
1773 |
+
},
|
1774 |
+
"128221": {
|
1775 |
+
"content": "<|reserved_special_token_213|>",
|
1776 |
+
"lstrip": false,
|
1777 |
+
"normalized": false,
|
1778 |
+
"rstrip": false,
|
1779 |
+
"single_word": false,
|
1780 |
+
"special": true
|
1781 |
+
},
|
1782 |
+
"128222": {
|
1783 |
+
"content": "<|reserved_special_token_214|>",
|
1784 |
+
"lstrip": false,
|
1785 |
+
"normalized": false,
|
1786 |
+
"rstrip": false,
|
1787 |
+
"single_word": false,
|
1788 |
+
"special": true
|
1789 |
+
},
|
1790 |
+
"128223": {
|
1791 |
+
"content": "<|reserved_special_token_215|>",
|
1792 |
+
"lstrip": false,
|
1793 |
+
"normalized": false,
|
1794 |
+
"rstrip": false,
|
1795 |
+
"single_word": false,
|
1796 |
+
"special": true
|
1797 |
+
},
|
1798 |
+
"128224": {
|
1799 |
+
"content": "<|reserved_special_token_216|>",
|
1800 |
+
"lstrip": false,
|
1801 |
+
"normalized": false,
|
1802 |
+
"rstrip": false,
|
1803 |
+
"single_word": false,
|
1804 |
+
"special": true
|
1805 |
+
},
|
1806 |
+
"128225": {
|
1807 |
+
"content": "<|reserved_special_token_217|>",
|
1808 |
+
"lstrip": false,
|
1809 |
+
"normalized": false,
|
1810 |
+
"rstrip": false,
|
1811 |
+
"single_word": false,
|
1812 |
+
"special": true
|
1813 |
+
},
|
1814 |
+
"128226": {
|
1815 |
+
"content": "<|reserved_special_token_218|>",
|
1816 |
+
"lstrip": false,
|
1817 |
+
"normalized": false,
|
1818 |
+
"rstrip": false,
|
1819 |
+
"single_word": false,
|
1820 |
+
"special": true
|
1821 |
+
},
|
1822 |
+
"128227": {
|
1823 |
+
"content": "<|reserved_special_token_219|>",
|
1824 |
+
"lstrip": false,
|
1825 |
+
"normalized": false,
|
1826 |
+
"rstrip": false,
|
1827 |
+
"single_word": false,
|
1828 |
+
"special": true
|
1829 |
+
},
|
1830 |
+
"128228": {
|
1831 |
+
"content": "<|reserved_special_token_220|>",
|
1832 |
+
"lstrip": false,
|
1833 |
+
"normalized": false,
|
1834 |
+
"rstrip": false,
|
1835 |
+
"single_word": false,
|
1836 |
+
"special": true
|
1837 |
+
},
|
1838 |
+
"128229": {
|
1839 |
+
"content": "<|reserved_special_token_221|>",
|
1840 |
+
"lstrip": false,
|
1841 |
+
"normalized": false,
|
1842 |
+
"rstrip": false,
|
1843 |
+
"single_word": false,
|
1844 |
+
"special": true
|
1845 |
+
},
|
1846 |
+
"128230": {
|
1847 |
+
"content": "<|reserved_special_token_222|>",
|
1848 |
+
"lstrip": false,
|
1849 |
+
"normalized": false,
|
1850 |
+
"rstrip": false,
|
1851 |
+
"single_word": false,
|
1852 |
+
"special": true
|
1853 |
+
},
|
1854 |
+
"128231": {
|
1855 |
+
"content": "<|reserved_special_token_223|>",
|
1856 |
+
"lstrip": false,
|
1857 |
+
"normalized": false,
|
1858 |
+
"rstrip": false,
|
1859 |
+
"single_word": false,
|
1860 |
+
"special": true
|
1861 |
+
},
|
1862 |
+
"128232": {
|
1863 |
+
"content": "<|reserved_special_token_224|>",
|
1864 |
+
"lstrip": false,
|
1865 |
+
"normalized": false,
|
1866 |
+
"rstrip": false,
|
1867 |
+
"single_word": false,
|
1868 |
+
"special": true
|
1869 |
+
},
|
1870 |
+
"128233": {
|
1871 |
+
"content": "<|reserved_special_token_225|>",
|
1872 |
+
"lstrip": false,
|
1873 |
+
"normalized": false,
|
1874 |
+
"rstrip": false,
|
1875 |
+
"single_word": false,
|
1876 |
+
"special": true
|
1877 |
+
},
|
1878 |
+
"128234": {
|
1879 |
+
"content": "<|reserved_special_token_226|>",
|
1880 |
+
"lstrip": false,
|
1881 |
+
"normalized": false,
|
1882 |
+
"rstrip": false,
|
1883 |
+
"single_word": false,
|
1884 |
+
"special": true
|
1885 |
+
},
|
1886 |
+
"128235": {
|
1887 |
+
"content": "<|reserved_special_token_227|>",
|
1888 |
+
"lstrip": false,
|
1889 |
+
"normalized": false,
|
1890 |
+
"rstrip": false,
|
1891 |
+
"single_word": false,
|
1892 |
+
"special": true
|
1893 |
+
},
|
1894 |
+
"128236": {
|
1895 |
+
"content": "<|reserved_special_token_228|>",
|
1896 |
+
"lstrip": false,
|
1897 |
+
"normalized": false,
|
1898 |
+
"rstrip": false,
|
1899 |
+
"single_word": false,
|
1900 |
+
"special": true
|
1901 |
+
},
|
1902 |
+
"128237": {
|
1903 |
+
"content": "<|reserved_special_token_229|>",
|
1904 |
+
"lstrip": false,
|
1905 |
+
"normalized": false,
|
1906 |
+
"rstrip": false,
|
1907 |
+
"single_word": false,
|
1908 |
+
"special": true
|
1909 |
+
},
|
1910 |
+
"128238": {
|
1911 |
+
"content": "<|reserved_special_token_230|>",
|
1912 |
+
"lstrip": false,
|
1913 |
+
"normalized": false,
|
1914 |
+
"rstrip": false,
|
1915 |
+
"single_word": false,
|
1916 |
+
"special": true
|
1917 |
+
},
|
1918 |
+
"128239": {
|
1919 |
+
"content": "<|reserved_special_token_231|>",
|
1920 |
+
"lstrip": false,
|
1921 |
+
"normalized": false,
|
1922 |
+
"rstrip": false,
|
1923 |
+
"single_word": false,
|
1924 |
+
"special": true
|
1925 |
+
},
|
1926 |
+
"128240": {
|
1927 |
+
"content": "<|reserved_special_token_232|>",
|
1928 |
+
"lstrip": false,
|
1929 |
+
"normalized": false,
|
1930 |
+
"rstrip": false,
|
1931 |
+
"single_word": false,
|
1932 |
+
"special": true
|
1933 |
+
},
|
1934 |
+
"128241": {
|
1935 |
+
"content": "<|reserved_special_token_233|>",
|
1936 |
+
"lstrip": false,
|
1937 |
+
"normalized": false,
|
1938 |
+
"rstrip": false,
|
1939 |
+
"single_word": false,
|
1940 |
+
"special": true
|
1941 |
+
},
|
1942 |
+
"128242": {
|
1943 |
+
"content": "<|reserved_special_token_234|>",
|
1944 |
+
"lstrip": false,
|
1945 |
+
"normalized": false,
|
1946 |
+
"rstrip": false,
|
1947 |
+
"single_word": false,
|
1948 |
+
"special": true
|
1949 |
+
},
|
1950 |
+
"128243": {
|
1951 |
+
"content": "<|reserved_special_token_235|>",
|
1952 |
+
"lstrip": false,
|
1953 |
+
"normalized": false,
|
1954 |
+
"rstrip": false,
|
1955 |
+
"single_word": false,
|
1956 |
+
"special": true
|
1957 |
+
},
|
1958 |
+
"128244": {
|
1959 |
+
"content": "<|reserved_special_token_236|>",
|
1960 |
+
"lstrip": false,
|
1961 |
+
"normalized": false,
|
1962 |
+
"rstrip": false,
|
1963 |
+
"single_word": false,
|
1964 |
+
"special": true
|
1965 |
+
},
|
1966 |
+
"128245": {
|
1967 |
+
"content": "<|reserved_special_token_237|>",
|
1968 |
+
"lstrip": false,
|
1969 |
+
"normalized": false,
|
1970 |
+
"rstrip": false,
|
1971 |
+
"single_word": false,
|
1972 |
+
"special": true
|
1973 |
+
},
|
1974 |
+
"128246": {
|
1975 |
+
"content": "<|reserved_special_token_238|>",
|
1976 |
+
"lstrip": false,
|
1977 |
+
"normalized": false,
|
1978 |
+
"rstrip": false,
|
1979 |
+
"single_word": false,
|
1980 |
+
"special": true
|
1981 |
+
},
|
1982 |
+
"128247": {
|
1983 |
+
"content": "<|reserved_special_token_239|>",
|
1984 |
+
"lstrip": false,
|
1985 |
+
"normalized": false,
|
1986 |
+
"rstrip": false,
|
1987 |
+
"single_word": false,
|
1988 |
+
"special": true
|
1989 |
+
},
|
1990 |
+
"128248": {
|
1991 |
+
"content": "<|reserved_special_token_240|>",
|
1992 |
+
"lstrip": false,
|
1993 |
+
"normalized": false,
|
1994 |
+
"rstrip": false,
|
1995 |
+
"single_word": false,
|
1996 |
+
"special": true
|
1997 |
+
},
|
1998 |
+
"128249": {
|
1999 |
+
"content": "<|reserved_special_token_241|>",
|
2000 |
+
"lstrip": false,
|
2001 |
+
"normalized": false,
|
2002 |
+
"rstrip": false,
|
2003 |
+
"single_word": false,
|
2004 |
+
"special": true
|
2005 |
+
},
|
2006 |
+
"128250": {
|
2007 |
+
"content": "<|reserved_special_token_242|>",
|
2008 |
+
"lstrip": false,
|
2009 |
+
"normalized": false,
|
2010 |
+
"rstrip": false,
|
2011 |
+
"single_word": false,
|
2012 |
+
"special": true
|
2013 |
+
},
|
2014 |
+
"128251": {
|
2015 |
+
"content": "<|reserved_special_token_243|>",
|
2016 |
+
"lstrip": false,
|
2017 |
+
"normalized": false,
|
2018 |
+
"rstrip": false,
|
2019 |
+
"single_word": false,
|
2020 |
+
"special": true
|
2021 |
+
},
|
2022 |
+
"128252": {
|
2023 |
+
"content": "<|reserved_special_token_244|>",
|
2024 |
+
"lstrip": false,
|
2025 |
+
"normalized": false,
|
2026 |
+
"rstrip": false,
|
2027 |
+
"single_word": false,
|
2028 |
+
"special": true
|
2029 |
+
},
|
2030 |
+
"128253": {
|
2031 |
+
"content": "<|reserved_special_token_245|>",
|
2032 |
+
"lstrip": false,
|
2033 |
+
"normalized": false,
|
2034 |
+
"rstrip": false,
|
2035 |
+
"single_word": false,
|
2036 |
+
"special": true
|
2037 |
+
},
|
2038 |
+
"128254": {
|
2039 |
+
"content": "<|reserved_special_token_246|>",
|
2040 |
+
"lstrip": false,
|
2041 |
+
"normalized": false,
|
2042 |
+
"rstrip": false,
|
2043 |
+
"single_word": false,
|
2044 |
+
"special": true
|
2045 |
+
},
|
2046 |
+
"128255": {
|
2047 |
+
"content": "<|reserved_special_token_247|>",
|
2048 |
+
"lstrip": false,
|
2049 |
+
"normalized": false,
|
2050 |
+
"rstrip": false,
|
2051 |
+
"single_word": false,
|
2052 |
+
"special": true
|
2053 |
+
},
|
2054 |
+
"128256": {
|
2055 |
+
"content": "<|end_of_text|>",
|
2056 |
+
"lstrip": false,
|
2057 |
+
"normalized": false,
|
2058 |
+
"rstrip": false,
|
2059 |
+
"single_word": false,
|
2060 |
+
"special": true
|
2061 |
+
}
|
2062 |
+
},
|
2063 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
2064 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2065 |
+
"clean_up_tokenization_spaces": false,
|
2066 |
+
"eos_token": "<|end▁of▁sentence|>",
|
2067 |
+
"extra_special_tokens": {},
|
2068 |
+
"legacy": true,
|
2069 |
+
"model_max_length": 16384,
|
2070 |
+
"pad_token": "<|end_of_text|>",
|
2071 |
+
"sp_model_kwargs": {},
|
2072 |
+
"tokenizer_class": "LlamaTokenizer",
|
2073 |
+
"unk_token": null,
|
2074 |
+
"use_default_system_prompt": false
|
2075 |
+
}
|
checkpoint-run1-246/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-run1-246/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bfa7ff9d80b63c0ea349797dad26a60df3805ba7517614bd0d61390fa2637b7
|
3 |
+
size 7416
|
checkpoint-run1-62/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: /cpool/DeepSeek-R1-Distill-Llama-70B-Uncensored-v2
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.14.0
|
checkpoint-run1-62/adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "/cpool/DeepSeek-R1-Distill-Llama-70B-Uncensored-v2",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": null,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 32,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"v_proj",
|
27 |
+
"o_proj",
|
28 |
+
"q_proj",
|
29 |
+
"k_proj",
|
30 |
+
"gate_proj",
|
31 |
+
"down_proj",
|
32 |
+
"up_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
checkpoint-run1-62/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4bc601007008f4b26a0d313e4e7b673a1a5f93c4558d8a6c9a844db9987ee7c
|
3 |
+
size 1656902648
|
checkpoint-run1-62/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:071e8e4950308ba0b7a507303ec485a6947f71eaac69fd2d82aebb74ffe8f6e3
|
3 |
+
size 3314505202
|
checkpoint-run1-62/pytorch_model_fsdp.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf1a1a01ee5ce4d2d5ec8e33997157edc9d8570e1800bef0fade086fb70e8a56
|
3 |
+
size 1657168758
|
checkpoint-run1-62/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8d6a959372d5e0c2ea025dd26c9d0ad2046fce19352056cae8074dcbd0a6fd4
|
3 |
+
size 14512
|
checkpoint-run1-62/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f68a37892a1b445d21bb35cc10bf7a058a6f9ec8c363f5ed156ff4f49d90fb6
|
3 |
+
size 14512
|