aleegis12 commited on
Commit
ee5bf3a
·
verified ·
1 Parent(s): 20bfcc0

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Qwen2.5-Coder-1.5B-Instruct
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 0.13.2
last-checkpoint/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Qwen2.5-Coder-1.5B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "o_proj",
25
+ "up_proj",
26
+ "down_proj",
27
+ "gate_proj",
28
+ "k_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c46ac7abc9a1cfee9f0145a0e3537b3139361012671091b9f5536991db7830
3
+ size 295488936
last-checkpoint/added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|PAD_TOKEN|>": 151665,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|endoftext|>": 151643,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|video_pad|>": 151656,
22
+ "<|vision_end|>": 151653,
23
+ "<|vision_pad|>": 151654,
24
+ "<|vision_start|>": 151652
25
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69707d60d93437fc566484328a21150222baa761a930fca19948b2ec170d9d79
3
+ size 150486964
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793bd55ee90ba322d8530d91edb6b50a5fe6adf74d5270b85ad3c95df7d51155
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e9f0c2a27af03f3c1874438820d046de94b36aaec3b0cc778f96def4616314
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|PAD_TOKEN|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
3
+ size 11422086
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<|PAD_TOKEN|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ }
189
+ },
190
+ "additional_special_tokens": [
191
+ "<|im_start|>",
192
+ "<|im_end|>",
193
+ "<|object_ref_start|>",
194
+ "<|object_ref_end|>",
195
+ "<|box_start|>",
196
+ "<|box_end|>",
197
+ "<|quad_start|>",
198
+ "<|quad_end|>",
199
+ "<|vision_start|>",
200
+ "<|vision_end|>",
201
+ "<|vision_pad|>",
202
+ "<|image_pad|>",
203
+ "<|video_pad|>"
204
+ ],
205
+ "bos_token": null,
206
+ "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 %}",
207
+ "clean_up_tokenization_spaces": false,
208
+ "eos_token": "<|im_end|>",
209
+ "errors": "replace",
210
+ "model_max_length": 131072,
211
+ "pad_token": "<|PAD_TOKEN|>",
212
+ "padding_side": "left",
213
+ "split_special_tokens": false,
214
+ "tokenizer_class": "Qwen2Tokenizer",
215
+ "unk_token": null
216
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,758 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8690917491912842,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.05032079506856208,
5
+ "eval_steps": 100,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0005032079506856208,
13
+ "grad_norm": 0.38297849893569946,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.5872,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0005032079506856208,
20
+ "eval_loss": 1.0933938026428223,
21
+ "eval_runtime": 104.1253,
22
+ "eval_samples_per_second": 32.144,
23
+ "eval_steps_per_second": 8.038,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0010064159013712416,
28
+ "grad_norm": 0.4977751076221466,
29
+ "learning_rate": 1e-05,
30
+ "loss": 0.7907,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0015096238520568624,
35
+ "grad_norm": 0.4053085148334503,
36
+ "learning_rate": 1.5e-05,
37
+ "loss": 0.7258,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.0020128318027424832,
42
+ "grad_norm": 0.3187407851219177,
43
+ "learning_rate": 2e-05,
44
+ "loss": 0.6408,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.002516039753428104,
49
+ "grad_norm": 0.3603987395763397,
50
+ "learning_rate": 2.5e-05,
51
+ "loss": 0.8964,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.003019247704113725,
56
+ "grad_norm": 0.4167505204677582,
57
+ "learning_rate": 3e-05,
58
+ "loss": 0.7977,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.0035224556547993457,
63
+ "grad_norm": 0.33529505133628845,
64
+ "learning_rate": 3.5e-05,
65
+ "loss": 0.741,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.0040256636054849665,
70
+ "grad_norm": 0.3075070083141327,
71
+ "learning_rate": 4e-05,
72
+ "loss": 0.69,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.004528871556170587,
77
+ "grad_norm": 0.374713271856308,
78
+ "learning_rate": 4.5e-05,
79
+ "loss": 0.7692,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.005032079506856208,
84
+ "grad_norm": 0.42237210273742676,
85
+ "learning_rate": 5e-05,
86
+ "loss": 0.8035,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.005535287457541829,
91
+ "grad_norm": 0.44411763548851013,
92
+ "learning_rate": 5.500000000000001e-05,
93
+ "loss": 0.8701,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.00603849540822745,
98
+ "grad_norm": 0.41626623272895813,
99
+ "learning_rate": 6e-05,
100
+ "loss": 0.8624,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.0065417033589130705,
105
+ "grad_norm": 0.40315064787864685,
106
+ "learning_rate": 6.500000000000001e-05,
107
+ "loss": 0.8356,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.007044911309598691,
112
+ "grad_norm": 0.40788719058036804,
113
+ "learning_rate": 7e-05,
114
+ "loss": 0.9516,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.007548119260284312,
119
+ "grad_norm": 0.40332308411598206,
120
+ "learning_rate": 7.500000000000001e-05,
121
+ "loss": 0.9631,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.008051327210969933,
126
+ "grad_norm": 0.4551430344581604,
127
+ "learning_rate": 8e-05,
128
+ "loss": 0.9224,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.008554535161655554,
133
+ "grad_norm": 0.4207383096218109,
134
+ "learning_rate": 8.5e-05,
135
+ "loss": 0.8631,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.009057743112341175,
140
+ "grad_norm": 0.45070353150367737,
141
+ "learning_rate": 9e-05,
142
+ "loss": 0.867,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.009560951063026795,
147
+ "grad_norm": 0.41204211115837097,
148
+ "learning_rate": 9.5e-05,
149
+ "loss": 0.8123,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.010064159013712416,
154
+ "grad_norm": 0.4532608985900879,
155
+ "learning_rate": 0.0001,
156
+ "loss": 0.8152,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.010567366964398037,
161
+ "grad_norm": 0.42522719502449036,
162
+ "learning_rate": 9.999892908320647e-05,
163
+ "loss": 0.9145,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.011070574915083658,
168
+ "grad_norm": 0.43336769938468933,
169
+ "learning_rate": 9.999571637870036e-05,
170
+ "loss": 0.9232,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.011573782865769279,
175
+ "grad_norm": 0.43486812710762024,
176
+ "learning_rate": 9.999036202410325e-05,
177
+ "loss": 0.9012,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.0120769908164549,
182
+ "grad_norm": 0.43434756994247437,
183
+ "learning_rate": 9.998286624877786e-05,
184
+ "loss": 0.8315,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.01258019876714052,
189
+ "grad_norm": 0.4306849539279938,
190
+ "learning_rate": 9.997322937381829e-05,
191
+ "loss": 0.9571,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.013083406717826141,
196
+ "grad_norm": 0.4672311246395111,
197
+ "learning_rate": 9.996145181203615e-05,
198
+ "loss": 0.8713,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.013586614668511762,
203
+ "grad_norm": 0.4402594268321991,
204
+ "learning_rate": 9.994753406794301e-05,
205
+ "loss": 0.8639,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.014089822619197383,
210
+ "grad_norm": 0.45539745688438416,
211
+ "learning_rate": 9.99314767377287e-05,
212
+ "loss": 0.8925,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.014593030569883004,
217
+ "grad_norm": 0.48189201951026917,
218
+ "learning_rate": 9.991328050923581e-05,
219
+ "loss": 0.9734,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.015096238520568624,
224
+ "grad_norm": 0.44766247272491455,
225
+ "learning_rate": 9.989294616193017e-05,
226
+ "loss": 0.8371,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.015599446471254245,
231
+ "grad_norm": 0.5342682003974915,
232
+ "learning_rate": 9.98704745668676e-05,
233
+ "loss": 0.9424,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.016102654421939866,
238
+ "grad_norm": 0.5079587697982788,
239
+ "learning_rate": 9.98458666866564e-05,
240
+ "loss": 0.8545,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.01660586237262549,
245
+ "grad_norm": 0.5153644680976868,
246
+ "learning_rate": 9.981912357541627e-05,
247
+ "loss": 0.8507,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.017109070323311108,
252
+ "grad_norm": 0.5304479002952576,
253
+ "learning_rate": 9.97902463787331e-05,
254
+ "loss": 0.7365,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.01761227827399673,
259
+ "grad_norm": 0.5784561634063721,
260
+ "learning_rate": 9.975923633360985e-05,
261
+ "loss": 0.8531,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.01811548622468235,
266
+ "grad_norm": 0.6525458097457886,
267
+ "learning_rate": 9.972609476841367e-05,
268
+ "loss": 0.9531,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.018618694175367972,
273
+ "grad_norm": 0.59874427318573,
274
+ "learning_rate": 9.969082310281891e-05,
275
+ "loss": 0.8825,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.01912190212605359,
280
+ "grad_norm": 0.6657208800315857,
281
+ "learning_rate": 9.965342284774632e-05,
282
+ "loss": 1.013,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.019625110076739213,
287
+ "grad_norm": 0.673851490020752,
288
+ "learning_rate": 9.961389560529836e-05,
289
+ "loss": 1.0122,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.020128318027424832,
294
+ "grad_norm": 0.7437425255775452,
295
+ "learning_rate": 9.957224306869053e-05,
296
+ "loss": 0.9996,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.020631525978110455,
301
+ "grad_norm": 0.6888524293899536,
302
+ "learning_rate": 9.952846702217886e-05,
303
+ "loss": 0.9479,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.021134733928796074,
308
+ "grad_norm": 0.665365993976593,
309
+ "learning_rate": 9.948256934098352e-05,
310
+ "loss": 0.8076,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.021637941879481697,
315
+ "grad_norm": 0.9384682774543762,
316
+ "learning_rate": 9.943455199120837e-05,
317
+ "loss": 1.1964,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.022141149830167316,
322
+ "grad_norm": 1.06331205368042,
323
+ "learning_rate": 9.938441702975689e-05,
324
+ "loss": 1.1962,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.022644357780852938,
329
+ "grad_norm": 1.0956038236618042,
330
+ "learning_rate": 9.933216660424395e-05,
331
+ "loss": 1.0293,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.023147565731538557,
336
+ "grad_norm": 1.0600272417068481,
337
+ "learning_rate": 9.927780295290389e-05,
338
+ "loss": 1.2817,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.02365077368222418,
343
+ "grad_norm": 1.032386064529419,
344
+ "learning_rate": 9.922132840449459e-05,
345
+ "loss": 1.1316,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.0241539816329098,
350
+ "grad_norm": 1.1418523788452148,
351
+ "learning_rate": 9.916274537819775e-05,
352
+ "loss": 0.9598,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.02465718958359542,
357
+ "grad_norm": 1.591659426689148,
358
+ "learning_rate": 9.91020563835152e-05,
359
+ "loss": 1.1625,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.02516039753428104,
364
+ "grad_norm": 1.7732504606246948,
365
+ "learning_rate": 9.903926402016153e-05,
366
+ "loss": 1.0553,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.025663605484966663,
371
+ "grad_norm": 0.5284194946289062,
372
+ "learning_rate": 9.897437097795257e-05,
373
+ "loss": 0.6376,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.026166813435652282,
378
+ "grad_norm": 0.6791232824325562,
379
+ "learning_rate": 9.890738003669029e-05,
380
+ "loss": 0.5686,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.026670021386337905,
385
+ "grad_norm": 0.4423704445362091,
386
+ "learning_rate": 9.883829406604363e-05,
387
+ "loss": 0.6714,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.027173229337023524,
392
+ "grad_norm": 0.4226953387260437,
393
+ "learning_rate": 9.876711602542563e-05,
394
+ "loss": 0.7254,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.027676437287709146,
399
+ "grad_norm": 0.3696565628051758,
400
+ "learning_rate": 9.869384896386668e-05,
401
+ "loss": 0.8249,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.028179645238394765,
406
+ "grad_norm": 0.2843206822872162,
407
+ "learning_rate": 9.861849601988383e-05,
408
+ "loss": 0.6783,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.028682853189080388,
413
+ "grad_norm": 0.3041861057281494,
414
+ "learning_rate": 9.854106042134641e-05,
415
+ "loss": 0.7137,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.029186061139766007,
420
+ "grad_norm": 0.39011338353157043,
421
+ "learning_rate": 9.846154548533773e-05,
422
+ "loss": 0.8799,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.02968926909045163,
427
+ "grad_norm": 0.40477269887924194,
428
+ "learning_rate": 9.837995461801299e-05,
429
+ "loss": 0.8491,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.03019247704113725,
434
+ "grad_norm": 0.3500373363494873,
435
+ "learning_rate": 9.829629131445342e-05,
436
+ "loss": 0.7849,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.03069568499182287,
441
+ "grad_norm": 0.3607657849788666,
442
+ "learning_rate": 9.821055915851647e-05,
443
+ "loss": 0.8036,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.03119889294250849,
448
+ "grad_norm": 0.3407435417175293,
449
+ "learning_rate": 9.812276182268236e-05,
450
+ "loss": 0.8677,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.03170210089319411,
455
+ "grad_norm": 0.34367769956588745,
456
+ "learning_rate": 9.803290306789676e-05,
457
+ "loss": 0.7972,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.03220530884387973,
462
+ "grad_norm": 0.3393014371395111,
463
+ "learning_rate": 9.794098674340965e-05,
464
+ "loss": 0.7821,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.03270851679456535,
469
+ "grad_norm": 0.399403840303421,
470
+ "learning_rate": 9.784701678661045e-05,
471
+ "loss": 0.9752,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.03321172474525098,
476
+ "grad_norm": 0.336550772190094,
477
+ "learning_rate": 9.775099722285935e-05,
478
+ "loss": 0.8358,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.033714932695936596,
483
+ "grad_norm": 0.42282477021217346,
484
+ "learning_rate": 9.765293216531486e-05,
485
+ "loss": 0.8486,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.034218140646622215,
490
+ "grad_norm": 0.3811139464378357,
491
+ "learning_rate": 9.755282581475769e-05,
492
+ "loss": 0.8015,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.034721348597307834,
497
+ "grad_norm": 0.38650673627853394,
498
+ "learning_rate": 9.74506824594107e-05,
499
+ "loss": 0.8441,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.03522455654799346,
504
+ "grad_norm": 0.39965903759002686,
505
+ "learning_rate": 9.73465064747553e-05,
506
+ "loss": 0.9519,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.03572776449867908,
511
+ "grad_norm": 0.3865853548049927,
512
+ "learning_rate": 9.724030232334391e-05,
513
+ "loss": 0.8355,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.0362309724493647,
518
+ "grad_norm": 0.3812100887298584,
519
+ "learning_rate": 9.713207455460894e-05,
520
+ "loss": 0.815,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.03673418040005032,
525
+ "grad_norm": 0.40402311086654663,
526
+ "learning_rate": 9.702182780466775e-05,
527
+ "loss": 0.7945,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.037237388350735943,
532
+ "grad_norm": 0.43912094831466675,
533
+ "learning_rate": 9.690956679612421e-05,
534
+ "loss": 0.9382,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.03774059630142156,
539
+ "grad_norm": 0.48043292760849,
540
+ "learning_rate": 9.67952963378663e-05,
541
+ "loss": 0.9166,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.03824380425210718,
546
+ "grad_norm": 0.47702670097351074,
547
+ "learning_rate": 9.667902132486009e-05,
548
+ "loss": 0.8208,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.0387470122027928,
553
+ "grad_norm": 0.4606092870235443,
554
+ "learning_rate": 9.656074673794018e-05,
555
+ "loss": 0.7812,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.03925022015347843,
560
+ "grad_norm": 0.410383403301239,
561
+ "learning_rate": 9.644047764359622e-05,
562
+ "loss": 0.7814,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.039753428104164046,
567
+ "grad_norm": 0.43723535537719727,
568
+ "learning_rate": 9.631821919375591e-05,
569
+ "loss": 0.7831,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.040256636054849665,
574
+ "grad_norm": 0.47842466831207275,
575
+ "learning_rate": 9.619397662556435e-05,
576
+ "loss": 0.8328,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.04075984400553529,
581
+ "grad_norm": 0.5565553903579712,
582
+ "learning_rate": 9.606775526115963e-05,
583
+ "loss": 0.8564,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.04126305195622091,
588
+ "grad_norm": 0.5389965772628784,
589
+ "learning_rate": 9.593956050744492e-05,
590
+ "loss": 0.9588,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.04176625990690653,
595
+ "grad_norm": 0.5707739591598511,
596
+ "learning_rate": 9.580939785585681e-05,
597
+ "loss": 0.8665,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.04226946785759215,
602
+ "grad_norm": 0.5401300191879272,
603
+ "learning_rate": 9.567727288213005e-05,
604
+ "loss": 0.8702,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.042772675808277774,
609
+ "grad_norm": 0.5842973589897156,
610
+ "learning_rate": 9.554319124605879e-05,
611
+ "loss": 0.8452,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.04327588375896339,
616
+ "grad_norm": 0.526501476764679,
617
+ "learning_rate": 9.540715869125407e-05,
618
+ "loss": 0.8399,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.04377909170964901,
623
+ "grad_norm": 0.609856128692627,
624
+ "learning_rate": 9.526918104489777e-05,
625
+ "loss": 1.1022,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.04428229966033463,
630
+ "grad_norm": 0.6386977434158325,
631
+ "learning_rate": 9.512926421749304e-05,
632
+ "loss": 0.9333,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.04478550761102026,
637
+ "grad_norm": 0.6148085594177246,
638
+ "learning_rate": 9.498741420261108e-05,
639
+ "loss": 0.8722,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.045288715561705876,
644
+ "grad_norm": 0.610058069229126,
645
+ "learning_rate": 9.484363707663442e-05,
646
+ "loss": 0.9483,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.045791923512391496,
651
+ "grad_norm": 0.6424174904823303,
652
+ "learning_rate": 9.469793899849661e-05,
653
+ "loss": 0.9546,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.046295131463077115,
658
+ "grad_norm": 0.6571527719497681,
659
+ "learning_rate": 9.45503262094184e-05,
660
+ "loss": 0.84,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.04679833941376274,
665
+ "grad_norm": 0.9009180665016174,
666
+ "learning_rate": 9.440080503264037e-05,
667
+ "loss": 1.2002,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.04730154736444836,
672
+ "grad_norm": 0.8972412347793579,
673
+ "learning_rate": 9.42493818731521e-05,
674
+ "loss": 0.9899,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.04780475531513398,
679
+ "grad_norm": 0.8759328722953796,
680
+ "learning_rate": 9.409606321741775e-05,
681
+ "loss": 0.9973,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.0483079632658196,
686
+ "grad_norm": 0.880595326423645,
687
+ "learning_rate": 9.394085563309827e-05,
688
+ "loss": 0.9668,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.048811171216505224,
693
+ "grad_norm": 1.0916500091552734,
694
+ "learning_rate": 9.378376576876999e-05,
695
+ "loss": 1.0941,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.04931437916719084,
700
+ "grad_norm": 0.9800620675086975,
701
+ "learning_rate": 9.362480035363986e-05,
702
+ "loss": 1.0244,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.04981758711787646,
707
+ "grad_norm": 1.3642239570617676,
708
+ "learning_rate": 9.34639661972572e-05,
709
+ "loss": 1.1874,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.05032079506856208,
714
+ "grad_norm": 1.7741835117340088,
715
+ "learning_rate": 9.330127018922194e-05,
716
+ "loss": 1.1594,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.05032079506856208,
721
+ "eval_loss": 0.8690917491912842,
722
+ "eval_runtime": 104.3719,
723
+ "eval_samples_per_second": 32.068,
724
+ "eval_steps_per_second": 8.019,
725
+ "step": 100
726
+ }
727
+ ],
728
+ "logging_steps": 1,
729
+ "max_steps": 500,
730
+ "num_input_tokens_seen": 0,
731
+ "num_train_epochs": 1,
732
+ "save_steps": 100,
733
+ "stateful_callbacks": {
734
+ "EarlyStoppingCallback": {
735
+ "args": {
736
+ "early_stopping_patience": 5,
737
+ "early_stopping_threshold": 0.0
738
+ },
739
+ "attributes": {
740
+ "early_stopping_patience_counter": 0
741
+ }
742
+ },
743
+ "TrainerControl": {
744
+ "args": {
745
+ "should_epoch_stop": false,
746
+ "should_evaluate": false,
747
+ "should_log": false,
748
+ "should_save": true,
749
+ "should_training_stop": false
750
+ },
751
+ "attributes": {}
752
+ }
753
+ },
754
+ "total_flos": 2.85751967219712e+16,
755
+ "train_batch_size": 8,
756
+ "trial_name": null,
757
+ "trial_params": null
758
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b4b8c7d2bdacc39a3e7dfbf6b49ec9067af9fc3a473b4a12fd90017ddaeb3c5
3
+ size 6840
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff