Hugging Face's logo

amazingvince
/
zephyr-smol_llama-100m-sft-full

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
amazingvince commited on
Commit
f5c4e3d
•
1 Parent(s): fbe74c3

Model save

Browse files
Files changed (16) hide show
  1. README.md +62 -0
  2. all_results.json +13 -0
  3. config.json +27 -0
  4. eval_results.json +8 -0
  5. generation_config.json +6 -0
  6. model.safetensors +3 -0
  7. runs/Nov20_11-49-42_VincentPC/events.out.tfevents.1700499033.VincentPC.20220.0 +3 -0
  8. runs/Nov20_11-50-59_VincentPC/events.out.tfevents.1700499063.VincentPC.20959.0 +3 -0
  9. runs/Nov20_11-50-59_VincentPC/events.out.tfevents.1700501231.VincentPC.20959.1 +3 -0
  10. special_tokens_map.json +24 -0
  11. tokenizer.json +0 -0
  12. tokenizer.model +3 -0
  13. tokenizer_config.json +43 -0
  14. train_results.json +8 -0
  15. trainer_state.json +1410 -0
  16. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: BEE-spoke-data/smol_llama-101M-GQA
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: zephyr-smol_llama-100m-sft-full
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # zephyr-smol_llama-100m-sft-full
15
+
16
+ This model is a fine-tuned version of [BEE-spoke-data/smol_llama-101M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.9579
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - distributed_type: multi-GPU
42
+ - num_devices: 2
43
+ - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 128
45
+ - total_eval_batch_size: 32
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - num_epochs: 1
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 1.9642 | 0.7 | 1141 | 1.9578 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.35.0
60
+ - Pytorch 2.1.0
61
+ - Datasets 2.14.6
62
+ - Tokenizers 0.14.1
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.7,
3
+ "eval_loss": 1.957854151725769,
4
+ "eval_runtime": 82.132,
5
+ "eval_samples": 23110,
6
+ "eval_samples_per_second": 281.376,
7
+ "eval_steps_per_second": 8.803,
8
+ "train_loss": 2.1211067035885676,
9
+ "train_runtime": 2085.5853,
10
+ "train_samples": 207865,
11
+ "train_samples_per_second": 99.667,
12
+ "train_steps_per_second": 0.779
13
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BEE-spoke-data/smol_llama-101M-GQA",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "max_position_embeddings": 1024,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 24,
16
+ "num_hidden_layers": 6,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.35.0",
25
+ "use_cache": false,
26
+ "vocab_size": 32128
27
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.7,
3
+ "eval_loss": 1.957854151725769,
4
+ "eval_runtime": 82.132,
5
+ "eval_samples": 23110,
6
+ "eval_samples_per_second": 281.376,
7
+ "eval_steps_per_second": 8.803
8
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.35.0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9390ceab7b1dea494c49d23421e61bb29cb8b62da3612abdcdcf34a455ddd7bb
3
+ size 202532568
runs/Nov20_11-49-42_VincentPC/events.out.tfevents.1700499033.VincentPC.20220.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6574576da94d17627c4c7ca084864ad17cdb60fd2e65181f0e900ae9d881e1cb
3
+ size 4330
runs/Nov20_11-50-59_VincentPC/events.out.tfevents.1700499063.VincentPC.20959.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f70ce1938b120dc792dfaca6fb0d31a43ad2bdb79530afcc9505ca779d2761fa
3
+ size 40830
runs/Nov20_11-50-59_VincentPC/events.out.tfevents.1700501231.VincentPC.20959.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0b3f9a33428ff51c509d6fe3920ecbbe89d33b79c13c8731ffe3265bf1cf14f
3
+ size 359
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": true
43
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.7,
3
+ "train_loss": 2.1211067035885676,
4
+ "train_runtime": 2085.5853,
5
+ "train_samples": 207865,
6
+ "train_samples_per_second": 99.667,
7
+ "train_steps_per_second": 0.779
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1410 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.7025862068965517,
5
+ "eval_steps": 500,
6
+ "global_step": 1141,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 1.9999981288975627e-05,
14
+ "loss": 4.3158,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 1.9999532227891695e-05,
20
+ "loss": 3.8969,
21
+ "step": 5
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 1.9998128955328933e-05,
26
+ "loss": 3.4446,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 1.9995790313594056e-05,
32
+ "loss": 3.2177,
33
+ "step": 15
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 1.999251652147735e-05,
38
+ "loss": 3.0663,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 1.998830788525654e-05,
44
+ "loss": 2.9812,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 1.9983164798668152e-05,
50
+ "loss": 2.9121,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 1.9977087742870683e-05,
56
+ "loss": 2.8353,
57
+ "step": 35
58
+ },
59
+ {
60
+ "epoch": 0.02,
61
+ "learning_rate": 1.997007728639956e-05,
62
+ "loss": 2.7443,
63
+ "step": 40
64
+ },
65
+ {
66
+ "epoch": 0.03,
67
+ "learning_rate": 1.9962134085114e-05,
68
+ "loss": 2.7275,
69
+ "step": 45
70
+ },
71
+ {
72
+ "epoch": 0.03,
73
+ "learning_rate": 1.9953258882135594e-05,
74
+ "loss": 2.6533,
75
+ "step": 50
76
+ },
77
+ {
78
+ "epoch": 0.03,
79
+ "learning_rate": 1.9943452507778832e-05,
80
+ "loss": 2.6084,
81
+ "step": 55
82
+ },
83
+ {
84
+ "epoch": 0.04,
85
+ "learning_rate": 1.9932715879473385e-05,
86
+ "loss": 2.5925,
87
+ "step": 60
88
+ },
89
+ {
90
+ "epoch": 0.04,
91
+ "learning_rate": 1.9921050001678316e-05,
92
+ "loss": 2.5301,
93
+ "step": 65
94
+ },
95
+ {
96
+ "epoch": 0.04,
97
+ "learning_rate": 1.990845596578807e-05,
98
+ "loss": 2.5413,
99
+ "step": 70
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "learning_rate": 1.989493495003039e-05,
104
+ "loss": 2.5204,
105
+ "step": 75
106
+ },
107
+ {
108
+ "epoch": 0.05,
109
+ "learning_rate": 1.9880488219356086e-05,
110
+ "loss": 2.5032,
111
+ "step": 80
112
+ },
113
+ {
114
+ "epoch": 0.05,
115
+ "learning_rate": 1.9865117125320693e-05,
116
+ "loss": 2.457,
117
+ "step": 85
118
+ },
119
+ {
120
+ "epoch": 0.06,
121
+ "learning_rate": 1.9848823105958023e-05,
122
+ "loss": 2.4431,
123
+ "step": 90
124
+ },
125
+ {
126
+ "epoch": 0.06,
127
+ "learning_rate": 1.9831607685645636e-05,
128
+ "loss": 2.4166,
129
+ "step": 95
130
+ },
131
+ {
132
+ "epoch": 0.06,
133
+ "learning_rate": 1.981347247496222e-05,
134
+ "loss": 2.4134,
135
+ "step": 100
136
+ },
137
+ {
138
+ "epoch": 0.06,
139
+ "learning_rate": 1.9794419170536918e-05,
140
+ "loss": 2.402,
141
+ "step": 105
142
+ },
143
+ {
144
+ "epoch": 0.07,
145
+ "learning_rate": 1.9774449554890615e-05,
146
+ "loss": 2.391,
147
+ "step": 110
148
+ },
149
+ {
150
+ "epoch": 0.07,
151
+ "learning_rate": 1.975356549626915e-05,
152
+ "loss": 2.35,
153
+ "step": 115
154
+ },
155
+ {
156
+ "epoch": 0.07,
157
+ "learning_rate": 1.973176894846855e-05,
158
+ "loss": 2.3311,
159
+ "step": 120
160
+ },
161
+ {
162
+ "epoch": 0.08,
163
+ "learning_rate": 1.9709061950652237e-05,
164
+ "loss": 2.3511,
165
+ "step": 125
166
+ },
167
+ {
168
+ "epoch": 0.08,
169
+ "learning_rate": 1.968544662716026e-05,
170
+ "loss": 2.3209,
171
+ "step": 130
172
+ },
173
+ {
174
+ "epoch": 0.08,
175
+ "learning_rate": 1.966092518731055e-05,
176
+ "loss": 2.3085,
177
+ "step": 135
178
+ },
179
+ {
180
+ "epoch": 0.09,
181
+ "learning_rate": 1.963549992519223e-05,
182
+ "loss": 2.3357,
183
+ "step": 140
184
+ },
185
+ {
186
+ "epoch": 0.09,
187
+ "learning_rate": 1.9609173219450998e-05,
188
+ "loss": 2.3342,
189
+ "step": 145
190
+ },
191
+ {
192
+ "epoch": 0.09,
193
+ "learning_rate": 1.9581947533066577e-05,
194
+ "loss": 2.2873,
195
+ "step": 150
196
+ },
197
+ {
198
+ "epoch": 0.1,
199
+ "learning_rate": 1.9553825413122313e-05,
200
+ "loss": 2.2924,
201
+ "step": 155
202
+ },
203
+ {
204
+ "epoch": 0.1,
205
+ "learning_rate": 1.9524809490566878e-05,
206
+ "loss": 2.2737,
207
+ "step": 160
208
+ },
209
+ {
210
+ "epoch": 0.1,
211
+ "learning_rate": 1.949490247996812e-05,
212
+ "loss": 2.2558,
213
+ "step": 165
214
+ },
215
+ {
216
+ "epoch": 0.1,
217
+ "learning_rate": 1.9464107179259126e-05,
218
+ "loss": 2.2746,
219
+ "step": 170
220
+ },
221
+ {
222
+ "epoch": 0.11,
223
+ "learning_rate": 1.9432426469476432e-05,
224
+ "loss": 2.2444,
225
+ "step": 175
226
+ },
227
+ {
228
+ "epoch": 0.11,
229
+ "learning_rate": 1.939986331449053e-05,
230
+ "loss": 2.2759,
231
+ "step": 180
232
+ },
233
+ {
234
+ "epoch": 0.11,
235
+ "learning_rate": 1.9366420760728546e-05,
236
+ "loss": 2.2103,
237
+ "step": 185
238
+ },
239
+ {
240
+ "epoch": 0.12,
241
+ "learning_rate": 1.9332101936889262e-05,
242
+ "loss": 2.2509,
243
+ "step": 190
244
+ },
245
+ {
246
+ "epoch": 0.12,
247
+ "learning_rate": 1.9296910053650388e-05,
248
+ "loss": 2.2346,
249
+ "step": 195
250
+ },
251
+ {
252
+ "epoch": 0.12,
253
+ "learning_rate": 1.926084840336821e-05,
254
+ "loss": 2.244,
255
+ "step": 200
256
+ },
257
+ {
258
+ "epoch": 0.13,
259
+ "learning_rate": 1.922392035976957e-05,
260
+ "loss": 2.2383,
261
+ "step": 205
262
+ },
263
+ {
264
+ "epoch": 0.13,
265
+ "learning_rate": 1.918612937763622e-05,
266
+ "loss": 2.2148,
267
+ "step": 210
268
+ },
269
+ {
270
+ "epoch": 0.13,
271
+ "learning_rate": 1.9147478992481642e-05,
272
+ "loss": 2.2032,
273
+ "step": 215
274
+ },
275
+ {
276
+ "epoch": 0.14,
277
+ "learning_rate": 1.910797282022027e-05,
278
+ "loss": 2.2073,
279
+ "step": 220
280
+ },
281
+ {
282
+ "epoch": 0.14,
283
+ "learning_rate": 1.9067614556829195e-05,
284
+ "loss": 2.2182,
285
+ "step": 225
286
+ },
287
+ {
288
+ "epoch": 0.14,
289
+ "learning_rate": 1.9026407978002415e-05,
290
+ "loss": 2.202,
291
+ "step": 230
292
+ },
293
+ {
294
+ "epoch": 0.14,
295
+ "learning_rate": 1.8984356938797573e-05,
296
+ "loss": 2.1799,
297
+ "step": 235
298
+ },
299
+ {
300
+ "epoch": 0.15,
301
+ "learning_rate": 1.894146537327533e-05,
302
+ "loss": 2.1912,
303
+ "step": 240
304
+ },
305
+ {
306
+ "epoch": 0.15,
307
+ "learning_rate": 1.8897737294131288e-05,
308
+ "loss": 2.1655,
309
+ "step": 245
310
+ },
311
+ {
312
+ "epoch": 0.15,
313
+ "learning_rate": 1.8853176792320598e-05,
314
+ "loss": 2.1951,
315
+ "step": 250
316
+ },
317
+ {
318
+ "epoch": 0.16,
319
+ "learning_rate": 1.8807788036675243e-05,
320
+ "loss": 2.1734,
321
+ "step": 255
322
+ },
323
+ {
324
+ "epoch": 0.16,
325
+ "learning_rate": 1.8761575273514005e-05,
326
+ "loss": 2.1795,
327
+ "step": 260
328
+ },
329
+ {
330
+ "epoch": 0.16,
331
+ "learning_rate": 1.8714542826245214e-05,
332
+ "loss": 2.1636,
333
+ "step": 265
334
+ },
335
+ {
336
+ "epoch": 0.17,
337
+ "learning_rate": 1.866669509496227e-05,
338
+ "loss": 2.1574,
339
+ "step": 270
340
+ },
341
+ {
342
+ "epoch": 0.17,
343
+ "learning_rate": 1.861803655603201e-05,
344
+ "loss": 2.1472,
345
+ "step": 275
346
+ },
347
+ {
348
+ "epoch": 0.17,
349
+ "learning_rate": 1.8568571761675893e-05,
350
+ "loss": 2.1517,
351
+ "step": 280
352
+ },
353
+ {
354
+ "epoch": 0.18,
355
+ "learning_rate": 1.8518305339544157e-05,
356
+ "loss": 2.1589,
357
+ "step": 285
358
+ },
359
+ {
360
+ "epoch": 0.18,
361
+ "learning_rate": 1.8467241992282842e-05,
362
+ "loss": 2.1256,
363
+ "step": 290
364
+ },
365
+ {
366
+ "epoch": 0.18,
367
+ "learning_rate": 1.841538649709388e-05,
368
+ "loss": 2.143,
369
+ "step": 295
370
+ },
371
+ {
372
+ "epoch": 0.18,
373
+ "learning_rate": 1.8362743705288127e-05,
374
+ "loss": 2.1449,
375
+ "step": 300
376
+ },
377
+ {
378
+ "epoch": 0.19,
379
+ "learning_rate": 1.830931854183153e-05,
380
+ "loss": 2.1219,
381
+ "step": 305
382
+ },
383
+ {
384
+ "epoch": 0.19,
385
+ "learning_rate": 1.825511600488435e-05,
386
+ "loss": 2.1384,
387
+ "step": 310
388
+ },
389
+ {
390
+ "epoch": 0.19,
391
+ "learning_rate": 1.8200141165333592e-05,
392
+ "loss": 2.1217,
393
+ "step": 315
394
+ },
395
+ {
396
+ "epoch": 0.2,
397
+ "learning_rate": 1.814439916631857e-05,
398
+ "loss": 2.1361,
399
+ "step": 320
400
+ },
401
+ {
402
+ "epoch": 0.2,
403
+ "learning_rate": 1.8087895222749773e-05,
404
+ "loss": 2.1502,
405
+ "step": 325
406
+ },
407
+ {
408
+ "epoch": 0.2,
409
+ "learning_rate": 1.803063462082095e-05,
410
+ "loss": 2.1199,
411
+ "step": 330
412
+ },
413
+ {
414
+ "epoch": 0.21,
415
+ "learning_rate": 1.7972622717514608e-05,
416
+ "loss": 2.1221,
417
+ "step": 335
418
+ },
419
+ {
420
+ "epoch": 0.21,
421
+ "learning_rate": 1.791386494010081e-05,
422
+ "loss": 2.1148,
423
+ "step": 340
424
+ },
425
+ {
426
+ "epoch": 0.21,
427
+ "learning_rate": 1.7854366785629435e-05,
428
+ "loss": 2.1336,
429
+ "step": 345
430
+ },
431
+ {
432
+ "epoch": 0.22,
433
+ "learning_rate": 1.7794133820415916e-05,
434
+ "loss": 2.1189,
435
+ "step": 350
436
+ },
437
+ {
438
+ "epoch": 0.22,
439
+ "learning_rate": 1.7733171679520485e-05,
440
+ "loss": 2.1288,
441
+ "step": 355
442
+ },
443
+ {
444
+ "epoch": 0.22,
445
+ "learning_rate": 1.7671486066220965e-05,
446
+ "loss": 2.1152,
447
+ "step": 360
448
+ },
449
+ {
450
+ "epoch": 0.22,
451
+ "learning_rate": 1.7609082751479246e-05,
452
+ "loss": 2.0836,
453
+ "step": 365
454
+ },
455
+ {
456
+ "epoch": 0.23,
457
+ "learning_rate": 1.7545967573401336e-05,
458
+ "loss": 2.0997,
459
+ "step": 370
460
+ },
461
+ {
462
+ "epoch": 0.23,
463
+ "learning_rate": 1.7482146436691227e-05,
464
+ "loss": 2.0885,
465
+ "step": 375
466
+ },
467
+ {
468
+ "epoch": 0.23,
469
+ "learning_rate": 1.7417625312098453e-05,
470
+ "loss": 2.1141,
471
+ "step": 380
472
+ },
473
+ {
474
+ "epoch": 0.24,
475
+ "learning_rate": 1.7352410235859503e-05,
476
+ "loss": 2.097,
477
+ "step": 385
478
+ },
479
+ {
480
+ "epoch": 0.24,
481
+ "learning_rate": 1.728650730913312e-05,
482
+ "loss": 2.0704,
483
+ "step": 390
484
+ },
485
+ {
486
+ "epoch": 0.24,
487
+ "learning_rate": 1.721992269742951e-05,
488
+ "loss": 2.0772,
489
+ "step": 395
490
+ },
491
+ {
492
+ "epoch": 0.25,
493
+ "learning_rate": 1.7152662630033506e-05,
494
+ "loss": 2.0714,
495
+ "step": 400
496
+ },
497
+ {
498
+ "epoch": 0.25,
499
+ "learning_rate": 1.7084733399421808e-05,
500
+ "loss": 2.0872,
501
+ "step": 405
502
+ },
503
+ {
504
+ "epoch": 0.25,
505
+ "learning_rate": 1.7016141360674307e-05,
506
+ "loss": 2.1176,
507
+ "step": 410
508
+ },
509
+ {
510
+ "epoch": 0.26,
511
+ "learning_rate": 1.6946892930879516e-05,
512
+ "loss": 2.0739,
513
+ "step": 415
514
+ },
515
+ {
516
+ "epoch": 0.26,
517
+ "learning_rate": 1.6876994588534234e-05,
518
+ "loss": 2.0703,
519
+ "step": 420
520
+ },
521
+ {
522
+ "epoch": 0.26,
523
+ "learning_rate": 1.680645287293746e-05,
524
+ "loss": 2.1082,
525
+ "step": 425
526
+ },
527
+ {
528
+ "epoch": 0.26,
529
+ "learning_rate": 1.6735274383578593e-05,
530
+ "loss": 2.1068,
531
+ "step": 430
532
+ },
533
+ {
534
+ "epoch": 0.27,
535
+ "learning_rate": 1.6663465779520042e-05,
536
+ "loss": 2.0818,
537
+ "step": 435
538
+ },
539
+ {
540
+ "epoch": 0.27,
541
+ "learning_rate": 1.659103377877423e-05,
542
+ "loss": 2.0882,
543
+ "step": 440
544
+ },
545
+ {
546
+ "epoch": 0.27,
547
+ "learning_rate": 1.6517985157675097e-05,
548
+ "loss": 2.0793,
549
+ "step": 445
550
+ },
551
+ {
552
+ "epoch": 0.28,
553
+ "learning_rate": 1.6444326750244145e-05,
554
+ "loss": 2.0798,
555
+ "step": 450
556
+ },
557
+ {
558
+ "epoch": 0.28,
559
+ "learning_rate": 1.637006544755108e-05,
560
+ "loss": 2.0706,
561
+ "step": 455
562
+ },
563
+ {
564
+ "epoch": 0.28,
565
+ "learning_rate": 1.629520819706912e-05,
566
+ "loss": 2.0798,
567
+ "step": 460
568
+ },
569
+ {
570
+ "epoch": 0.29,
571
+ "learning_rate": 1.6219762002025055e-05,
572
+ "loss": 2.038,
573
+ "step": 465
574
+ },
575
+ {
576
+ "epoch": 0.29,
577
+ "learning_rate": 1.614373392074402e-05,
578
+ "loss": 2.049,
579
+ "step": 470
580
+ },
581
+ {
582
+ "epoch": 0.29,
583
+ "learning_rate": 1.6067131065989188e-05,
584
+ "loss": 2.0522,
585
+ "step": 475
586
+ },
587
+ {
588
+ "epoch": 0.3,
589
+ "learning_rate": 1.598996060429634e-05,
590
+ "loss": 2.054,
591
+ "step": 480
592
+ },
593
+ {
594
+ "epoch": 0.3,
595
+ "learning_rate": 1.591222975530338e-05,
596
+ "loss": 2.071,
597
+ "step": 485
598
+ },
599
+ {
600
+ "epoch": 0.3,
601
+ "learning_rate": 1.5833945791074943e-05,
602
+ "loss": 2.0592,
603
+ "step": 490
604
+ },
605
+ {
606
+ "epoch": 0.3,
607
+ "learning_rate": 1.5755116035422015e-05,
608
+ "loss": 2.0569,
609
+ "step": 495
610
+ },
611
+ {
612
+ "epoch": 0.31,
613
+ "learning_rate": 1.56757478632168e-05,
614
+ "loss": 2.0351,
615
+ "step": 500
616
+ },
617
+ {
618
+ "epoch": 0.31,
619
+ "learning_rate": 1.5595848699702752e-05,
620
+ "loss": 2.0399,
621
+ "step": 505
622
+ },
623
+ {
624
+ "epoch": 0.31,
625
+ "learning_rate": 1.5515426019799898e-05,
626
+ "loss": 2.0554,
627
+ "step": 510
628
+ },
629
+ {
630
+ "epoch": 0.32,
631
+ "learning_rate": 1.5434487347405553e-05,
632
+ "loss": 2.0537,
633
+ "step": 515
634
+ },
635
+ {
636
+ "epoch": 0.32,
637
+ "learning_rate": 1.5353040254690396e-05,
638
+ "loss": 2.0512,
639
+ "step": 520
640
+ },
641
+ {
642
+ "epoch": 0.32,
643
+ "learning_rate": 1.5271092361390078e-05,
644
+ "loss": 2.0567,
645
+ "step": 525
646
+ },
647
+ {
648
+ "epoch": 0.33,
649
+ "learning_rate": 1.5188651334092373e-05,
650
+ "loss": 2.0431,
651
+ "step": 530
652
+ },
653
+ {
654
+ "epoch": 0.33,
655
+ "learning_rate": 1.5105724885519908e-05,
656
+ "loss": 2.0529,
657
+ "step": 535
658
+ },
659
+ {
660
+ "epoch": 0.33,
661
+ "learning_rate": 1.5022320773808612e-05,
662
+ "loss": 2.0356,
663
+ "step": 540
664
+ },
665
+ {
666
+ "epoch": 0.34,
667
+ "learning_rate": 1.4938446801781932e-05,
668
+ "loss": 2.0464,
669
+ "step": 545
670
+ },
671
+ {
672
+ "epoch": 0.34,
673
+ "learning_rate": 1.4854110816220805e-05,
674
+ "loss": 2.0784,
675
+ "step": 550
676
+ },
677
+ {
678
+ "epoch": 0.34,
679
+ "learning_rate": 1.4769320707129588e-05,
680
+ "loss": 2.0447,
681
+ "step": 555
682
+ },
683
+ {
684
+ "epoch": 0.34,
685
+ "learning_rate": 1.4684084406997903e-05,
686
+ "loss": 2.0425,
687
+ "step": 560
688
+ },
689
+ {
690
+ "epoch": 0.35,
691
+ "learning_rate": 1.459840989005851e-05,
692
+ "loss": 2.0235,
693
+ "step": 565
694
+ },
695
+ {
696
+ "epoch": 0.35,
697
+ "learning_rate": 1.4512305171541287e-05,
698
+ "loss": 2.0436,
699
+ "step": 570
700
+ },
701
+ {
702
+ "epoch": 0.35,
703
+ "learning_rate": 1.4425778306923388e-05,
704
+ "loss": 2.0223,
705
+ "step": 575
706
+ },
707
+ {
708
+ "epoch": 0.36,
709
+ "learning_rate": 1.4338837391175582e-05,
710
+ "loss": 2.01,
711
+ "step": 580
712
+ },
713
+ {
714
+ "epoch": 0.36,
715
+ "learning_rate": 1.4251490558004965e-05,
716
+ "loss": 2.0334,
717
+ "step": 585
718
+ },
719
+ {
720
+ "epoch": 0.36,
721
+ "learning_rate": 1.4163745979093997e-05,
722
+ "loss": 2.035,
723
+ "step": 590
724
+ },
725
+ {
726
+ "epoch": 0.37,
727
+ "learning_rate": 1.4075611863336012e-05,
728
+ "loss": 2.0281,
729
+ "step": 595
730
+ },
731
+ {
732
+ "epoch": 0.37,
733
+ "learning_rate": 1.3987096456067236e-05,
734
+ "loss": 2.0242,
735
+ "step": 600
736
+ },
737
+ {
738
+ "epoch": 0.37,
739
+ "learning_rate": 1.3898208038295407e-05,
740
+ "loss": 2.0241,
741
+ "step": 605
742
+ },
743
+ {
744
+ "epoch": 0.38,
745
+ "learning_rate": 1.3808954925925042e-05,
746
+ "loss": 1.9977,
747
+ "step": 610
748
+ },
749
+ {
750
+ "epoch": 0.38,
751
+ "learning_rate": 1.3719345468979448e-05,
752
+ "loss": 2.0308,
753
+ "step": 615
754
+ },
755
+ {
756
+ "epoch": 0.38,
757
+ "learning_rate": 1.3629388050819547e-05,
758
+ "loss": 2.0139,
759
+ "step": 620
760
+ },
761
+ {
762
+ "epoch": 0.38,
763
+ "learning_rate": 1.353909108735957e-05,
764
+ "loss": 2.0126,
765
+ "step": 625
766
+ },
767
+ {
768
+ "epoch": 0.39,
769
+ "learning_rate": 1.3448463026279706e-05,
770
+ "loss": 2.0249,
771
+ "step": 630
772
+ },
773
+ {
774
+ "epoch": 0.39,
775
+ "learning_rate": 1.33575123462358e-05,
776
+ "loss": 2.0044,
777
+ "step": 635
778
+ },
779
+ {
780
+ "epoch": 0.39,
781
+ "learning_rate": 1.3266247556066122e-05,
782
+ "loss": 2.023,
783
+ "step": 640
784
+ },
785
+ {
786
+ "epoch": 0.4,
787
+ "learning_rate": 1.317467719399534e-05,
788
+ "loss": 2.0183,
789
+ "step": 645
790
+ },
791
+ {
792
+ "epoch": 0.4,
793
+ "learning_rate": 1.3082809826835707e-05,
794
+ "loss": 1.9861,
795
+ "step": 650
796
+ },
797
+ {
798
+ "epoch": 0.4,
799
+ "learning_rate": 1.2990654049185636e-05,
800
+ "loss": 1.9841,
801
+ "step": 655
802
+ },
803
+ {
804
+ "epoch": 0.41,
805
+ "learning_rate": 1.2898218482625606e-05,
806
+ "loss": 2.0091,
807
+ "step": 660
808
+ },
809
+ {
810
+ "epoch": 0.41,
811
+ "learning_rate": 1.2805511774911585e-05,
812
+ "loss": 1.9951,
813
+ "step": 665
814
+ },
815
+ {
816
+ "epoch": 0.41,
817
+ "learning_rate": 1.2712542599165998e-05,
818
+ "loss": 1.9862,
819
+ "step": 670
820
+ },
821
+ {
822
+ "epoch": 0.42,
823
+ "learning_rate": 1.261931965306632e-05,
824
+ "loss": 2.0169,
825
+ "step": 675
826
+ },
827
+ {
828
+ "epoch": 0.42,
829
+ "learning_rate": 1.252585165803135e-05,
830
+ "loss": 2.0239,
831
+ "step": 680
832
+ },
833
+ {
834
+ "epoch": 0.42,
835
+ "learning_rate": 1.2432147358405313e-05,
836
+ "loss": 2.0428,
837
+ "step": 685
838
+ },
839
+ {
840
+ "epoch": 0.42,
841
+ "learning_rate": 1.233821552063977e-05,
842
+ "loss": 1.98,
843
+ "step": 690
844
+ },
845
+ {
846
+ "epoch": 0.43,
847
+ "learning_rate": 1.2244064932473467e-05,
848
+ "loss": 1.9918,
849
+ "step": 695
850
+ },
851
+ {
852
+ "epoch": 0.43,
853
+ "learning_rate": 1.2149704402110243e-05,
854
+ "loss": 1.9996,
855
+ "step": 700
856
+ },
857
+ {
858
+ "epoch": 0.43,
859
+ "learning_rate": 1.2055142757394936e-05,
860
+ "loss": 1.9917,
861
+ "step": 705
862
+ },
863
+ {
864
+ "epoch": 0.44,
865
+ "learning_rate": 1.1960388844987529e-05,
866
+ "loss": 2.0338,
867
+ "step": 710
868
+ },
869
+ {
870
+ "epoch": 0.44,
871
+ "learning_rate": 1.1865451529535496e-05,
872
+ "loss": 2.003,
873
+ "step": 715
874
+ },
875
+ {
876
+ "epoch": 0.44,
877
+ "learning_rate": 1.1770339692844484e-05,
878
+ "loss": 1.978,
879
+ "step": 720
880
+ },
881
+ {
882
+ "epoch": 0.45,
883
+ "learning_rate": 1.1675062233047365e-05,
884
+ "loss": 1.992,
885
+ "step": 725
886
+ },
887
+ {
888
+ "epoch": 0.45,
889
+ "learning_rate": 1.157962806377179e-05,
890
+ "loss": 1.998,
891
+ "step": 730
892
+ },
893
+ {
894
+ "epoch": 0.45,
895
+ "learning_rate": 1.1484046113306262e-05,
896
+ "loss": 2.003,
897
+ "step": 735
898
+ },
899
+ {
900
+ "epoch": 0.46,
901
+ "learning_rate": 1.1388325323764889e-05,
902
+ "loss": 1.9771,
903
+ "step": 740
904
+ },
905
+ {
906
+ "epoch": 0.46,
907
+ "learning_rate": 1.1292474650250776e-05,
908
+ "loss": 1.9918,
909
+ "step": 745
910
+ },
911
+ {
912
+ "epoch": 0.46,
913
+ "learning_rate": 1.1196503060018243e-05,
914
+ "loss": 1.9963,
915
+ "step": 750
916
+ },
917
+ {
918
+ "epoch": 0.46,
919
+ "learning_rate": 1.1100419531633917e-05,
920
+ "loss": 1.9926,
921
+ "step": 755
922
+ },
923
+ {
924
+ "epoch": 0.47,
925
+ "learning_rate": 1.1004233054136726e-05,
926
+ "loss": 2.0016,
927
+ "step": 760
928
+ },
929
+ {
930
+ "epoch": 0.47,
931
+ "learning_rate": 1.090795262619694e-05,
932
+ "loss": 1.9745,
933
+ "step": 765
934
+ },
935
+ {
936
+ "epoch": 0.47,
937
+ "learning_rate": 1.0811587255274313e-05,
938
+ "loss": 1.9952,
939
+ "step": 770
940
+ },
941
+ {
942
+ "epoch": 0.48,
943
+ "learning_rate": 1.0715145956775395e-05,
944
+ "loss": 2.009,
945
+ "step": 775
946
+ },
947
+ {
948
+ "epoch": 0.48,
949
+ "learning_rate": 1.0618637753210086e-05,
950
+ "loss": 2.0072,
951
+ "step": 780
952
+ },
953
+ {
954
+ "epoch": 0.48,
955
+ "learning_rate": 1.0522071673347558e-05,
956
+ "loss": 1.9818,
957
+ "step": 785
958
+ },
959
+ {
960
+ "epoch": 0.49,
961
+ "learning_rate": 1.0425456751371564e-05,
962
+ "loss": 1.9788,
963
+ "step": 790
964
+ },
965
+ {
966
+ "epoch": 0.49,
967
+ "learning_rate": 1.0328802026035254e-05,
968
+ "loss": 1.994,
969
+ "step": 795
970
+ },
971
+ {
972
+ "epoch": 0.49,
973
+ "learning_rate": 1.0232116539815558e-05,
974
+ "loss": 1.9926,
975
+ "step": 800
976
+ },
977
+ {
978
+ "epoch": 0.5,
979
+ "learning_rate": 1.013540933806722e-05,
980
+ "loss": 1.9933,
981
+ "step": 805
982
+ },
983
+ {
984
+ "epoch": 0.5,
985
+ "learning_rate": 1.0038689468176575e-05,
986
+ "loss": 1.9848,
987
+ "step": 810
988
+ },
989
+ {
990
+ "epoch": 0.5,
991
+ "learning_rate": 9.941965978715105e-06,
992
+ "loss": 2.0002,
993
+ "step": 815
994
+ },
995
+ {
996
+ "epoch": 0.5,
997
+ "learning_rate": 9.845247918592937e-06,
998
+ "loss": 1.9681,
999
+ "step": 820
1000
+ },
1001
+ {
1002
+ "epoch": 0.51,
1003
+ "learning_rate": 9.748544336212246e-06,
1004
+ "loss": 1.9588,
1005
+ "step": 825
1006
+ },
1007
+ {
1008
+ "epoch": 0.51,
1009
+ "learning_rate": 9.651864278620752e-06,
1010
+ "loss": 1.9817,
1011
+ "step": 830
1012
+ },
1013
+ {
1014
+ "epoch": 0.51,
1015
+ "learning_rate": 9.555216790665334e-06,
1016
+ "loss": 1.9991,
1017
+ "step": 835
1018
+ },
1019
+ {
1020
+ "epoch": 0.52,
1021
+ "learning_rate": 9.458610914145826e-06,
1022
+ "loss": 1.9723,
1023
+ "step": 840
1024
+ },
1025
+ {
1026
+ "epoch": 0.52,
1027
+ "learning_rate": 9.362055686969141e-06,
1028
+ "loss": 1.9725,
1029
+ "step": 845
1030
+ },
1031
+ {
1032
+ "epoch": 0.52,
1033
+ "learning_rate": 9.26556014230371e-06,
1034
+ "loss": 1.9663,
1035
+ "step": 850
1036
+ },
1037
+ {
1038
+ "epoch": 0.53,
1039
+ "learning_rate": 9.169133307734415e-06,
1040
+ "loss": 1.9989,
1041
+ "step": 855
1042
+ },
1043
+ {
1044
+ "epoch": 0.53,
1045
+ "learning_rate": 9.072784204417995e-06,
1046
+ "loss": 1.9618,
1047
+ "step": 860
1048
+ },
1049
+ {
1050
+ "epoch": 0.53,
1051
+ "learning_rate": 8.976521846239076e-06,
1052
+ "loss": 1.988,
1053
+ "step": 865
1054
+ },
1055
+ {
1056
+ "epoch": 0.54,
1057
+ "learning_rate": 8.880355238966923e-06,
1058
+ "loss": 1.9748,
1059
+ "step": 870
1060
+ },
1061
+ {
1062
+ "epoch": 0.54,
1063
+ "learning_rate": 8.784293379412851e-06,
1064
+ "loss": 1.9679,
1065
+ "step": 875
1066
+ },
1067
+ {
1068
+ "epoch": 0.54,
1069
+ "learning_rate": 8.688345254588579e-06,
1070
+ "loss": 1.977,
1071
+ "step": 880
1072
+ },
1073
+ {
1074
+ "epoch": 0.54,
1075
+ "learning_rate": 8.592519840865432e-06,
1076
+ "loss": 1.9859,
1077
+ "step": 885
1078
+ },
1079
+ {
1080
+ "epoch": 0.55,
1081
+ "learning_rate": 8.496826103134572e-06,
1082
+ "loss": 1.9748,
1083
+ "step": 890
1084
+ },
1085
+ {
1086
+ "epoch": 0.55,
1087
+ "learning_rate": 8.401272993968288e-06,
1088
+ "loss": 1.9848,
1089
+ "step": 895
1090
+ },
1091
+ {
1092
+ "epoch": 0.55,
1093
+ "learning_rate": 8.305869452782446e-06,
1094
+ "loss": 1.9853,
1095
+ "step": 900
1096
+ },
1097
+ {
1098
+ "epoch": 0.56,
1099
+ "learning_rate": 8.210624405000169e-06,
1100
+ "loss": 1.9828,
1101
+ "step": 905
1102
+ },
1103
+ {
1104
+ "epoch": 0.56,
1105
+ "learning_rate": 8.115546761216822e-06,
1106
+ "loss": 1.9695,
1107
+ "step": 910
1108
+ },
1109
+ {
1110
+ "epoch": 0.56,
1111
+ "learning_rate": 8.020645416366367e-06,
1112
+ "loss": 1.9649,
1113
+ "step": 915
1114
+ },
1115
+ {
1116
+ "epoch": 0.57,
1117
+ "learning_rate": 7.92592924888925e-06,
1118
+ "loss": 1.9531,
1119
+ "step": 920
1120
+ },
1121
+ {
1122
+ "epoch": 0.57,
1123
+ "learning_rate": 7.831407119901737e-06,
1124
+ "loss": 1.9787,
1125
+ "step": 925
1126
+ },
1127
+ {
1128
+ "epoch": 0.57,
1129
+ "learning_rate": 7.73708787236694e-06,
1130
+ "loss": 1.978,
1131
+ "step": 930
1132
+ },
1133
+ {
1134
+ "epoch": 0.58,
1135
+ "learning_rate": 7.642980330267516e-06,
1136
+ "loss": 1.9794,
1137
+ "step": 935
1138
+ },
1139
+ {
1140
+ "epoch": 0.58,
1141
+ "learning_rate": 7.549093297780133e-06,
1142
+ "loss": 1.9848,
1143
+ "step": 940
1144
+ },
1145
+ {
1146
+ "epoch": 0.58,
1147
+ "learning_rate": 7.455435558451824e-06,
1148
+ "loss": 1.9669,
1149
+ "step": 945
1150
+ },
1151
+ {
1152
+ "epoch": 0.58,
1153
+ "learning_rate": 7.362015874378219e-06,
1154
+ "loss": 1.9532,
1155
+ "step": 950
1156
+ },
1157
+ {
1158
+ "epoch": 0.59,
1159
+ "learning_rate": 7.268842985383841e-06,
1160
+ "loss": 1.9685,
1161
+ "step": 955
1162
+ },
1163
+ {
1164
+ "epoch": 0.59,
1165
+ "learning_rate": 7.175925608204428e-06,
1166
+ "loss": 1.974,
1167
+ "step": 960
1168
+ },
1169
+ {
1170
+ "epoch": 0.59,
1171
+ "learning_rate": 7.0832724356714715e-06,
1172
+ "loss": 1.9563,
1173
+ "step": 965
1174
+ },
1175
+ {
1176
+ "epoch": 0.6,
1177
+ "learning_rate": 6.990892135898937e-06,
1178
+ "loss": 1.9648,
1179
+ "step": 970
1180
+ },
1181
+ {
1182
+ "epoch": 0.6,
1183
+ "learning_rate": 6.898793351472341e-06,
1184
+ "loss": 1.9784,
1185
+ "step": 975
1186
+ },
1187
+ {
1188
+ "epoch": 0.6,
1189
+ "learning_rate": 6.806984698640202e-06,
1190
+ "loss": 1.9783,
1191
+ "step": 980
1192
+ },
1193
+ {
1194
+ "epoch": 0.61,
1195
+ "learning_rate": 6.715474766507932e-06,
1196
+ "loss": 1.9725,
1197
+ "step": 985
1198
+ },
1199
+ {
1200
+ "epoch": 0.61,
1201
+ "learning_rate": 6.624272116234319e-06,
1202
+ "loss": 1.9531,
1203
+ "step": 990
1204
+ },
1205
+ {
1206
+ "epoch": 0.61,
1207
+ "learning_rate": 6.5333852802305556e-06,
1208
+ "loss": 1.9508,
1209
+ "step": 995
1210
+ },
1211
+ {
1212
+ "epoch": 0.62,
1213
+ "learning_rate": 6.442822761362015e-06,
1214
+ "loss": 1.9733,
1215
+ "step": 1000
1216
+ },
1217
+ {
1218
+ "epoch": 0.62,
1219
+ "learning_rate": 6.352593032152787e-06,
1220
+ "loss": 1.9748,
1221
+ "step": 1005
1222
+ },
1223
+ {
1224
+ "epoch": 0.62,
1225
+ "learning_rate": 6.262704533992995e-06,
1226
+ "loss": 1.9624,
1227
+ "step": 1010
1228
+ },
1229
+ {
1230
+ "epoch": 0.62,
1231
+ "learning_rate": 6.173165676349103e-06,
1232
+ "loss": 1.9534,
1233
+ "step": 1015
1234
+ },
1235
+ {
1236
+ "epoch": 0.63,
1237
+ "learning_rate": 6.083984835977154e-06,
1238
+ "loss": 1.9787,
1239
+ "step": 1020
1240
+ },
1241
+ {
1242
+ "epoch": 0.63,
1243
+ "learning_rate": 5.995170356139088e-06,
1244
+ "loss": 1.9767,
1245
+ "step": 1025
1246
+ },
1247
+ {
1248
+ "epoch": 0.63,
1249
+ "learning_rate": 5.9067305458222054e-06,
1250
+ "loss": 1.9736,
1251
+ "step": 1030
1252
+ },
1253
+ {
1254
+ "epoch": 0.64,
1255
+ "learning_rate": 5.8186736789618105e-06,
1256
+ "loss": 1.9583,
1257
+ "step": 1035
1258
+ },
1259
+ {
1260
+ "epoch": 0.64,
1261
+ "learning_rate": 5.731007993667155e-06,
1262
+ "loss": 1.9596,
1263
+ "step": 1040
1264
+ },
1265
+ {
1266
+ "epoch": 0.64,
1267
+ "learning_rate": 5.643741691450733e-06,
1268
+ "loss": 1.9644,
1269
+ "step": 1045
1270
+ },
1271
+ {
1272
+ "epoch": 0.65,
1273
+ "learning_rate": 5.556882936460966e-06,
1274
+ "loss": 1.9409,
1275
+ "step": 1050
1276
+ },
1277
+ {
1278
+ "epoch": 0.65,
1279
+ "learning_rate": 5.4704398547184535e-06,
1280
+ "loss": 1.9409,
1281
+ "step": 1055
1282
+ },
1283
+ {
1284
+ "epoch": 0.65,
1285
+ "learning_rate": 5.38442053335571e-06,
1286
+ "loss": 1.9568,
1287
+ "step": 1060
1288
+ },
1289
+ {
1290
+ "epoch": 0.66,
1291
+ "learning_rate": 5.298833019860599e-06,
1292
+ "loss": 1.9416,
1293
+ "step": 1065
1294
+ },
1295
+ {
1296
+ "epoch": 0.66,
1297
+ "learning_rate": 5.213685321323451e-06,
1298
+ "loss": 1.9614,
1299
+ "step": 1070
1300
+ },
1301
+ {
1302
+ "epoch": 0.66,
1303
+ "learning_rate": 5.128985403687949e-06,
1304
+ "loss": 1.9659,
1305
+ "step": 1075
1306
+ },
1307
+ {
1308
+ "epoch": 0.67,
1309
+ "learning_rate": 5.044741191005908e-06,
1310
+ "loss": 1.9459,
1311
+ "step": 1080
1312
+ },
1313
+ {
1314
+ "epoch": 0.67,
1315
+ "learning_rate": 4.960960564695922e-06,
1316
+ "loss": 1.9613,
1317
+ "step": 1085
1318
+ },
1319
+ {
1320
+ "epoch": 0.67,
1321
+ "learning_rate": 4.877651362806038e-06,
1322
+ "loss": 1.9665,
1323
+ "step": 1090
1324
+ },
1325
+ {
1326
+ "epoch": 0.67,
1327
+ "learning_rate": 4.7948213792804475e-06,
1328
+ "loss": 1.9656,
1329
+ "step": 1095
1330
+ },
1331
+ {
1332
+ "epoch": 0.68,
1333
+ "learning_rate": 4.712478363230361e-06,
1334
+ "loss": 1.9454,
1335
+ "step": 1100
1336
+ },
1337
+ {
1338
+ "epoch": 0.68,
1339
+ "learning_rate": 4.630630018209027e-06,
1340
+ "loss": 1.9412,
1341
+ "step": 1105
1342
+ },
1343
+ {
1344
+ "epoch": 0.68,
1345
+ "learning_rate": 4.5492840014910145e-06,
1346
+ "loss": 1.9516,
1347
+ "step": 1110
1348
+ },
1349
+ {
1350
+ "epoch": 0.69,
1351
+ "learning_rate": 4.468447923355888e-06,
1352
+ "loss": 1.9871,
1353
+ "step": 1115
1354
+ },
1355
+ {
1356
+ "epoch": 0.69,
1357
+ "learning_rate": 4.388129346376177e-06,
1358
+ "loss": 1.9627,
1359
+ "step": 1120
1360
+ },
1361
+ {
1362
+ "epoch": 0.69,
1363
+ "learning_rate": 4.308335784709902e-06,
1364
+ "loss": 1.9765,
1365
+ "step": 1125
1366
+ },
1367
+ {
1368
+ "epoch": 0.7,
1369
+ "learning_rate": 4.22907470339758e-06,
1370
+ "loss": 1.9573,
1371
+ "step": 1130
1372
+ },
1373
+ {
1374
+ "epoch": 0.7,
1375
+ "learning_rate": 4.1503535176638264e-06,
1376
+ "loss": 1.9348,
1377
+ "step": 1135
1378
+ },
1379
+ {
1380
+ "epoch": 0.7,
1381
+ "learning_rate": 4.07217959222365e-06,
1382
+ "loss": 1.9642,
1383
+ "step": 1140
1384
+ },
1385
+ {
1386
+ "epoch": 0.7,
1387
+ "eval_loss": 1.9577815532684326,
1388
+ "eval_runtime": 81.9871,
1389
+ "eval_samples_per_second": 281.874,
1390
+ "eval_steps_per_second": 8.818,
1391
+ "step": 1141
1392
+ },
1393
+ {
1394
+ "epoch": 0.7,
1395
+ "step": 1141,
1396
+ "total_flos": 17914719633408.0,
1397
+ "train_loss": 2.1211067035885676,
1398
+ "train_runtime": 2085.5853,
1399
+ "train_samples_per_second": 99.667,
1400
+ "train_steps_per_second": 0.779
1401
+ }
1402
+ ],
1403
+ "logging_steps": 5,
1404
+ "max_steps": 1624,
1405
+ "num_train_epochs": 1,
1406
+ "save_steps": 500,
1407
+ "total_flos": 17914719633408.0,
1408
+ "trial_name": null,
1409
+ "trial_params": null
1410
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7af23feb043256fd27caf66183f0c49da62333f365b3ddc450802a7f1397cd8
3
+ size 5624