Hugging Face's logo

loubnabnl
/
smollm-360M-instruct-add-basics-w-math

TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
Model card Files
xet
Metrics Community
loubnabnl HF Staff commited on
Commit
71f2d39
·
verified ·
1 Parent(s): 334459e

Model save

Browse files
Files changed (14) hide show
  1. README.md +68 -0
  2. all_results.json +9 -0
  3. config.json +30 -0
  4. generation_config.json +7 -0
  5. merges.txt +0 -0
  6. model.safetensors +3 -0
  7. runs/Aug13_15-03-58_ip-26-0-165-24/events.out.tfevents.1723562054.ip-26-0-165-24.693749.0 +3 -0
  8. special_tokens_map.json +28 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +154 -0
  11. train_results.json +9 -0
  12. trainer_state.json +1198 -0
  13. training_args.bin +3 -0
  14. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: HuggingFaceTB/SmolLM-360M
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ datasets:
9
+ - generator
10
+ model-index:
11
+ - name: smollm-360M-instruct-add-basics-w-math
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/nb39wz01)
19
+ # smollm-360M-instruct-add-basics-w-math
20
+
21
+ This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M](https://huggingface.co/HuggingFaceTB/SmolLM-360M) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.2017
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.001
43
+ - train_batch_size: 4
44
+ - eval_batch_size: 4
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - num_devices: 8
48
+ - gradient_accumulation_steps: 4
49
+ - total_train_batch_size: 128
50
+ - total_eval_batch_size: 32
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: cosine
53
+ - lr_scheduler_warmup_ratio: 0.1
54
+ - num_epochs: 1
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss |
59
+ |:-------------:|:------:|:----:|:---------------:|
60
+ | 0.857 | 0.9991 | 817 | 1.2017 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.42.3
66
+ - Pytorch 2.1.2
67
+ - Datasets 2.20.0
68
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9990828492815653,
3
+ "total_flos": 80161328332800.0,
4
+ "train_loss": 0.9151807048767258,
5
+ "train_runtime": 1859.3287,
6
+ "train_samples": 321430,
7
+ "train_samples_per_second": 56.289,
8
+ "train_steps_per_second": 0.439
9
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM-360M",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 960,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2560,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 15,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 5,
20
+ "pad_token_id": 2,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": true,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.42.3",
28
+ "use_cache": false,
29
+ "vocab_size": 49152
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.42.3"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b950e19b8f8fe812bfb1472b5523f4dd73bb4bc53625432e400387d1ba7275
3
+ size 723674912
runs/Aug13_15-03-58_ip-26-0-165-24/events.out.tfevents.1723562054.ip-26-0-165-24.693749.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a40c8b699c97d2bdc24c0b9289c7e304b0a074e122a69937e3f674b5e7a011
3
+ size 40305
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>",
21
+ "unk_token": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|im_start|>",
143
+ "<|im_end|>"
144
+ ],
145
+ "bos_token": "<|im_start|>",
146
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
147
+ "clean_up_tokenization_spaces": false,
148
+ "eos_token": "<|im_end|>",
149
+ "model_max_length": 2048,
150
+ "pad_token": "<|im_end|>",
151
+ "tokenizer_class": "GPT2Tokenizer",
152
+ "unk_token": "<|endoftext|>",
153
+ "vocab_size": 49152
154
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9990828492815653,
3
+ "total_flos": 80161328332800.0,
4
+ "train_loss": 0.9151807048767258,
5
+ "train_runtime": 1859.3287,
6
+ "train_samples": 321430,
7
+ "train_samples_per_second": 56.289,
8
+ "train_steps_per_second": 0.439
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9990828492815653,
5
+ "eval_steps": 500,
6
+ "global_step": 817,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0012228676245796392,
13
+ "grad_norm": 1.5651791434848155,
14
+ "learning_rate": 1.2195121951219513e-05,
15
+ "loss": 1.3765,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.006114338122898196,
20
+ "grad_norm": 1.4895397594466544,
21
+ "learning_rate": 6.097560975609756e-05,
22
+ "loss": 1.3626,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.012228676245796393,
27
+ "grad_norm": 1.5249099144693075,
28
+ "learning_rate": 0.00012195121951219512,
29
+ "loss": 1.3248,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.01834301436869459,
34
+ "grad_norm": 0.6182572105126181,
35
+ "learning_rate": 0.00018292682926829268,
36
+ "loss": 1.2243,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.024457352491592785,
41
+ "grad_norm": 0.41445396549550984,
42
+ "learning_rate": 0.00024390243902439024,
43
+ "loss": 1.1402,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.03057169061449098,
48
+ "grad_norm": 0.3150276194376965,
49
+ "learning_rate": 0.0003048780487804878,
50
+ "loss": 1.1038,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.03668602873738918,
55
+ "grad_norm": 0.14810738565646345,
56
+ "learning_rate": 0.00036585365853658537,
57
+ "loss": 1.0666,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.042800366860287375,
62
+ "grad_norm": 0.1469799790499961,
63
+ "learning_rate": 0.0004268292682926829,
64
+ "loss": 1.0788,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.04891470498318557,
69
+ "grad_norm": 0.11813746835657694,
70
+ "learning_rate": 0.0004878048780487805,
71
+ "loss": 1.0383,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.055029043106083766,
76
+ "grad_norm": 0.11458144940287407,
77
+ "learning_rate": 0.0005487804878048781,
78
+ "loss": 1.0344,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.06114338122898196,
83
+ "grad_norm": 0.12431506889021993,
84
+ "learning_rate": 0.0006097560975609756,
85
+ "loss": 1.0212,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.06725771935188016,
90
+ "grad_norm": 0.1442069213894891,
91
+ "learning_rate": 0.0006707317073170732,
92
+ "loss": 1.0225,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.07337205747477836,
97
+ "grad_norm": 0.10867878877350798,
98
+ "learning_rate": 0.0007317073170731707,
99
+ "loss": 1.0146,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.07948639559767655,
104
+ "grad_norm": 0.11956283604570934,
105
+ "learning_rate": 0.0007926829268292683,
106
+ "loss": 1.01,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.08560073372057475,
111
+ "grad_norm": 0.12502860090742626,
112
+ "learning_rate": 0.0008536585365853659,
113
+ "loss": 1.0053,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.09171507184347294,
118
+ "grad_norm": 0.12326167917218363,
119
+ "learning_rate": 0.0009146341463414635,
120
+ "loss": 1.0029,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.09782940996637114,
125
+ "grad_norm": 0.12744417766871155,
126
+ "learning_rate": 0.000975609756097561,
127
+ "loss": 0.9936,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.10394374808926933,
132
+ "grad_norm": 0.2031560386367655,
133
+ "learning_rate": 0.0009999588943391596,
134
+ "loss": 0.9976,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.11005808621216753,
139
+ "grad_norm": 0.17021719270809427,
140
+ "learning_rate": 0.0009997077175540067,
141
+ "loss": 0.9974,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.11617242433506574,
146
+ "grad_norm": 0.16256998958046662,
147
+ "learning_rate": 0.0009992283150399447,
148
+ "loss": 0.9981,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.12228676245796392,
153
+ "grad_norm": 0.16488934277544587,
154
+ "learning_rate": 0.000998520905748941,
155
+ "loss": 0.994,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.12840110058086213,
160
+ "grad_norm": 0.12662055003888464,
161
+ "learning_rate": 0.0009975858127678633,
162
+ "loss": 0.985,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.13451543870376031,
167
+ "grad_norm": 0.12183795639733393,
168
+ "learning_rate": 0.0009964234631709187,
169
+ "loss": 0.982,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.1406297768266585,
174
+ "grad_norm": 0.14273430665729847,
175
+ "learning_rate": 0.0009950343878246009,
176
+ "loss": 0.9944,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.14674411494955672,
181
+ "grad_norm": 0.13530053769850683,
182
+ "learning_rate": 0.0009934192211452344,
183
+ "loss": 0.9868,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.1528584530724549,
188
+ "grad_norm": 0.16040856740605441,
189
+ "learning_rate": 0.0009915787008092246,
190
+ "loss": 0.9821,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.1589727911953531,
195
+ "grad_norm": 0.14036184991824666,
196
+ "learning_rate": 0.0009895136674161465,
197
+ "loss": 0.9726,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.16508712931825129,
202
+ "grad_norm": 0.16453999088527366,
203
+ "learning_rate": 0.0009872250641048289,
204
+ "loss": 0.9803,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.1712014674411495,
209
+ "grad_norm": 0.12609483380818387,
210
+ "learning_rate": 0.0009847139361226047,
211
+ "loss": 0.9747,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.1773158055640477,
216
+ "grad_norm": 0.11833511610560972,
217
+ "learning_rate": 0.0009819814303479266,
218
+ "loss": 0.9764,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.18343014368694588,
223
+ "grad_norm": 0.13867903334188714,
224
+ "learning_rate": 0.0009790287947665682,
225
+ "loss": 0.9705,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.1895444818098441,
230
+ "grad_norm": 0.16359704719067755,
231
+ "learning_rate": 0.0009758573779016438,
232
+ "loss": 0.973,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.19565881993274228,
237
+ "grad_norm": 0.1521247586416416,
238
+ "learning_rate": 0.0009724686281977146,
239
+ "loss": 0.9572,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.20177315805564047,
244
+ "grad_norm": 0.12042783871397957,
245
+ "learning_rate": 0.0009688640933592572,
246
+ "loss": 0.9567,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.20788749617853866,
251
+ "grad_norm": 0.12309002079679088,
252
+ "learning_rate": 0.0009650454196437975,
253
+ "loss": 0.9563,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.21400183430143688,
258
+ "grad_norm": 0.18172628896470117,
259
+ "learning_rate": 0.0009610143511100353,
260
+ "loss": 0.9552,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.22011617242433507,
265
+ "grad_norm": 0.15193832095784507,
266
+ "learning_rate": 0.0009567727288213005,
267
+ "loss": 0.9554,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.22623051054723325,
272
+ "grad_norm": 0.11071517374274199,
273
+ "learning_rate": 0.0009523224900047051,
274
+ "loss": 0.944,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.23234484867013147,
279
+ "grad_norm": 0.16605306055042693,
280
+ "learning_rate": 0.0009476656671663766,
281
+ "loss": 0.9515,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.23845918679302966,
286
+ "grad_norm": 0.14817549608028274,
287
+ "learning_rate": 0.0009428043871631739,
288
+ "loss": 0.9394,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.24457352491592785,
293
+ "grad_norm": 0.1220114307763855,
294
+ "learning_rate": 0.0009377408702313137,
295
+ "loss": 0.95,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.25068786303882606,
300
+ "grad_norm": 0.11567261614693129,
301
+ "learning_rate": 0.0009324774289723468,
302
+ "loss": 0.9492,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.25680220116172425,
307
+ "grad_norm": 0.15943169108613203,
308
+ "learning_rate": 0.0009270164672969508,
309
+ "loss": 0.9466,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.26291653928462244,
314
+ "grad_norm": 0.10563236585959133,
315
+ "learning_rate": 0.0009213604793270196,
316
+ "loss": 0.9437,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.26903087740752063,
321
+ "grad_norm": 0.12137894462956439,
322
+ "learning_rate": 0.000915512048256552,
323
+ "loss": 0.946,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.2751452155304188,
328
+ "grad_norm": 0.1254514821868344,
329
+ "learning_rate": 0.0009094738451718594,
330
+ "loss": 0.9448,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.281259553653317,
335
+ "grad_norm": 0.12275607048530816,
336
+ "learning_rate": 0.0009032486278316315,
337
+ "loss": 0.9486,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.28737389177621525,
342
+ "grad_norm": 0.11222179304998407,
343
+ "learning_rate": 0.0008968392394074163,
344
+ "loss": 0.944,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.29348822989911344,
349
+ "grad_norm": 0.13700620863862228,
350
+ "learning_rate": 0.0008902486071850926,
351
+ "loss": 0.9413,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.29960256802201163,
356
+ "grad_norm": 0.12147382100215783,
357
+ "learning_rate": 0.0008834797412279236,
358
+ "loss": 0.9314,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.3057169061449098,
363
+ "grad_norm": 0.10835379277656058,
364
+ "learning_rate": 0.0008765357330018055,
365
+ "loss": 0.9272,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.311831244267808,
370
+ "grad_norm": 0.11862083478281513,
371
+ "learning_rate": 0.0008694197539633384,
372
+ "loss": 0.9404,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.3179455823907062,
377
+ "grad_norm": 0.10703516760798883,
378
+ "learning_rate": 0.0008621350541113637,
379
+ "loss": 0.9327,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.3240599205136044,
384
+ "grad_norm": 0.14408727173165917,
385
+ "learning_rate": 0.0008546849605026289,
386
+ "loss": 0.93,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.33017425863650257,
391
+ "grad_norm": 0.1352262854726781,
392
+ "learning_rate": 0.0008470728757322603,
393
+ "loss": 0.927,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.3362885967594008,
398
+ "grad_norm": 0.17065892900202725,
399
+ "learning_rate": 0.0008393022763797346,
400
+ "loss": 0.9361,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.342402934882299,
405
+ "grad_norm": 0.15109584505284554,
406
+ "learning_rate": 0.0008313767114210615,
407
+ "loss": 0.9357,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.3485172730051972,
412
+ "grad_norm": 0.10720327809906864,
413
+ "learning_rate": 0.0008232998006078997,
414
+ "loss": 0.928,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.3546316111280954,
419
+ "grad_norm": 0.12388797358800836,
420
+ "learning_rate": 0.0008150752328143514,
421
+ "loss": 0.9254,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.36074594925099357,
426
+ "grad_norm": 0.12765973869133845,
427
+ "learning_rate": 0.0008067067643521834,
428
+ "loss": 0.903,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.36686028737389176,
433
+ "grad_norm": 0.22025311153904717,
434
+ "learning_rate": 0.0007981982172552517,
435
+ "loss": 0.9312,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.37297462549678995,
440
+ "grad_norm": 0.11123495383204336,
441
+ "learning_rate": 0.0007895534775339084,
442
+ "loss": 0.9157,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.3790889636196882,
447
+ "grad_norm": 0.12003692642329743,
448
+ "learning_rate": 0.0007807764934001874,
449
+ "loss": 0.9033,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.3852033017425864,
454
+ "grad_norm": 0.15092887769329769,
455
+ "learning_rate": 0.000771871273464585,
456
+ "loss": 0.92,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.39131763986548457,
461
+ "grad_norm": 0.1053602258718211,
462
+ "learning_rate": 0.0007628418849052523,
463
+ "loss": 0.9129,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.39743197798838276,
468
+ "grad_norm": 0.12125259732003754,
469
+ "learning_rate": 0.0007536924516104411,
470
+ "loss": 0.913,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.40354631611128094,
475
+ "grad_norm": 0.13999049875939493,
476
+ "learning_rate": 0.0007444271522950469,
477
+ "loss": 0.9008,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.40966065423417913,
482
+ "grad_norm": 0.11628169728091785,
483
+ "learning_rate": 0.0007350502185921132,
484
+ "loss": 0.9095,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.4157749923570773,
489
+ "grad_norm": 0.12414661387014203,
490
+ "learning_rate": 0.0007255659331201672,
491
+ "loss": 0.9173,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.42188933047997557,
496
+ "grad_norm": 0.12133875571492429,
497
+ "learning_rate": 0.0007159786275272686,
498
+ "loss": 0.9052,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.42800366860287375,
503
+ "grad_norm": 0.10406959912373474,
504
+ "learning_rate": 0.0007062926805126653,
505
+ "loss": 0.9131,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.43411800672577194,
510
+ "grad_norm": 0.12728690442797477,
511
+ "learning_rate": 0.0006965125158269618,
512
+ "loss": 0.9072,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.44023234484867013,
517
+ "grad_norm": 0.1170318049898702,
518
+ "learning_rate": 0.0006866426002517105,
519
+ "loss": 0.9059,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.4463466829715683,
524
+ "grad_norm": 0.10171836143290221,
525
+ "learning_rate": 0.0006766874415593496,
526
+ "loss": 0.9101,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.4524610210944665,
531
+ "grad_norm": 0.09660525775453423,
532
+ "learning_rate": 0.0006666515864544209,
533
+ "loss": 0.9065,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.4585753592173647,
538
+ "grad_norm": 0.12897677659098664,
539
+ "learning_rate": 0.0006565396184970059,
540
+ "loss": 0.9158,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.46468969734026294,
545
+ "grad_norm": 0.12229565064806812,
546
+ "learning_rate": 0.0006463561560093292,
547
+ "loss": 0.9028,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.47080403546316113,
552
+ "grad_norm": 0.11734011152355654,
553
+ "learning_rate": 0.0006361058499664855,
554
+ "loss": 0.8985,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.4769183735860593,
559
+ "grad_norm": 0.10225820834821302,
560
+ "learning_rate": 0.0006257933818722543,
561
+ "loss": 0.8992,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.4830327117089575,
566
+ "grad_norm": 0.1210863256030476,
567
+ "learning_rate": 0.0006154234616209693,
568
+ "loss": 0.9004,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.4891470498318557,
573
+ "grad_norm": 0.14049274054700558,
574
+ "learning_rate": 0.0006050008253464246,
575
+ "loss": 0.894,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.4952613879547539,
580
+ "grad_norm": 0.11520417692209506,
581
+ "learning_rate": 0.0005945302332587938,
582
+ "loss": 0.8941,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.5013757260776521,
587
+ "grad_norm": 0.11679009305377734,
588
+ "learning_rate": 0.0005840164674705543,
589
+ "loss": 0.8875,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.5074900642005503,
594
+ "grad_norm": 0.10841284729961655,
595
+ "learning_rate": 0.000573464329812409,
596
+ "loss": 0.8896,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.5136044023234485,
601
+ "grad_norm": 0.08635350201084568,
602
+ "learning_rate": 0.0005628786396402013,
603
+ "loss": 0.8905,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.5197187404463467,
608
+ "grad_norm": 0.09367583733135104,
609
+ "learning_rate": 0.0005522642316338268,
610
+ "loss": 0.8961,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.5258330785692449,
615
+ "grad_norm": 0.11185275146645236,
616
+ "learning_rate": 0.0005416259535891447,
617
+ "loss": 0.8923,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.5319474166921431,
622
+ "grad_norm": 0.09083283056030737,
623
+ "learning_rate": 0.0005309686642039016,
624
+ "loss": 0.8803,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.5380617548150413,
629
+ "grad_norm": 0.10225155676046674,
630
+ "learning_rate": 0.0005202972308586735,
631
+ "loss": 0.898,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.5441760929379394,
636
+ "grad_norm": 0.09491178641730136,
637
+ "learning_rate": 0.0005096165273938436,
638
+ "loss": 0.8941,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.5502904310608376,
643
+ "grad_norm": 0.10185484555043305,
644
+ "learning_rate": 0.0004989314318836302,
645
+ "loss": 0.8872,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.5564047691837358,
650
+ "grad_norm": 0.09988997099687283,
651
+ "learning_rate": 0.00048824682440817927,
652
+ "loss": 0.8886,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.562519107306634,
657
+ "grad_norm": 0.10706473271135161,
658
+ "learning_rate": 0.0004775675848247427,
659
+ "loss": 0.8921,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.5686334454295322,
664
+ "grad_norm": 0.11773894458274514,
665
+ "learning_rate": 0.0004668985905389563,
666
+ "loss": 0.881,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.5747477835524305,
671
+ "grad_norm": 0.09095900658172308,
672
+ "learning_rate": 0.0004562447142772404,
673
+ "loss": 0.8833,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.5808621216753287,
678
+ "grad_norm": 0.09485196310765555,
679
+ "learning_rate": 0.0004456108218613346,
680
+ "loss": 0.8738,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.5869764597982269,
685
+ "grad_norm": 0.09527296343968149,
686
+ "learning_rate": 0.00043500176998598775,
687
+ "loss": 0.8716,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.5930907979211251,
692
+ "grad_norm": 0.09706717496523788,
693
+ "learning_rate": 0.0004244224040008156,
694
+ "loss": 0.8683,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.5992051360440233,
699
+ "grad_norm": 0.0924175028621673,
700
+ "learning_rate": 0.00041387755569734057,
701
+ "loss": 0.8804,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.6053194741669214,
706
+ "grad_norm": 0.09217501490527663,
707
+ "learning_rate": 0.0004033720411022235,
708
+ "loss": 0.8725,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.6114338122898196,
713
+ "grad_norm": 0.08372781939532938,
714
+ "learning_rate": 0.00039291065827769484,
715
+ "loss": 0.8702,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.6175481504127178,
720
+ "grad_norm": 0.09199560200708774,
721
+ "learning_rate": 0.0003824981851301924,
722
+ "loss": 0.8659,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.623662488535616,
727
+ "grad_norm": 0.09842312407252246,
728
+ "learning_rate": 0.0003721393772282022,
729
+ "loss": 0.8697,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.6297768266585142,
734
+ "grad_norm": 0.10750466193891031,
735
+ "learning_rate": 0.00036183896563030295,
736
+ "loss": 0.881,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.6358911647814124,
741
+ "grad_norm": 0.11299900150340132,
742
+ "learning_rate": 0.0003516016547244047,
743
+ "loss": 0.8737,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.6420055029043106,
748
+ "grad_norm": 0.4042681858963164,
749
+ "learning_rate": 0.00034143212007916793,
750
+ "loss": 0.876,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.6481198410272088,
755
+ "grad_norm": 0.0999580549896975,
756
+ "learning_rate": 0.00033133500630858504,
757
+ "loss": 0.863,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.654234179150107,
762
+ "grad_norm": 0.09704623218277748,
763
+ "learning_rate": 0.0003213149249506997,
764
+ "loss": 0.8726,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.6603485172730051,
769
+ "grad_norm": 0.10372675529566282,
770
+ "learning_rate": 0.00031137645236143204,
771
+ "loss": 0.8616,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.6664628553959034,
776
+ "grad_norm": 0.09213896359947416,
777
+ "learning_rate": 0.0003015241276244729,
778
+ "loss": 0.8706,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.6725771935188016,
783
+ "grad_norm": 0.10042976905418785,
784
+ "learning_rate": 0.00029176245047820063,
785
+ "loss": 0.8491,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.6786915316416998,
790
+ "grad_norm": 0.10028696192833891,
791
+ "learning_rate": 0.0002820958792605669,
792
+ "loss": 0.8574,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.684805869764598,
797
+ "grad_norm": 0.09020811948567081,
798
+ "learning_rate": 0.00027252882887289287,
799
+ "loss": 0.8588,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.6909202078874962,
804
+ "grad_norm": 0.10345140225018136,
805
+ "learning_rate": 0.0002630656687635007,
806
+ "loss": 0.8696,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.6970345460103944,
811
+ "grad_norm": 0.10749740190617728,
812
+ "learning_rate": 0.0002537107209321074,
813
+ "loss": 0.8654,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.7031488841332926,
818
+ "grad_norm": 0.08655101600658618,
819
+ "learning_rate": 0.0002444682579558872,
820
+ "loss": 0.8634,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.7092632222561908,
825
+ "grad_norm": 0.11313373365287832,
826
+ "learning_rate": 0.00023534250103810628,
827
+ "loss": 0.8545,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.715377560379089,
832
+ "grad_norm": 0.10389782206053953,
833
+ "learning_rate": 0.00022633761808022273,
834
+ "loss": 0.8563,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.7214918985019871,
839
+ "grad_norm": 0.09141224639004816,
840
+ "learning_rate": 0.00021745772177832756,
841
+ "loss": 0.8678,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.7276062366248853,
846
+ "grad_norm": 0.08733638591751752,
847
+ "learning_rate": 0.00020870686774480197,
848
+ "loss": 0.8587,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.7337205747477835,
853
+ "grad_norm": 0.08848072887713172,
854
+ "learning_rate": 0.00020008905265604316,
855
+ "loss": 0.8514,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.7398349128706817,
860
+ "grad_norm": 0.09707736850029325,
861
+ "learning_rate": 0.00019160821242710958,
862
+ "loss": 0.8633,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.7459492509935799,
867
+ "grad_norm": 0.08787799540475368,
868
+ "learning_rate": 0.00018326822041411523,
869
+ "loss": 0.8576,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.7520635891164782,
874
+ "grad_norm": 0.15694998805819793,
875
+ "learning_rate": 0.00017507288564519647,
876
+ "loss": 0.8526,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.7581779272393764,
881
+ "grad_norm": 0.08920551112607182,
882
+ "learning_rate": 0.00016702595108085945,
883
+ "loss": 0.8684,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.7642922653622746,
888
+ "grad_norm": 0.08761186010488109,
889
+ "learning_rate": 0.0001591310919045003,
890
+ "loss": 0.8665,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.7704066034851728,
895
+ "grad_norm": 0.09195087795786469,
896
+ "learning_rate": 0.00015139191384388095,
897
+ "loss": 0.8454,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.776520941608071,
902
+ "grad_norm": 0.10138883693988116,
903
+ "learning_rate": 0.00014381195152432768,
904
+ "loss": 0.8561,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.7826352797309691,
909
+ "grad_norm": 0.08632117453676007,
910
+ "learning_rate": 0.00013639466685440134,
911
+ "loss": 0.8527,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.7887496178538673,
916
+ "grad_norm": 0.09976824535412168,
917
+ "learning_rate": 0.00012914344744478112,
918
+ "loss": 0.8614,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.7948639559767655,
923
+ "grad_norm": 0.0905710833584601,
924
+ "learning_rate": 0.0001220616050610791,
925
+ "loss": 0.8492,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.8009782940996637,
930
+ "grad_norm": 0.1010968459506448,
931
+ "learning_rate": 0.00011515237411129698,
932
+ "loss": 0.8562,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.8070926322225619,
937
+ "grad_norm": 0.08701870226697464,
938
+ "learning_rate": 0.00010841891016861154,
939
+ "loss": 0.8451,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.8132069703454601,
944
+ "grad_norm": 0.0905216571291058,
945
+ "learning_rate": 0.00010186428853016605,
946
+ "loss": 0.8505,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.8193213084683583,
951
+ "grad_norm": 0.08450629810354952,
952
+ "learning_rate": 9.549150281252633e-05,
953
+ "loss": 0.8548,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.8254356465912565,
958
+ "grad_norm": 0.07782082601508845,
959
+ "learning_rate": 8.930346358443952e-05,
960
+ "loss": 0.8537,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.8315499847141546,
965
+ "grad_norm": 0.07932529243696208,
966
+ "learning_rate": 8.330299703752498e-05,
967
+ "loss": 0.8516,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.8376643228370529,
972
+ "grad_norm": 0.08755277608836383,
973
+ "learning_rate": 7.749284369549953e-05,
974
+ "loss": 0.8492,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.8437786609599511,
979
+ "grad_norm": 0.08663207768299419,
980
+ "learning_rate": 7.187565716252992e-05,
981
+ "loss": 0.8571,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.8498929990828493,
986
+ "grad_norm": 0.09041918396193563,
987
+ "learning_rate": 6.645400291128356e-05,
988
+ "loss": 0.8522,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.8560073372057475,
993
+ "grad_norm": 0.08393639987821447,
994
+ "learning_rate": 6.123035711122859e-05,
995
+ "loss": 0.8462,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.8621216753286457,
1000
+ "grad_norm": 0.13260901574408163,
1001
+ "learning_rate": 5.6207105497722956e-05,
1002
+ "loss": 0.8454,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.8682360134515439,
1007
+ "grad_norm": 0.0901850885792999,
1008
+ "learning_rate": 5.138654228240425e-05,
1009
+ "loss": 0.8474,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.8743503515744421,
1014
+ "grad_norm": 0.07895758711701614,
1015
+ "learning_rate": 4.677086910538092e-05,
1016
+ "loss": 0.845,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.8804646896973403,
1021
+ "grad_norm": 0.07735814272716246,
1022
+ "learning_rate": 4.236219402970326e-05,
1023
+ "loss": 0.8582,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.8865790278202385,
1028
+ "grad_norm": 0.08201034719715149,
1029
+ "learning_rate": 3.816253057857144e-05,
1030
+ "loss": 0.8429,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.8926933659431366,
1035
+ "grad_norm": 0.9278041030137772,
1036
+ "learning_rate": 3.417379681572297e-05,
1037
+ "loss": 0.8571,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.8988077040660348,
1042
+ "grad_norm": 0.07949661992375699,
1043
+ "learning_rate": 3.0397814469416973e-05,
1044
+ "loss": 0.8534,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.904922042188933,
1049
+ "grad_norm": 0.08460584169650966,
1050
+ "learning_rate": 2.683630810041787e-05,
1051
+ "loss": 0.8517,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.9110363803118312,
1056
+ "grad_norm": 0.07824416631858255,
1057
+ "learning_rate": 2.349090431435641e-05,
1058
+ "loss": 0.8422,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.9171507184347294,
1063
+ "grad_norm": 0.08718216227123719,
1064
+ "learning_rate": 2.0363131018828753e-05,
1065
+ "loss": 0.8475,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.9232650565576276,
1070
+ "grad_norm": 0.07763832558735692,
1071
+ "learning_rate": 1.7454416725573353e-05,
1072
+ "loss": 0.8383,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.9293793946805259,
1077
+ "grad_norm": 0.07705992848954801,
1078
+ "learning_rate": 1.4766089898042678e-05,
1079
+ "loss": 0.8518,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.9354937328034241,
1084
+ "grad_norm": 0.08210162590156625,
1085
+ "learning_rate": 1.2299378344669988e-05,
1086
+ "loss": 0.8462,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.9416080709263223,
1091
+ "grad_norm": 0.07772244992401371,
1092
+ "learning_rate": 1.0055408658106447e-05,
1093
+ "loss": 0.8479,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.9477224090492204,
1098
+ "grad_norm": 0.08562907738973832,
1099
+ "learning_rate": 8.035205700685167e-06,
1100
+ "loss": 0.8588,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.9538367471721186,
1105
+ "grad_norm": 0.08630642465450503,
1106
+ "learning_rate": 6.239692136348285e-06,
1107
+ "loss": 0.8528,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.9599510852950168,
1112
+ "grad_norm": 0.07836684511882595,
1113
+ "learning_rate": 4.669688009248607e-06,
1114
+ "loss": 0.8361,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.966065423417915,
1119
+ "grad_norm": 0.0787423003956017,
1120
+ "learning_rate": 3.325910369220975e-06,
1121
+ "loss": 0.8372,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.9721797615408132,
1126
+ "grad_norm": 0.07733940581906677,
1127
+ "learning_rate": 2.20897294429212e-06,
1128
+ "loss": 0.8405,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.9782940996637114,
1133
+ "grad_norm": 0.07748645453278243,
1134
+ "learning_rate": 1.3193858603794961e-06,
1135
+ "loss": 0.8582,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.9844084377866096,
1140
+ "grad_norm": 0.07696238659021956,
1141
+ "learning_rate": 6.575554083078084e-07,
1142
+ "loss": 0.8446,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.9905227759095078,
1147
+ "grad_norm": 0.08299813015507701,
1148
+ "learning_rate": 2.2378385824833868e-07,
1149
+ "loss": 0.8424,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.996637114032406,
1154
+ "grad_norm": 0.08001939447953087,
1155
+ "learning_rate": 1.8269321666375404e-08,
1156
+ "loss": 0.857,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.9990828492815653,
1161
+ "eval_loss": 1.2017358541488647,
1162
+ "eval_runtime": 112.3291,
1163
+ "eval_samples_per_second": 186.506,
1164
+ "eval_steps_per_second": 5.831,
1165
+ "step": 817
1166
+ },
1167
+ {
1168
+ "epoch": 0.9990828492815653,
1169
+ "step": 817,
1170
+ "total_flos": 80161328332800.0,
1171
+ "train_loss": 0.9151807048767258,
1172
+ "train_runtime": 1859.3287,
1173
+ "train_samples_per_second": 56.289,
1174
+ "train_steps_per_second": 0.439
1175
+ }
1176
+ ],
1177
+ "logging_steps": 5,
1178
+ "max_steps": 817,
1179
+ "num_input_tokens_seen": 0,
1180
+ "num_train_epochs": 1,
1181
+ "save_steps": 500,
1182
+ "stateful_callbacks": {
1183
+ "TrainerControl": {
1184
+ "args": {
1185
+ "should_epoch_stop": false,
1186
+ "should_evaluate": false,
1187
+ "should_log": false,
1188
+ "should_save": false,
1189
+ "should_training_stop": false
1190
+ },
1191
+ "attributes": {}
1192
+ }
1193
+ },
1194
+ "total_flos": 80161328332800.0,
1195
+ "train_batch_size": 4,
1196
+ "trial_name": null,
1197
+ "trial_params": null
1198
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb469433ff2062571afd51b27deed8a8363d68d8662629150e583fe65fb2eda5
3
+ size 6520
vocab.json ADDED
The diff for this file is too large to render. See raw diff