Hugging Face's logo

loubnabnl
/
smollm-350M-instruct-test2

TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
Model card Files Metrics Community
loubnabnl HF staff commited on
Commit
a565f82
•
1 Parent(s): b6d644b

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/Aug12_13-29-20_ip-26-0-165-24/events.out.tfevents.1723469948.ip-26-0-165-24.482336.0 +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-350M-instruct-test2
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/3q0xqph6)
19
+ # smollm-350M-instruct-test2
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: 1.2029
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
+ | 0.8399 | 1.0 | 816 | 1.2029 |
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": 1.0,
3
+ "total_flos": 80063181619200.0,
4
+ "train_loss": 0.9145085595402063,
5
+ "train_runtime": 1902.7506,
6
+ "train_samples": 319078,
7
+ "train_samples_per_second": 54.885,
8
+ "train_steps_per_second": 0.429
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:c53544daf87a240d40ccb96ac60c525d7a2d397a3ab661fe5bf6f6928f6fbf9f
3
+ size 723674912
runs/Aug12_13-29-20_ip-26-0-165-24/events.out.tfevents.1723469948.ip-26-0-165-24.482336.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c4601a1b9ae75ee2eb712595432c62b5ce1acd26149e4ca473a23fd530d8e89
3
+ size 40257
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": 1.0,
3
+ "total_flos": 80063181619200.0,
4
+ "train_loss": 0.9145085595402063,
5
+ "train_runtime": 1902.7506,
6
+ "train_samples": 319078,
7
+ "train_samples_per_second": 54.885,
8
+ "train_steps_per_second": 0.429
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 816,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0012254901960784314,
13
+ "grad_norm": 1.6036396146523473,
14
+ "learning_rate": 1.2195121951219513e-05,
15
+ "loss": 1.3541,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.006127450980392157,
20
+ "grad_norm": 1.4541999892274449,
21
+ "learning_rate": 6.097560975609756e-05,
22
+ "loss": 1.355,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.012254901960784314,
27
+ "grad_norm": 1.5390535097118918,
28
+ "learning_rate": 0.00012195121951219512,
29
+ "loss": 1.3083,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.01838235294117647,
34
+ "grad_norm": 0.5811818759637415,
35
+ "learning_rate": 0.00018292682926829268,
36
+ "loss": 1.2226,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.024509803921568627,
41
+ "grad_norm": 0.3755084090839048,
42
+ "learning_rate": 0.00024390243902439024,
43
+ "loss": 1.14,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.030637254901960783,
48
+ "grad_norm": 0.24648929470069889,
49
+ "learning_rate": 0.0003048780487804878,
50
+ "loss": 1.0942,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.03676470588235294,
55
+ "grad_norm": 0.18518290277618207,
56
+ "learning_rate": 0.00036585365853658537,
57
+ "loss": 1.0785,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.0428921568627451,
62
+ "grad_norm": 0.14372846391436536,
63
+ "learning_rate": 0.0004268292682926829,
64
+ "loss": 1.0549,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.049019607843137254,
69
+ "grad_norm": 0.1389801769443967,
70
+ "learning_rate": 0.0004878048780487805,
71
+ "loss": 1.0493,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.05514705882352941,
76
+ "grad_norm": 0.15520999728279067,
77
+ "learning_rate": 0.0005487804878048781,
78
+ "loss": 1.0306,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.061274509803921566,
83
+ "grad_norm": 0.13121885809742784,
84
+ "learning_rate": 0.0006097560975609756,
85
+ "loss": 1.0204,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.06740196078431372,
90
+ "grad_norm": 0.11703518229748765,
91
+ "learning_rate": 0.0006707317073170732,
92
+ "loss": 1.0281,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.07352941176470588,
97
+ "grad_norm": 0.12071199354118181,
98
+ "learning_rate": 0.0007317073170731707,
99
+ "loss": 1.0188,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.07965686274509803,
104
+ "grad_norm": 0.11482998270254378,
105
+ "learning_rate": 0.0007926829268292683,
106
+ "loss": 1.0019,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.0857843137254902,
111
+ "grad_norm": 0.13413766368345428,
112
+ "learning_rate": 0.0008536585365853659,
113
+ "loss": 1.0043,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.09191176470588236,
118
+ "grad_norm": 0.1471493243236106,
119
+ "learning_rate": 0.0009146341463414635,
120
+ "loss": 1.0071,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.09803921568627451,
125
+ "grad_norm": 0.1259997868133445,
126
+ "learning_rate": 0.000975609756097561,
127
+ "loss": 0.9962,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.10416666666666667,
132
+ "grad_norm": 0.16099811489081525,
133
+ "learning_rate": 0.000999958782259877,
134
+ "loss": 0.9999,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.11029411764705882,
139
+ "grad_norm": 0.13529736823555488,
140
+ "learning_rate": 0.0009997069206794246,
141
+ "loss": 1.01,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.11642156862745098,
146
+ "grad_norm": 0.1287112736990173,
147
+ "learning_rate": 0.0009992262114666653,
148
+ "loss": 0.9904,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.12254901960784313,
153
+ "grad_norm": 0.13096915650623966,
154
+ "learning_rate": 0.0009985168747689707,
155
+ "loss": 0.9859,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.12867647058823528,
160
+ "grad_norm": 0.14334941177812624,
161
+ "learning_rate": 0.0009975792354368017,
162
+ "loss": 0.9934,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.13480392156862744,
167
+ "grad_norm": 0.13671174612094514,
168
+ "learning_rate": 0.0009964137228749407,
169
+ "loss": 0.9961,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.1409313725490196,
174
+ "grad_norm": 0.12218713761592166,
175
+ "learning_rate": 0.000995020870845837,
176
+ "loss": 0.9948,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.14705882352941177,
181
+ "grad_norm": 0.1291445702524626,
182
+ "learning_rate": 0.0009934013172251653,
183
+ "loss": 0.9824,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.15318627450980393,
188
+ "grad_norm": 0.1346131782998567,
189
+ "learning_rate": 0.0009915558037097002,
190
+ "loss": 0.977,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.15931372549019607,
195
+ "grad_norm": 0.13410866481050307,
196
+ "learning_rate": 0.0009894851754776472,
197
+ "loss": 0.9712,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.16544117647058823,
202
+ "grad_norm": 0.12662709799384195,
203
+ "learning_rate": 0.0009871903808015812,
204
+ "loss": 0.9807,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.1715686274509804,
209
+ "grad_norm": 0.10699714724935337,
210
+ "learning_rate": 0.0009846724706141716,
211
+ "loss": 0.977,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.17769607843137256,
216
+ "grad_norm": 0.11416365647326593,
217
+ "learning_rate": 0.0009819325980268945,
218
+ "loss": 0.9743,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.18382352941176472,
223
+ "grad_norm": 0.11826552720186441,
224
+ "learning_rate": 0.0009789720178019483,
225
+ "loss": 0.9741,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.18995098039215685,
230
+ "grad_norm": 0.11966728016095998,
231
+ "learning_rate": 0.0009757920857776188,
232
+ "loss": 0.9633,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.19607843137254902,
237
+ "grad_norm": 0.1224502041103689,
238
+ "learning_rate": 0.0009723942582473544,
239
+ "loss": 0.9544,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.20220588235294118,
244
+ "grad_norm": 0.14383092165933975,
245
+ "learning_rate": 0.0009687800912928362,
246
+ "loss": 0.9696,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.20833333333333334,
251
+ "grad_norm": 0.11172166270095091,
252
+ "learning_rate": 0.0009649512400713498,
253
+ "loss": 0.963,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.21446078431372548,
258
+ "grad_norm": 0.15338163624311216,
259
+ "learning_rate": 0.0009609094580577824,
260
+ "loss": 0.96,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.22058823529411764,
265
+ "grad_norm": 0.13464799651247097,
266
+ "learning_rate": 0.0009566565962415959,
267
+ "loss": 0.9578,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.2267156862745098,
272
+ "grad_norm": 0.14069989404410843,
273
+ "learning_rate": 0.0009521946022791401,
274
+ "loss": 0.9555,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.23284313725490197,
279
+ "grad_norm": 0.1563880044910766,
280
+ "learning_rate": 0.0009475255196016972,
281
+ "loss": 0.9579,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.23897058823529413,
286
+ "grad_norm": 0.1354522777364055,
287
+ "learning_rate": 0.0009426514864796647,
288
+ "loss": 0.9494,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.24509803921568626,
293
+ "grad_norm": 0.14141184524556524,
294
+ "learning_rate": 0.0009375747350433044,
295
+ "loss": 0.9479,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.2512254901960784,
300
+ "grad_norm": 0.16178153584659036,
301
+ "learning_rate": 0.0009322975902605082,
302
+ "loss": 0.9655,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.25735294117647056,
307
+ "grad_norm": 0.12500026452110888,
308
+ "learning_rate": 0.0009268224688720474,
309
+ "loss": 0.9446,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.26348039215686275,
314
+ "grad_norm": 0.11225181351597031,
315
+ "learning_rate": 0.0009211518782847931,
316
+ "loss": 0.9425,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.2696078431372549,
321
+ "grad_norm": 0.11760271912658449,
322
+ "learning_rate": 0.0009152884154234145,
323
+ "loss": 0.9451,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.2757352941176471,
328
+ "grad_norm": 0.1118694290603578,
329
+ "learning_rate": 0.0009092347655410818,
330
+ "loss": 0.9403,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.2818627450980392,
335
+ "grad_norm": 0.1420082600855828,
336
+ "learning_rate": 0.0009029937009897176,
337
+ "loss": 0.9349,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.28799019607843135,
342
+ "grad_norm": 0.1056893276215326,
343
+ "learning_rate": 0.0008965680799503608,
344
+ "loss": 0.9329,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.29411764705882354,
349
+ "grad_norm": 0.11697165985204966,
350
+ "learning_rate": 0.0008899608451242233,
351
+ "loss": 0.9396,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.3002450980392157,
356
+ "grad_norm": 0.11807737475048682,
357
+ "learning_rate": 0.0008831750223850389,
358
+ "loss": 0.923,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.30637254901960786,
363
+ "grad_norm": 0.1050901075842651,
364
+ "learning_rate": 0.0008762137193933241,
365
+ "loss": 0.9296,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.3125,
370
+ "grad_norm": 0.12149544868604345,
371
+ "learning_rate": 0.0008690801241731818,
372
+ "loss": 0.9209,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.31862745098039214,
377
+ "grad_norm": 1.9072328081474224,
378
+ "learning_rate": 0.0008617775036523015,
379
+ "loss": 0.9392,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.3247549019607843,
384
+ "grad_norm": 0.11658317470657904,
385
+ "learning_rate": 0.0008543092021658259,
386
+ "loss": 0.9367,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.33088235294117646,
391
+ "grad_norm": 0.11777705186781876,
392
+ "learning_rate": 0.0008466786399247663,
393
+ "loss": 0.9285,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.33700980392156865,
398
+ "grad_norm": 0.10974224954880234,
399
+ "learning_rate": 0.0008388893114496705,
400
+ "loss": 0.9357,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.3431372549019608,
405
+ "grad_norm": 0.10762311122261868,
406
+ "learning_rate": 0.0008309447839702582,
407
+ "loss": 0.9303,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.3492647058823529,
412
+ "grad_norm": 0.10853358544847327,
413
+ "learning_rate": 0.0008228486957917607,
414
+ "loss": 0.9222,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.3553921568627451,
419
+ "grad_norm": 0.11469387675689356,
420
+ "learning_rate": 0.0008146047546287076,
421
+ "loss": 0.9343,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.36151960784313725,
426
+ "grad_norm": 0.11795665158917668,
427
+ "learning_rate": 0.0008062167359069301,
428
+ "loss": 0.9277,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.36764705882352944,
433
+ "grad_norm": 0.11929317566114471,
434
+ "learning_rate": 0.000797688481034551,
435
+ "loss": 0.9176,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.3737745098039216,
440
+ "grad_norm": 0.10301604347512731,
441
+ "learning_rate": 0.00078902389564276,
442
+ "loss": 0.9239,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.3799019607843137,
447
+ "grad_norm": 0.1271379375111038,
448
+ "learning_rate": 0.0007802269477971771,
449
+ "loss": 0.9166,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.3860294117647059,
454
+ "grad_norm": 0.13842829612868068,
455
+ "learning_rate": 0.0007713016661806211,
456
+ "loss": 0.9162,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.39215686274509803,
461
+ "grad_norm": 0.1258803633770378,
462
+ "learning_rate": 0.0007622521382481208,
463
+ "loss": 0.9096,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.39828431372549017,
468
+ "grad_norm": 0.10943327109661027,
469
+ "learning_rate": 0.0007530825083550073,
470
+ "loss": 0.9031,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.40441176470588236,
475
+ "grad_norm": 0.10473608787205252,
476
+ "learning_rate": 0.0007437969758589507,
477
+ "loss": 0.9144,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.4105392156862745,
482
+ "grad_norm": 0.1120426574406447,
483
+ "learning_rate": 0.0007343997931968067,
484
+ "loss": 0.9073,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.4166666666666667,
489
+ "grad_norm": 0.10888401544172292,
490
+ "learning_rate": 0.0007248952639371542,
491
+ "loss": 0.9073,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.4227941176470588,
496
+ "grad_norm": 0.11326294156455767,
497
+ "learning_rate": 0.0007152877408094178,
498
+ "loss": 0.8996,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.42892156862745096,
503
+ "grad_norm": 0.12674079463497812,
504
+ "learning_rate": 0.0007055816237104753,
505
+ "loss": 0.9092,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.43504901960784315,
510
+ "grad_norm": 0.12252284768767446,
511
+ "learning_rate": 0.0006957813576896647,
512
+ "loss": 0.8988,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.4411764705882353,
517
+ "grad_norm": 0.12424572403107578,
518
+ "learning_rate": 0.000685891430913113,
519
+ "loss": 0.9088,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.44730392156862747,
524
+ "grad_norm": 0.11202550868881908,
525
+ "learning_rate": 0.0006759163726083191,
526
+ "loss": 0.9002,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.4534313725490196,
531
+ "grad_norm": 0.09998982889163562,
532
+ "learning_rate": 0.0006658607509899319,
533
+ "loss": 0.8993,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.45955882352941174,
538
+ "grad_norm": 0.11977953776420541,
539
+ "learning_rate": 0.0006557291711676738,
540
+ "loss": 0.9062,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.46568627450980393,
545
+ "grad_norm": 0.11102474447162053,
546
+ "learning_rate": 0.0006455262730373672,
547
+ "loss": 0.8898,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.47181372549019607,
552
+ "grad_norm": 0.12262996603961465,
553
+ "learning_rate": 0.0006352567291560318,
554
+ "loss": 0.8945,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.47794117647058826,
559
+ "grad_norm": 0.11193151635262173,
560
+ "learning_rate": 0.0006249252426020216,
561
+ "loss": 0.8974,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.4840686274509804,
566
+ "grad_norm": 0.11911248377352072,
567
+ "learning_rate": 0.0006145365448211866,
568
+ "loss": 0.8995,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.49019607843137253,
573
+ "grad_norm": 0.11024344557839909,
574
+ "learning_rate": 0.0006040953934600423,
575
+ "loss": 0.8919,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.4963235294117647,
580
+ "grad_norm": 0.10313300838358162,
581
+ "learning_rate": 0.0005936065701869403,
582
+ "loss": 0.8965,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.5024509803921569,
587
+ "grad_norm": 0.1517513971243366,
588
+ "learning_rate": 0.0005830748785022368,
589
+ "loss": 0.8951,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.508578431372549,
594
+ "grad_norm": 0.10621777821428764,
595
+ "learning_rate": 0.0005725051415384657,
596
+ "loss": 0.9009,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.5147058823529411,
601
+ "grad_norm": 0.120824242008392,
602
+ "learning_rate": 0.0005619021998515165,
603
+ "loss": 0.8916,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.5208333333333334,
608
+ "grad_norm": 0.10796312687200485,
609
+ "learning_rate": 0.000551270909203838,
610
+ "loss": 0.8875,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.5269607843137255,
615
+ "grad_norm": 0.10485643705406462,
616
+ "learning_rate": 0.0005406161383406731,
617
+ "loss": 0.8995,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.5330882352941176,
622
+ "grad_norm": 0.1040747798660248,
623
+ "learning_rate": 0.0005299427667603515,
624
+ "loss": 0.9022,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.5392156862745098,
629
+ "grad_norm": 0.10303234276114956,
630
+ "learning_rate": 0.0005192556824796568,
631
+ "loss": 0.8858,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.5453431372549019,
636
+ "grad_norm": 0.13041962513060196,
637
+ "learning_rate": 0.0005085597797952905,
638
+ "loss": 0.8842,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.5514705882352942,
643
+ "grad_norm": 0.09392051916112838,
644
+ "learning_rate": 0.0004978599570424639,
645
+ "loss": 0.8832,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.5575980392156863,
650
+ "grad_norm": 0.11180233058561544,
651
+ "learning_rate": 0.0004871611143516367,
652
+ "loss": 0.8878,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.5637254901960784,
657
+ "grad_norm": 0.12367570385780484,
658
+ "learning_rate": 0.0004764681514044362,
659
+ "loss": 0.8859,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.5698529411764706,
664
+ "grad_norm": 0.10034153908219615,
665
+ "learning_rate": 0.0004657859651897806,
666
+ "loss": 0.8889,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.5759803921568627,
671
+ "grad_norm": 0.09279117510206411,
672
+ "learning_rate": 0.00045511944776123513,
673
+ "loss": 0.878,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.5821078431372549,
678
+ "grad_norm": 0.09436846491514878,
679
+ "learning_rate": 0.00044447348399663056,
680
+ "loss": 0.8842,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.5882352941176471,
685
+ "grad_norm": 0.2016423837068627,
686
+ "learning_rate": 0.0004338529493609647,
687
+ "loss": 0.8815,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.5943627450980392,
692
+ "grad_norm": 0.1280806078271419,
693
+ "learning_rate": 0.00042326270767361815,
694
+ "loss": 0.8877,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.6004901960784313,
699
+ "grad_norm": 0.08986898470466548,
700
+ "learning_rate": 0.00041270760888089997,
701
+ "loss": 0.8819,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.6066176470588235,
706
+ "grad_norm": 0.0982311145214648,
707
+ "learning_rate": 0.00040219248683494925,
708
+ "loss": 0.8629,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.6127450980392157,
713
+ "grad_norm": 0.12205296661938488,
714
+ "learning_rate": 0.0003917221570800065,
715
+ "loss": 0.8713,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.6188725490196079,
720
+ "grad_norm": 0.10671335419272648,
721
+ "learning_rate": 0.000381301414647068,
722
+ "loss": 0.8703,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.625,
727
+ "grad_norm": 0.10436549804544415,
728
+ "learning_rate": 0.0003709350318579371,
729
+ "loss": 0.8929,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.6311274509803921,
734
+ "grad_norm": 0.09117916773772033,
735
+ "learning_rate": 0.0003606277561396726,
736
+ "loss": 0.8591,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.6372549019607843,
741
+ "grad_norm": 0.09178929014053801,
742
+ "learning_rate": 0.00035038430785044053,
743
+ "loss": 0.8625,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.6433823529411765,
748
+ "grad_norm": 0.09612760306153695,
749
+ "learning_rate": 0.00034020937811776156,
750
+ "loss": 0.8594,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.6495098039215687,
755
+ "grad_norm": 0.09538202932858882,
756
+ "learning_rate": 0.00033010762669014347,
757
+ "loss": 0.867,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.6556372549019608,
762
+ "grad_norm": 0.09494219161832793,
763
+ "learning_rate": 0.00032008367980308734,
764
+ "loss": 0.872,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.6617647058823529,
769
+ "grad_norm": 0.08714205666482473,
770
+ "learning_rate": 0.0003101421280604379,
771
+ "loss": 0.8838,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.6678921568627451,
776
+ "grad_norm": 0.0969140933539997,
777
+ "learning_rate": 0.00030028752433205476,
778
+ "loss": 0.8608,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.6740196078431373,
783
+ "grad_norm": 0.09815891195004724,
784
+ "learning_rate": 0.00029052438166876307,
785
+ "loss": 0.8525,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.6801470588235294,
790
+ "grad_norm": 0.09615743129166938,
791
+ "learning_rate": 0.0002808571712355389,
792
+ "loss": 0.8638,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.6862745098039216,
797
+ "grad_norm": 0.10788692448970114,
798
+ "learning_rate": 0.00027129032026388045,
799
+ "loss": 0.8579,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.6924019607843137,
804
+ "grad_norm": 0.09213201587158737,
805
+ "learning_rate": 0.00026182821002429345,
806
+ "loss": 0.8615,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.6985294117647058,
811
+ "grad_norm": 0.09011406445898068,
812
+ "learning_rate": 0.00025247517381983136,
813
+ "loss": 0.8653,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.7046568627450981,
818
+ "grad_norm": 0.09736667368082612,
819
+ "learning_rate": 0.00024323549500159802,
820
+ "loss": 0.8617,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.7107843137254902,
825
+ "grad_norm": 0.09441622008962705,
826
+ "learning_rate": 0.0002341134050071283,
827
+ "loss": 0.8549,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.7169117647058824,
832
+ "grad_norm": 0.10000573346346127,
833
+ "learning_rate": 0.00022511308142254488,
834
+ "loss": 0.8575,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.7230392156862745,
839
+ "grad_norm": 0.1122829077347512,
840
+ "learning_rate": 0.000216238646069373,
841
+ "loss": 0.8604,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.7291666666666666,
846
+ "grad_norm": 0.09161355750906706,
847
+ "learning_rate": 0.00020749416311689845,
848
+ "loss": 0.8604,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.7352941176470589,
853
+ "grad_norm": 0.10349631376405924,
854
+ "learning_rate": 0.00019888363722092372,
855
+ "loss": 0.8629,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.741421568627451,
860
+ "grad_norm": 0.088451467518437,
861
+ "learning_rate": 0.00019041101168978093,
862
+ "loss": 0.8587,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.7475490196078431,
867
+ "grad_norm": 0.09610692111696861,
868
+ "learning_rate": 0.00018208016667844152,
869
+ "loss": 0.8613,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.7536764705882353,
874
+ "grad_norm": 0.09635232236992683,
875
+ "learning_rate": 0.00017389491741154372,
876
+ "loss": 0.8541,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.7598039215686274,
881
+ "grad_norm": 0.08400718304881724,
882
+ "learning_rate": 0.00016585901243616042,
883
+ "loss": 0.8564,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.7659313725490197,
888
+ "grad_norm": 0.08527935145250837,
889
+ "learning_rate": 0.0001579761319050991,
890
+ "loss": 0.8545,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.7720588235294118,
895
+ "grad_norm": 0.08535848929061582,
896
+ "learning_rate": 0.00015024988589152537,
897
+ "loss": 0.858,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.7781862745098039,
902
+ "grad_norm": 0.08525484362176303,
903
+ "learning_rate": 0.0001426838127356823,
904
+ "loss": 0.8538,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.7843137254901961,
909
+ "grad_norm": 0.08278907118602048,
910
+ "learning_rate": 0.0001352813774244565,
911
+ "loss": 0.8488,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.7904411764705882,
916
+ "grad_norm": 0.08784154420560207,
917
+ "learning_rate": 0.00012804597000454215,
918
+ "loss": 0.8556,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.7965686274509803,
923
+ "grad_norm": 0.08728645873334986,
924
+ "learning_rate": 0.00012098090402992085,
925
+ "loss": 0.8662,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.8026960784313726,
930
+ "grad_norm": 0.08368590385119791,
931
+ "learning_rate": 0.00011408941504437532,
932
+ "loss": 0.8541,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.8088235294117647,
937
+ "grad_norm": 0.12573965965935716,
938
+ "learning_rate": 0.00010737465909972776,
939
+ "loss": 0.8472,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.8149509803921569,
944
+ "grad_norm": 0.08047884146311494,
945
+ "learning_rate": 0.00010083971131048159,
946
+ "loss": 0.8492,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.821078431372549,
951
+ "grad_norm": 0.07946237543030905,
952
+ "learning_rate": 9.448756444553224e-05,
953
+ "loss": 0.8503,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.8272058823529411,
958
+ "grad_norm": 0.08237915177176067,
959
+ "learning_rate": 8.832112755758598e-05,
960
+ "loss": 0.848,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.8333333333333334,
965
+ "grad_norm": 0.08064567161653642,
966
+ "learning_rate": 8.234322465092047e-05,
967
+ "loss": 0.8489,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.8394607843137255,
972
+ "grad_norm": 0.08580518309504229,
973
+ "learning_rate": 7.655659338809329e-05,
974
+ "loss": 0.8481,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.8455882352941176,
979
+ "grad_norm": 0.08240105778083462,
980
+ "learning_rate": 7.096388383619079e-05,
981
+ "loss": 0.8434,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.8517156862745098,
986
+ "grad_norm": 0.10667272643643334,
987
+ "learning_rate": 6.556765725319525e-05,
988
+ "loss": 0.8477,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.8578431372549019,
993
+ "grad_norm": 0.09351829478479391,
994
+ "learning_rate": 6.037038491501978e-05,
995
+ "loss": 0.8521,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.8639705882352942,
1000
+ "grad_norm": 0.07805110075360967,
1001
+ "learning_rate": 5.53744469837551e-05,
1002
+ "loss": 0.843,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.8700980392156863,
1007
+ "grad_norm": 0.08112250711019013,
1008
+ "learning_rate": 5.058213141764151e-05,
1009
+ "loss": 0.8434,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.8762254901960784,
1014
+ "grad_norm": 0.09988697539615195,
1015
+ "learning_rate": 4.599563292326592e-05,
1016
+ "loss": 0.8483,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.8823529411764706,
1021
+ "grad_norm": 0.08158094478141424,
1022
+ "learning_rate": 4.161705195046761e-05,
1023
+ "loss": 0.8441,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.8884803921568627,
1028
+ "grad_norm": 0.08831427591672994,
1029
+ "learning_rate": 3.744839373040682e-05,
1030
+ "loss": 0.8465,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.8946078431372549,
1035
+ "grad_norm": 0.08621255370586131,
1036
+ "learning_rate": 3.349156735724274e-05,
1037
+ "loss": 0.8478,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.9007352941176471,
1042
+ "grad_norm": 0.07423138411019962,
1043
+ "learning_rate": 2.9748384913837522e-05,
1044
+ "loss": 0.8345,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.9068627450980392,
1049
+ "grad_norm": 0.0795306653386215,
1050
+ "learning_rate": 2.622056064188738e-05,
1051
+ "loss": 0.8537,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.9129901960784313,
1056
+ "grad_norm": 0.07964808233910256,
1057
+ "learning_rate": 2.2909710156863274e-05,
1058
+ "loss": 0.8512,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.9191176470588235,
1063
+ "grad_norm": 0.08073502455884987,
1064
+ "learning_rate": 1.981734970811644e-05,
1065
+ "loss": 0.8415,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.9252450980392157,
1070
+ "grad_norm": 0.07585958934986796,
1071
+ "learning_rate": 1.6944895484492072e-05,
1072
+ "loss": 0.8521,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.9313725490196079,
1077
+ "grad_norm": 0.08108459367268084,
1078
+ "learning_rate": 1.429366296576623e-05,
1079
+ "loss": 0.851,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.9375,
1084
+ "grad_norm": 0.08450154778950293,
1085
+ "learning_rate": 1.1864866320203115e-05,
1086
+ "loss": 0.8478,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.9436274509803921,
1091
+ "grad_norm": 0.08368284039729793,
1092
+ "learning_rate": 9.659617848510882e-06,
1093
+ "loss": 0.8447,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.9497549019607843,
1098
+ "grad_norm": 0.08046653108562293,
1099
+ "learning_rate": 7.678927474447817e-06,
1100
+ "loss": 0.8443,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.9558823529411765,
1105
+ "grad_norm": 0.08163069514122503,
1106
+ "learning_rate": 5.923702282314092e-06,
1107
+ "loss": 0.8467,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.9620098039215687,
1112
+ "grad_norm": 0.07894532908798362,
1113
+ "learning_rate": 4.394746101540115e-06,
1114
+ "loss": 0.8421,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.9681372549019608,
1119
+ "grad_norm": 0.08066759347765237,
1120
+ "learning_rate": 3.092759138561607e-06,
1121
+ "loss": 0.8403,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.9742647058823529,
1126
+ "grad_norm": 0.08225885021056388,
1127
+ "learning_rate": 2.018337656150726e-06,
1128
+ "loss": 0.8459,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.9803921568627451,
1133
+ "grad_norm": 0.0939601026942546,
1134
+ "learning_rate": 1.1719737003492159e-06,
1135
+ "loss": 0.8385,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.9865196078431373,
1140
+ "grad_norm": 0.07754259049318248,
1141
+ "learning_rate": 5.540548751292173e-07,
1142
+ "loss": 0.8343,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.9926470588235294,
1147
+ "grad_norm": 0.08221470163380953,
1148
+ "learning_rate": 1.6486416488459277e-07,
1149
+ "loss": 0.8475,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.9987745098039216,
1154
+ "grad_norm": 0.08134157509220469,
1155
+ "learning_rate": 4.579804834703438e-09,
1156
+ "loss": 0.8399,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 1.0,
1161
+ "eval_loss": 1.202902913093567,
1162
+ "eval_runtime": 113.99,
1163
+ "eval_samples_per_second": 183.709,
1164
+ "eval_steps_per_second": 5.746,
1165
+ "step": 816
1166
+ },
1167
+ {
1168
+ "epoch": 1.0,
1169
+ "step": 816,
1170
+ "total_flos": 80063181619200.0,
1171
+ "train_loss": 0.9145085595402063,
1172
+ "train_runtime": 1902.7506,
1173
+ "train_samples_per_second": 54.885,
1174
+ "train_steps_per_second": 0.429
1175
+ }
1176
+ ],
1177
+ "logging_steps": 5,
1178
+ "max_steps": 816,
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": 80063181619200.0,
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 sha256:12a9a33d258da7c5a8d74e680d5374bc12f9dafc4e54f34a88d1cc9259dfaa7c
3
+ size 6456
vocab.json ADDED
The diff for this file is too large to render. See raw diff