loubnabnl HF staff commited on
Commit
749c6e9
1 Parent(s): f66bfa0

Model save

Browse files
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-ep2
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/0xku06ks)
19
+ # smollm-350M-instruct-test2-ep2
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: 1.1973
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: 2
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss |
59
+ |:-------------:|:-----:|:----:|:---------------:|
60
+ | 0.8575 | 1.0 | 816 | 1.2251 |
61
+ | 0.7238 | 2.0 | 1632 | 1.1973 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.42.3
67
+ - Pytorch 2.1.2
68
+ - Datasets 2.20.0
69
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 160150899916800.0,
4
+ "train_loss": 0.8347952699690473,
5
+ "train_runtime": 3713.7533,
6
+ "train_samples": 319078,
7
+ "train_samples_per_second": 56.241,
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 sha256:640015f1937a908787ccf252e2bcf1697b9fb0fd1d89412445e96847c726ed7e
3
+ size 723674912
runs/Aug12_15-34-38_ip-26-0-166-125/events.out.tfevents.1723476927.ip-26-0-166-125.2357729.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d48657a3f5bf97651684d6f5a5f905dddeed80bffed0b765b93b58a7a5c69b3
3
+ size 74938
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": 2.0,
3
+ "total_flos": 160150899916800.0,
4
+ "train_loss": 0.8347952699690473,
5
+ "train_runtime": 3713.7533,
6
+ "train_samples": 319078,
7
+ "train_samples_per_second": 56.241,
8
+ "train_steps_per_second": 0.439
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,2347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1632,
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": 1.6059832937437346,
14
+ "learning_rate": 6.0975609756097564e-06,
15
+ "loss": 1.3541,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.006127450980392157,
20
+ "grad_norm": 1.5281382037952618,
21
+ "learning_rate": 3.048780487804878e-05,
22
+ "loss": 1.3583,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.012254901960784314,
27
+ "grad_norm": 0.5993529609680898,
28
+ "learning_rate": 6.097560975609756e-05,
29
+ "loss": 1.3375,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.01838235294117647,
34
+ "grad_norm": 0.7098761948973563,
35
+ "learning_rate": 9.146341463414634e-05,
36
+ "loss": 1.2793,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.024509803921568627,
41
+ "grad_norm": 0.4448928165735333,
42
+ "learning_rate": 0.00012195121951219512,
43
+ "loss": 1.2037,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.030637254901960783,
48
+ "grad_norm": 0.40161131951951523,
49
+ "learning_rate": 0.0001524390243902439,
50
+ "loss": 1.1336,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.03676470588235294,
55
+ "grad_norm": 0.2541806870693389,
56
+ "learning_rate": 0.00018292682926829268,
57
+ "loss": 1.1063,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.0428921568627451,
62
+ "grad_norm": 0.1491059867354642,
63
+ "learning_rate": 0.00021341463414634146,
64
+ "loss": 1.0795,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.049019607843137254,
69
+ "grad_norm": 0.14162648176415202,
70
+ "learning_rate": 0.00024390243902439024,
71
+ "loss": 1.0729,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.05514705882352941,
76
+ "grad_norm": 0.14138145278805817,
77
+ "learning_rate": 0.00027439024390243905,
78
+ "loss": 1.0504,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.061274509803921566,
83
+ "grad_norm": 0.11598136180137979,
84
+ "learning_rate": 0.0003048780487804878,
85
+ "loss": 1.0378,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.06740196078431372,
90
+ "grad_norm": 0.14589294245833054,
91
+ "learning_rate": 0.0003353658536585366,
92
+ "loss": 1.0446,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.07352941176470588,
97
+ "grad_norm": 0.14730649378552943,
98
+ "learning_rate": 0.00036585365853658537,
99
+ "loss": 1.0333,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.07965686274509803,
104
+ "grad_norm": 0.11759388636190853,
105
+ "learning_rate": 0.0003963414634146342,
106
+ "loss": 1.0143,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.0857843137254902,
111
+ "grad_norm": 0.12311842814802663,
112
+ "learning_rate": 0.0004268292682926829,
113
+ "loss": 1.0148,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.09191176470588236,
118
+ "grad_norm": 0.11751325803408062,
119
+ "learning_rate": 0.00045731707317073173,
120
+ "loss": 1.0176,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.09803921568627451,
125
+ "grad_norm": 0.13732149342206665,
126
+ "learning_rate": 0.0004878048780487805,
127
+ "loss": 1.0042,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.10416666666666667,
132
+ "grad_norm": 0.11309991089195273,
133
+ "learning_rate": 0.0005182926829268293,
134
+ "loss": 1.0065,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.11029411764705882,
139
+ "grad_norm": 0.12583526404678766,
140
+ "learning_rate": 0.0005487804878048781,
141
+ "loss": 1.0149,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.11642156862745098,
146
+ "grad_norm": 0.12017272173906957,
147
+ "learning_rate": 0.0005792682926829268,
148
+ "loss": 0.9948,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.12254901960784313,
153
+ "grad_norm": 0.11719746827044987,
154
+ "learning_rate": 0.0006097560975609756,
155
+ "loss": 0.9905,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.12867647058823528,
160
+ "grad_norm": 0.13729668356371552,
161
+ "learning_rate": 0.0006402439024390244,
162
+ "loss": 0.9977,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.13480392156862744,
167
+ "grad_norm": 0.12981775917103477,
168
+ "learning_rate": 0.0006707317073170732,
169
+ "loss": 1.0017,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.1409313725490196,
174
+ "grad_norm": 0.13870526825011106,
175
+ "learning_rate": 0.0007012195121951219,
176
+ "loss": 0.9997,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.14705882352941177,
181
+ "grad_norm": 0.12747253256734123,
182
+ "learning_rate": 0.0007317073170731707,
183
+ "loss": 0.9877,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.15318627450980393,
188
+ "grad_norm": 0.12869096982052203,
189
+ "learning_rate": 0.0007621951219512195,
190
+ "loss": 0.9823,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.15931372549019607,
195
+ "grad_norm": 0.12889388640011323,
196
+ "learning_rate": 0.0007926829268292683,
197
+ "loss": 0.9774,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.16544117647058823,
202
+ "grad_norm": 0.13890909917337924,
203
+ "learning_rate": 0.000823170731707317,
204
+ "loss": 0.9874,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.1715686274509804,
209
+ "grad_norm": 0.167350127299137,
210
+ "learning_rate": 0.0008536585365853659,
211
+ "loss": 0.9855,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.17769607843137256,
216
+ "grad_norm": 0.12637500439423752,
217
+ "learning_rate": 0.0008841463414634147,
218
+ "loss": 0.9837,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.18382352941176472,
223
+ "grad_norm": 0.13036804871454152,
224
+ "learning_rate": 0.0009146341463414635,
225
+ "loss": 0.9846,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.18995098039215685,
230
+ "grad_norm": 0.13716320964191064,
231
+ "learning_rate": 0.0009451219512195122,
232
+ "loss": 0.9742,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.19607843137254902,
237
+ "grad_norm": 0.1505410439189676,
238
+ "learning_rate": 0.000975609756097561,
239
+ "loss": 0.9657,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.20220588235294118,
244
+ "grad_norm": 0.13939847463577426,
245
+ "learning_rate": 0.0009999988550474805,
246
+ "loss": 0.982,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.20833333333333334,
251
+ "grad_norm": 0.1723912783342495,
252
+ "learning_rate": 0.000999958782259877,
253
+ "loss": 0.9771,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.21446078431372548,
258
+ "grad_norm": 0.20339647033601935,
259
+ "learning_rate": 0.0009998614670898504,
260
+ "loss": 0.9742,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.22058823529411764,
265
+ "grad_norm": 0.1805520187680447,
266
+ "learning_rate": 0.0009997069206794246,
267
+ "loss": 0.9724,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.2267156862745098,
272
+ "grad_norm": 0.14101202234864954,
273
+ "learning_rate": 0.000999495160723267,
274
+ "loss": 0.9699,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.23284313725490197,
279
+ "grad_norm": 0.14408773000983136,
280
+ "learning_rate": 0.0009992262114666653,
281
+ "loss": 0.9721,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.23897058823529413,
286
+ "grad_norm": 0.12211770445331499,
287
+ "learning_rate": 0.0009989001037027502,
288
+ "loss": 0.9638,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.24509803921568626,
293
+ "grad_norm": 0.11058292325672553,
294
+ "learning_rate": 0.0009985168747689707,
295
+ "loss": 0.9613,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.2512254901960784,
300
+ "grad_norm": 0.151326097792135,
301
+ "learning_rate": 0.0009980765685428175,
302
+ "loss": 0.9784,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.25735294117647056,
307
+ "grad_norm": 0.13748406413323222,
308
+ "learning_rate": 0.0009975792354368017,
309
+ "loss": 0.9578,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.26348039215686275,
314
+ "grad_norm": 0.13529789016829663,
315
+ "learning_rate": 0.000997024932392681,
316
+ "loss": 0.9561,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.2696078431372549,
321
+ "grad_norm": 0.11913360946345405,
322
+ "learning_rate": 0.0009964137228749407,
323
+ "loss": 0.9587,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.2757352941176471,
328
+ "grad_norm": 0.11311287494378686,
329
+ "learning_rate": 0.0009957456768635274,
330
+ "loss": 0.9534,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.2818627450980392,
335
+ "grad_norm": 0.1687787460034738,
336
+ "learning_rate": 0.000995020870845837,
337
+ "loss": 0.9483,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.28799019607843135,
342
+ "grad_norm": 0.13894852921173279,
343
+ "learning_rate": 0.000994239387807957,
344
+ "loss": 0.9465,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.29411764705882354,
349
+ "grad_norm": 0.15098532770679463,
350
+ "learning_rate": 0.0009934013172251653,
351
+ "loss": 0.9512,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.3002450980392157,
356
+ "grad_norm": 0.1603820773467054,
357
+ "learning_rate": 0.0009925067550516852,
358
+ "loss": 0.9364,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.30637254901960786,
363
+ "grad_norm": 0.20531045303348816,
364
+ "learning_rate": 0.0009915558037097002,
365
+ "loss": 0.9436,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.3125,
370
+ "grad_norm": 0.1373133786573118,
371
+ "learning_rate": 0.0009905485720776265,
372
+ "loss": 0.934,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.31862745098039214,
377
+ "grad_norm": 1.8470429009125096,
378
+ "learning_rate": 0.0009894851754776472,
379
+ "loss": 0.9526,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.3247549019607843,
384
+ "grad_norm": 0.11771908587868915,
385
+ "learning_rate": 0.000988365735662509,
386
+ "loss": 0.9513,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.33088235294117646,
391
+ "grad_norm": 0.14600554728304563,
392
+ "learning_rate": 0.0009871903808015812,
393
+ "loss": 0.9424,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.33700980392156865,
398
+ "grad_norm": 0.12078857521986237,
399
+ "learning_rate": 0.0009859592454661823,
400
+ "loss": 0.9501,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.3431372549019608,
405
+ "grad_norm": 0.12236086569601477,
406
+ "learning_rate": 0.0009846724706141716,
407
+ "loss": 0.9445,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.3492647058823529,
412
+ "grad_norm": 0.13112435126866281,
413
+ "learning_rate": 0.0009833302035738107,
414
+ "loss": 0.9363,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.3553921568627451,
419
+ "grad_norm": 0.14235863463223497,
420
+ "learning_rate": 0.0009819325980268945,
421
+ "loss": 0.9485,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.36151960784313725,
426
+ "grad_norm": 0.12952693104841728,
427
+ "learning_rate": 0.0009804798139911568,
428
+ "loss": 0.9421,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.36764705882352944,
433
+ "grad_norm": 0.11889525565491425,
434
+ "learning_rate": 0.0009789720178019483,
435
+ "loss": 0.9321,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.3737745098039216,
440
+ "grad_norm": 0.10497064780361466,
441
+ "learning_rate": 0.0009774093820931922,
442
+ "loss": 0.9383,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.3799019607843137,
447
+ "grad_norm": 0.1297312332951932,
448
+ "learning_rate": 0.0009757920857776188,
449
+ "loss": 0.9315,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.3860294117647059,
454
+ "grad_norm": 0.12939401003239853,
455
+ "learning_rate": 0.0009741203140262813,
456
+ "loss": 0.931,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.39215686274509803,
461
+ "grad_norm": 0.1724687096774714,
462
+ "learning_rate": 0.0009723942582473544,
463
+ "loss": 0.9244,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.39828431372549017,
468
+ "grad_norm": 0.1440746949158844,
469
+ "learning_rate": 0.000970614116064219,
470
+ "loss": 0.9186,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.40441176470588236,
475
+ "grad_norm": 0.11601098074712127,
476
+ "learning_rate": 0.0009687800912928362,
477
+ "loss": 0.9331,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.4105392156862745,
482
+ "grad_norm": 0.16676922492027155,
483
+ "learning_rate": 0.0009668923939184109,
484
+ "loss": 0.9282,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.4166666666666667,
489
+ "grad_norm": 0.16264723211095694,
490
+ "learning_rate": 0.0009649512400713498,
491
+ "loss": 0.931,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.4227941176470588,
496
+ "grad_norm": 0.12835068212058262,
497
+ "learning_rate": 0.000962956852002516,
498
+ "loss": 0.9212,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.42892156862745096,
503
+ "grad_norm": 0.11722967905017813,
504
+ "learning_rate": 0.0009609094580577824,
505
+ "loss": 0.9301,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.43504901960784315,
510
+ "grad_norm": 0.11753159563989828,
511
+ "learning_rate": 0.0009588092926518875,
512
+ "loss": 0.9181,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.4411764705882353,
517
+ "grad_norm": 0.3058794099499992,
518
+ "learning_rate": 0.0009566565962415959,
519
+ "loss": 0.9276,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.44730392156862747,
524
+ "grad_norm": 0.11638001282284417,
525
+ "learning_rate": 0.0009544516152981679,
526
+ "loss": 0.9187,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.4534313725490196,
531
+ "grad_norm": 0.0979888983879341,
532
+ "learning_rate": 0.0009521946022791401,
533
+ "loss": 0.9178,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.45955882352941174,
538
+ "grad_norm": 0.12474491987381439,
539
+ "learning_rate": 0.0009498858155994194,
540
+ "loss": 0.9248,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.46568627450980393,
545
+ "grad_norm": 0.11539100379640589,
546
+ "learning_rate": 0.0009475255196016972,
547
+ "loss": 0.9082,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.47181372549019607,
552
+ "grad_norm": 0.11060768973607205,
553
+ "learning_rate": 0.0009451139845261834,
554
+ "loss": 0.913,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.47794117647058826,
559
+ "grad_norm": 0.10933884625046772,
560
+ "learning_rate": 0.0009426514864796647,
561
+ "loss": 0.9164,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.4840686274509804,
566
+ "grad_norm": 0.12110040734071437,
567
+ "learning_rate": 0.000940138307403893,
568
+ "loss": 0.918,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.49019607843137253,
573
+ "grad_norm": 0.12516912467922992,
574
+ "learning_rate": 0.0009375747350433044,
575
+ "loss": 0.9099,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.4963235294117647,
580
+ "grad_norm": 0.15405339011075656,
581
+ "learning_rate": 0.0009349610629120733,
582
+ "loss": 0.9153,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.5024509803921569,
587
+ "grad_norm": 0.15983105881560317,
588
+ "learning_rate": 0.0009322975902605082,
589
+ "loss": 0.9139,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.508578431372549,
594
+ "grad_norm": 0.12456698491529061,
595
+ "learning_rate": 0.000929584622040788,
596
+ "loss": 0.9196,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.5147058823529411,
601
+ "grad_norm": 0.39391857600951824,
602
+ "learning_rate": 0.0009268224688720474,
603
+ "loss": 0.911,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.5208333333333334,
608
+ "grad_norm": 0.135863544001222,
609
+ "learning_rate": 0.0009240114470048129,
610
+ "loss": 0.9082,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.5269607843137255,
615
+ "grad_norm": 0.16266736226237394,
616
+ "learning_rate": 0.0009211518782847931,
617
+ "loss": 0.9208,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.5330882352941176,
622
+ "grad_norm": 0.14823148129955332,
623
+ "learning_rate": 0.0009182440901160307,
624
+ "loss": 0.9243,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.5392156862745098,
629
+ "grad_norm": 0.14300453285294948,
630
+ "learning_rate": 0.0009152884154234145,
631
+ "loss": 0.9082,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.5453431372549019,
636
+ "grad_norm": 0.11464976577167021,
637
+ "learning_rate": 0.0009122851926145641,
638
+ "loss": 0.9066,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.5514705882352942,
643
+ "grad_norm": 0.1380022527629278,
644
+ "learning_rate": 0.0009092347655410818,
645
+ "loss": 0.9059,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.5575980392156863,
650
+ "grad_norm": 0.12505924658066125,
651
+ "learning_rate": 0.0009061374834591849,
652
+ "loss": 0.9106,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.5637254901960784,
657
+ "grad_norm": 0.14573814560545809,
658
+ "learning_rate": 0.0009029937009897176,
659
+ "loss": 0.9085,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.5698529411764706,
664
+ "grad_norm": 0.12549980653285886,
665
+ "learning_rate": 0.0008998037780775488,
666
+ "loss": 0.9134,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.5759803921568627,
671
+ "grad_norm": 1.0091372919881914,
672
+ "learning_rate": 0.0008965680799503608,
673
+ "loss": 0.9012,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.5821078431372549,
678
+ "grad_norm": 0.12482100803406715,
679
+ "learning_rate": 0.0008932869770768326,
680
+ "loss": 0.9083,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.5882352941176471,
685
+ "grad_norm": 0.16842450336753725,
686
+ "learning_rate": 0.0008899608451242233,
687
+ "loss": 0.906,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.5943627450980392,
692
+ "grad_norm": 0.37435753717247394,
693
+ "learning_rate": 0.0008865900649153606,
694
+ "loss": 0.9116,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.6004901960784313,
699
+ "grad_norm": 0.1504221848097725,
700
+ "learning_rate": 0.0008831750223850389,
701
+ "loss": 0.9069,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.6066176470588235,
706
+ "grad_norm": 0.6779799933680686,
707
+ "learning_rate": 0.0008797161085358317,
708
+ "loss": 0.8935,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.6127450980392157,
713
+ "grad_norm": 0.4033225235584718,
714
+ "learning_rate": 0.0008762137193933241,
715
+ "loss": 0.898,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.6188725490196079,
720
+ "grad_norm": 0.12597786237207237,
721
+ "learning_rate": 0.0008726682559607706,
722
+ "loss": 0.8965,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.625,
727
+ "grad_norm": 0.12434445433374085,
728
+ "learning_rate": 0.0008690801241731818,
729
+ "loss": 0.9195,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.6311274509803921,
734
+ "grad_norm": 0.11180950505927977,
735
+ "learning_rate": 0.0008654497348508476,
736
+ "loss": 0.8856,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.6372549019607843,
741
+ "grad_norm": 0.11471149278729899,
742
+ "learning_rate": 0.0008617775036523015,
743
+ "loss": 0.888,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.6433823529411765,
748
+ "grad_norm": 0.10661278460678202,
749
+ "learning_rate": 0.000858063851026728,
750
+ "loss": 0.8844,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.6495098039215687,
755
+ "grad_norm": 0.13323867388840102,
756
+ "learning_rate": 0.0008543092021658259,
757
+ "loss": 0.8917,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.6556372549019608,
762
+ "grad_norm": 0.11051797161585711,
763
+ "learning_rate": 0.0008505139869551248,
764
+ "loss": 0.8966,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.6617647058823529,
769
+ "grad_norm": 0.10201940027044504,
770
+ "learning_rate": 0.0008466786399247663,
771
+ "loss": 0.9086,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.6678921568627451,
776
+ "grad_norm": 0.11341681063010137,
777
+ "learning_rate": 0.000842803600199753,
778
+ "loss": 0.885,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.6740196078431373,
783
+ "grad_norm": 0.11249706294845149,
784
+ "learning_rate": 0.0008388893114496705,
785
+ "loss": 0.8761,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.6801470588235294,
790
+ "grad_norm": 0.10372930065250463,
791
+ "learning_rate": 0.0008349362218378904,
792
+ "loss": 0.8875,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.6862745098039216,
797
+ "grad_norm": 0.1473106555936528,
798
+ "learning_rate": 0.0008309447839702582,
799
+ "loss": 0.8813,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.6924019607843137,
804
+ "grad_norm": 0.11251651358057665,
805
+ "learning_rate": 0.0008269154548432722,
806
+ "loss": 0.8856,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.6985294117647058,
811
+ "grad_norm": 0.18983642337639475,
812
+ "learning_rate": 0.0008228486957917607,
813
+ "loss": 0.8893,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.7046568627450981,
818
+ "grad_norm": 0.1926017574087406,
819
+ "learning_rate": 0.0008187449724360605,
820
+ "loss": 0.8853,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.7107843137254902,
825
+ "grad_norm": 0.10232469720003605,
826
+ "learning_rate": 0.0008146047546287076,
827
+ "loss": 0.8786,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.7169117647058824,
832
+ "grad_norm": 0.1029258945252611,
833
+ "learning_rate": 0.0008104285164006415,
834
+ "loss": 0.8799,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.7230392156862745,
839
+ "grad_norm": 0.14002711821151018,
840
+ "learning_rate": 0.0008062167359069301,
841
+ "loss": 0.8827,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.7291666666666666,
846
+ "grad_norm": 0.11144023976662691,
847
+ "learning_rate": 0.0008019698953720256,
848
+ "loss": 0.8832,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.7352941176470589,
853
+ "grad_norm": 0.12878152634910894,
854
+ "learning_rate": 0.000797688481034551,
855
+ "loss": 0.8852,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.741421568627451,
860
+ "grad_norm": 0.12427328372120441,
861
+ "learning_rate": 0.0007933729830916297,
862
+ "loss": 0.8807,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.7475490196078431,
867
+ "grad_norm": 0.10823708822180528,
868
+ "learning_rate": 0.00078902389564276,
869
+ "loss": 0.8839,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.7536764705882353,
874
+ "grad_norm": 0.106769228793293,
875
+ "learning_rate": 0.0007846417166332445,
876
+ "loss": 0.8756,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.7598039215686274,
881
+ "grad_norm": 0.10610630308145001,
882
+ "learning_rate": 0.0007802269477971771,
883
+ "loss": 0.8786,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.7659313725490197,
888
+ "grad_norm": 0.11560264922747754,
889
+ "learning_rate": 0.000775780094599998,
890
+ "loss": 0.8769,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.7720588235294118,
895
+ "grad_norm": 0.14907985785369013,
896
+ "learning_rate": 0.0007713016661806211,
897
+ "loss": 0.8795,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.7781862745098039,
902
+ "grad_norm": 0.11129324500895409,
903
+ "learning_rate": 0.00076679217529314,
904
+ "loss": 0.875,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.7843137254901961,
909
+ "grad_norm": 0.14839037572821354,
910
+ "learning_rate": 0.0007622521382481208,
911
+ "loss": 0.8703,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.7904411764705882,
916
+ "grad_norm": 0.13899413539068264,
917
+ "learning_rate": 0.0007576820748534875,
918
+ "loss": 0.8763,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.7965686274509803,
923
+ "grad_norm": 0.11601000036057739,
924
+ "learning_rate": 0.0007530825083550073,
925
+ "loss": 0.887,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.8026960784313726,
930
+ "grad_norm": 0.10442455243797781,
931
+ "learning_rate": 0.0007484539653763815,
932
+ "loss": 0.8751,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.8088235294117647,
937
+ "grad_norm": 0.12520557374066849,
938
+ "learning_rate": 0.0007437969758589507,
939
+ "loss": 0.8673,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.8149509803921569,
944
+ "grad_norm": 0.11448612465079618,
945
+ "learning_rate": 0.0007391120730010193,
946
+ "loss": 0.8694,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.821078431372549,
951
+ "grad_norm": 0.13153196077249837,
952
+ "learning_rate": 0.0007343997931968067,
953
+ "loss": 0.87,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.8272058823529411,
958
+ "grad_norm": 0.11840806919932775,
959
+ "learning_rate": 0.0007296606759750351,
960
+ "loss": 0.8672,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.8333333333333334,
965
+ "grad_norm": 0.09757556694809401,
966
+ "learning_rate": 0.0007248952639371542,
967
+ "loss": 0.8676,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.8394607843137255,
972
+ "grad_norm": 0.09022546372550531,
973
+ "learning_rate": 0.0007201041026952188,
974
+ "loss": 0.8664,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.8455882352941176,
979
+ "grad_norm": 0.10331609924034306,
980
+ "learning_rate": 0.0007152877408094178,
981
+ "loss": 0.8616,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.8517156862745098,
986
+ "grad_norm": 0.12505516849755346,
987
+ "learning_rate": 0.0007104467297252677,
988
+ "loss": 0.8652,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.8578431372549019,
993
+ "grad_norm": 0.09465790589490469,
994
+ "learning_rate": 0.0007055816237104753,
995
+ "loss": 0.8699,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.8639705882352942,
1000
+ "grad_norm": 0.12150502920638975,
1001
+ "learning_rate": 0.0007006929797914775,
1002
+ "loss": 0.8597,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.8700980392156863,
1007
+ "grad_norm": 0.10318640070426116,
1008
+ "learning_rate": 0.0006957813576896647,
1009
+ "loss": 0.8603,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.8762254901960784,
1014
+ "grad_norm": 0.11768219039546857,
1015
+ "learning_rate": 0.000690847319757296,
1016
+ "loss": 0.8653,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.8823529411764706,
1021
+ "grad_norm": 0.13084092032465588,
1022
+ "learning_rate": 0.000685891430913113,
1023
+ "loss": 0.8599,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.8884803921568627,
1028
+ "grad_norm": 0.1378907468788972,
1029
+ "learning_rate": 0.0006809142585776604,
1030
+ "loss": 0.8625,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.8946078431372549,
1035
+ "grad_norm": 0.1137277604032764,
1036
+ "learning_rate": 0.0006759163726083191,
1037
+ "loss": 0.8626,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.9007352941176471,
1042
+ "grad_norm": 0.10001539507212627,
1043
+ "learning_rate": 0.0006708983452340609,
1044
+ "loss": 0.849,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.9068627450980392,
1049
+ "grad_norm": 0.10484673231574948,
1050
+ "learning_rate": 0.0006658607509899319,
1051
+ "loss": 0.8682,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.9129901960784313,
1056
+ "grad_norm": 0.15431021500080286,
1057
+ "learning_rate": 0.0006608041666512712,
1058
+ "loss": 0.8645,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.9191176470588235,
1063
+ "grad_norm": 0.11219846062082936,
1064
+ "learning_rate": 0.0006557291711676738,
1065
+ "loss": 0.8541,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.9252450980392157,
1070
+ "grad_norm": 0.11968297539967529,
1071
+ "learning_rate": 0.0006506363455967037,
1072
+ "loss": 0.8645,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.9313725490196079,
1077
+ "grad_norm": 0.1421862868626235,
1078
+ "learning_rate": 0.0006455262730373672,
1079
+ "loss": 0.8628,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.9375,
1084
+ "grad_norm": 0.09419342625695648,
1085
+ "learning_rate": 0.0006403995385633503,
1086
+ "loss": 0.859,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.9436274509803921,
1091
+ "grad_norm": 0.10436946711990462,
1092
+ "learning_rate": 0.0006352567291560318,
1093
+ "loss": 0.8564,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.9497549019607843,
1098
+ "grad_norm": 0.11378998198564375,
1099
+ "learning_rate": 0.0006300984336372771,
1100
+ "loss": 0.8552,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.9558823529411765,
1105
+ "grad_norm": 0.11204753073504012,
1106
+ "learning_rate": 0.0006249252426020216,
1107
+ "loss": 0.8567,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.9620098039215687,
1112
+ "grad_norm": 0.13969543336270682,
1113
+ "learning_rate": 0.000619737748350651,
1114
+ "loss": 0.8521,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.9681372549019608,
1119
+ "grad_norm": 0.10178000324550646,
1120
+ "learning_rate": 0.0006145365448211866,
1121
+ "loss": 0.849,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.9742647058823529,
1126
+ "grad_norm": 0.28123512574152176,
1127
+ "learning_rate": 0.0006093222275212822,
1128
+ "loss": 0.8539,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.9803921568627451,
1133
+ "grad_norm": 0.11687237794199178,
1134
+ "learning_rate": 0.0006040953934600423,
1135
+ "loss": 0.8466,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.9865196078431373,
1140
+ "grad_norm": 0.08664193399778343,
1141
+ "learning_rate": 0.0005988566410796687,
1142
+ "loss": 0.8408,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.9926470588235294,
1147
+ "grad_norm": 0.1332025987779646,
1148
+ "learning_rate": 0.0005936065701869403,
1149
+ "loss": 0.8545,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.9987745098039216,
1154
+ "grad_norm": 2.6257846647757304,
1155
+ "learning_rate": 0.0005883457818845414,
1156
+ "loss": 0.8575,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 1.0,
1161
+ "eval_loss": 1.2250986099243164,
1162
+ "eval_runtime": 111.2787,
1163
+ "eval_samples_per_second": 188.185,
1164
+ "eval_steps_per_second": 5.886,
1165
+ "step": 816
1166
+ },
1167
+ {
1168
+ "epoch": 1.0049019607843137,
1169
+ "grad_norm": 1.2727033946666415,
1170
+ "learning_rate": 0.0005830748785022368,
1171
+ "loss": 0.7791,
1172
+ "step": 820
1173
+ },
1174
+ {
1175
+ "epoch": 1.0110294117647058,
1176
+ "grad_norm": 0.1911261436318345,
1177
+ "learning_rate": 0.0005777944635279099,
1178
+ "loss": 0.7643,
1179
+ "step": 825
1180
+ },
1181
+ {
1182
+ "epoch": 1.017156862745098,
1183
+ "grad_norm": 0.1586922694379843,
1184
+ "learning_rate": 0.0005725051415384657,
1185
+ "loss": 0.7516,
1186
+ "step": 830
1187
+ },
1188
+ {
1189
+ "epoch": 1.0232843137254901,
1190
+ "grad_norm": 0.11186631342494315,
1191
+ "learning_rate": 0.0005672075181306108,
1192
+ "loss": 0.7526,
1193
+ "step": 835
1194
+ },
1195
+ {
1196
+ "epoch": 1.0294117647058822,
1197
+ "grad_norm": 0.13268928121380016,
1198
+ "learning_rate": 0.0005619021998515165,
1199
+ "loss": 0.7699,
1200
+ "step": 840
1201
+ },
1202
+ {
1203
+ "epoch": 1.0355392156862746,
1204
+ "grad_norm": 0.11229206406982119,
1205
+ "learning_rate": 0.0005565897941293721,
1206
+ "loss": 0.7813,
1207
+ "step": 845
1208
+ },
1209
+ {
1210
+ "epoch": 1.0416666666666667,
1211
+ "grad_norm": 0.12012493868077331,
1212
+ "learning_rate": 0.000551270909203838,
1213
+ "loss": 0.7606,
1214
+ "step": 850
1215
+ },
1216
+ {
1217
+ "epoch": 1.0477941176470589,
1218
+ "grad_norm": 0.11528601274141542,
1219
+ "learning_rate": 0.0005459461540564057,
1220
+ "loss": 0.7597,
1221
+ "step": 855
1222
+ },
1223
+ {
1224
+ "epoch": 1.053921568627451,
1225
+ "grad_norm": 0.10690663798544056,
1226
+ "learning_rate": 0.0005406161383406731,
1227
+ "loss": 0.7595,
1228
+ "step": 860
1229
+ },
1230
+ {
1231
+ "epoch": 1.0600490196078431,
1232
+ "grad_norm": 0.13779006322984594,
1233
+ "learning_rate": 0.000535281472312543,
1234
+ "loss": 0.7604,
1235
+ "step": 865
1236
+ },
1237
+ {
1238
+ "epoch": 1.0661764705882353,
1239
+ "grad_norm": 0.1286321993738431,
1240
+ "learning_rate": 0.0005299427667603515,
1241
+ "loss": 0.7591,
1242
+ "step": 870
1243
+ },
1244
+ {
1245
+ "epoch": 1.0723039215686274,
1246
+ "grad_norm": 0.11691581398274645,
1247
+ "learning_rate": 0.0005246006329349376,
1248
+ "loss": 0.7539,
1249
+ "step": 875
1250
+ },
1251
+ {
1252
+ "epoch": 1.0784313725490196,
1253
+ "grad_norm": 0.1359966051449655,
1254
+ "learning_rate": 0.0005192556824796568,
1255
+ "loss": 0.7478,
1256
+ "step": 880
1257
+ },
1258
+ {
1259
+ "epoch": 1.0845588235294117,
1260
+ "grad_norm": 0.11784308765572785,
1261
+ "learning_rate": 0.0005139085273603527,
1262
+ "loss": 0.7526,
1263
+ "step": 885
1264
+ },
1265
+ {
1266
+ "epoch": 1.0906862745098038,
1267
+ "grad_norm": 0.08243234125547984,
1268
+ "learning_rate": 0.0005085597797952905,
1269
+ "loss": 0.7503,
1270
+ "step": 890
1271
+ },
1272
+ {
1273
+ "epoch": 1.0968137254901962,
1274
+ "grad_norm": 0.10687199207970824,
1275
+ "learning_rate": 0.0005032100521850608,
1276
+ "loss": 0.7639,
1277
+ "step": 895
1278
+ },
1279
+ {
1280
+ "epoch": 1.1029411764705883,
1281
+ "grad_norm": 0.09754168316674887,
1282
+ "learning_rate": 0.0004978599570424639,
1283
+ "loss": 0.7648,
1284
+ "step": 900
1285
+ },
1286
+ {
1287
+ "epoch": 1.1090686274509804,
1288
+ "grad_norm": 0.09597242384268918,
1289
+ "learning_rate": 0.0004925101069223802,
1290
+ "loss": 0.7618,
1291
+ "step": 905
1292
+ },
1293
+ {
1294
+ "epoch": 1.1151960784313726,
1295
+ "grad_norm": 0.16042928535903608,
1296
+ "learning_rate": 0.0004871611143516367,
1297
+ "loss": 0.7488,
1298
+ "step": 910
1299
+ },
1300
+ {
1301
+ "epoch": 1.1213235294117647,
1302
+ "grad_norm": 0.11558221571064126,
1303
+ "learning_rate": 0.00048181359175887594,
1304
+ "loss": 0.758,
1305
+ "step": 915
1306
+ },
1307
+ {
1308
+ "epoch": 1.1274509803921569,
1309
+ "grad_norm": 0.10187875911094818,
1310
+ "learning_rate": 0.0004764681514044362,
1311
+ "loss": 0.7548,
1312
+ "step": 920
1313
+ },
1314
+ {
1315
+ "epoch": 1.133578431372549,
1316
+ "grad_norm": 0.10845733289411896,
1317
+ "learning_rate": 0.0004711254053102521,
1318
+ "loss": 0.7447,
1319
+ "step": 925
1320
+ },
1321
+ {
1322
+ "epoch": 1.1397058823529411,
1323
+ "grad_norm": 0.12423589225823602,
1324
+ "learning_rate": 0.0004657859651897806,
1325
+ "loss": 0.7567,
1326
+ "step": 930
1327
+ },
1328
+ {
1329
+ "epoch": 1.1458333333333333,
1330
+ "grad_norm": 0.101823111875683,
1331
+ "learning_rate": 0.0004604504423779639,
1332
+ "loss": 0.7496,
1333
+ "step": 935
1334
+ },
1335
+ {
1336
+ "epoch": 1.1519607843137254,
1337
+ "grad_norm": 0.1490251916250933,
1338
+ "learning_rate": 0.00045511944776123513,
1339
+ "loss": 0.7476,
1340
+ "step": 940
1341
+ },
1342
+ {
1343
+ "epoch": 1.1580882352941178,
1344
+ "grad_norm": 0.0909899046261831,
1345
+ "learning_rate": 0.00044979359170757555,
1346
+ "loss": 0.7557,
1347
+ "step": 945
1348
+ },
1349
+ {
1350
+ "epoch": 1.1642156862745099,
1351
+ "grad_norm": 0.10504026034830631,
1352
+ "learning_rate": 0.00044447348399663056,
1353
+ "loss": 0.7551,
1354
+ "step": 950
1355
+ },
1356
+ {
1357
+ "epoch": 1.170343137254902,
1358
+ "grad_norm": 0.10154008572100809,
1359
+ "learning_rate": 0.00043915973374989326,
1360
+ "loss": 0.7553,
1361
+ "step": 955
1362
+ },
1363
+ {
1364
+ "epoch": 1.1764705882352942,
1365
+ "grad_norm": 0.0948668753989249,
1366
+ "learning_rate": 0.0004338529493609647,
1367
+ "loss": 0.7529,
1368
+ "step": 960
1369
+ },
1370
+ {
1371
+ "epoch": 1.1825980392156863,
1372
+ "grad_norm": 0.12214475449625242,
1373
+ "learning_rate": 0.0004285537384258951,
1374
+ "loss": 0.7544,
1375
+ "step": 965
1376
+ },
1377
+ {
1378
+ "epoch": 1.1887254901960784,
1379
+ "grad_norm": 0.10021333779503093,
1380
+ "learning_rate": 0.00042326270767361815,
1381
+ "loss": 0.7561,
1382
+ "step": 970
1383
+ },
1384
+ {
1385
+ "epoch": 1.1948529411764706,
1386
+ "grad_norm": 0.10089690279960518,
1387
+ "learning_rate": 0.0004179804628964839,
1388
+ "loss": 0.7473,
1389
+ "step": 975
1390
+ },
1391
+ {
1392
+ "epoch": 1.2009803921568627,
1393
+ "grad_norm": 0.09480462930649244,
1394
+ "learning_rate": 0.00041270760888089997,
1395
+ "loss": 0.7543,
1396
+ "step": 980
1397
+ },
1398
+ {
1399
+ "epoch": 1.2071078431372548,
1400
+ "grad_norm": 0.13593486404780272,
1401
+ "learning_rate": 0.000407444749338085,
1402
+ "loss": 0.7447,
1403
+ "step": 985
1404
+ },
1405
+ {
1406
+ "epoch": 1.213235294117647,
1407
+ "grad_norm": 0.09373417852720169,
1408
+ "learning_rate": 0.00040219248683494925,
1409
+ "loss": 0.7516,
1410
+ "step": 990
1411
+ },
1412
+ {
1413
+ "epoch": 1.219362745098039,
1414
+ "grad_norm": 0.09327325503229338,
1415
+ "learning_rate": 0.00039695142272510334,
1416
+ "loss": 0.7443,
1417
+ "step": 995
1418
+ },
1419
+ {
1420
+ "epoch": 1.2254901960784315,
1421
+ "grad_norm": 0.10034654814592268,
1422
+ "learning_rate": 0.0003917221570800065,
1423
+ "loss": 0.7475,
1424
+ "step": 1000
1425
+ },
1426
+ {
1427
+ "epoch": 1.2316176470588236,
1428
+ "grad_norm": 0.09837253795265176,
1429
+ "learning_rate": 0.0003865052886202621,
1430
+ "loss": 0.7438,
1431
+ "step": 1005
1432
+ },
1433
+ {
1434
+ "epoch": 1.2377450980392157,
1435
+ "grad_norm": 0.09051967236076873,
1436
+ "learning_rate": 0.000381301414647068,
1437
+ "loss": 0.7537,
1438
+ "step": 1010
1439
+ },
1440
+ {
1441
+ "epoch": 1.2438725490196079,
1442
+ "grad_norm": 0.08928603737077674,
1443
+ "learning_rate": 0.0003761111309738285,
1444
+ "loss": 0.7372,
1445
+ "step": 1015
1446
+ },
1447
+ {
1448
+ "epoch": 1.25,
1449
+ "grad_norm": 0.10153157943466443,
1450
+ "learning_rate": 0.0003709350318579371,
1451
+ "loss": 0.748,
1452
+ "step": 1020
1453
+ },
1454
+ {
1455
+ "epoch": 1.2561274509803921,
1456
+ "grad_norm": 0.09687550081111064,
1457
+ "learning_rate": 0.0003657737099327378,
1458
+ "loss": 0.7445,
1459
+ "step": 1025
1460
+ },
1461
+ {
1462
+ "epoch": 1.2622549019607843,
1463
+ "grad_norm": 0.08345067550046266,
1464
+ "learning_rate": 0.0003606277561396726,
1465
+ "loss": 0.7459,
1466
+ "step": 1030
1467
+ },
1468
+ {
1469
+ "epoch": 1.2683823529411764,
1470
+ "grad_norm": 0.09822605701018818,
1471
+ "learning_rate": 0.0003554977596606203,
1472
+ "loss": 0.7473,
1473
+ "step": 1035
1474
+ },
1475
+ {
1476
+ "epoch": 1.2745098039215685,
1477
+ "grad_norm": 0.08897185232535443,
1478
+ "learning_rate": 0.00035038430785044053,
1479
+ "loss": 0.7485,
1480
+ "step": 1040
1481
+ },
1482
+ {
1483
+ "epoch": 1.280637254901961,
1484
+ "grad_norm": 0.09625591066370137,
1485
+ "learning_rate": 0.00034528798616972434,
1486
+ "loss": 0.739,
1487
+ "step": 1045
1488
+ },
1489
+ {
1490
+ "epoch": 1.2867647058823528,
1491
+ "grad_norm": 0.09405754837547836,
1492
+ "learning_rate": 0.00034020937811776156,
1493
+ "loss": 0.7558,
1494
+ "step": 1050
1495
+ },
1496
+ {
1497
+ "epoch": 1.2928921568627452,
1498
+ "grad_norm": 0.10283887592029052,
1499
+ "learning_rate": 0.0003351490651657347,
1500
+ "loss": 0.7576,
1501
+ "step": 1055
1502
+ },
1503
+ {
1504
+ "epoch": 1.2990196078431373,
1505
+ "grad_norm": 0.09668902027134954,
1506
+ "learning_rate": 0.00033010762669014347,
1507
+ "loss": 0.7339,
1508
+ "step": 1060
1509
+ },
1510
+ {
1511
+ "epoch": 1.3051470588235294,
1512
+ "grad_norm": 0.09491296282202684,
1513
+ "learning_rate": 0.00032508563990646925,
1514
+ "loss": 0.74,
1515
+ "step": 1065
1516
+ },
1517
+ {
1518
+ "epoch": 1.3112745098039216,
1519
+ "grad_norm": 0.08614797698276408,
1520
+ "learning_rate": 0.00032008367980308734,
1521
+ "loss": 0.7491,
1522
+ "step": 1070
1523
+ },
1524
+ {
1525
+ "epoch": 1.3174019607843137,
1526
+ "grad_norm": 0.11385248252735118,
1527
+ "learning_rate": 0.0003151023190754343,
1528
+ "loss": 0.7424,
1529
+ "step": 1075
1530
+ },
1531
+ {
1532
+ "epoch": 1.3235294117647058,
1533
+ "grad_norm": 0.09914180185658039,
1534
+ "learning_rate": 0.0003101421280604379,
1535
+ "loss": 0.7386,
1536
+ "step": 1080
1537
+ },
1538
+ {
1539
+ "epoch": 1.329656862745098,
1540
+ "grad_norm": 0.23046737698236164,
1541
+ "learning_rate": 0.000305203674671216,
1542
+ "loss": 0.7429,
1543
+ "step": 1085
1544
+ },
1545
+ {
1546
+ "epoch": 1.3357843137254901,
1547
+ "grad_norm": 0.08999049028390338,
1548
+ "learning_rate": 0.00030028752433205476,
1549
+ "loss": 0.7504,
1550
+ "step": 1090
1551
+ },
1552
+ {
1553
+ "epoch": 1.3419117647058822,
1554
+ "grad_norm": 0.08798822285342148,
1555
+ "learning_rate": 0.0002953942399136702,
1556
+ "loss": 0.7475,
1557
+ "step": 1095
1558
+ },
1559
+ {
1560
+ "epoch": 1.3480392156862746,
1561
+ "grad_norm": 0.11440187719573272,
1562
+ "learning_rate": 0.00029052438166876307,
1563
+ "loss": 0.745,
1564
+ "step": 1100
1565
+ },
1566
+ {
1567
+ "epoch": 1.3541666666666667,
1568
+ "grad_norm": 0.09680996894090088,
1569
+ "learning_rate": 0.00028567850716787257,
1570
+ "loss": 0.7493,
1571
+ "step": 1105
1572
+ },
1573
+ {
1574
+ "epoch": 1.3602941176470589,
1575
+ "grad_norm": 0.08285996425508975,
1576
+ "learning_rate": 0.0002808571712355389,
1577
+ "loss": 0.7503,
1578
+ "step": 1110
1579
+ },
1580
+ {
1581
+ "epoch": 1.366421568627451,
1582
+ "grad_norm": 0.09255457708748827,
1583
+ "learning_rate": 0.0002760609258867784,
1584
+ "loss": 0.7318,
1585
+ "step": 1115
1586
+ },
1587
+ {
1588
+ "epoch": 1.3725490196078431,
1589
+ "grad_norm": 0.09572569889952495,
1590
+ "learning_rate": 0.00027129032026388045,
1591
+ "loss": 0.7348,
1592
+ "step": 1120
1593
+ },
1594
+ {
1595
+ "epoch": 1.3786764705882353,
1596
+ "grad_norm": 0.0909286336173143,
1597
+ "learning_rate": 0.00026654590057353467,
1598
+ "loss": 0.7403,
1599
+ "step": 1125
1600
+ },
1601
+ {
1602
+ "epoch": 1.3848039215686274,
1603
+ "grad_norm": 0.08684037452287134,
1604
+ "learning_rate": 0.00026182821002429345,
1605
+ "loss": 0.7492,
1606
+ "step": 1130
1607
+ },
1608
+ {
1609
+ "epoch": 1.3909313725490196,
1610
+ "grad_norm": 0.09039702206887036,
1611
+ "learning_rate": 0.00025713778876437744,
1612
+ "loss": 0.7271,
1613
+ "step": 1135
1614
+ },
1615
+ {
1616
+ "epoch": 1.3970588235294117,
1617
+ "grad_norm": 0.10259305111827258,
1618
+ "learning_rate": 0.00025247517381983136,
1619
+ "loss": 0.7334,
1620
+ "step": 1140
1621
+ },
1622
+ {
1623
+ "epoch": 1.403186274509804,
1624
+ "grad_norm": 0.09305514839850722,
1625
+ "learning_rate": 0.00024784089903303854,
1626
+ "loss": 0.7342,
1627
+ "step": 1145
1628
+ },
1629
+ {
1630
+ "epoch": 1.409313725490196,
1631
+ "grad_norm": 0.09362025462459474,
1632
+ "learning_rate": 0.00024323549500159802,
1633
+ "loss": 0.7287,
1634
+ "step": 1150
1635
+ },
1636
+ {
1637
+ "epoch": 1.4154411764705883,
1638
+ "grad_norm": 0.09297020814808991,
1639
+ "learning_rate": 0.0002386594890175749,
1640
+ "loss": 0.7424,
1641
+ "step": 1155
1642
+ },
1643
+ {
1644
+ "epoch": 1.4215686274509804,
1645
+ "grad_norm": 0.08353530769016755,
1646
+ "learning_rate": 0.0002341134050071283,
1647
+ "loss": 0.7485,
1648
+ "step": 1160
1649
+ },
1650
+ {
1651
+ "epoch": 1.4276960784313726,
1652
+ "grad_norm": 0.08590929777722105,
1653
+ "learning_rate": 0.00022959776347052509,
1654
+ "loss": 0.7347,
1655
+ "step": 1165
1656
+ },
1657
+ {
1658
+ "epoch": 1.4338235294117647,
1659
+ "grad_norm": 0.09926401747517187,
1660
+ "learning_rate": 0.00022511308142254488,
1661
+ "loss": 0.7529,
1662
+ "step": 1170
1663
+ },
1664
+ {
1665
+ "epoch": 1.4399509803921569,
1666
+ "grad_norm": 0.08954546869195683,
1667
+ "learning_rate": 0.00022065987233328528,
1668
+ "loss": 0.741,
1669
+ "step": 1175
1670
+ },
1671
+ {
1672
+ "epoch": 1.446078431372549,
1673
+ "grad_norm": 0.08807524417797259,
1674
+ "learning_rate": 0.000216238646069373,
1675
+ "loss": 0.7409,
1676
+ "step": 1180
1677
+ },
1678
+ {
1679
+ "epoch": 1.4522058823529411,
1680
+ "grad_norm": 0.09243225975101937,
1681
+ "learning_rate": 0.00021184990883558658,
1682
+ "loss": 0.7358,
1683
+ "step": 1185
1684
+ },
1685
+ {
1686
+ "epoch": 1.4583333333333333,
1687
+ "grad_norm": 0.09464124110688574,
1688
+ "learning_rate": 0.00020749416311689845,
1689
+ "loss": 0.7346,
1690
+ "step": 1190
1691
+ },
1692
+ {
1693
+ "epoch": 1.4644607843137254,
1694
+ "grad_norm": 0.09316779183905147,
1695
+ "learning_rate": 0.0002031719076209445,
1696
+ "loss": 0.7313,
1697
+ "step": 1195
1698
+ },
1699
+ {
1700
+ "epoch": 1.4705882352941178,
1701
+ "grad_norm": 0.09732126328149814,
1702
+ "learning_rate": 0.00019888363722092372,
1703
+ "loss": 0.7341,
1704
+ "step": 1200
1705
+ },
1706
+ {
1707
+ "epoch": 1.4767156862745099,
1708
+ "grad_norm": 0.08886419656539418,
1709
+ "learning_rate": 0.0001946298428989386,
1710
+ "loss": 0.7375,
1711
+ "step": 1205
1712
+ },
1713
+ {
1714
+ "epoch": 1.482843137254902,
1715
+ "grad_norm": 0.07850103787876181,
1716
+ "learning_rate": 0.00019041101168978093,
1717
+ "loss": 0.7287,
1718
+ "step": 1210
1719
+ },
1720
+ {
1721
+ "epoch": 1.4889705882352942,
1722
+ "grad_norm": 0.08830903517712305,
1723
+ "learning_rate": 0.00018622762662516868,
1724
+ "loss": 0.735,
1725
+ "step": 1215
1726
+ },
1727
+ {
1728
+ "epoch": 1.4950980392156863,
1729
+ "grad_norm": 0.08702420978835,
1730
+ "learning_rate": 0.00018208016667844152,
1731
+ "loss": 0.7393,
1732
+ "step": 1220
1733
+ },
1734
+ {
1735
+ "epoch": 1.5012254901960784,
1736
+ "grad_norm": 0.08438557069126026,
1737
+ "learning_rate": 0.00017796910670972132,
1738
+ "loss": 0.7423,
1739
+ "step": 1225
1740
+ },
1741
+ {
1742
+ "epoch": 1.5073529411764706,
1743
+ "grad_norm": 0.0874124625381899,
1744
+ "learning_rate": 0.00017389491741154372,
1745
+ "loss": 0.7417,
1746
+ "step": 1230
1747
+ },
1748
+ {
1749
+ "epoch": 1.5134803921568627,
1750
+ "grad_norm": 0.08983974571361636,
1751
+ "learning_rate": 0.0001698580652549665,
1752
+ "loss": 0.7284,
1753
+ "step": 1235
1754
+ },
1755
+ {
1756
+ "epoch": 1.5196078431372548,
1757
+ "grad_norm": 0.09655404504961941,
1758
+ "learning_rate": 0.00016585901243616042,
1759
+ "loss": 0.732,
1760
+ "step": 1240
1761
+ },
1762
+ {
1763
+ "epoch": 1.5257352941176472,
1764
+ "grad_norm": 0.08637672179778699,
1765
+ "learning_rate": 0.00016189821682349205,
1766
+ "loss": 0.7293,
1767
+ "step": 1245
1768
+ },
1769
+ {
1770
+ "epoch": 1.531862745098039,
1771
+ "grad_norm": 0.08546099516549688,
1772
+ "learning_rate": 0.0001579761319050991,
1773
+ "loss": 0.7356,
1774
+ "step": 1250
1775
+ },
1776
+ {
1777
+ "epoch": 1.5379901960784315,
1778
+ "grad_norm": 0.07907834707353141,
1779
+ "learning_rate": 0.00015409320673696902,
1780
+ "loss": 0.731,
1781
+ "step": 1255
1782
+ },
1783
+ {
1784
+ "epoch": 1.5441176470588234,
1785
+ "grad_norm": 0.08633766548134404,
1786
+ "learning_rate": 0.00015024988589152537,
1787
+ "loss": 0.7254,
1788
+ "step": 1260
1789
+ },
1790
+ {
1791
+ "epoch": 1.5502450980392157,
1792
+ "grad_norm": 0.09255543384492604,
1793
+ "learning_rate": 0.00014644660940672628,
1794
+ "loss": 0.7352,
1795
+ "step": 1265
1796
+ },
1797
+ {
1798
+ "epoch": 1.5563725490196079,
1799
+ "grad_norm": 0.07948954260097911,
1800
+ "learning_rate": 0.0001426838127356823,
1801
+ "loss": 0.7281,
1802
+ "step": 1270
1803
+ },
1804
+ {
1805
+ "epoch": 1.5625,
1806
+ "grad_norm": 0.0858902101428744,
1807
+ "learning_rate": 0.0001389619266968002,
1808
+ "loss": 0.7404,
1809
+ "step": 1275
1810
+ },
1811
+ {
1812
+ "epoch": 1.5686274509803921,
1813
+ "grad_norm": 0.08099715928187635,
1814
+ "learning_rate": 0.0001352813774244565,
1815
+ "loss": 0.729,
1816
+ "step": 1280
1817
+ },
1818
+ {
1819
+ "epoch": 1.5747549019607843,
1820
+ "grad_norm": 0.08675937769241077,
1821
+ "learning_rate": 0.0001316425863202078,
1822
+ "loss": 0.7289,
1823
+ "step": 1285
1824
+ },
1825
+ {
1826
+ "epoch": 1.5808823529411766,
1827
+ "grad_norm": 0.08712801365461889,
1828
+ "learning_rate": 0.00012804597000454215,
1829
+ "loss": 0.7368,
1830
+ "step": 1290
1831
+ },
1832
+ {
1833
+ "epoch": 1.5870098039215685,
1834
+ "grad_norm": 0.09259317971708025,
1835
+ "learning_rate": 0.00012449194026917883,
1836
+ "loss": 0.7254,
1837
+ "step": 1295
1838
+ },
1839
+ {
1840
+ "epoch": 1.593137254901961,
1841
+ "grad_norm": 0.0821781596676491,
1842
+ "learning_rate": 0.00012098090402992085,
1843
+ "loss": 0.7307,
1844
+ "step": 1300
1845
+ },
1846
+ {
1847
+ "epoch": 1.5992647058823528,
1848
+ "grad_norm": 0.08514490094990651,
1849
+ "learning_rate": 0.00011751326328006473,
1850
+ "loss": 0.7226,
1851
+ "step": 1305
1852
+ },
1853
+ {
1854
+ "epoch": 1.6053921568627452,
1855
+ "grad_norm": 0.08798702323560283,
1856
+ "learning_rate": 0.00011408941504437532,
1857
+ "loss": 0.7274,
1858
+ "step": 1310
1859
+ },
1860
+ {
1861
+ "epoch": 1.6115196078431373,
1862
+ "grad_norm": 0.08477334907464082,
1863
+ "learning_rate": 0.00011070975133362842,
1864
+ "loss": 0.7351,
1865
+ "step": 1315
1866
+ },
1867
+ {
1868
+ "epoch": 1.6176470588235294,
1869
+ "grad_norm": 0.08440769123912943,
1870
+ "learning_rate": 0.00010737465909972776,
1871
+ "loss": 0.7322,
1872
+ "step": 1320
1873
+ },
1874
+ {
1875
+ "epoch": 1.6237745098039216,
1876
+ "grad_norm": 0.08816338400851521,
1877
+ "learning_rate": 0.00010408452019140119,
1878
+ "loss": 0.7257,
1879
+ "step": 1325
1880
+ },
1881
+ {
1882
+ "epoch": 1.6299019607843137,
1883
+ "grad_norm": 0.0889764540813042,
1884
+ "learning_rate": 0.00010083971131048159,
1885
+ "loss": 0.7285,
1886
+ "step": 1330
1887
+ },
1888
+ {
1889
+ "epoch": 1.6360294117647058,
1890
+ "grad_norm": 0.08514875374173311,
1891
+ "learning_rate": 9.764060396877661e-05,
1892
+ "loss": 0.7323,
1893
+ "step": 1335
1894
+ },
1895
+ {
1896
+ "epoch": 1.642156862745098,
1897
+ "grad_norm": 0.08728092386538332,
1898
+ "learning_rate": 9.448756444553224e-05,
1899
+ "loss": 0.7256,
1900
+ "step": 1340
1901
+ },
1902
+ {
1903
+ "epoch": 1.6482843137254903,
1904
+ "grad_norm": 0.08430901480786084,
1905
+ "learning_rate": 9.138095374549633e-05,
1906
+ "loss": 0.7278,
1907
+ "step": 1345
1908
+ },
1909
+ {
1910
+ "epoch": 1.6544117647058822,
1911
+ "grad_norm": 0.08407206279064601,
1912
+ "learning_rate": 8.832112755758598e-05,
1913
+ "loss": 0.7232,
1914
+ "step": 1350
1915
+ },
1916
+ {
1917
+ "epoch": 1.6605392156862746,
1918
+ "grad_norm": 0.09172008766801877,
1919
+ "learning_rate": 8.530843621416234e-05,
1920
+ "loss": 0.7262,
1921
+ "step": 1355
1922
+ },
1923
+ {
1924
+ "epoch": 1.6666666666666665,
1925
+ "grad_norm": 0.088740049378598,
1926
+ "learning_rate": 8.234322465092047e-05,
1927
+ "loss": 0.7294,
1928
+ "step": 1360
1929
+ },
1930
+ {
1931
+ "epoch": 1.6727941176470589,
1932
+ "grad_norm": 0.08733287037829676,
1933
+ "learning_rate": 7.942583236739581e-05,
1934
+ "loss": 0.7326,
1935
+ "step": 1365
1936
+ },
1937
+ {
1938
+ "epoch": 1.678921568627451,
1939
+ "grad_norm": 0.08946029254025908,
1940
+ "learning_rate": 7.655659338809329e-05,
1941
+ "loss": 0.7302,
1942
+ "step": 1370
1943
+ },
1944
+ {
1945
+ "epoch": 1.6850490196078431,
1946
+ "grad_norm": 0.08125225656437084,
1947
+ "learning_rate": 7.373583622424358e-05,
1948
+ "loss": 0.7243,
1949
+ "step": 1375
1950
+ },
1951
+ {
1952
+ "epoch": 1.6911764705882353,
1953
+ "grad_norm": 0.08262402915263288,
1954
+ "learning_rate": 7.096388383619079e-05,
1955
+ "loss": 0.722,
1956
+ "step": 1380
1957
+ },
1958
+ {
1959
+ "epoch": 1.6973039215686274,
1960
+ "grad_norm": 0.0983748828611407,
1961
+ "learning_rate": 6.824105359641513e-05,
1962
+ "loss": 0.7224,
1963
+ "step": 1385
1964
+ },
1965
+ {
1966
+ "epoch": 1.7034313725490198,
1967
+ "grad_norm": 0.09511486159825465,
1968
+ "learning_rate": 6.556765725319525e-05,
1969
+ "loss": 0.7353,
1970
+ "step": 1390
1971
+ },
1972
+ {
1973
+ "epoch": 1.7095588235294117,
1974
+ "grad_norm": 0.08406547135240365,
1975
+ "learning_rate": 6.294400089491526e-05,
1976
+ "loss": 0.7249,
1977
+ "step": 1395
1978
+ },
1979
+ {
1980
+ "epoch": 1.715686274509804,
1981
+ "grad_norm": 0.09349436979698456,
1982
+ "learning_rate": 6.037038491501978e-05,
1983
+ "loss": 0.7199,
1984
+ "step": 1400
1985
+ },
1986
+ {
1987
+ "epoch": 1.721813725490196,
1988
+ "grad_norm": 0.0859858185739073,
1989
+ "learning_rate": 5.7847103977619555e-05,
1990
+ "loss": 0.7231,
1991
+ "step": 1405
1992
+ },
1993
+ {
1994
+ "epoch": 1.7279411764705883,
1995
+ "grad_norm": 0.08083261397597263,
1996
+ "learning_rate": 5.53744469837551e-05,
1997
+ "loss": 0.7331,
1998
+ "step": 1410
1999
+ },
2000
+ {
2001
+ "epoch": 1.7340686274509802,
2002
+ "grad_norm": 0.08197105924202848,
2003
+ "learning_rate": 5.295269703831901e-05,
2004
+ "loss": 0.725,
2005
+ "step": 1415
2006
+ },
2007
+ {
2008
+ "epoch": 1.7401960784313726,
2009
+ "grad_norm": 0.07809550724924257,
2010
+ "learning_rate": 5.058213141764151e-05,
2011
+ "loss": 0.718,
2012
+ "step": 1420
2013
+ },
2014
+ {
2015
+ "epoch": 1.7463235294117647,
2016
+ "grad_norm": 0.08030689228502133,
2017
+ "learning_rate": 4.826302153774448e-05,
2018
+ "loss": 0.7171,
2019
+ "step": 1425
2020
+ },
2021
+ {
2022
+ "epoch": 1.7524509803921569,
2023
+ "grad_norm": 0.08468169044962492,
2024
+ "learning_rate": 4.599563292326592e-05,
2025
+ "loss": 0.7267,
2026
+ "step": 1430
2027
+ },
2028
+ {
2029
+ "epoch": 1.758578431372549,
2030
+ "grad_norm": 0.0820979728898519,
2031
+ "learning_rate": 4.3780225177058766e-05,
2032
+ "loss": 0.7166,
2033
+ "step": 1435
2034
+ },
2035
+ {
2036
+ "epoch": 1.7647058823529411,
2037
+ "grad_norm": 0.07927753918146413,
2038
+ "learning_rate": 4.161705195046761e-05,
2039
+ "loss": 0.718,
2040
+ "step": 1440
2041
+ },
2042
+ {
2043
+ "epoch": 1.7708333333333335,
2044
+ "grad_norm": 0.0840926492467221,
2045
+ "learning_rate": 3.9506360914287386e-05,
2046
+ "loss": 0.728,
2047
+ "step": 1445
2048
+ },
2049
+ {
2050
+ "epoch": 1.7769607843137254,
2051
+ "grad_norm": 0.08436514170292973,
2052
+ "learning_rate": 3.744839373040682e-05,
2053
+ "loss": 0.7214,
2054
+ "step": 1450
2055
+ },
2056
+ {
2057
+ "epoch": 1.7830882352941178,
2058
+ "grad_norm": 0.08999651739438058,
2059
+ "learning_rate": 3.5443386024138605e-05,
2060
+ "loss": 0.7296,
2061
+ "step": 1455
2062
+ },
2063
+ {
2064
+ "epoch": 1.7892156862745097,
2065
+ "grad_norm": 0.08092101714415846,
2066
+ "learning_rate": 3.349156735724274e-05,
2067
+ "loss": 0.7196,
2068
+ "step": 1460
2069
+ },
2070
+ {
2071
+ "epoch": 1.795343137254902,
2072
+ "grad_norm": 0.08061728201126263,
2073
+ "learning_rate": 3.1593161201642354e-05,
2074
+ "loss": 0.7284,
2075
+ "step": 1465
2076
+ },
2077
+ {
2078
+ "epoch": 1.8014705882352942,
2079
+ "grad_norm": 0.07834911210493091,
2080
+ "learning_rate": 2.9748384913837522e-05,
2081
+ "loss": 0.7325,
2082
+ "step": 1470
2083
+ },
2084
+ {
2085
+ "epoch": 1.8075980392156863,
2086
+ "grad_norm": 0.0790057426287298,
2087
+ "learning_rate": 2.7957449710019512e-05,
2088
+ "loss": 0.7286,
2089
+ "step": 1475
2090
+ },
2091
+ {
2092
+ "epoch": 1.8137254901960784,
2093
+ "grad_norm": 0.07695722244990424,
2094
+ "learning_rate": 2.622056064188738e-05,
2095
+ "loss": 0.7276,
2096
+ "step": 1480
2097
+ },
2098
+ {
2099
+ "epoch": 1.8198529411764706,
2100
+ "grad_norm": 0.09150941908302032,
2101
+ "learning_rate": 2.4537916573171337e-05,
2102
+ "loss": 0.7239,
2103
+ "step": 1485
2104
+ },
2105
+ {
2106
+ "epoch": 1.8259803921568627,
2107
+ "grad_norm": 0.09154350521364844,
2108
+ "learning_rate": 2.2909710156863274e-05,
2109
+ "loss": 0.7312,
2110
+ "step": 1490
2111
+ },
2112
+ {
2113
+ "epoch": 1.8321078431372548,
2114
+ "grad_norm": 0.08002699190491802,
2115
+ "learning_rate": 2.1336127813159355e-05,
2116
+ "loss": 0.7254,
2117
+ "step": 1495
2118
+ },
2119
+ {
2120
+ "epoch": 1.8382352941176472,
2121
+ "grad_norm": 0.08021887418189992,
2122
+ "learning_rate": 1.981734970811644e-05,
2123
+ "loss": 0.7222,
2124
+ "step": 1500
2125
+ },
2126
+ {
2127
+ "epoch": 1.844362745098039,
2128
+ "grad_norm": 0.08930992030073814,
2129
+ "learning_rate": 1.8353549733023333e-05,
2130
+ "loss": 0.7383,
2131
+ "step": 1505
2132
+ },
2133
+ {
2134
+ "epoch": 1.8504901960784315,
2135
+ "grad_norm": 0.08303320455844895,
2136
+ "learning_rate": 1.6944895484492072e-05,
2137
+ "loss": 0.7133,
2138
+ "step": 1510
2139
+ },
2140
+ {
2141
+ "epoch": 1.8566176470588234,
2142
+ "grad_norm": 0.08729988838797742,
2143
+ "learning_rate": 1.5591548245268428e-05,
2144
+ "loss": 0.7315,
2145
+ "step": 1515
2146
+ },
2147
+ {
2148
+ "epoch": 1.8627450980392157,
2149
+ "grad_norm": 0.08890946616187734,
2150
+ "learning_rate": 1.429366296576623e-05,
2151
+ "loss": 0.7197,
2152
+ "step": 1520
2153
+ },
2154
+ {
2155
+ "epoch": 1.8688725490196079,
2156
+ "grad_norm": 0.08151959163399713,
2157
+ "learning_rate": 1.30513882463264e-05,
2158
+ "loss": 0.7263,
2159
+ "step": 1525
2160
+ },
2161
+ {
2162
+ "epoch": 1.875,
2163
+ "grad_norm": 0.09562764992899297,
2164
+ "learning_rate": 1.1864866320203115e-05,
2165
+ "loss": 0.7188,
2166
+ "step": 1530
2167
+ },
2168
+ {
2169
+ "epoch": 1.8811274509803921,
2170
+ "grad_norm": 0.07846982174735893,
2171
+ "learning_rate": 1.073423303727894e-05,
2172
+ "loss": 0.7237,
2173
+ "step": 1535
2174
+ },
2175
+ {
2176
+ "epoch": 1.8872549019607843,
2177
+ "grad_norm": 0.07663001458145507,
2178
+ "learning_rate": 9.659617848510882e-06,
2179
+ "loss": 0.7252,
2180
+ "step": 1540
2181
+ },
2182
+ {
2183
+ "epoch": 1.8933823529411766,
2184
+ "grad_norm": 0.08080118998190498,
2185
+ "learning_rate": 8.64114379110853e-06,
2186
+ "loss": 0.7112,
2187
+ "step": 1545
2188
+ },
2189
+ {
2190
+ "epoch": 1.8995098039215685,
2191
+ "grad_norm": 0.08484892902062172,
2192
+ "learning_rate": 7.678927474447817e-06,
2193
+ "loss": 0.7264,
2194
+ "step": 1550
2195
+ },
2196
+ {
2197
+ "epoch": 1.905637254901961,
2198
+ "grad_norm": 0.08516868212628753,
2199
+ "learning_rate": 6.77307906671909e-06,
2200
+ "loss": 0.7271,
2201
+ "step": 1555
2202
+ },
2203
+ {
2204
+ "epoch": 1.9117647058823528,
2205
+ "grad_norm": 0.08133640776409674,
2206
+ "learning_rate": 5.923702282314092e-06,
2207
+ "loss": 0.7324,
2208
+ "step": 1560
2209
+ },
2210
+ {
2211
+ "epoch": 1.9178921568627452,
2212
+ "grad_norm": 0.08097758322239303,
2213
+ "learning_rate": 5.130894369951011e-06,
2214
+ "loss": 0.7273,
2215
+ "step": 1565
2216
+ },
2217
+ {
2218
+ "epoch": 1.9240196078431373,
2219
+ "grad_norm": 0.08298253969927805,
2220
+ "learning_rate": 4.394746101540115e-06,
2221
+ "loss": 0.7298,
2222
+ "step": 1570
2223
+ },
2224
+ {
2225
+ "epoch": 1.9301470588235294,
2226
+ "grad_norm": 0.0776674873026092,
2227
+ "learning_rate": 3.7153417617907802e-06,
2228
+ "loss": 0.7199,
2229
+ "step": 1575
2230
+ },
2231
+ {
2232
+ "epoch": 1.9362745098039216,
2233
+ "grad_norm": 0.08136684261699478,
2234
+ "learning_rate": 3.092759138561607e-06,
2235
+ "loss": 0.727,
2236
+ "step": 1580
2237
+ },
2238
+ {
2239
+ "epoch": 1.9424019607843137,
2240
+ "grad_norm": 0.21064147236672387,
2241
+ "learning_rate": 2.5270695139539833e-06,
2242
+ "loss": 0.7305,
2243
+ "step": 1585
2244
+ },
2245
+ {
2246
+ "epoch": 1.9485294117647058,
2247
+ "grad_norm": 0.07856752844029326,
2248
+ "learning_rate": 2.018337656150726e-06,
2249
+ "loss": 0.7259,
2250
+ "step": 1590
2251
+ },
2252
+ {
2253
+ "epoch": 1.954656862745098,
2254
+ "grad_norm": 0.07818237444191369,
2255
+ "learning_rate": 1.5666218120005682e-06,
2256
+ "loss": 0.724,
2257
+ "step": 1595
2258
+ },
2259
+ {
2260
+ "epoch": 1.9607843137254903,
2261
+ "grad_norm": 0.07498630792024302,
2262
+ "learning_rate": 1.1719737003492159e-06,
2263
+ "loss": 0.7205,
2264
+ "step": 1600
2265
+ },
2266
+ {
2267
+ "epoch": 1.9669117647058822,
2268
+ "grad_norm": 0.07974040781241311,
2269
+ "learning_rate": 8.344385061176962e-07,
2270
+ "loss": 0.7228,
2271
+ "step": 1605
2272
+ },
2273
+ {
2274
+ "epoch": 1.9730392156862746,
2275
+ "grad_norm": 0.08674324039372262,
2276
+ "learning_rate": 5.540548751292173e-07,
2277
+ "loss": 0.7364,
2278
+ "step": 1610
2279
+ },
2280
+ {
2281
+ "epoch": 1.9791666666666665,
2282
+ "grad_norm": 0.08126471002081247,
2283
+ "learning_rate": 3.3085490968409737e-07,
2284
+ "loss": 0.7232,
2285
+ "step": 1615
2286
+ },
2287
+ {
2288
+ "epoch": 1.9852941176470589,
2289
+ "grad_norm": 0.08409713343077478,
2290
+ "learning_rate": 1.6486416488459277e-07,
2291
+ "loss": 0.7251,
2292
+ "step": 1620
2293
+ },
2294
+ {
2295
+ "epoch": 1.991421568627451,
2296
+ "grad_norm": 0.08609959331430181,
2297
+ "learning_rate": 5.6101645708850346e-08,
2298
+ "loss": 0.7326,
2299
+ "step": 1625
2300
+ },
2301
+ {
2302
+ "epoch": 1.9975490196078431,
2303
+ "grad_norm": 0.0748443586344328,
2304
+ "learning_rate": 4.579804834703438e-09,
2305
+ "loss": 0.7238,
2306
+ "step": 1630
2307
+ },
2308
+ {
2309
+ "epoch": 2.0,
2310
+ "eval_loss": 1.1972506046295166,
2311
+ "eval_runtime": 112.8302,
2312
+ "eval_samples_per_second": 185.598,
2313
+ "eval_steps_per_second": 5.805,
2314
+ "step": 1632
2315
+ },
2316
+ {
2317
+ "epoch": 2.0,
2318
+ "step": 1632,
2319
+ "total_flos": 160150899916800.0,
2320
+ "train_loss": 0.8347952699690473,
2321
+ "train_runtime": 3713.7533,
2322
+ "train_samples_per_second": 56.241,
2323
+ "train_steps_per_second": 0.439
2324
+ }
2325
+ ],
2326
+ "logging_steps": 5,
2327
+ "max_steps": 1632,
2328
+ "num_input_tokens_seen": 0,
2329
+ "num_train_epochs": 2,
2330
+ "save_steps": 500,
2331
+ "stateful_callbacks": {
2332
+ "TrainerControl": {
2333
+ "args": {
2334
+ "should_epoch_stop": false,
2335
+ "should_evaluate": false,
2336
+ "should_log": false,
2337
+ "should_save": false,
2338
+ "should_training_stop": false
2339
+ },
2340
+ "attributes": {}
2341
+ }
2342
+ },
2343
+ "total_flos": 160150899916800.0,
2344
+ "train_batch_size": 4,
2345
+ "trial_name": null,
2346
+ "trial_params": null
2347
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ef99d4dec4b3d9c3e52d1cd6999ef20d3f6c3cafc7f5d3a6867f962f202d87
3
+ size 6520
vocab.json ADDED
The diff for this file is too large to render. See raw diff