TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
loubnabnl HF staff commited on
Commit
2b29917
1 Parent(s): 17ad1f5

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-noOH
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/3ofu55ed)
19
+ # smollm-350M-instruct-test2-noOH
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: 0.8306
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
+ | 0.8625 | 0.9997 | 733 | 0.8650 |
61
+ | 0.7335 | 1.9993 | 1466 | 0.8306 |
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": 1.9993181043300376,
3
+ "total_flos": 143858545459200.0,
4
+ "train_loss": 0.8359313647060732,
5
+ "train_runtime": 3324.125,
6
+ "train_samples": 286314,
7
+ "train_samples_per_second": 56.452,
8
+ "train_steps_per_second": 0.441
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 sha256:6fcb4b3ec12850f906c87613915e6f10f9e73404bf49df20d3906c9bc72c3a22
3
+ size 723674912
runs/Aug12_16-20-22_ip-26-0-165-24/events.out.tfevents.1723480080.ip-26-0-165-24.509824.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51fafcd39b006877d20020dd6a7429c329d1541837d0c5badfb950d18895effe
3
+ size 67978
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": 1.9993181043300376,
3
+ "total_flos": 143858545459200.0,
4
+ "train_loss": 0.8359313647060732,
5
+ "train_runtime": 3324.125,
6
+ "train_samples": 286314,
7
+ "train_samples_per_second": 56.452,
8
+ "train_steps_per_second": 0.441
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,2116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9993181043300376,
5
+ "eval_steps": 500,
6
+ "global_step": 1466,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0013637913399249914,
13
+ "grad_norm": 1.598020721574378,
14
+ "learning_rate": 6.8027210884353745e-06,
15
+ "loss": 1.3936,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.006818956699624957,
20
+ "grad_norm": 1.582179170492486,
21
+ "learning_rate": 3.4013605442176877e-05,
22
+ "loss": 1.3732,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.013637913399249914,
27
+ "grad_norm": 0.5247209097240487,
28
+ "learning_rate": 6.802721088435375e-05,
29
+ "loss": 1.3443,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.020456870098874872,
34
+ "grad_norm": 0.8017522199019398,
35
+ "learning_rate": 0.00010204081632653062,
36
+ "loss": 1.2617,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.02727582679849983,
41
+ "grad_norm": 0.4014040737926046,
42
+ "learning_rate": 0.0001360544217687075,
43
+ "loss": 1.1857,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.03409478349812479,
48
+ "grad_norm": 0.32790437534680206,
49
+ "learning_rate": 0.00017006802721088434,
50
+ "loss": 1.1436,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.040913740197749744,
55
+ "grad_norm": 0.2966698205141879,
56
+ "learning_rate": 0.00020408163265306123,
57
+ "loss": 1.0996,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.0477326968973747,
62
+ "grad_norm": 0.17808447662676022,
63
+ "learning_rate": 0.0002380952380952381,
64
+ "loss": 1.0757,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.05455165359699966,
69
+ "grad_norm": 0.14553030270593192,
70
+ "learning_rate": 0.000272108843537415,
71
+ "loss": 1.07,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.06137061029662462,
76
+ "grad_norm": 0.12365194167763814,
77
+ "learning_rate": 0.0003061224489795919,
78
+ "loss": 1.0494,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.06818956699624958,
83
+ "grad_norm": 0.19450168087415454,
84
+ "learning_rate": 0.0003401360544217687,
85
+ "loss": 1.0515,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.07500852369587453,
90
+ "grad_norm": 0.1207148840427689,
91
+ "learning_rate": 0.0003741496598639456,
92
+ "loss": 1.0253,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.08182748039549949,
97
+ "grad_norm": 0.10854420757501072,
98
+ "learning_rate": 0.00040816326530612246,
99
+ "loss": 1.0353,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.08864643709512444,
104
+ "grad_norm": 0.16561709445658757,
105
+ "learning_rate": 0.0004421768707482993,
106
+ "loss": 1.0285,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.0954653937947494,
111
+ "grad_norm": 0.524524123408497,
112
+ "learning_rate": 0.0004761904761904762,
113
+ "loss": 1.0379,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.10228435049437436,
118
+ "grad_norm": 0.12853108179786138,
119
+ "learning_rate": 0.0005102040816326531,
120
+ "loss": 1.0186,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.10910330719399931,
125
+ "grad_norm": 0.2734451972437396,
126
+ "learning_rate": 0.00054421768707483,
127
+ "loss": 1.0063,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.11592226389362427,
132
+ "grad_norm": 0.14711225612929515,
133
+ "learning_rate": 0.0005782312925170068,
134
+ "loss": 1.0132,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.12274122059324924,
139
+ "grad_norm": 0.11857109812836017,
140
+ "learning_rate": 0.0006122448979591838,
141
+ "loss": 1.0131,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.1295601772928742,
146
+ "grad_norm": 0.16843211920179874,
147
+ "learning_rate": 0.0006462585034013606,
148
+ "loss": 0.9969,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.13637913399249915,
153
+ "grad_norm": 0.15975057567245052,
154
+ "learning_rate": 0.0006802721088435374,
155
+ "loss": 0.9909,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.1431980906921241,
160
+ "grad_norm": 0.15632985298714983,
161
+ "learning_rate": 0.0007142857142857143,
162
+ "loss": 0.9966,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.15001704739174906,
167
+ "grad_norm": 0.1621684383980749,
168
+ "learning_rate": 0.0007482993197278912,
169
+ "loss": 0.9915,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.15683600409137402,
174
+ "grad_norm": 0.12303095362829028,
175
+ "learning_rate": 0.000782312925170068,
176
+ "loss": 0.9787,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.16365496079099898,
181
+ "grad_norm": 0.14599562372712946,
182
+ "learning_rate": 0.0008163265306122449,
183
+ "loss": 0.9882,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.17047391749062393,
188
+ "grad_norm": 0.14693955034453152,
189
+ "learning_rate": 0.0008503401360544217,
190
+ "loss": 0.9801,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.1772928741902489,
195
+ "grad_norm": 0.22554930118958344,
196
+ "learning_rate": 0.0008843537414965987,
197
+ "loss": 0.9767,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.18411183088987385,
202
+ "grad_norm": 0.15209662483639966,
203
+ "learning_rate": 0.0009183673469387756,
204
+ "loss": 0.9827,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.1909307875894988,
209
+ "grad_norm": 0.1338153825791751,
210
+ "learning_rate": 0.0009523809523809524,
211
+ "loss": 0.9725,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.19774974428912376,
216
+ "grad_norm": 0.16873273473563985,
217
+ "learning_rate": 0.0009863945578231293,
218
+ "loss": 0.9747,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.20456870098874871,
223
+ "grad_norm": 0.18631348995548455,
224
+ "learning_rate": 0.000999987235881584,
225
+ "loss": 0.9737,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.21138765768837367,
230
+ "grad_norm": 0.1398209387998964,
231
+ "learning_rate": 0.0009999092352957284,
232
+ "loss": 0.9848,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.21820661438799863,
237
+ "grad_norm": 0.13947559562857936,
238
+ "learning_rate": 0.0009997603363497414,
239
+ "loss": 0.9643,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.22502557108762358,
244
+ "grad_norm": 0.14313053783616825,
245
+ "learning_rate": 0.000999540560160838,
246
+ "loss": 0.974,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.23184452778724854,
251
+ "grad_norm": 0.13580380953886942,
252
+ "learning_rate": 0.0009992499378982194,
253
+ "loss": 0.9761,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.2386634844868735,
258
+ "grad_norm": 0.14428497093865783,
259
+ "learning_rate": 0.0009988885107786517,
260
+ "loss": 0.9652,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.24548244118649848,
265
+ "grad_norm": 0.12382971206501955,
266
+ "learning_rate": 0.0009984563300606192,
267
+ "loss": 0.9678,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.25230139788612344,
272
+ "grad_norm": 0.14065780649342097,
273
+ "learning_rate": 0.0009979534570370575,
274
+ "loss": 0.969,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.2591203545857484,
279
+ "grad_norm": 0.11357268655774008,
280
+ "learning_rate": 0.000997379963026658,
281
+ "loss": 0.9692,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.26593931128537335,
286
+ "grad_norm": 0.1622202809625719,
287
+ "learning_rate": 0.0009967359293637553,
288
+ "loss": 0.9588,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.2727582679849983,
293
+ "grad_norm": 0.1776637907272292,
294
+ "learning_rate": 0.0009960214473867907,
295
+ "loss": 0.9613,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.27957722468462326,
300
+ "grad_norm": 0.1215741064620054,
301
+ "learning_rate": 0.0009952366184253602,
302
+ "loss": 0.963,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.2863961813842482,
307
+ "grad_norm": 0.1302207261176898,
308
+ "learning_rate": 0.0009943815537858415,
309
+ "loss": 0.9551,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.2932151380838732,
314
+ "grad_norm": 0.11682895510290592,
315
+ "learning_rate": 0.00099345637473561,
316
+ "loss": 0.9598,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.30003409478349813,
321
+ "grad_norm": 0.15188852916347045,
322
+ "learning_rate": 0.0009924612124858389,
323
+ "loss": 0.9583,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.3068530514831231,
328
+ "grad_norm": 0.13240495035670563,
329
+ "learning_rate": 0.0009913962081728918,
330
+ "loss": 0.9538,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.31367200818274804,
335
+ "grad_norm": 0.16120589037533914,
336
+ "learning_rate": 0.0009902615128383062,
337
+ "loss": 0.9464,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.320490964882373,
342
+ "grad_norm": 0.1382061477313828,
343
+ "learning_rate": 0.0009890572874073713,
344
+ "loss": 0.9434,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.32730992158199795,
349
+ "grad_norm": 0.11549986617558586,
350
+ "learning_rate": 0.0009877837026663068,
351
+ "loss": 0.9441,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.3341288782816229,
356
+ "grad_norm": 0.10980499757109458,
357
+ "learning_rate": 0.00098644093923804,
358
+ "loss": 0.96,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.34094783498124787,
363
+ "grad_norm": 0.19062656435818273,
364
+ "learning_rate": 0.0009850291875565908,
365
+ "loss": 0.9577,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.3477667916808728,
370
+ "grad_norm": 0.12141161965377588,
371
+ "learning_rate": 0.0009835486478400625,
372
+ "loss": 0.9456,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.3545857483804978,
377
+ "grad_norm": 0.11932394138168441,
378
+ "learning_rate": 0.000981999530062248,
379
+ "loss": 0.9546,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.36140470508012273,
384
+ "grad_norm": 0.1277558444188088,
385
+ "learning_rate": 0.0009803820539228492,
386
+ "loss": 0.9375,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.3682236617797477,
391
+ "grad_norm": 0.11354346745136285,
392
+ "learning_rate": 0.0009786964488163194,
393
+ "loss": 0.9473,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.37504261847937265,
398
+ "grad_norm": 0.10871503403228854,
399
+ "learning_rate": 0.000976942953799331,
400
+ "loss": 0.9321,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.3818615751789976,
405
+ "grad_norm": 0.14107095714136358,
406
+ "learning_rate": 0.0009751218175568688,
407
+ "loss": 0.9346,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.38868053187862256,
412
+ "grad_norm": 0.11468378232954199,
413
+ "learning_rate": 0.0009732332983669651,
414
+ "loss": 0.9333,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.3954994885782475,
419
+ "grad_norm": 0.11614073571579422,
420
+ "learning_rate": 0.0009712776640640671,
421
+ "loss": 0.933,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.40231844527787247,
426
+ "grad_norm": 0.14233058701254916,
427
+ "learning_rate": 0.0009692551920010519,
428
+ "loss": 0.9365,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.40913740197749743,
433
+ "grad_norm": 0.16365059288233255,
434
+ "learning_rate": 0.0009671661690098941,
435
+ "loss": 0.9345,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.4159563586771224,
440
+ "grad_norm": 0.2778458797011963,
441
+ "learning_rate": 0.0009650108913609837,
442
+ "loss": 0.9243,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.42277531537674734,
447
+ "grad_norm": 0.12497969488106986,
448
+ "learning_rate": 0.0009627896647211103,
449
+ "loss": 0.915,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.4295942720763723,
454
+ "grad_norm": 0.12132320992585822,
455
+ "learning_rate": 0.0009605028041101116,
456
+ "loss": 0.9306,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.43641322877599725,
461
+ "grad_norm": 0.15422956629129714,
462
+ "learning_rate": 0.0009581506338561974,
463
+ "loss": 0.9229,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.4432321854756222,
468
+ "grad_norm": 0.10857379661878619,
469
+ "learning_rate": 0.0009557334875499513,
470
+ "loss": 0.9295,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.45005114217524717,
475
+ "grad_norm": 0.09700456702304185,
476
+ "learning_rate": 0.0009532517079970214,
477
+ "loss": 0.9144,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.4568700988748721,
482
+ "grad_norm": 0.1574301623396698,
483
+ "learning_rate": 0.000950705647169502,
484
+ "loss": 0.9303,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.4636890555744971,
489
+ "grad_norm": 0.12653500024100792,
490
+ "learning_rate": 0.000948095666156016,
491
+ "loss": 0.9145,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.47050801227412203,
496
+ "grad_norm": 0.12348356194845742,
497
+ "learning_rate": 0.0009454221351105055,
498
+ "loss": 0.9115,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.477326968973747,
503
+ "grad_norm": 0.1307740739484115,
504
+ "learning_rate": 0.0009426854331997334,
505
+ "loss": 0.9188,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.484145925673372,
510
+ "grad_norm": 0.10835447562048035,
511
+ "learning_rate": 0.0009398859485495119,
512
+ "loss": 0.9247,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.49096488237299696,
517
+ "grad_norm": 0.11863788647430744,
518
+ "learning_rate": 0.0009370240781896553,
519
+ "loss": 0.9102,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.4977838390726219,
524
+ "grad_norm": 0.14783785955650325,
525
+ "learning_rate": 0.0009341002279976728,
526
+ "loss": 0.9136,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.5046027957722469,
531
+ "grad_norm": 0.11185935178347504,
532
+ "learning_rate": 0.0009311148126412067,
533
+ "loss": 0.9108,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.5114217524718718,
538
+ "grad_norm": 0.11360824911697796,
539
+ "learning_rate": 0.0009280682555192229,
540
+ "loss": 0.9167,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.5182407091714968,
545
+ "grad_norm": 0.10219440421235579,
546
+ "learning_rate": 0.0009249609887019624,
547
+ "loss": 0.9125,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.5250596658711217,
552
+ "grad_norm": 0.1063437764241102,
553
+ "learning_rate": 0.0009217934528696652,
554
+ "loss": 0.9135,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.5318786225707467,
559
+ "grad_norm": 0.12924256438154388,
560
+ "learning_rate": 0.000918566097250072,
561
+ "loss": 0.9044,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.5386975792703717,
566
+ "grad_norm": 0.1672822885194737,
567
+ "learning_rate": 0.0009152793795547129,
568
+ "loss": 0.905,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.5455165359699966,
573
+ "grad_norm": 0.18170913356641202,
574
+ "learning_rate": 0.0009119337659139939,
575
+ "loss": 0.9077,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.5523354926696216,
580
+ "grad_norm": 0.14583299571955888,
581
+ "learning_rate": 0.0009085297308110889,
582
+ "loss": 0.9013,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.5591544493692465,
587
+ "grad_norm": 0.1328861894472585,
588
+ "learning_rate": 0.0009050677570146482,
589
+ "loss": 0.8972,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.5659734060688715,
594
+ "grad_norm": 0.12732498687417756,
595
+ "learning_rate": 0.0009015483355103298,
596
+ "loss": 0.8948,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.5727923627684964,
601
+ "grad_norm": 0.10225924635313659,
602
+ "learning_rate": 0.0008979719654311677,
603
+ "loss": 0.8977,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.5796113194681214,
608
+ "grad_norm": 0.11222734733135577,
609
+ "learning_rate": 0.0008943391539867831,
610
+ "loss": 0.9086,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.5864302761677463,
615
+ "grad_norm": 0.10007024319396716,
616
+ "learning_rate": 0.0008906504163914506,
617
+ "loss": 0.9047,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.5932492328673713,
622
+ "grad_norm": 0.11019466700605089,
623
+ "learning_rate": 0.0008869062757910296,
624
+ "loss": 0.8998,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.6000681895669963,
629
+ "grad_norm": 0.12131434093089721,
630
+ "learning_rate": 0.00088310726318877,
631
+ "loss": 0.9073,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.6068871462666212,
636
+ "grad_norm": 0.09939916214847802,
637
+ "learning_rate": 0.0008792539173700046,
638
+ "loss": 0.9056,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.6137061029662462,
643
+ "grad_norm": 0.11240353319322192,
644
+ "learning_rate": 0.0008753467848257366,
645
+ "loss": 0.9023,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.6205250596658711,
650
+ "grad_norm": 0.12884203346821665,
651
+ "learning_rate": 0.0008713864196751353,
652
+ "loss": 0.891,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.6273440163654961,
657
+ "grad_norm": 0.13107538778471978,
658
+ "learning_rate": 0.0008673733835869496,
659
+ "loss": 0.9053,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.634162973065121,
664
+ "grad_norm": 0.1265128902066715,
665
+ "learning_rate": 0.0008633082456998505,
666
+ "loss": 0.8765,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.640981929764746,
671
+ "grad_norm": 0.11168557466408092,
672
+ "learning_rate": 0.0008591915825417144,
673
+ "loss": 0.8937,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.647800886464371,
678
+ "grad_norm": 0.10749488343940884,
679
+ "learning_rate": 0.0008550239779478592,
680
+ "loss": 0.8936,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.6546198431639959,
685
+ "grad_norm": 0.12116636988129866,
686
+ "learning_rate": 0.0008508060229782422,
687
+ "loss": 0.8985,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.6614387998636209,
692
+ "grad_norm": 0.11248409191993927,
693
+ "learning_rate": 0.0008465383158336352,
694
+ "loss": 0.9068,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.6682577565632458,
699
+ "grad_norm": 0.09616110942207395,
700
+ "learning_rate": 0.0008422214617707864,
701
+ "loss": 0.893,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.6750767132628708,
706
+ "grad_norm": 0.10944978412158525,
707
+ "learning_rate": 0.000837856073016581,
708
+ "loss": 0.9015,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.6818956699624957,
713
+ "grad_norm": 0.12373353259009305,
714
+ "learning_rate": 0.0008334427686812137,
715
+ "loss": 0.8805,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.6887146266621207,
720
+ "grad_norm": 0.10998182720982563,
721
+ "learning_rate": 0.000828982174670385,
722
+ "loss": 0.8764,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.6955335833617456,
727
+ "grad_norm": 0.11981879919775634,
728
+ "learning_rate": 0.0008244749235965338,
729
+ "loss": 0.8972,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.7023525400613706,
734
+ "grad_norm": 0.11009515701872061,
735
+ "learning_rate": 0.000819921654689119,
736
+ "loss": 0.883,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.7091714967609956,
741
+ "grad_norm": 0.1206592530642094,
742
+ "learning_rate": 0.0008153230137039615,
743
+ "loss": 0.8887,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.7159904534606205,
748
+ "grad_norm": 0.10679229804484212,
749
+ "learning_rate": 0.0008106796528316626,
750
+ "loss": 0.8894,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.7228094101602455,
755
+ "grad_norm": 0.11030470444996518,
756
+ "learning_rate": 0.000805992230605108,
757
+ "loss": 0.8881,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.7296283668598704,
762
+ "grad_norm": 0.14989020257644473,
763
+ "learning_rate": 0.0008012614118060733,
764
+ "loss": 0.8758,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.7364473235594954,
769
+ "grad_norm": 0.19608291727965096,
770
+ "learning_rate": 0.0007964878673709432,
771
+ "loss": 0.873,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.7432662802591203,
776
+ "grad_norm": 0.1357305661381077,
777
+ "learning_rate": 0.0007916722742955573,
778
+ "loss": 0.878,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.7500852369587453,
783
+ "grad_norm": 0.09279906563803725,
784
+ "learning_rate": 0.0007868153155391968,
785
+ "loss": 0.8844,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.7569041936583703,
790
+ "grad_norm": 0.1003975725083102,
791
+ "learning_rate": 0.0007819176799277262,
792
+ "loss": 0.8875,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.7637231503579952,
797
+ "grad_norm": 0.09978871199012411,
798
+ "learning_rate": 0.0007769800620559015,
799
+ "loss": 0.8866,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.7705421070576202,
804
+ "grad_norm": 0.13532770031312716,
805
+ "learning_rate": 0.0007720031621888615,
806
+ "loss": 0.879,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.7773610637572451,
811
+ "grad_norm": 0.10118664495666357,
812
+ "learning_rate": 0.0007669876861628144,
813
+ "loss": 0.87,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.7841800204568701,
818
+ "grad_norm": 0.09994831940420743,
819
+ "learning_rate": 0.0007619343452849349,
820
+ "loss": 0.8759,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.790998977156495,
825
+ "grad_norm": 0.12994411471721243,
826
+ "learning_rate": 0.0007568438562324833,
827
+ "loss": 0.8783,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.79781793385612,
832
+ "grad_norm": 0.1169831966799223,
833
+ "learning_rate": 0.0007517169409511664,
834
+ "loss": 0.8672,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.8046368905557449,
839
+ "grad_norm": 0.10141671278849922,
840
+ "learning_rate": 0.0007465543265527482,
841
+ "loss": 0.8695,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.8114558472553699,
846
+ "grad_norm": 0.11783176873723326,
847
+ "learning_rate": 0.0007413567452119298,
848
+ "loss": 0.8689,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.8182748039549949,
853
+ "grad_norm": 0.12718960852527547,
854
+ "learning_rate": 0.00073612493406251,
855
+ "loss": 0.8708,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.8250937606546198,
860
+ "grad_norm": 0.12649370297868867,
861
+ "learning_rate": 0.0007308596350928434,
862
+ "loss": 0.8759,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.8319127173542448,
867
+ "grad_norm": 0.1009142565676403,
868
+ "learning_rate": 0.0007255615950406102,
869
+ "loss": 0.862,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.8387316740538697,
874
+ "grad_norm": 0.10490423262148889,
875
+ "learning_rate": 0.0007202315652869112,
876
+ "loss": 0.87,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.8455506307534947,
881
+ "grad_norm": 0.09903668718402683,
882
+ "learning_rate": 0.0007148703017497058,
883
+ "loss": 0.8705,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.8523695874531196,
888
+ "grad_norm": 0.14442585966687965,
889
+ "learning_rate": 0.0007094785647766055,
890
+ "loss": 0.8681,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.8591885441527446,
895
+ "grad_norm": 0.16498073796059864,
896
+ "learning_rate": 0.0007040571190370397,
897
+ "loss": 0.8656,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.8660075008523695,
902
+ "grad_norm": 0.1129999366359928,
903
+ "learning_rate": 0.0006986067334138079,
904
+ "loss": 0.8686,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.8728264575519945,
909
+ "grad_norm": 0.09929311073474267,
910
+ "learning_rate": 0.0006931281808940361,
911
+ "loss": 0.8687,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.8796454142516195,
916
+ "grad_norm": 0.11972041401629113,
917
+ "learning_rate": 0.0006876222384595477,
918
+ "loss": 0.8652,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.8864643709512444,
923
+ "grad_norm": 0.09934940714328987,
924
+ "learning_rate": 0.0006820896869766725,
925
+ "loss": 0.8709,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.8932833276508694,
930
+ "grad_norm": 0.10973507676224258,
931
+ "learning_rate": 0.0006765313110855009,
932
+ "loss": 0.8652,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.9001022843504943,
937
+ "grad_norm": 0.09165992876326395,
938
+ "learning_rate": 0.0006709478990886039,
939
+ "loss": 0.8611,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.9069212410501193,
944
+ "grad_norm": 0.09988220618681196,
945
+ "learning_rate": 0.0006653402428392354,
946
+ "loss": 0.8556,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.9137401977497442,
951
+ "grad_norm": 0.09446350263562757,
952
+ "learning_rate": 0.0006597091376290288,
953
+ "loss": 0.8528,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.9205591544493692,
958
+ "grad_norm": 0.08902820350532409,
959
+ "learning_rate": 0.0006540553820752069,
960
+ "loss": 0.8609,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.9273781111489942,
965
+ "grad_norm": 0.10011816954581992,
966
+ "learning_rate": 0.00064837977800732,
967
+ "loss": 0.8625,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.9341970678486191,
972
+ "grad_norm": 0.08775726631732685,
973
+ "learning_rate": 0.0006426831303535284,
974
+ "loss": 0.8576,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.9410160245482441,
979
+ "grad_norm": 0.11117730920395297,
980
+ "learning_rate": 0.0006369662470264462,
981
+ "loss": 0.8704,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.947834981247869,
986
+ "grad_norm": 0.139154974071725,
987
+ "learning_rate": 0.0006312299388085596,
988
+ "loss": 0.8584,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.954653937947494,
993
+ "grad_norm": 0.10346972946518294,
994
+ "learning_rate": 0.0006254750192372418,
995
+ "loss": 0.8709,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.9614728946471189,
1000
+ "grad_norm": 0.09900042387283375,
1001
+ "learning_rate": 0.0006197023044893734,
1002
+ "loss": 0.8482,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.968291851346744,
1007
+ "grad_norm": 0.09908280186750126,
1008
+ "learning_rate": 0.0006139126132655905,
1009
+ "loss": 0.8597,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.975110808046369,
1014
+ "grad_norm": 0.13127044402154367,
1015
+ "learning_rate": 0.0006081067666741757,
1016
+ "loss": 0.8483,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.9819297647459939,
1021
+ "grad_norm": 0.09623829465725477,
1022
+ "learning_rate": 0.0006022855881146053,
1023
+ "loss": 0.8589,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.9887487214456189,
1028
+ "grad_norm": 0.09762948252187646,
1029
+ "learning_rate": 0.0005964499031607727,
1030
+ "loss": 0.8479,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.9955676781452438,
1035
+ "grad_norm": 0.11109345413298818,
1036
+ "learning_rate": 0.0005906005394439044,
1037
+ "loss": 0.8625,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.9996590521650187,
1042
+ "eval_loss": 0.8650394678115845,
1043
+ "eval_runtime": 60.297,
1044
+ "eval_samples_per_second": 184.404,
1045
+ "eval_steps_per_second": 5.771,
1046
+ "step": 733
1047
+ },
1048
+ {
1049
+ "epoch": 1.0023866348448687,
1050
+ "grad_norm": 0.150003136868036,
1051
+ "learning_rate": 0.0005847383265351828,
1052
+ "loss": 0.8218,
1053
+ "step": 735
1054
+ },
1055
+ {
1056
+ "epoch": 1.0092055915444937,
1057
+ "grad_norm": 0.1668337683466409,
1058
+ "learning_rate": 0.0005788640958280941,
1059
+ "loss": 0.7516,
1060
+ "step": 740
1061
+ },
1062
+ {
1063
+ "epoch": 1.0160245482441186,
1064
+ "grad_norm": 0.14142825658305677,
1065
+ "learning_rate": 0.0005729786804205181,
1066
+ "loss": 0.7548,
1067
+ "step": 745
1068
+ },
1069
+ {
1070
+ "epoch": 1.0228435049437437,
1071
+ "grad_norm": 0.12528810569521878,
1072
+ "learning_rate": 0.0005670829149965773,
1073
+ "loss": 0.7473,
1074
+ "step": 750
1075
+ },
1076
+ {
1077
+ "epoch": 1.0296624616433685,
1078
+ "grad_norm": 0.11736651721866655,
1079
+ "learning_rate": 0.0005611776357082579,
1080
+ "loss": 0.747,
1081
+ "step": 755
1082
+ },
1083
+ {
1084
+ "epoch": 1.0364814183429936,
1085
+ "grad_norm": 0.09403020504249461,
1086
+ "learning_rate": 0.0005552636800568266,
1087
+ "loss": 0.7621,
1088
+ "step": 760
1089
+ },
1090
+ {
1091
+ "epoch": 1.0433003750426184,
1092
+ "grad_norm": 0.11315198038951943,
1093
+ "learning_rate": 0.0005493418867740529,
1094
+ "loss": 0.745,
1095
+ "step": 765
1096
+ },
1097
+ {
1098
+ "epoch": 1.0501193317422435,
1099
+ "grad_norm": 0.1022560757959738,
1100
+ "learning_rate": 0.0005434130957032589,
1101
+ "loss": 0.7459,
1102
+ "step": 770
1103
+ },
1104
+ {
1105
+ "epoch": 1.0569382884418683,
1106
+ "grad_norm": 0.10922375995449658,
1107
+ "learning_rate": 0.0005374781476802096,
1108
+ "loss": 0.7466,
1109
+ "step": 775
1110
+ },
1111
+ {
1112
+ "epoch": 1.0637572451414934,
1113
+ "grad_norm": 0.5193070680732547,
1114
+ "learning_rate": 0.0005315378844138647,
1115
+ "loss": 0.7627,
1116
+ "step": 780
1117
+ },
1118
+ {
1119
+ "epoch": 1.0705762018411182,
1120
+ "grad_norm": 0.12177144687559627,
1121
+ "learning_rate": 0.0005255931483670049,
1122
+ "loss": 0.7546,
1123
+ "step": 785
1124
+ },
1125
+ {
1126
+ "epoch": 1.0773951585407433,
1127
+ "grad_norm": 0.7694014802591276,
1128
+ "learning_rate": 0.000519644782636751,
1129
+ "loss": 0.7528,
1130
+ "step": 790
1131
+ },
1132
+ {
1133
+ "epoch": 1.0842141152403681,
1134
+ "grad_norm": 0.11357197300498553,
1135
+ "learning_rate": 0.000513693630834995,
1136
+ "loss": 0.7533,
1137
+ "step": 795
1138
+ },
1139
+ {
1140
+ "epoch": 1.0910330719399932,
1141
+ "grad_norm": 0.09386251189985013,
1142
+ "learning_rate": 0.0005077405369687564,
1143
+ "loss": 0.7542,
1144
+ "step": 800
1145
+ },
1146
+ {
1147
+ "epoch": 1.097852028639618,
1148
+ "grad_norm": 0.09656492984059917,
1149
+ "learning_rate": 0.0005017863453204828,
1150
+ "loss": 0.7453,
1151
+ "step": 805
1152
+ },
1153
+ {
1154
+ "epoch": 1.1046709853392431,
1155
+ "grad_norm": 0.09988629196548339,
1156
+ "learning_rate": 0.0004958319003283121,
1157
+ "loss": 0.7567,
1158
+ "step": 810
1159
+ },
1160
+ {
1161
+ "epoch": 1.111489942038868,
1162
+ "grad_norm": 0.1340291294865019,
1163
+ "learning_rate": 0.0004898780464663119,
1164
+ "loss": 0.7572,
1165
+ "step": 815
1166
+ },
1167
+ {
1168
+ "epoch": 1.118308898738493,
1169
+ "grad_norm": 0.12216818040509048,
1170
+ "learning_rate": 0.00048392562812471485,
1171
+ "loss": 0.7386,
1172
+ "step": 820
1173
+ },
1174
+ {
1175
+ "epoch": 1.1251278554381179,
1176
+ "grad_norm": 0.10511324731067179,
1177
+ "learning_rate": 0.0004779754894901638,
1178
+ "loss": 0.7551,
1179
+ "step": 825
1180
+ },
1181
+ {
1182
+ "epoch": 1.131946812137743,
1183
+ "grad_norm": 0.08878475250721538,
1184
+ "learning_rate": 0.00047202847442598845,
1185
+ "loss": 0.7476,
1186
+ "step": 830
1187
+ },
1188
+ {
1189
+ "epoch": 1.1387657688373678,
1190
+ "grad_norm": 0.10961153167460981,
1191
+ "learning_rate": 0.0004660854263525255,
1192
+ "loss": 0.7501,
1193
+ "step": 835
1194
+ },
1195
+ {
1196
+ "epoch": 1.1455847255369929,
1197
+ "grad_norm": 0.11227235770228143,
1198
+ "learning_rate": 0.0004601471881275041,
1199
+ "loss": 0.7468,
1200
+ "step": 840
1201
+ },
1202
+ {
1203
+ "epoch": 1.1524036822366177,
1204
+ "grad_norm": 0.14319195588727593,
1205
+ "learning_rate": 0.00045421460192650786,
1206
+ "loss": 0.7459,
1207
+ "step": 845
1208
+ },
1209
+ {
1210
+ "epoch": 1.1592226389362428,
1211
+ "grad_norm": 0.12581674820255845,
1212
+ "learning_rate": 0.00044828850912353703,
1213
+ "loss": 0.7496,
1214
+ "step": 850
1215
+ },
1216
+ {
1217
+ "epoch": 1.1660415956358676,
1218
+ "grad_norm": 0.10879564209007402,
1219
+ "learning_rate": 0.0004423697501716823,
1220
+ "loss": 0.7377,
1221
+ "step": 855
1222
+ },
1223
+ {
1224
+ "epoch": 1.1728605523354927,
1225
+ "grad_norm": 0.10910700864864685,
1226
+ "learning_rate": 0.00043645916448392885,
1227
+ "loss": 0.7569,
1228
+ "step": 860
1229
+ },
1230
+ {
1231
+ "epoch": 1.1796795090351175,
1232
+ "grad_norm": 0.12233584779335835,
1233
+ "learning_rate": 0.00043055759031411007,
1234
+ "loss": 0.7451,
1235
+ "step": 865
1236
+ },
1237
+ {
1238
+ "epoch": 1.1864984657347426,
1239
+ "grad_norm": 0.09336996907684925,
1240
+ "learning_rate": 0.0004246658646380229,
1241
+ "loss": 0.7486,
1242
+ "step": 870
1243
+ },
1244
+ {
1245
+ "epoch": 1.1933174224343674,
1246
+ "grad_norm": 0.09297895821672336,
1247
+ "learning_rate": 0.00041878482303472745,
1248
+ "loss": 0.7522,
1249
+ "step": 875
1250
+ },
1251
+ {
1252
+ "epoch": 1.2001363791339925,
1253
+ "grad_norm": 0.09998221831882348,
1254
+ "learning_rate": 0.00041291529956804195,
1255
+ "loss": 0.756,
1256
+ "step": 880
1257
+ },
1258
+ {
1259
+ "epoch": 1.2069553358336174,
1260
+ "grad_norm": 0.09246595578930603,
1261
+ "learning_rate": 0.0004070581266682539,
1262
+ "loss": 0.7564,
1263
+ "step": 885
1264
+ },
1265
+ {
1266
+ "epoch": 1.2137742925332424,
1267
+ "grad_norm": 0.09888677663554202,
1268
+ "learning_rate": 0.000401214135014063,
1269
+ "loss": 0.7406,
1270
+ "step": 890
1271
+ },
1272
+ {
1273
+ "epoch": 1.2205932492328673,
1274
+ "grad_norm": 0.09840879351277865,
1275
+ "learning_rate": 0.0003953841534147725,
1276
+ "loss": 0.7444,
1277
+ "step": 895
1278
+ },
1279
+ {
1280
+ "epoch": 1.2274122059324923,
1281
+ "grad_norm": 0.09608186181313223,
1282
+ "learning_rate": 0.000389569008692745,
1283
+ "loss": 0.7434,
1284
+ "step": 900
1285
+ },
1286
+ {
1287
+ "epoch": 1.2342311626321174,
1288
+ "grad_norm": 0.12027155555266326,
1289
+ "learning_rate": 0.0003837695255661403,
1290
+ "loss": 0.7505,
1291
+ "step": 905
1292
+ },
1293
+ {
1294
+ "epoch": 1.2410501193317423,
1295
+ "grad_norm": 0.09938398385533825,
1296
+ "learning_rate": 0.00037798652653195266,
1297
+ "loss": 0.7524,
1298
+ "step": 910
1299
+ },
1300
+ {
1301
+ "epoch": 1.247869076031367,
1302
+ "grad_norm": 0.0963922155626505,
1303
+ "learning_rate": 0.00037222083174936137,
1304
+ "loss": 0.7481,
1305
+ "step": 915
1306
+ },
1307
+ {
1308
+ "epoch": 1.2546880327309922,
1309
+ "grad_norm": 0.0959346234671189,
1310
+ "learning_rate": 0.00036647325892341393,
1311
+ "loss": 0.7398,
1312
+ "step": 920
1313
+ },
1314
+ {
1315
+ "epoch": 1.2615069894306172,
1316
+ "grad_norm": 0.08820345622198668,
1317
+ "learning_rate": 0.0003607446231890575,
1318
+ "loss": 0.7405,
1319
+ "step": 925
1320
+ },
1321
+ {
1322
+ "epoch": 1.268325946130242,
1323
+ "grad_norm": 0.11589956732636802,
1324
+ "learning_rate": 0.0003550357369955347,
1325
+ "loss": 0.7509,
1326
+ "step": 930
1327
+ },
1328
+ {
1329
+ "epoch": 1.275144902829867,
1330
+ "grad_norm": 0.10547612256066802,
1331
+ "learning_rate": 0.00034934740999115866,
1332
+ "loss": 0.7502,
1333
+ "step": 935
1334
+ },
1335
+ {
1336
+ "epoch": 1.281963859529492,
1337
+ "grad_norm": 0.11823191257134831,
1338
+ "learning_rate": 0.00034368044890848814,
1339
+ "loss": 0.7661,
1340
+ "step": 940
1341
+ },
1342
+ {
1343
+ "epoch": 1.288782816229117,
1344
+ "grad_norm": 0.09346920096074791,
1345
+ "learning_rate": 0.0003380356574499141,
1346
+ "loss": 0.7409,
1347
+ "step": 945
1348
+ },
1349
+ {
1350
+ "epoch": 1.295601772928742,
1351
+ "grad_norm": 0.09247106405202875,
1352
+ "learning_rate": 0.00033241383617367706,
1353
+ "loss": 0.7448,
1354
+ "step": 950
1355
+ },
1356
+ {
1357
+ "epoch": 1.3024207296283667,
1358
+ "grad_norm": 0.10126097744075767,
1359
+ "learning_rate": 0.00032681578238032914,
1360
+ "loss": 0.7455,
1361
+ "step": 955
1362
+ },
1363
+ {
1364
+ "epoch": 1.3092396863279918,
1365
+ "grad_norm": 0.10957664402150283,
1366
+ "learning_rate": 0.0003212422899996599,
1367
+ "loss": 0.7442,
1368
+ "step": 960
1369
+ },
1370
+ {
1371
+ "epoch": 1.3160586430276169,
1372
+ "grad_norm": 0.08997598908036177,
1373
+ "learning_rate": 0.0003156941494780983,
1374
+ "loss": 0.7399,
1375
+ "step": 965
1376
+ },
1377
+ {
1378
+ "epoch": 1.3228775997272417,
1379
+ "grad_norm": 0.09339106504051306,
1380
+ "learning_rate": 0.0003101721476666106,
1381
+ "loss": 0.7473,
1382
+ "step": 970
1383
+ },
1384
+ {
1385
+ "epoch": 1.3296965564268666,
1386
+ "grad_norm": 0.09094074237158431,
1387
+ "learning_rate": 0.00030467706770910687,
1388
+ "loss": 0.7349,
1389
+ "step": 975
1390
+ },
1391
+ {
1392
+ "epoch": 1.3365155131264916,
1393
+ "grad_norm": 0.08949096519435662,
1394
+ "learning_rate": 0.00029920968893137277,
1395
+ "loss": 0.7335,
1396
+ "step": 980
1397
+ },
1398
+ {
1399
+ "epoch": 1.3433344698261167,
1400
+ "grad_norm": 0.10666408169466289,
1401
+ "learning_rate": 0.00029377078673054524,
1402
+ "loss": 0.7431,
1403
+ "step": 985
1404
+ },
1405
+ {
1406
+ "epoch": 1.3501534265257416,
1407
+ "grad_norm": 0.09360456030533196,
1408
+ "learning_rate": 0.00028836113246514215,
1409
+ "loss": 0.7504,
1410
+ "step": 990
1411
+ },
1412
+ {
1413
+ "epoch": 1.3569723832253664,
1414
+ "grad_norm": 0.0857322076398207,
1415
+ "learning_rate": 0.00028298149334566745,
1416
+ "loss": 0.7461,
1417
+ "step": 995
1418
+ },
1419
+ {
1420
+ "epoch": 1.3637913399249915,
1421
+ "grad_norm": 0.08664863370331233,
1422
+ "learning_rate": 0.0002776326323258029,
1423
+ "loss": 0.7347,
1424
+ "step": 1000
1425
+ },
1426
+ {
1427
+ "epoch": 1.3706102966246165,
1428
+ "grad_norm": 0.09553160941014031,
1429
+ "learning_rate": 0.0002723153079942047,
1430
+ "loss": 0.7432,
1431
+ "step": 1005
1432
+ },
1433
+ {
1434
+ "epoch": 1.3774292533242414,
1435
+ "grad_norm": 0.09757917450665214,
1436
+ "learning_rate": 0.00026703027446691753,
1437
+ "loss": 0.7319,
1438
+ "step": 1010
1439
+ },
1440
+ {
1441
+ "epoch": 1.3842482100238662,
1442
+ "grad_norm": 0.13001681090880932,
1443
+ "learning_rate": 0.0002617782812804252,
1444
+ "loss": 0.731,
1445
+ "step": 1015
1446
+ },
1447
+ {
1448
+ "epoch": 1.3910671667234913,
1449
+ "grad_norm": 0.09842205689754281,
1450
+ "learning_rate": 0.00025656007328534857,
1451
+ "loss": 0.7377,
1452
+ "step": 1020
1453
+ },
1454
+ {
1455
+ "epoch": 1.3978861234231164,
1456
+ "grad_norm": 0.08966471368100484,
1457
+ "learning_rate": 0.00025137639054080975,
1458
+ "loss": 0.7393,
1459
+ "step": 1025
1460
+ },
1461
+ {
1462
+ "epoch": 1.4047050801227412,
1463
+ "grad_norm": 0.09544505949561016,
1464
+ "learning_rate": 0.0002462279682094742,
1465
+ "loss": 0.7448,
1466
+ "step": 1030
1467
+ },
1468
+ {
1469
+ "epoch": 1.411524036822366,
1470
+ "grad_norm": 0.09721892448809809,
1471
+ "learning_rate": 0.00024111553645328872,
1472
+ "loss": 0.7383,
1473
+ "step": 1035
1474
+ },
1475
+ {
1476
+ "epoch": 1.4183429935219911,
1477
+ "grad_norm": 0.09528944859478844,
1478
+ "learning_rate": 0.00023603982032992861,
1479
+ "loss": 0.743,
1480
+ "step": 1040
1481
+ },
1482
+ {
1483
+ "epoch": 1.4251619502216162,
1484
+ "grad_norm": 0.09295756990644403,
1485
+ "learning_rate": 0.00023100153968996678,
1486
+ "loss": 0.7354,
1487
+ "step": 1045
1488
+ },
1489
+ {
1490
+ "epoch": 1.431980906921241,
1491
+ "grad_norm": 0.09085933894422743,
1492
+ "learning_rate": 0.0002260014090747845,
1493
+ "loss": 0.7363,
1494
+ "step": 1050
1495
+ },
1496
+ {
1497
+ "epoch": 1.4387998636208659,
1498
+ "grad_norm": 0.09685032026741523,
1499
+ "learning_rate": 0.00022104013761523156,
1500
+ "loss": 0.7457,
1501
+ "step": 1055
1502
+ },
1503
+ {
1504
+ "epoch": 1.445618820320491,
1505
+ "grad_norm": 0.08857516230100924,
1506
+ "learning_rate": 0.00021611842893105726,
1507
+ "loss": 0.742,
1508
+ "step": 1060
1509
+ },
1510
+ {
1511
+ "epoch": 1.452437777020116,
1512
+ "grad_norm": 0.08773056464470375,
1513
+ "learning_rate": 0.0002112369810311201,
1514
+ "loss": 0.7332,
1515
+ "step": 1065
1516
+ },
1517
+ {
1518
+ "epoch": 1.4592567337197409,
1519
+ "grad_norm": 0.0900763405573559,
1520
+ "learning_rate": 0.00020639648621439488,
1521
+ "loss": 0.7449,
1522
+ "step": 1070
1523
+ },
1524
+ {
1525
+ "epoch": 1.466075690419366,
1526
+ "grad_norm": 0.09851993938416971,
1527
+ "learning_rate": 0.00020159763097178952,
1528
+ "loss": 0.7402,
1529
+ "step": 1075
1530
+ },
1531
+ {
1532
+ "epoch": 1.4728946471189908,
1533
+ "grad_norm": 0.08759892676999576,
1534
+ "learning_rate": 0.0001968410958887849,
1535
+ "loss": 0.7445,
1536
+ "step": 1080
1537
+ },
1538
+ {
1539
+ "epoch": 1.4797136038186158,
1540
+ "grad_norm": 0.0907347079072196,
1541
+ "learning_rate": 0.0001921275555489122,
1542
+ "loss": 0.7399,
1543
+ "step": 1085
1544
+ },
1545
+ {
1546
+ "epoch": 1.4865325605182407,
1547
+ "grad_norm": 0.08112607532285956,
1548
+ "learning_rate": 0.00018745767843808209,
1549
+ "loss": 0.7304,
1550
+ "step": 1090
1551
+ },
1552
+ {
1553
+ "epoch": 1.4933515172178657,
1554
+ "grad_norm": 0.09161753107862378,
1555
+ "learning_rate": 0.000182832126849779,
1556
+ "loss": 0.7285,
1557
+ "step": 1095
1558
+ },
1559
+ {
1560
+ "epoch": 1.5001704739174906,
1561
+ "grad_norm": 0.08358605650538908,
1562
+ "learning_rate": 0.00017825155679113204,
1563
+ "loss": 0.7348,
1564
+ "step": 1100
1565
+ },
1566
+ {
1567
+ "epoch": 1.5069894306171157,
1568
+ "grad_norm": 0.08675686822052969,
1569
+ "learning_rate": 0.00017371661788987875,
1570
+ "loss": 0.7409,
1571
+ "step": 1105
1572
+ },
1573
+ {
1574
+ "epoch": 1.5138083873167405,
1575
+ "grad_norm": 0.08810226317282835,
1576
+ "learning_rate": 0.0001692279533022339,
1577
+ "loss": 0.7384,
1578
+ "step": 1110
1579
+ },
1580
+ {
1581
+ "epoch": 1.5206273440163653,
1582
+ "grad_norm": 0.08950130348184156,
1583
+ "learning_rate": 0.00016478619962167495,
1584
+ "loss": 0.7492,
1585
+ "step": 1115
1586
+ },
1587
+ {
1588
+ "epoch": 1.5274463007159904,
1589
+ "grad_norm": 0.08034358957544274,
1590
+ "learning_rate": 0.00016039198678865861,
1591
+ "loss": 0.7332,
1592
+ "step": 1120
1593
+ },
1594
+ {
1595
+ "epoch": 1.5342652574156155,
1596
+ "grad_norm": 0.09875564116278145,
1597
+ "learning_rate": 0.00015604593800128157,
1598
+ "loss": 0.7245,
1599
+ "step": 1125
1600
+ },
1601
+ {
1602
+ "epoch": 1.5410842141152403,
1603
+ "grad_norm": 0.08654215732134887,
1604
+ "learning_rate": 0.00015174866962689655,
1605
+ "loss": 0.735,
1606
+ "step": 1130
1607
+ },
1608
+ {
1609
+ "epoch": 1.5479031708148652,
1610
+ "grad_norm": 0.08592984519220763,
1611
+ "learning_rate": 0.00014750079111469844,
1612
+ "loss": 0.7409,
1613
+ "step": 1135
1614
+ },
1615
+ {
1616
+ "epoch": 1.5547221275144902,
1617
+ "grad_norm": 0.09146622488124098,
1618
+ "learning_rate": 0.00014330290490928936,
1619
+ "loss": 0.7307,
1620
+ "step": 1140
1621
+ },
1622
+ {
1623
+ "epoch": 1.5615410842141153,
1624
+ "grad_norm": 0.09107009139517197,
1625
+ "learning_rate": 0.00013915560636524005,
1626
+ "loss": 0.7298,
1627
+ "step": 1145
1628
+ },
1629
+ {
1630
+ "epoch": 1.5683600409137401,
1631
+ "grad_norm": 0.08290920543587224,
1632
+ "learning_rate": 0.0001350594836626537,
1633
+ "loss": 0.7288,
1634
+ "step": 1150
1635
+ },
1636
+ {
1637
+ "epoch": 1.575178997613365,
1638
+ "grad_norm": 0.089017743866575,
1639
+ "learning_rate": 0.00013101511772375002,
1640
+ "loss": 0.721,
1641
+ "step": 1155
1642
+ },
1643
+ {
1644
+ "epoch": 1.58199795431299,
1645
+ "grad_norm": 0.08395496088906577,
1646
+ "learning_rate": 0.00012702308213047653,
1647
+ "loss": 0.7369,
1648
+ "step": 1160
1649
+ },
1650
+ {
1651
+ "epoch": 1.5888169110126151,
1652
+ "grad_norm": 0.09332825258379267,
1653
+ "learning_rate": 0.00012308394304316224,
1654
+ "loss": 0.7331,
1655
+ "step": 1165
1656
+ },
1657
+ {
1658
+ "epoch": 1.59563586771224,
1659
+ "grad_norm": 0.08663551849922511,
1660
+ "learning_rate": 0.00011919825912022336,
1661
+ "loss": 0.7284,
1662
+ "step": 1170
1663
+ },
1664
+ {
1665
+ "epoch": 1.6024548244118648,
1666
+ "grad_norm": 0.08467643435872389,
1667
+ "learning_rate": 0.00011536658143893309,
1668
+ "loss": 0.73,
1669
+ "step": 1175
1670
+ },
1671
+ {
1672
+ "epoch": 1.6092737811114899,
1673
+ "grad_norm": 0.10792296188935317,
1674
+ "learning_rate": 0.0001115894534172659,
1675
+ "loss": 0.7304,
1676
+ "step": 1180
1677
+ },
1678
+ {
1679
+ "epoch": 1.616092737811115,
1680
+ "grad_norm": 0.08665506882217053,
1681
+ "learning_rate": 0.0001078674107368291,
1682
+ "loss": 0.7365,
1683
+ "step": 1185
1684
+ },
1685
+ {
1686
+ "epoch": 1.6229116945107398,
1687
+ "grad_norm": 0.0869258591144236,
1688
+ "learning_rate": 0.00010420098126689159,
1689
+ "loss": 0.7271,
1690
+ "step": 1190
1691
+ },
1692
+ {
1693
+ "epoch": 1.6297306512103649,
1694
+ "grad_norm": 0.08082381008828005,
1695
+ "learning_rate": 0.00010059068498951912,
1696
+ "loss": 0.7334,
1697
+ "step": 1195
1698
+ },
1699
+ {
1700
+ "epoch": 1.63654960790999,
1701
+ "grad_norm": 0.09653014658305435,
1702
+ "learning_rate": 9.70370339258298e-05,
1703
+ "loss": 0.733,
1704
+ "step": 1200
1705
+ },
1706
+ {
1707
+ "epoch": 1.6433685646096148,
1708
+ "grad_norm": 0.08209631476731684,
1709
+ "learning_rate": 9.354053206337803e-05,
1710
+ "loss": 0.7295,
1711
+ "step": 1205
1712
+ },
1713
+ {
1714
+ "epoch": 1.6501875213092396,
1715
+ "grad_norm": 0.08281543379309102,
1716
+ "learning_rate": 9.010167528467784e-05,
1717
+ "loss": 0.7282,
1718
+ "step": 1210
1719
+ },
1720
+ {
1721
+ "epoch": 1.6570064780088647,
1722
+ "grad_norm": 0.09079242657548177,
1723
+ "learning_rate": 8.672095129687485e-05,
1724
+ "loss": 0.7332,
1725
+ "step": 1215
1726
+ },
1727
+ {
1728
+ "epoch": 1.6638254347084898,
1729
+ "grad_norm": 0.08732562104521625,
1730
+ "learning_rate": 8.33988395625791e-05,
1731
+ "loss": 0.7196,
1732
+ "step": 1220
1733
+ },
1734
+ {
1735
+ "epoch": 1.6706443914081146,
1736
+ "grad_norm": 0.09634799774642026,
1737
+ "learning_rate": 8.013581123186675e-05,
1738
+ "loss": 0.7243,
1739
+ "step": 1225
1740
+ },
1741
+ {
1742
+ "epoch": 1.6774633481077394,
1743
+ "grad_norm": 0.0892053596550817,
1744
+ "learning_rate": 7.693232907545955e-05,
1745
+ "loss": 0.7284,
1746
+ "step": 1230
1747
+ },
1748
+ {
1749
+ "epoch": 1.6842823048073645,
1750
+ "grad_norm": 0.08080152740232713,
1751
+ "learning_rate": 7.378884741909409e-05,
1752
+ "loss": 0.7226,
1753
+ "step": 1235
1754
+ },
1755
+ {
1756
+ "epoch": 1.6911012615069896,
1757
+ "grad_norm": 0.08211682147824328,
1758
+ "learning_rate": 7.070581207908832e-05,
1759
+ "loss": 0.7293,
1760
+ "step": 1240
1761
+ },
1762
+ {
1763
+ "epoch": 1.6979202182066144,
1764
+ "grad_norm": 0.08125416074026208,
1765
+ "learning_rate": 6.76836602991146e-05,
1766
+ "loss": 0.7241,
1767
+ "step": 1245
1768
+ },
1769
+ {
1770
+ "epoch": 1.7047391749062393,
1771
+ "grad_norm": 0.08118597843483698,
1772
+ "learning_rate": 6.472282068818857e-05,
1773
+ "loss": 0.7176,
1774
+ "step": 1250
1775
+ },
1776
+ {
1777
+ "epoch": 1.7115581316058643,
1778
+ "grad_norm": 0.08444459255476687,
1779
+ "learning_rate": 6.182371315988283e-05,
1780
+ "loss": 0.7345,
1781
+ "step": 1255
1782
+ },
1783
+ {
1784
+ "epoch": 1.7183770883054894,
1785
+ "grad_norm": 0.08993862852560496,
1786
+ "learning_rate": 5.898674887277394e-05,
1787
+ "loss": 0.7287,
1788
+ "step": 1260
1789
+ },
1790
+ {
1791
+ "epoch": 1.7251960450051143,
1792
+ "grad_norm": 0.09172625446804755,
1793
+ "learning_rate": 5.621233017213095e-05,
1794
+ "loss": 0.728,
1795
+ "step": 1265
1796
+ },
1797
+ {
1798
+ "epoch": 1.732015001704739,
1799
+ "grad_norm": 0.09728192339349417,
1800
+ "learning_rate": 5.3500850532853477e-05,
1801
+ "loss": 0.7252,
1802
+ "step": 1270
1803
+ },
1804
+ {
1805
+ "epoch": 1.7388339584043642,
1806
+ "grad_norm": 0.08183637004716483,
1807
+ "learning_rate": 5.085269450366836e-05,
1808
+ "loss": 0.7249,
1809
+ "step": 1275
1810
+ },
1811
+ {
1812
+ "epoch": 1.7456529151039892,
1813
+ "grad_norm": 0.08417398467645139,
1814
+ "learning_rate": 4.8268237652591805e-05,
1815
+ "loss": 0.7263,
1816
+ "step": 1280
1817
+ },
1818
+ {
1819
+ "epoch": 1.752471871803614,
1820
+ "grad_norm": 0.08559525343966955,
1821
+ "learning_rate": 4.574784651366581e-05,
1822
+ "loss": 0.7307,
1823
+ "step": 1285
1824
+ },
1825
+ {
1826
+ "epoch": 1.759290828503239,
1827
+ "grad_norm": 0.08652462817281027,
1828
+ "learning_rate": 4.329187853497491e-05,
1829
+ "loss": 0.7321,
1830
+ "step": 1290
1831
+ },
1832
+ {
1833
+ "epoch": 1.766109785202864,
1834
+ "grad_norm": 0.07780149732014437,
1835
+ "learning_rate": 4.0900682027952274e-05,
1836
+ "loss": 0.7259,
1837
+ "step": 1295
1838
+ },
1839
+ {
1840
+ "epoch": 1.772928741902489,
1841
+ "grad_norm": 0.08073420987197251,
1842
+ "learning_rate": 3.8574596117981367e-05,
1843
+ "loss": 0.7318,
1844
+ "step": 1300
1845
+ },
1846
+ {
1847
+ "epoch": 1.779747698602114,
1848
+ "grad_norm": 0.09399125884464814,
1849
+ "learning_rate": 3.631395069630039e-05,
1850
+ "loss": 0.7286,
1851
+ "step": 1305
1852
+ },
1853
+ {
1854
+ "epoch": 1.7865666553017387,
1855
+ "grad_norm": 0.08683728371693161,
1856
+ "learning_rate": 3.411906637321588e-05,
1857
+ "loss": 0.7281,
1858
+ "step": 1310
1859
+ },
1860
+ {
1861
+ "epoch": 1.7933856120013638,
1862
+ "grad_norm": 0.08220865889050938,
1863
+ "learning_rate": 3.199025443263331e-05,
1864
+ "loss": 0.7214,
1865
+ "step": 1315
1866
+ },
1867
+ {
1868
+ "epoch": 1.8002045687009889,
1869
+ "grad_norm": 0.08394991114226853,
1870
+ "learning_rate": 2.9927816787910233e-05,
1871
+ "loss": 0.7274,
1872
+ "step": 1320
1873
+ },
1874
+ {
1875
+ "epoch": 1.8070235254006137,
1876
+ "grad_norm": 0.08648979166756451,
1877
+ "learning_rate": 2.79320459390377e-05,
1878
+ "loss": 0.728,
1879
+ "step": 1325
1880
+ },
1881
+ {
1882
+ "epoch": 1.8138424821002386,
1883
+ "grad_norm": 0.0809919030945408,
1884
+ "learning_rate": 2.600322493115742e-05,
1885
+ "loss": 0.7207,
1886
+ "step": 1330
1887
+ },
1888
+ {
1889
+ "epoch": 1.8206614387998636,
1890
+ "grad_norm": 0.08146420956821185,
1891
+ "learning_rate": 2.414162731441971e-05,
1892
+ "loss": 0.7279,
1893
+ "step": 1335
1894
+ },
1895
+ {
1896
+ "epoch": 1.8274803954994887,
1897
+ "grad_norm": 0.08991080627514368,
1898
+ "learning_rate": 2.2347517105187952e-05,
1899
+ "loss": 0.7285,
1900
+ "step": 1340
1901
+ },
1902
+ {
1903
+ "epoch": 1.8342993521991136,
1904
+ "grad_norm": 0.08113174604843235,
1905
+ "learning_rate": 2.062114874859483e-05,
1906
+ "loss": 0.7212,
1907
+ "step": 1345
1908
+ },
1909
+ {
1910
+ "epoch": 1.8411183088987384,
1911
+ "grad_norm": 0.0890991046050432,
1912
+ "learning_rate": 1.8962767082456368e-05,
1913
+ "loss": 0.7238,
1914
+ "step": 1350
1915
+ },
1916
+ {
1917
+ "epoch": 1.8479372655983635,
1918
+ "grad_norm": 0.08194468587127682,
1919
+ "learning_rate": 1.7372607302548916e-05,
1920
+ "loss": 0.7278,
1921
+ "step": 1355
1922
+ },
1923
+ {
1924
+ "epoch": 1.8547562222979885,
1925
+ "grad_norm": 0.0796060532873072,
1926
+ "learning_rate": 1.58508949292524e-05,
1927
+ "loss": 0.7303,
1928
+ "step": 1360
1929
+ },
1930
+ {
1931
+ "epoch": 1.8615751789976134,
1932
+ "grad_norm": 0.08325978355636353,
1933
+ "learning_rate": 1.439784577556702e-05,
1934
+ "loss": 0.7259,
1935
+ "step": 1365
1936
+ },
1937
+ {
1938
+ "epoch": 1.8683941356972382,
1939
+ "grad_norm": 0.08101951703165321,
1940
+ "learning_rate": 1.3013665916505824e-05,
1941
+ "loss": 0.7213,
1942
+ "step": 1370
1943
+ },
1944
+ {
1945
+ "epoch": 1.8752130923968633,
1946
+ "grad_norm": 0.07474258489762015,
1947
+ "learning_rate": 1.1698551659868716e-05,
1948
+ "loss": 0.7251,
1949
+ "step": 1375
1950
+ },
1951
+ {
1952
+ "epoch": 1.8820320490964884,
1953
+ "grad_norm": 0.07988354824659524,
1954
+ "learning_rate": 1.0452689518401615e-05,
1955
+ "loss": 0.7336,
1956
+ "step": 1380
1957
+ },
1958
+ {
1959
+ "epoch": 1.8888510057961132,
1960
+ "grad_norm": 0.0869204045893242,
1961
+ "learning_rate": 9.276256183344767e-06,
1962
+ "loss": 0.7225,
1963
+ "step": 1385
1964
+ },
1965
+ {
1966
+ "epoch": 1.895669962495738,
1967
+ "grad_norm": 0.08073129640276419,
1968
+ "learning_rate": 8.169418499373749e-06,
1969
+ "loss": 0.719,
1970
+ "step": 1390
1971
+ },
1972
+ {
1973
+ "epoch": 1.9024889191953631,
1974
+ "grad_norm": 0.09277363778878074,
1975
+ "learning_rate": 7.132333440937666e-06,
1976
+ "loss": 0.7163,
1977
+ "step": 1395
1978
+ },
1979
+ {
1980
+ "epoch": 1.9093078758949882,
1981
+ "grad_norm": 0.08156654600969289,
1982
+ "learning_rate": 6.165148089996075e-06,
1983
+ "loss": 0.7294,
1984
+ "step": 1400
1985
+ },
1986
+ {
1987
+ "epoch": 1.916126832594613,
1988
+ "grad_norm": 0.07931208656000137,
1989
+ "learning_rate": 5.267999615159724e-06,
1990
+ "loss": 0.7188,
1991
+ "step": 1405
1992
+ },
1993
+ {
1994
+ "epoch": 1.9229457892942379,
1995
+ "grad_norm": 0.08734085147118956,
1996
+ "learning_rate": 4.441015252237113e-06,
1997
+ "loss": 0.7239,
1998
+ "step": 1410
1999
+ },
2000
+ {
2001
+ "epoch": 1.929764745993863,
2002
+ "grad_norm": 0.07927625348774799,
2003
+ "learning_rate": 3.684312286189151e-06,
2004
+ "loss": 0.737,
2005
+ "step": 1415
2006
+ },
2007
+ {
2008
+ "epoch": 1.936583702693488,
2009
+ "grad_norm": 0.08278514720419748,
2010
+ "learning_rate": 2.997998034495908e-06,
2011
+ "loss": 0.7232,
2012
+ "step": 1420
2013
+ },
2014
+ {
2015
+ "epoch": 1.9434026593931129,
2016
+ "grad_norm": 0.09337537685419582,
2017
+ "learning_rate": 2.382169831936565e-06,
2018
+ "loss": 0.7327,
2019
+ "step": 1425
2020
+ },
2021
+ {
2022
+ "epoch": 1.9502216160927377,
2023
+ "grad_norm": 0.07802348568191127,
2024
+ "learning_rate": 1.8369150167848459e-06,
2025
+ "loss": 0.7168,
2026
+ "step": 1430
2027
+ },
2028
+ {
2029
+ "epoch": 1.9570405727923628,
2030
+ "grad_norm": 0.07582457656438514,
2031
+ "learning_rate": 1.3623109184228711e-06,
2032
+ "loss": 0.7111,
2033
+ "step": 1435
2034
+ },
2035
+ {
2036
+ "epoch": 1.9638595294919878,
2037
+ "grad_norm": 0.07999706762970123,
2038
+ "learning_rate": 9.584248463739288e-07,
2039
+ "loss": 0.7251,
2040
+ "step": 1440
2041
+ },
2042
+ {
2043
+ "epoch": 1.9706784861916127,
2044
+ "grad_norm": 0.08421307868632791,
2045
+ "learning_rate": 6.253140807562785e-07,
2046
+ "loss": 0.7172,
2047
+ "step": 1445
2048
+ },
2049
+ {
2050
+ "epoch": 1.9774974428912375,
2051
+ "grad_norm": 0.08148471965897129,
2052
+ "learning_rate": 3.630258641600381e-07,
2053
+ "loss": 0.7198,
2054
+ "step": 1450
2055
+ },
2056
+ {
2057
+ "epoch": 1.9843163995908626,
2058
+ "grad_norm": 0.0748791624620726,
2059
+ "learning_rate": 1.7159739494654325e-07,
2060
+ "loss": 0.7267,
2061
+ "step": 1455
2062
+ },
2063
+ {
2064
+ "epoch": 1.9911353562904877,
2065
+ "grad_norm": 0.08613985665976748,
2066
+ "learning_rate": 5.1055821973289286e-08,
2067
+ "loss": 0.7258,
2068
+ "step": 1460
2069
+ },
2070
+ {
2071
+ "epoch": 1.9979543129901125,
2072
+ "grad_norm": 0.07749130518414991,
2073
+ "learning_rate": 1.418240743289445e-09,
2074
+ "loss": 0.7335,
2075
+ "step": 1465
2076
+ },
2077
+ {
2078
+ "epoch": 1.9993181043300376,
2079
+ "eval_loss": 0.8305559158325195,
2080
+ "eval_runtime": 60.2883,
2081
+ "eval_samples_per_second": 184.43,
2082
+ "eval_steps_per_second": 5.772,
2083
+ "step": 1466
2084
+ },
2085
+ {
2086
+ "epoch": 1.9993181043300376,
2087
+ "step": 1466,
2088
+ "total_flos": 143858545459200.0,
2089
+ "train_loss": 0.8359313647060732,
2090
+ "train_runtime": 3324.125,
2091
+ "train_samples_per_second": 56.452,
2092
+ "train_steps_per_second": 0.441
2093
+ }
2094
+ ],
2095
+ "logging_steps": 5,
2096
+ "max_steps": 1466,
2097
+ "num_input_tokens_seen": 0,
2098
+ "num_train_epochs": 2,
2099
+ "save_steps": 500,
2100
+ "stateful_callbacks": {
2101
+ "TrainerControl": {
2102
+ "args": {
2103
+ "should_epoch_stop": false,
2104
+ "should_evaluate": false,
2105
+ "should_log": false,
2106
+ "should_save": false,
2107
+ "should_training_stop": false
2108
+ },
2109
+ "attributes": {}
2110
+ }
2111
+ },
2112
+ "total_flos": 143858545459200.0,
2113
+ "train_batch_size": 4,
2114
+ "trial_name": null,
2115
+ "trial_params": null
2116
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96cca02508b727e076d57c43ce4884c2f90972aa53af1c053ec444d70216adbc
3
+ size 6520
vocab.json ADDED
The diff for this file is too large to render. See raw diff