cutelemonlili commited on
Commit
3797171
·
verified ·
1 Parent(s): 5686798

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-0.5B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: MATH_training_sdft_response_Qwen2.5_0.5B_only_right
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # MATH_training_sdft_response_Qwen2.5_0.5B_only_right
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the MATH_training_sdft_response_Qwen2.5_0.5B_only_right dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1223
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - total_train_batch_size: 8
47
+ - total_eval_batch_size: 4
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - num_epochs: 2
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.1647 | 0.9390 | 200 | 0.1349 |
57
+ | 0.0539 | 1.8779 | 400 | 0.1225 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.46.1
63
+ - Pytorch 2.5.1+cu124
64
+ - Datasets 3.1.0
65
+ - Tokenizers 0.20.3
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.12230074405670166,
4
+ "eval_runtime": 0.7137,
5
+ "eval_samples_per_second": 25.22,
6
+ "eval_steps_per_second": 7.006,
7
+ "total_flos": 1768470073344.0,
8
+ "train_loss": 0.13181914092684296,
9
+ "train_runtime": 275.8873,
10
+ "train_samples_per_second": 12.317,
11
+ "train_steps_per_second": 1.544
12
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 14,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 151936
29
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.12230074405670166,
4
+ "eval_runtime": 0.7137,
5
+ "eval_samples_per_second": 25.22,
6
+ "eval_steps_per_second": 7.006
7
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.1"
14
+ }
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 sha256:50b1161fc9c1073f47f879c65325fcb9c38748df4368780dab4e98f8fff55f47
3
+ size 988097824
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 1768470073344.0,
4
+ "train_loss": 0.13181914092684296,
5
+ "train_runtime": 275.8873,
6
+ "train_samples_per_second": 12.317,
7
+ "train_steps_per_second": 1.544
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,429 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 426, "loss": 0.5112, "lr": 9.999864037673424e-06, "epoch": 0.004694835680751174, "percentage": 0.23, "elapsed_time": "0:00:01", "remaining_time": "0:12:32"}
2
+ {"current_steps": 2, "total_steps": 426, "loss": 0.5814, "lr": 9.999456158087994e-06, "epoch": 0.009389671361502348, "percentage": 0.47, "elapsed_time": "0:00:05", "remaining_time": "0:20:32"}
3
+ {"current_steps": 3, "total_steps": 426, "loss": 0.479, "lr": 9.998776383426217e-06, "epoch": 0.014084507042253521, "percentage": 0.7, "elapsed_time": "0:00:06", "remaining_time": "0:15:07"}
4
+ {"current_steps": 4, "total_steps": 426, "loss": 0.5216, "lr": 9.997824750657586e-06, "epoch": 0.018779342723004695, "percentage": 0.94, "elapsed_time": "0:00:07", "remaining_time": "0:12:23"}
5
+ {"current_steps": 5, "total_steps": 426, "loss": 0.4186, "lr": 9.996601311536586e-06, "epoch": 0.023474178403755867, "percentage": 1.17, "elapsed_time": "0:00:07", "remaining_time": "0:10:47"}
6
+ {"current_steps": 6, "total_steps": 426, "loss": 0.3469, "lr": 9.995106132599869e-06, "epoch": 0.028169014084507043, "percentage": 1.41, "elapsed_time": "0:00:08", "remaining_time": "0:09:41"}
7
+ {"current_steps": 7, "total_steps": 426, "loss": 0.3785, "lr": 9.993339295162637e-06, "epoch": 0.03286384976525822, "percentage": 1.64, "elapsed_time": "0:00:08", "remaining_time": "0:08:53"}
8
+ {"current_steps": 8, "total_steps": 426, "loss": 0.3432, "lr": 9.99130089531422e-06, "epoch": 0.03755868544600939, "percentage": 1.88, "elapsed_time": "0:00:09", "remaining_time": "0:08:18"}
9
+ {"current_steps": 9, "total_steps": 426, "loss": 0.3235, "lr": 9.988991043912857e-06, "epoch": 0.04225352112676056, "percentage": 2.11, "elapsed_time": "0:00:10", "remaining_time": "0:07:50"}
10
+ {"current_steps": 10, "total_steps": 426, "loss": 0.3698, "lr": 9.98640986657965e-06, "epoch": 0.046948356807511735, "percentage": 2.35, "elapsed_time": "0:00:10", "remaining_time": "0:07:28"}
11
+ {"current_steps": 11, "total_steps": 426, "loss": 0.2923, "lr": 9.983557503691755e-06, "epoch": 0.051643192488262914, "percentage": 2.58, "elapsed_time": "0:00:11", "remaining_time": "0:07:10"}
12
+ {"current_steps": 12, "total_steps": 426, "loss": 0.3107, "lr": 9.980434110374725e-06, "epoch": 0.056338028169014086, "percentage": 2.82, "elapsed_time": "0:00:12", "remaining_time": "0:06:56"}
13
+ {"current_steps": 13, "total_steps": 426, "loss": 0.2975, "lr": 9.977039856494091e-06, "epoch": 0.06103286384976526, "percentage": 3.05, "elapsed_time": "0:00:12", "remaining_time": "0:06:42"}
14
+ {"current_steps": 14, "total_steps": 426, "loss": 0.3518, "lr": 9.973374926646117e-06, "epoch": 0.06572769953051644, "percentage": 3.29, "elapsed_time": "0:00:13", "remaining_time": "0:06:31"}
15
+ {"current_steps": 15, "total_steps": 426, "loss": 0.2697, "lr": 9.969439520147754e-06, "epoch": 0.07042253521126761, "percentage": 3.52, "elapsed_time": "0:00:13", "remaining_time": "0:06:21"}
16
+ {"current_steps": 16, "total_steps": 426, "loss": 0.2818, "lr": 9.965233851025816e-06, "epoch": 0.07511737089201878, "percentage": 3.76, "elapsed_time": "0:00:14", "remaining_time": "0:06:12"}
17
+ {"current_steps": 17, "total_steps": 426, "loss": 0.2619, "lr": 9.960758148005323e-06, "epoch": 0.07981220657276995, "percentage": 3.99, "elapsed_time": "0:00:15", "remaining_time": "0:06:05"}
18
+ {"current_steps": 18, "total_steps": 426, "loss": 0.2755, "lr": 9.956012654497073e-06, "epoch": 0.08450704225352113, "percentage": 4.23, "elapsed_time": "0:00:15", "remaining_time": "0:05:57"}
19
+ {"current_steps": 19, "total_steps": 426, "loss": 0.2486, "lr": 9.950997628584404e-06, "epoch": 0.0892018779342723, "percentage": 4.46, "elapsed_time": "0:00:16", "remaining_time": "0:05:52"}
20
+ {"current_steps": 20, "total_steps": 426, "loss": 0.2501, "lr": 9.945713343009154e-06, "epoch": 0.09389671361502347, "percentage": 4.69, "elapsed_time": "0:00:17", "remaining_time": "0:05:46"}
21
+ {"current_steps": 21, "total_steps": 426, "loss": 0.2854, "lr": 9.94016008515682e-06, "epoch": 0.09859154929577464, "percentage": 4.93, "elapsed_time": "0:00:17", "remaining_time": "0:05:40"}
22
+ {"current_steps": 22, "total_steps": 426, "loss": 0.2531, "lr": 9.934338157040953e-06, "epoch": 0.10328638497652583, "percentage": 5.16, "elapsed_time": "0:00:18", "remaining_time": "0:05:35"}
23
+ {"current_steps": 23, "total_steps": 426, "loss": 0.2523, "lr": 9.928247875286705e-06, "epoch": 0.107981220657277, "percentage": 5.4, "elapsed_time": "0:00:18", "remaining_time": "0:05:31"}
24
+ {"current_steps": 24, "total_steps": 426, "loss": 0.2434, "lr": 9.921889571113629e-06, "epoch": 0.11267605633802817, "percentage": 5.63, "elapsed_time": "0:00:19", "remaining_time": "0:05:27"}
25
+ {"current_steps": 25, "total_steps": 426, "loss": 0.2718, "lr": 9.915263590317654e-06, "epoch": 0.11737089201877934, "percentage": 5.87, "elapsed_time": "0:00:20", "remaining_time": "0:05:23"}
26
+ {"current_steps": 26, "total_steps": 426, "loss": 0.2921, "lr": 9.90837029325229e-06, "epoch": 0.12206572769953052, "percentage": 6.1, "elapsed_time": "0:00:20", "remaining_time": "0:05:19"}
27
+ {"current_steps": 27, "total_steps": 426, "loss": 0.2147, "lr": 9.901210054809015e-06, "epoch": 0.1267605633802817, "percentage": 6.34, "elapsed_time": "0:00:21", "remaining_time": "0:05:16"}
28
+ {"current_steps": 28, "total_steps": 426, "loss": 0.2637, "lr": 9.893783264396903e-06, "epoch": 0.13145539906103287, "percentage": 6.57, "elapsed_time": "0:00:22", "remaining_time": "0:05:12"}
29
+ {"current_steps": 29, "total_steps": 426, "loss": 0.2321, "lr": 9.886090325921435e-06, "epoch": 0.13615023474178403, "percentage": 6.81, "elapsed_time": "0:00:22", "remaining_time": "0:05:09"}
30
+ {"current_steps": 30, "total_steps": 426, "loss": 0.3077, "lr": 9.878131657762535e-06, "epoch": 0.14084507042253522, "percentage": 7.04, "elapsed_time": "0:00:23", "remaining_time": "0:05:06"}
31
+ {"current_steps": 31, "total_steps": 426, "loss": 0.2806, "lr": 9.86990769275182e-06, "epoch": 0.14553990610328638, "percentage": 7.28, "elapsed_time": "0:00:23", "remaining_time": "0:05:03"}
32
+ {"current_steps": 32, "total_steps": 426, "loss": 0.2824, "lr": 9.861418878149056e-06, "epoch": 0.15023474178403756, "percentage": 7.51, "elapsed_time": "0:00:24", "remaining_time": "0:05:00"}
33
+ {"current_steps": 33, "total_steps": 426, "loss": 0.2407, "lr": 9.852665675617837e-06, "epoch": 0.15492957746478872, "percentage": 7.75, "elapsed_time": "0:00:25", "remaining_time": "0:04:58"}
34
+ {"current_steps": 34, "total_steps": 426, "loss": 0.2418, "lr": 9.843648561200476e-06, "epoch": 0.1596244131455399, "percentage": 7.98, "elapsed_time": "0:00:25", "remaining_time": "0:04:56"}
35
+ {"current_steps": 35, "total_steps": 426, "loss": 0.2238, "lr": 9.834368025292112e-06, "epoch": 0.1643192488262911, "percentage": 8.22, "elapsed_time": "0:00:26", "remaining_time": "0:04:53"}
36
+ {"current_steps": 36, "total_steps": 426, "loss": 0.1777, "lr": 9.82482457261405e-06, "epoch": 0.16901408450704225, "percentage": 8.45, "elapsed_time": "0:00:26", "remaining_time": "0:04:51"}
37
+ {"current_steps": 37, "total_steps": 426, "loss": 0.2386, "lr": 9.8150187221863e-06, "epoch": 0.17370892018779344, "percentage": 8.69, "elapsed_time": "0:00:27", "remaining_time": "0:04:49"}
38
+ {"current_steps": 38, "total_steps": 426, "loss": 0.2047, "lr": 9.80495100729936e-06, "epoch": 0.1784037558685446, "percentage": 8.92, "elapsed_time": "0:00:28", "remaining_time": "0:04:47"}
39
+ {"current_steps": 39, "total_steps": 426, "loss": 0.1926, "lr": 9.7946219754852e-06, "epoch": 0.18309859154929578, "percentage": 9.15, "elapsed_time": "0:00:28", "remaining_time": "0:04:45"}
40
+ {"current_steps": 40, "total_steps": 426, "loss": 0.215, "lr": 9.784032188487507e-06, "epoch": 0.18779342723004694, "percentage": 9.39, "elapsed_time": "0:00:29", "remaining_time": "0:04:43"}
41
+ {"current_steps": 41, "total_steps": 426, "loss": 0.2514, "lr": 9.773182222231104e-06, "epoch": 0.19248826291079812, "percentage": 9.62, "elapsed_time": "0:00:29", "remaining_time": "0:04:41"}
42
+ {"current_steps": 42, "total_steps": 426, "loss": 0.1938, "lr": 9.762072666790658e-06, "epoch": 0.19718309859154928, "percentage": 9.86, "elapsed_time": "0:00:30", "remaining_time": "0:04:39"}
43
+ {"current_steps": 43, "total_steps": 426, "loss": 0.1956, "lr": 9.750704126358568e-06, "epoch": 0.20187793427230047, "percentage": 10.09, "elapsed_time": "0:00:31", "remaining_time": "0:04:38"}
44
+ {"current_steps": 44, "total_steps": 426, "loss": 0.2453, "lr": 9.73907721921212e-06, "epoch": 0.20657276995305165, "percentage": 10.33, "elapsed_time": "0:00:31", "remaining_time": "0:04:36"}
45
+ {"current_steps": 45, "total_steps": 426, "loss": 0.2213, "lr": 9.727192577679852e-06, "epoch": 0.2112676056338028, "percentage": 10.56, "elapsed_time": "0:00:32", "remaining_time": "0:04:34"}
46
+ {"current_steps": 46, "total_steps": 426, "loss": 0.1572, "lr": 9.715050848107167e-06, "epoch": 0.215962441314554, "percentage": 10.8, "elapsed_time": "0:00:33", "remaining_time": "0:04:35"}
47
+ {"current_steps": 47, "total_steps": 426, "loss": 0.197, "lr": 9.702652690821188e-06, "epoch": 0.22065727699530516, "percentage": 11.03, "elapsed_time": "0:00:33", "remaining_time": "0:04:33"}
48
+ {"current_steps": 48, "total_steps": 426, "loss": 0.1852, "lr": 9.689998780094839e-06, "epoch": 0.22535211267605634, "percentage": 11.27, "elapsed_time": "0:00:34", "remaining_time": "0:04:32"}
49
+ {"current_steps": 49, "total_steps": 426, "loss": 0.2511, "lr": 9.677089804110173e-06, "epoch": 0.2300469483568075, "percentage": 11.5, "elapsed_time": "0:00:35", "remaining_time": "0:04:30"}
50
+ {"current_steps": 50, "total_steps": 426, "loss": 0.2268, "lr": 9.663926464920959e-06, "epoch": 0.2347417840375587, "percentage": 11.74, "elapsed_time": "0:00:35", "remaining_time": "0:04:28"}
51
+ {"current_steps": 51, "total_steps": 426, "loss": 0.2202, "lr": 9.650509478414483e-06, "epoch": 0.23943661971830985, "percentage": 11.97, "elapsed_time": "0:00:36", "remaining_time": "0:04:27"}
52
+ {"current_steps": 52, "total_steps": 426, "loss": 0.2327, "lr": 9.636839574272623e-06, "epoch": 0.24413145539906103, "percentage": 12.21, "elapsed_time": "0:00:36", "remaining_time": "0:04:26"}
53
+ {"current_steps": 53, "total_steps": 426, "loss": 0.1751, "lr": 9.622917495932172e-06, "epoch": 0.24882629107981222, "percentage": 12.44, "elapsed_time": "0:00:37", "remaining_time": "0:04:24"}
54
+ {"current_steps": 54, "total_steps": 426, "loss": 0.1788, "lr": 9.608744000544392e-06, "epoch": 0.2535211267605634, "percentage": 12.68, "elapsed_time": "0:00:38", "remaining_time": "0:04:23"}
55
+ {"current_steps": 55, "total_steps": 426, "loss": 0.2295, "lr": 9.594319858933847e-06, "epoch": 0.25821596244131456, "percentage": 12.91, "elapsed_time": "0:00:38", "remaining_time": "0:04:22"}
56
+ {"current_steps": 56, "total_steps": 426, "loss": 0.1806, "lr": 9.579645855556481e-06, "epoch": 0.26291079812206575, "percentage": 13.15, "elapsed_time": "0:00:39", "remaining_time": "0:04:21"}
57
+ {"current_steps": 57, "total_steps": 426, "loss": 0.1775, "lr": 9.564722788456943e-06, "epoch": 0.2676056338028169, "percentage": 13.38, "elapsed_time": "0:00:40", "remaining_time": "0:04:20"}
58
+ {"current_steps": 58, "total_steps": 426, "loss": 0.1939, "lr": 9.54955146922521e-06, "epoch": 0.27230046948356806, "percentage": 13.62, "elapsed_time": "0:00:40", "remaining_time": "0:04:19"}
59
+ {"current_steps": 59, "total_steps": 426, "loss": 0.1721, "lr": 9.534132722952419e-06, "epoch": 0.27699530516431925, "percentage": 13.85, "elapsed_time": "0:00:41", "remaining_time": "0:04:17"}
60
+ {"current_steps": 60, "total_steps": 426, "loss": 0.184, "lr": 9.51846738818602e-06, "epoch": 0.28169014084507044, "percentage": 14.08, "elapsed_time": "0:00:42", "remaining_time": "0:04:16"}
61
+ {"current_steps": 61, "total_steps": 426, "loss": 0.1849, "lr": 9.502556316884157e-06, "epoch": 0.2863849765258216, "percentage": 14.32, "elapsed_time": "0:00:42", "remaining_time": "0:04:15"}
62
+ {"current_steps": 62, "total_steps": 426, "loss": 0.2188, "lr": 9.48640037436934e-06, "epoch": 0.29107981220657275, "percentage": 14.55, "elapsed_time": "0:00:43", "remaining_time": "0:04:14"}
63
+ {"current_steps": 63, "total_steps": 426, "loss": 0.2013, "lr": 9.470000439281379e-06, "epoch": 0.29577464788732394, "percentage": 14.79, "elapsed_time": "0:00:43", "remaining_time": "0:04:12"}
64
+ {"current_steps": 64, "total_steps": 426, "loss": 0.1902, "lr": 9.453357403529609e-06, "epoch": 0.3004694835680751, "percentage": 15.02, "elapsed_time": "0:00:44", "remaining_time": "0:04:11"}
65
+ {"current_steps": 65, "total_steps": 426, "loss": 0.1958, "lr": 9.436472172244374e-06, "epoch": 0.3051643192488263, "percentage": 15.26, "elapsed_time": "0:00:45", "remaining_time": "0:04:10"}
66
+ {"current_steps": 66, "total_steps": 426, "loss": 0.1856, "lr": 9.419345663727805e-06, "epoch": 0.30985915492957744, "percentage": 15.49, "elapsed_time": "0:00:45", "remaining_time": "0:04:09"}
67
+ {"current_steps": 67, "total_steps": 426, "loss": 0.1556, "lr": 9.401978809403882e-06, "epoch": 0.3145539906103286, "percentage": 15.73, "elapsed_time": "0:00:46", "remaining_time": "0:04:08"}
68
+ {"current_steps": 68, "total_steps": 426, "loss": 0.2187, "lr": 9.38437255376777e-06, "epoch": 0.3192488262910798, "percentage": 15.96, "elapsed_time": "0:00:47", "remaining_time": "0:04:07"}
69
+ {"current_steps": 69, "total_steps": 426, "loss": 0.2231, "lr": 9.366527854334464e-06, "epoch": 0.323943661971831, "percentage": 16.2, "elapsed_time": "0:00:47", "remaining_time": "0:04:06"}
70
+ {"current_steps": 70, "total_steps": 426, "loss": 0.1569, "lr": 9.348445681586703e-06, "epoch": 0.3286384976525822, "percentage": 16.43, "elapsed_time": "0:00:48", "remaining_time": "0:04:05"}
71
+ {"current_steps": 71, "total_steps": 426, "loss": 0.1597, "lr": 9.330127018922195e-06, "epoch": 0.3333333333333333, "percentage": 16.67, "elapsed_time": "0:00:48", "remaining_time": "0:04:04"}
72
+ {"current_steps": 72, "total_steps": 426, "loss": 0.2194, "lr": 9.31157286260014e-06, "epoch": 0.3380281690140845, "percentage": 16.9, "elapsed_time": "0:00:49", "remaining_time": "0:04:03"}
73
+ {"current_steps": 73, "total_steps": 426, "loss": 0.1803, "lr": 9.292784221687043e-06, "epoch": 0.3427230046948357, "percentage": 17.14, "elapsed_time": "0:00:50", "remaining_time": "0:04:02"}
74
+ {"current_steps": 74, "total_steps": 426, "loss": 0.2177, "lr": 9.273762118001837e-06, "epoch": 0.3474178403755869, "percentage": 17.37, "elapsed_time": "0:00:50", "remaining_time": "0:04:01"}
75
+ {"current_steps": 75, "total_steps": 426, "loss": 0.1675, "lr": 9.25450758606031e-06, "epoch": 0.352112676056338, "percentage": 17.61, "elapsed_time": "0:00:51", "remaining_time": "0:04:00"}
76
+ {"current_steps": 76, "total_steps": 426, "loss": 0.2049, "lr": 9.235021673018849e-06, "epoch": 0.3568075117370892, "percentage": 17.84, "elapsed_time": "0:00:52", "remaining_time": "0:03:59"}
77
+ {"current_steps": 77, "total_steps": 426, "loss": 0.174, "lr": 9.21530543861748e-06, "epoch": 0.3615023474178404, "percentage": 18.08, "elapsed_time": "0:00:52", "remaining_time": "0:03:58"}
78
+ {"current_steps": 78, "total_steps": 426, "loss": 0.1986, "lr": 9.195359955122244e-06, "epoch": 0.36619718309859156, "percentage": 18.31, "elapsed_time": "0:00:53", "remaining_time": "0:03:57"}
79
+ {"current_steps": 79, "total_steps": 426, "loss": 0.1991, "lr": 9.175186307266877e-06, "epoch": 0.37089201877934275, "percentage": 18.54, "elapsed_time": "0:00:53", "remaining_time": "0:03:56"}
80
+ {"current_steps": 80, "total_steps": 426, "loss": 0.1914, "lr": 9.15478559219382e-06, "epoch": 0.3755868544600939, "percentage": 18.78, "elapsed_time": "0:00:54", "remaining_time": "0:03:55"}
81
+ {"current_steps": 81, "total_steps": 426, "loss": 0.1921, "lr": 9.134158919394545e-06, "epoch": 0.38028169014084506, "percentage": 19.01, "elapsed_time": "0:00:55", "remaining_time": "0:03:54"}
82
+ {"current_steps": 82, "total_steps": 426, "loss": 0.2081, "lr": 9.113307410649222e-06, "epoch": 0.38497652582159625, "percentage": 19.25, "elapsed_time": "0:00:55", "remaining_time": "0:03:53"}
83
+ {"current_steps": 83, "total_steps": 426, "loss": 0.1836, "lr": 9.092232199965707e-06, "epoch": 0.38967136150234744, "percentage": 19.48, "elapsed_time": "0:00:56", "remaining_time": "0:03:53"}
84
+ {"current_steps": 84, "total_steps": 426, "loss": 0.1781, "lr": 9.070934433517872e-06, "epoch": 0.39436619718309857, "percentage": 19.72, "elapsed_time": "0:00:57", "remaining_time": "0:03:52"}
85
+ {"current_steps": 85, "total_steps": 426, "loss": 0.1924, "lr": 9.049415269583268e-06, "epoch": 0.39906103286384975, "percentage": 19.95, "elapsed_time": "0:00:57", "remaining_time": "0:03:51"}
86
+ {"current_steps": 86, "total_steps": 426, "loss": 0.2079, "lr": 9.027675878480131e-06, "epoch": 0.40375586854460094, "percentage": 20.19, "elapsed_time": "0:00:58", "remaining_time": "0:03:50"}
87
+ {"current_steps": 87, "total_steps": 426, "loss": 0.2016, "lr": 9.005717442503741e-06, "epoch": 0.4084507042253521, "percentage": 20.42, "elapsed_time": "0:00:58", "remaining_time": "0:03:49"}
88
+ {"current_steps": 88, "total_steps": 426, "loss": 0.2229, "lr": 8.983541155862114e-06, "epoch": 0.4131455399061033, "percentage": 20.66, "elapsed_time": "0:00:59", "remaining_time": "0:03:48"}
89
+ {"current_steps": 89, "total_steps": 426, "loss": 0.1736, "lr": 8.96114822461106e-06, "epoch": 0.41784037558685444, "percentage": 20.89, "elapsed_time": "0:01:00", "remaining_time": "0:03:47"}
90
+ {"current_steps": 90, "total_steps": 426, "loss": 0.1647, "lr": 8.938539866588593e-06, "epoch": 0.4225352112676056, "percentage": 21.13, "elapsed_time": "0:01:00", "remaining_time": "0:03:46"}
91
+ {"current_steps": 91, "total_steps": 426, "loss": 0.1854, "lr": 8.915717311348693e-06, "epoch": 0.4272300469483568, "percentage": 21.36, "elapsed_time": "0:01:01", "remaining_time": "0:03:45"}
92
+ {"current_steps": 92, "total_steps": 426, "loss": 0.1802, "lr": 8.892681800094447e-06, "epoch": 0.431924882629108, "percentage": 21.6, "elapsed_time": "0:01:01", "remaining_time": "0:03:45"}
93
+ {"current_steps": 93, "total_steps": 426, "loss": 0.1934, "lr": 8.869434585610534e-06, "epoch": 0.43661971830985913, "percentage": 21.83, "elapsed_time": "0:01:02", "remaining_time": "0:03:44"}
94
+ {"current_steps": 94, "total_steps": 426, "loss": 0.1899, "lr": 8.845976932195104e-06, "epoch": 0.4413145539906103, "percentage": 22.07, "elapsed_time": "0:01:03", "remaining_time": "0:03:43"}
95
+ {"current_steps": 95, "total_steps": 426, "loss": 0.1997, "lr": 8.822310115591008e-06, "epoch": 0.4460093896713615, "percentage": 22.3, "elapsed_time": "0:01:03", "remaining_time": "0:03:42"}
96
+ {"current_steps": 96, "total_steps": 426, "loss": 0.185, "lr": 8.798435422916425e-06, "epoch": 0.4507042253521127, "percentage": 22.54, "elapsed_time": "0:01:04", "remaining_time": "0:03:41"}
97
+ {"current_steps": 97, "total_steps": 426, "loss": 0.1785, "lr": 8.774354152594862e-06, "epoch": 0.45539906103286387, "percentage": 22.77, "elapsed_time": "0:01:05", "remaining_time": "0:03:40"}
98
+ {"current_steps": 98, "total_steps": 426, "loss": 0.1791, "lr": 8.750067614284534e-06, "epoch": 0.460093896713615, "percentage": 23.0, "elapsed_time": "0:01:05", "remaining_time": "0:03:40"}
99
+ {"current_steps": 99, "total_steps": 426, "loss": 0.1845, "lr": 8.725577128807144e-06, "epoch": 0.4647887323943662, "percentage": 23.24, "elapsed_time": "0:01:06", "remaining_time": "0:03:39"}
100
+ {"current_steps": 100, "total_steps": 426, "loss": 0.1769, "lr": 8.700884028076042e-06, "epoch": 0.4694835680751174, "percentage": 23.47, "elapsed_time": "0:01:07", "remaining_time": "0:03:38"}
101
+ {"current_steps": 101, "total_steps": 426, "loss": 0.162, "lr": 8.675989655023802e-06, "epoch": 0.47417840375586856, "percentage": 23.71, "elapsed_time": "0:01:07", "remaining_time": "0:03:37"}
102
+ {"current_steps": 102, "total_steps": 426, "loss": 0.155, "lr": 8.650895363529172e-06, "epoch": 0.4788732394366197, "percentage": 23.94, "elapsed_time": "0:01:08", "remaining_time": "0:03:37"}
103
+ {"current_steps": 103, "total_steps": 426, "loss": 0.191, "lr": 8.625602518343457e-06, "epoch": 0.4835680751173709, "percentage": 24.18, "elapsed_time": "0:01:09", "remaining_time": "0:03:36"}
104
+ {"current_steps": 104, "total_steps": 426, "loss": 0.1921, "lr": 8.600112495016289e-06, "epoch": 0.48826291079812206, "percentage": 24.41, "elapsed_time": "0:01:09", "remaining_time": "0:03:35"}
105
+ {"current_steps": 105, "total_steps": 426, "loss": 0.2151, "lr": 8.574426679820813e-06, "epoch": 0.49295774647887325, "percentage": 24.65, "elapsed_time": "0:01:10", "remaining_time": "0:03:34"}
106
+ {"current_steps": 106, "total_steps": 426, "loss": 0.2053, "lr": 8.548546469678311e-06, "epoch": 0.49765258215962443, "percentage": 24.88, "elapsed_time": "0:01:10", "remaining_time": "0:03:33"}
107
+ {"current_steps": 107, "total_steps": 426, "loss": 0.1923, "lr": 8.522473272082217e-06, "epoch": 0.5023474178403756, "percentage": 25.12, "elapsed_time": "0:01:11", "remaining_time": "0:03:33"}
108
+ {"current_steps": 108, "total_steps": 426, "loss": 0.1732, "lr": 8.496208505021572e-06, "epoch": 0.5070422535211268, "percentage": 25.35, "elapsed_time": "0:01:12", "remaining_time": "0:03:32"}
109
+ {"current_steps": 109, "total_steps": 426, "loss": 0.215, "lr": 8.469753596903909e-06, "epoch": 0.5117370892018779, "percentage": 25.59, "elapsed_time": "0:01:12", "remaining_time": "0:03:31"}
110
+ {"current_steps": 110, "total_steps": 426, "loss": 0.1535, "lr": 8.443109986477574e-06, "epoch": 0.5164319248826291, "percentage": 25.82, "elapsed_time": "0:01:13", "remaining_time": "0:03:30"}
111
+ {"current_steps": 111, "total_steps": 426, "loss": 0.1688, "lr": 8.416279122753468e-06, "epoch": 0.5211267605633803, "percentage": 26.06, "elapsed_time": "0:01:14", "remaining_time": "0:03:30"}
112
+ {"current_steps": 112, "total_steps": 426, "loss": 0.2148, "lr": 8.389262464926256e-06, "epoch": 0.5258215962441315, "percentage": 26.29, "elapsed_time": "0:01:14", "remaining_time": "0:03:29"}
113
+ {"current_steps": 113, "total_steps": 426, "loss": 0.201, "lr": 8.362061482295001e-06, "epoch": 0.5305164319248826, "percentage": 26.53, "elapsed_time": "0:01:15", "remaining_time": "0:03:28"}
114
+ {"current_steps": 114, "total_steps": 426, "loss": 0.1751, "lr": 8.334677654183254e-06, "epoch": 0.5352112676056338, "percentage": 26.76, "elapsed_time": "0:01:15", "remaining_time": "0:03:27"}
115
+ {"current_steps": 115, "total_steps": 426, "loss": 0.1623, "lr": 8.307112469858608e-06, "epoch": 0.539906103286385, "percentage": 27.0, "elapsed_time": "0:01:16", "remaining_time": "0:03:26"}
116
+ {"current_steps": 116, "total_steps": 426, "loss": 0.1709, "lr": 8.279367428451703e-06, "epoch": 0.5446009389671361, "percentage": 27.23, "elapsed_time": "0:01:17", "remaining_time": "0:03:26"}
117
+ {"current_steps": 117, "total_steps": 426, "loss": 0.1662, "lr": 8.251444038874685e-06, "epoch": 0.5492957746478874, "percentage": 27.46, "elapsed_time": "0:01:17", "remaining_time": "0:03:25"}
118
+ {"current_steps": 118, "total_steps": 426, "loss": 0.2016, "lr": 8.223343819739164e-06, "epoch": 0.5539906103286385, "percentage": 27.7, "elapsed_time": "0:01:18", "remaining_time": "0:03:24"}
119
+ {"current_steps": 119, "total_steps": 426, "loss": 0.2096, "lr": 8.19506829927361e-06, "epoch": 0.5586854460093896, "percentage": 27.93, "elapsed_time": "0:01:18", "remaining_time": "0:03:23"}
120
+ {"current_steps": 120, "total_steps": 426, "loss": 0.1666, "lr": 8.166619015240236e-06, "epoch": 0.5633802816901409, "percentage": 28.17, "elapsed_time": "0:01:19", "remaining_time": "0:03:22"}
121
+ {"current_steps": 121, "total_steps": 426, "loss": 0.1522, "lr": 8.137997514851385e-06, "epoch": 0.568075117370892, "percentage": 28.4, "elapsed_time": "0:01:20", "remaining_time": "0:03:22"}
122
+ {"current_steps": 122, "total_steps": 426, "loss": 0.1927, "lr": 8.109205354685367e-06, "epoch": 0.5727699530516432, "percentage": 28.64, "elapsed_time": "0:01:20", "remaining_time": "0:03:21"}
123
+ {"current_steps": 123, "total_steps": 426, "loss": 0.1589, "lr": 8.080244100601822e-06, "epoch": 0.5774647887323944, "percentage": 28.87, "elapsed_time": "0:01:21", "remaining_time": "0:03:20"}
124
+ {"current_steps": 124, "total_steps": 426, "loss": 0.1462, "lr": 8.051115327656538e-06, "epoch": 0.5821596244131455, "percentage": 29.11, "elapsed_time": "0:01:22", "remaining_time": "0:03:19"}
125
+ {"current_steps": 125, "total_steps": 426, "loss": 0.1604, "lr": 8.021820620015811e-06, "epoch": 0.5868544600938967, "percentage": 29.34, "elapsed_time": "0:01:22", "remaining_time": "0:03:19"}
126
+ {"current_steps": 126, "total_steps": 426, "loss": 0.2352, "lr": 7.992361570870289e-06, "epoch": 0.5915492957746479, "percentage": 29.58, "elapsed_time": "0:01:23", "remaining_time": "0:03:18"}
127
+ {"current_steps": 127, "total_steps": 426, "loss": 0.1765, "lr": 7.96273978234831e-06, "epoch": 0.596244131455399, "percentage": 29.81, "elapsed_time": "0:01:23", "remaining_time": "0:03:17"}
128
+ {"current_steps": 128, "total_steps": 426, "loss": 0.1899, "lr": 7.932956865428792e-06, "epoch": 0.6009389671361502, "percentage": 30.05, "elapsed_time": "0:01:24", "remaining_time": "0:03:16"}
129
+ {"current_steps": 129, "total_steps": 426, "loss": 0.1652, "lr": 7.903014439853605e-06, "epoch": 0.6056338028169014, "percentage": 30.28, "elapsed_time": "0:01:25", "remaining_time": "0:03:16"}
130
+ {"current_steps": 130, "total_steps": 426, "loss": 0.1878, "lr": 7.872914134039485e-06, "epoch": 0.6103286384976526, "percentage": 30.52, "elapsed_time": "0:01:25", "remaining_time": "0:03:15"}
131
+ {"current_steps": 131, "total_steps": 426, "loss": 0.1676, "lr": 7.842657584989477e-06, "epoch": 0.6150234741784038, "percentage": 30.75, "elapsed_time": "0:01:26", "remaining_time": "0:03:14"}
132
+ {"current_steps": 132, "total_steps": 426, "loss": 0.174, "lr": 7.812246438203905e-06, "epoch": 0.6197183098591549, "percentage": 30.99, "elapsed_time": "0:01:26", "remaining_time": "0:03:13"}
133
+ {"current_steps": 133, "total_steps": 426, "loss": 0.1498, "lr": 7.78168234759087e-06, "epoch": 0.6244131455399061, "percentage": 31.22, "elapsed_time": "0:01:27", "remaining_time": "0:03:12"}
134
+ {"current_steps": 134, "total_steps": 426, "loss": 0.1531, "lr": 7.750966975376328e-06, "epoch": 0.6291079812206573, "percentage": 31.46, "elapsed_time": "0:01:28", "remaining_time": "0:03:12"}
135
+ {"current_steps": 135, "total_steps": 426, "loss": 0.1548, "lr": 7.720101992013661e-06, "epoch": 0.6338028169014085, "percentage": 31.69, "elapsed_time": "0:01:28", "remaining_time": "0:03:11"}
136
+ {"current_steps": 136, "total_steps": 426, "loss": 0.1724, "lr": 7.689089076092851e-06, "epoch": 0.6384976525821596, "percentage": 31.92, "elapsed_time": "0:01:29", "remaining_time": "0:03:10"}
137
+ {"current_steps": 137, "total_steps": 426, "loss": 0.1757, "lr": 7.657929914249177e-06, "epoch": 0.6431924882629108, "percentage": 32.16, "elapsed_time": "0:01:30", "remaining_time": "0:03:10"}
138
+ {"current_steps": 138, "total_steps": 426, "loss": 0.1584, "lr": 7.626626201071494e-06, "epoch": 0.647887323943662, "percentage": 32.39, "elapsed_time": "0:01:30", "remaining_time": "0:03:09"}
139
+ {"current_steps": 139, "total_steps": 426, "loss": 0.2042, "lr": 7.5951796390100755e-06, "epoch": 0.6525821596244131, "percentage": 32.63, "elapsed_time": "0:01:31", "remaining_time": "0:03:08"}
140
+ {"current_steps": 140, "total_steps": 426, "loss": 0.1726, "lr": 7.563591938284012e-06, "epoch": 0.6572769953051644, "percentage": 32.86, "elapsed_time": "0:01:31", "remaining_time": "0:03:07"}
141
+ {"current_steps": 141, "total_steps": 426, "loss": 0.1674, "lr": 7.53186481678822e-06, "epoch": 0.6619718309859155, "percentage": 33.1, "elapsed_time": "0:01:32", "remaining_time": "0:03:07"}
142
+ {"current_steps": 142, "total_steps": 426, "loss": 0.175, "lr": 7.500000000000001e-06, "epoch": 0.6666666666666666, "percentage": 33.33, "elapsed_time": "0:01:33", "remaining_time": "0:03:06"}
143
+ {"current_steps": 143, "total_steps": 426, "loss": 0.1697, "lr": 7.467999220885204e-06, "epoch": 0.6713615023474179, "percentage": 33.57, "elapsed_time": "0:01:33", "remaining_time": "0:03:05"}
144
+ {"current_steps": 144, "total_steps": 426, "loss": 0.1817, "lr": 7.4358642198039835e-06, "epoch": 0.676056338028169, "percentage": 33.8, "elapsed_time": "0:01:34", "remaining_time": "0:03:04"}
145
+ {"current_steps": 145, "total_steps": 426, "loss": 0.1518, "lr": 7.403596744416142e-06, "epoch": 0.6807511737089202, "percentage": 34.04, "elapsed_time": "0:01:34", "remaining_time": "0:03:04"}
146
+ {"current_steps": 146, "total_steps": 426, "loss": 0.1529, "lr": 7.371198549586091e-06, "epoch": 0.6854460093896714, "percentage": 34.27, "elapsed_time": "0:01:35", "remaining_time": "0:03:03"}
147
+ {"current_steps": 147, "total_steps": 426, "loss": 0.1713, "lr": 7.338671397287409e-06, "epoch": 0.6901408450704225, "percentage": 34.51, "elapsed_time": "0:01:36", "remaining_time": "0:03:02"}
148
+ {"current_steps": 148, "total_steps": 426, "loss": 0.1774, "lr": 7.306017056507018e-06, "epoch": 0.6948356807511737, "percentage": 34.74, "elapsed_time": "0:01:36", "remaining_time": "0:03:01"}
149
+ {"current_steps": 149, "total_steps": 426, "loss": 0.1697, "lr": 7.273237303148976e-06, "epoch": 0.6995305164319249, "percentage": 34.98, "elapsed_time": "0:01:37", "remaining_time": "0:03:01"}
150
+ {"current_steps": 150, "total_steps": 426, "loss": 0.167, "lr": 7.240333919937893e-06, "epoch": 0.704225352112676, "percentage": 35.21, "elapsed_time": "0:01:38", "remaining_time": "0:03:00"}
151
+ {"current_steps": 151, "total_steps": 426, "loss": 0.1681, "lr": 7.207308696321985e-06, "epoch": 0.7089201877934272, "percentage": 35.45, "elapsed_time": "0:01:38", "remaining_time": "0:02:59"}
152
+ {"current_steps": 152, "total_steps": 426, "loss": 0.1763, "lr": 7.174163428375748e-06, "epoch": 0.7136150234741784, "percentage": 35.68, "elapsed_time": "0:01:39", "remaining_time": "0:02:58"}
153
+ {"current_steps": 153, "total_steps": 426, "loss": 0.1756, "lr": 7.140899918702276e-06, "epoch": 0.7183098591549296, "percentage": 35.92, "elapsed_time": "0:01:39", "remaining_time": "0:02:58"}
154
+ {"current_steps": 154, "total_steps": 426, "loss": 0.123, "lr": 7.107519976335241e-06, "epoch": 0.7230046948356808, "percentage": 36.15, "elapsed_time": "0:01:40", "remaining_time": "0:02:57"}
155
+ {"current_steps": 155, "total_steps": 426, "loss": 0.195, "lr": 7.0740254166404884e-06, "epoch": 0.7276995305164319, "percentage": 36.38, "elapsed_time": "0:01:41", "remaining_time": "0:02:57"}
156
+ {"current_steps": 156, "total_steps": 426, "loss": 0.1509, "lr": 7.040418061217325e-06, "epoch": 0.7323943661971831, "percentage": 36.62, "elapsed_time": "0:01:41", "remaining_time": "0:02:56"}
157
+ {"current_steps": 157, "total_steps": 426, "loss": 0.1627, "lr": 7.006699737799445e-06, "epoch": 0.7370892018779343, "percentage": 36.85, "elapsed_time": "0:01:42", "remaining_time": "0:02:55"}
158
+ {"current_steps": 158, "total_steps": 426, "loss": 0.1739, "lr": 6.972872280155528e-06, "epoch": 0.7417840375586855, "percentage": 37.09, "elapsed_time": "0:01:43", "remaining_time": "0:02:54"}
159
+ {"current_steps": 159, "total_steps": 426, "loss": 0.1743, "lr": 6.938937527989511e-06, "epoch": 0.7464788732394366, "percentage": 37.32, "elapsed_time": "0:01:43", "remaining_time": "0:02:54"}
160
+ {"current_steps": 160, "total_steps": 426, "loss": 0.1718, "lr": 6.9048973268405375e-06, "epoch": 0.7511737089201878, "percentage": 37.56, "elapsed_time": "0:01:44", "remaining_time": "0:02:53"}
161
+ {"current_steps": 161, "total_steps": 426, "loss": 0.1419, "lr": 6.8707535279825845e-06, "epoch": 0.755868544600939, "percentage": 37.79, "elapsed_time": "0:01:44", "remaining_time": "0:02:52"}
162
+ {"current_steps": 162, "total_steps": 426, "loss": 0.1626, "lr": 6.836507988323785e-06, "epoch": 0.7605633802816901, "percentage": 38.03, "elapsed_time": "0:01:45", "remaining_time": "0:02:52"}
163
+ {"current_steps": 163, "total_steps": 426, "loss": 0.1537, "lr": 6.802162570305436e-06, "epoch": 0.7652582159624414, "percentage": 38.26, "elapsed_time": "0:01:46", "remaining_time": "0:02:51"}
164
+ {"current_steps": 164, "total_steps": 426, "loss": 0.1735, "lr": 6.767719141800718e-06, "epoch": 0.7699530516431925, "percentage": 38.5, "elapsed_time": "0:01:46", "remaining_time": "0:02:50"}
165
+ {"current_steps": 165, "total_steps": 426, "loss": 0.1637, "lr": 6.733179576013098e-06, "epoch": 0.7746478873239436, "percentage": 38.73, "elapsed_time": "0:01:47", "remaining_time": "0:02:50"}
166
+ {"current_steps": 166, "total_steps": 426, "loss": 0.1501, "lr": 6.698545751374465e-06, "epoch": 0.7793427230046949, "percentage": 38.97, "elapsed_time": "0:01:48", "remaining_time": "0:02:49"}
167
+ {"current_steps": 167, "total_steps": 426, "loss": 0.1354, "lr": 6.663819551442969e-06, "epoch": 0.784037558685446, "percentage": 39.2, "elapsed_time": "0:01:48", "remaining_time": "0:02:48"}
168
+ {"current_steps": 168, "total_steps": 426, "loss": 0.1609, "lr": 6.629002864800589e-06, "epoch": 0.7887323943661971, "percentage": 39.44, "elapsed_time": "0:01:49", "remaining_time": "0:02:48"}
169
+ {"current_steps": 169, "total_steps": 426, "loss": 0.1688, "lr": 6.594097584950406e-06, "epoch": 0.7934272300469484, "percentage": 39.67, "elapsed_time": "0:01:50", "remaining_time": "0:02:47"}
170
+ {"current_steps": 170, "total_steps": 426, "loss": 0.1425, "lr": 6.55910561021365e-06, "epoch": 0.7981220657276995, "percentage": 39.91, "elapsed_time": "0:01:50", "remaining_time": "0:02:46"}
171
+ {"current_steps": 171, "total_steps": 426, "loss": 0.1737, "lr": 6.524028843626433e-06, "epoch": 0.8028169014084507, "percentage": 40.14, "elapsed_time": "0:01:51", "remaining_time": "0:02:45"}
172
+ {"current_steps": 172, "total_steps": 426, "loss": 0.1404, "lr": 6.488869192836279e-06, "epoch": 0.8075117370892019, "percentage": 40.38, "elapsed_time": "0:01:51", "remaining_time": "0:02:45"}
173
+ {"current_steps": 173, "total_steps": 426, "loss": 0.1594, "lr": 6.453628569998352e-06, "epoch": 0.812206572769953, "percentage": 40.61, "elapsed_time": "0:01:52", "remaining_time": "0:02:44"}
174
+ {"current_steps": 174, "total_steps": 426, "loss": 0.1098, "lr": 6.418308891671484e-06, "epoch": 0.8169014084507042, "percentage": 40.85, "elapsed_time": "0:01:53", "remaining_time": "0:02:43"}
175
+ {"current_steps": 175, "total_steps": 426, "loss": 0.1621, "lr": 6.38291207871393e-06, "epoch": 0.8215962441314554, "percentage": 41.08, "elapsed_time": "0:01:53", "remaining_time": "0:02:43"}
176
+ {"current_steps": 176, "total_steps": 426, "loss": 0.1683, "lr": 6.347440056178904e-06, "epoch": 0.8262910798122066, "percentage": 41.31, "elapsed_time": "0:01:54", "remaining_time": "0:02:42"}
177
+ {"current_steps": 177, "total_steps": 426, "loss": 0.1517, "lr": 6.311894753209896e-06, "epoch": 0.8309859154929577, "percentage": 41.55, "elapsed_time": "0:01:54", "remaining_time": "0:02:41"}
178
+ {"current_steps": 178, "total_steps": 426, "loss": 0.1289, "lr": 6.27627810293574e-06, "epoch": 0.8356807511737089, "percentage": 41.78, "elapsed_time": "0:01:55", "remaining_time": "0:02:41"}
179
+ {"current_steps": 179, "total_steps": 426, "loss": 0.134, "lr": 6.2405920423654885e-06, "epoch": 0.8403755868544601, "percentage": 42.02, "elapsed_time": "0:01:56", "remaining_time": "0:02:40"}
180
+ {"current_steps": 180, "total_steps": 426, "loss": 0.1452, "lr": 6.204838512283073e-06, "epoch": 0.8450704225352113, "percentage": 42.25, "elapsed_time": "0:01:57", "remaining_time": "0:02:39"}
181
+ {"current_steps": 181, "total_steps": 426, "loss": 0.1566, "lr": 6.169019457141745e-06, "epoch": 0.8497652582159625, "percentage": 42.49, "elapsed_time": "0:01:57", "remaining_time": "0:02:39"}
182
+ {"current_steps": 182, "total_steps": 426, "loss": 0.1419, "lr": 6.133136824958334e-06, "epoch": 0.8544600938967136, "percentage": 42.72, "elapsed_time": "0:01:58", "remaining_time": "0:02:38"}
183
+ {"current_steps": 183, "total_steps": 426, "loss": 0.1692, "lr": 6.097192567207304e-06, "epoch": 0.8591549295774648, "percentage": 42.96, "elapsed_time": "0:01:58", "remaining_time": "0:02:37"}
184
+ {"current_steps": 184, "total_steps": 426, "loss": 0.1647, "lr": 6.061188638714616e-06, "epoch": 0.863849765258216, "percentage": 43.19, "elapsed_time": "0:01:59", "remaining_time": "0:02:37"}
185
+ {"current_steps": 185, "total_steps": 426, "loss": 0.1516, "lr": 6.0251269975514275e-06, "epoch": 0.8685446009389671, "percentage": 43.43, "elapsed_time": "0:02:00", "remaining_time": "0:02:36"}
186
+ {"current_steps": 186, "total_steps": 426, "loss": 0.1532, "lr": 5.989009604927587e-06, "epoch": 0.8732394366197183, "percentage": 43.66, "elapsed_time": "0:02:00", "remaining_time": "0:02:35"}
187
+ {"current_steps": 187, "total_steps": 426, "loss": 0.1517, "lr": 5.95283842508499e-06, "epoch": 0.8779342723004695, "percentage": 43.9, "elapsed_time": "0:02:01", "remaining_time": "0:02:35"}
188
+ {"current_steps": 188, "total_steps": 426, "loss": 0.1388, "lr": 5.916615425190744e-06, "epoch": 0.8826291079812206, "percentage": 44.13, "elapsed_time": "0:02:02", "remaining_time": "0:02:34"}
189
+ {"current_steps": 189, "total_steps": 426, "loss": 0.1336, "lr": 5.8803425752301814e-06, "epoch": 0.8873239436619719, "percentage": 44.37, "elapsed_time": "0:02:02", "remaining_time": "0:02:33"}
190
+ {"current_steps": 190, "total_steps": 426, "loss": 0.1678, "lr": 5.844021847899735e-06, "epoch": 0.892018779342723, "percentage": 44.6, "elapsed_time": "0:02:03", "remaining_time": "0:02:33"}
191
+ {"current_steps": 191, "total_steps": 426, "loss": 0.1588, "lr": 5.80765521849964e-06, "epoch": 0.8967136150234741, "percentage": 44.84, "elapsed_time": "0:02:03", "remaining_time": "0:02:32"}
192
+ {"current_steps": 192, "total_steps": 426, "loss": 0.1862, "lr": 5.771244664826512e-06, "epoch": 0.9014084507042254, "percentage": 45.07, "elapsed_time": "0:02:04", "remaining_time": "0:02:31"}
193
+ {"current_steps": 193, "total_steps": 426, "loss": 0.1583, "lr": 5.734792167065789e-06, "epoch": 0.9061032863849765, "percentage": 45.31, "elapsed_time": "0:02:05", "remaining_time": "0:02:31"}
194
+ {"current_steps": 194, "total_steps": 426, "loss": 0.1606, "lr": 5.698299707684031e-06, "epoch": 0.9107981220657277, "percentage": 45.54, "elapsed_time": "0:02:05", "remaining_time": "0:02:30"}
195
+ {"current_steps": 195, "total_steps": 426, "loss": 0.1522, "lr": 5.661769271321113e-06, "epoch": 0.9154929577464789, "percentage": 45.77, "elapsed_time": "0:02:06", "remaining_time": "0:02:29"}
196
+ {"current_steps": 196, "total_steps": 426, "loss": 0.1488, "lr": 5.6252028446822805e-06, "epoch": 0.92018779342723, "percentage": 46.01, "elapsed_time": "0:02:06", "remaining_time": "0:02:29"}
197
+ {"current_steps": 197, "total_steps": 426, "loss": 0.1571, "lr": 5.588602416430107e-06, "epoch": 0.9248826291079812, "percentage": 46.24, "elapsed_time": "0:02:07", "remaining_time": "0:02:28"}
198
+ {"current_steps": 198, "total_steps": 426, "loss": 0.1739, "lr": 5.55196997707635e-06, "epoch": 0.9295774647887324, "percentage": 46.48, "elapsed_time": "0:02:08", "remaining_time": "0:02:27"}
199
+ {"current_steps": 199, "total_steps": 426, "loss": 0.1507, "lr": 5.515307518873677e-06, "epoch": 0.9342723004694836, "percentage": 46.71, "elapsed_time": "0:02:08", "remaining_time": "0:02:26"}
200
+ {"current_steps": 200, "total_steps": 426, "loss": 0.1647, "lr": 5.478617035707337e-06, "epoch": 0.9389671361502347, "percentage": 46.95, "elapsed_time": "0:02:09", "remaining_time": "0:02:26"}
201
+ {"current_steps": 200, "total_steps": 426, "eval_loss": 0.13491584360599518, "epoch": 0.9389671361502347, "percentage": 46.95, "elapsed_time": "0:02:10", "remaining_time": "0:02:27"}
202
+ {"current_steps": 201, "total_steps": 426, "loss": 0.1237, "lr": 5.441900522986712e-06, "epoch": 0.9436619718309859, "percentage": 47.18, "elapsed_time": "0:02:10", "remaining_time": "0:02:26"}
203
+ {"current_steps": 202, "total_steps": 426, "loss": 0.1671, "lr": 5.4051599775368e-06, "epoch": 0.9483568075117371, "percentage": 47.42, "elapsed_time": "0:02:11", "remaining_time": "0:02:25"}
204
+ {"current_steps": 203, "total_steps": 426, "loss": 0.1563, "lr": 5.368397397489615e-06, "epoch": 0.9530516431924883, "percentage": 47.65, "elapsed_time": "0:02:11", "remaining_time": "0:02:24"}
205
+ {"current_steps": 204, "total_steps": 426, "loss": 0.1635, "lr": 5.33161478217552e-06, "epoch": 0.9577464788732394, "percentage": 47.89, "elapsed_time": "0:02:12", "remaining_time": "0:02:24"}
206
+ {"current_steps": 205, "total_steps": 426, "loss": 0.1431, "lr": 5.294814132014503e-06, "epoch": 0.9624413145539906, "percentage": 48.12, "elapsed_time": "0:02:13", "remaining_time": "0:02:23"}
207
+ {"current_steps": 206, "total_steps": 426, "loss": 0.1683, "lr": 5.257997448407366e-06, "epoch": 0.9671361502347418, "percentage": 48.36, "elapsed_time": "0:02:13", "remaining_time": "0:02:22"}
208
+ {"current_steps": 207, "total_steps": 426, "loss": 0.1525, "lr": 5.221166733626895e-06, "epoch": 0.971830985915493, "percentage": 48.59, "elapsed_time": "0:02:14", "remaining_time": "0:02:22"}
209
+ {"current_steps": 208, "total_steps": 426, "loss": 0.1339, "lr": 5.184323990708959e-06, "epoch": 0.9765258215962441, "percentage": 48.83, "elapsed_time": "0:02:15", "remaining_time": "0:02:21"}
210
+ {"current_steps": 209, "total_steps": 426, "loss": 0.169, "lr": 5.147471223343573e-06, "epoch": 0.9812206572769953, "percentage": 49.06, "elapsed_time": "0:02:15", "remaining_time": "0:02:20"}
211
+ {"current_steps": 210, "total_steps": 426, "loss": 0.1405, "lr": 5.110610435765935e-06, "epoch": 0.9859154929577465, "percentage": 49.3, "elapsed_time": "0:02:16", "remaining_time": "0:02:20"}
212
+ {"current_steps": 211, "total_steps": 426, "loss": 0.1378, "lr": 5.073743632647422e-06, "epoch": 0.9906103286384976, "percentage": 49.53, "elapsed_time": "0:02:16", "remaining_time": "0:02:19"}
213
+ {"current_steps": 212, "total_steps": 426, "loss": 0.1598, "lr": 5.0368728189865624e-06, "epoch": 0.9953051643192489, "percentage": 49.77, "elapsed_time": "0:02:17", "remaining_time": "0:02:18"}
214
+ {"current_steps": 213, "total_steps": 426, "loss": 0.1034, "lr": 5e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:02:18", "remaining_time": "0:02:18"}
215
+ {"current_steps": 214, "total_steps": 426, "loss": 0.0972, "lr": 4.9631271810134375e-06, "epoch": 1.0046948356807512, "percentage": 50.23, "elapsed_time": "0:02:18", "remaining_time": "0:02:17"}
216
+ {"current_steps": 215, "total_steps": 426, "loss": 0.0888, "lr": 4.9262563673525795e-06, "epoch": 1.0093896713615023, "percentage": 50.47, "elapsed_time": "0:02:19", "remaining_time": "0:02:16"}
217
+ {"current_steps": 216, "total_steps": 426, "loss": 0.0834, "lr": 4.8893895642340665e-06, "epoch": 1.0140845070422535, "percentage": 50.7, "elapsed_time": "0:02:19", "remaining_time": "0:02:16"}
218
+ {"current_steps": 217, "total_steps": 426, "loss": 0.074, "lr": 4.852528776656428e-06, "epoch": 1.0187793427230047, "percentage": 50.94, "elapsed_time": "0:02:20", "remaining_time": "0:02:15"}
219
+ {"current_steps": 218, "total_steps": 426, "loss": 0.0773, "lr": 4.815676009291044e-06, "epoch": 1.0234741784037558, "percentage": 51.17, "elapsed_time": "0:02:21", "remaining_time": "0:02:14"}
220
+ {"current_steps": 219, "total_steps": 426, "loss": 0.0815, "lr": 4.778833266373107e-06, "epoch": 1.028169014084507, "percentage": 51.41, "elapsed_time": "0:02:21", "remaining_time": "0:02:14"}
221
+ {"current_steps": 220, "total_steps": 426, "loss": 0.0716, "lr": 4.742002551592635e-06, "epoch": 1.0328638497652582, "percentage": 51.64, "elapsed_time": "0:02:22", "remaining_time": "0:02:13"}
222
+ {"current_steps": 221, "total_steps": 426, "loss": 0.0807, "lr": 4.705185867985498e-06, "epoch": 1.0375586854460095, "percentage": 51.88, "elapsed_time": "0:02:23", "remaining_time": "0:02:12"}
223
+ {"current_steps": 222, "total_steps": 426, "loss": 0.09, "lr": 4.668385217824482e-06, "epoch": 1.0422535211267605, "percentage": 52.11, "elapsed_time": "0:02:23", "remaining_time": "0:02:12"}
224
+ {"current_steps": 223, "total_steps": 426, "loss": 0.0694, "lr": 4.631602602510388e-06, "epoch": 1.0469483568075117, "percentage": 52.35, "elapsed_time": "0:02:24", "remaining_time": "0:02:11"}
225
+ {"current_steps": 224, "total_steps": 426, "loss": 0.0764, "lr": 4.594840022463201e-06, "epoch": 1.051643192488263, "percentage": 52.58, "elapsed_time": "0:02:24", "remaining_time": "0:02:10"}
226
+ {"current_steps": 225, "total_steps": 426, "loss": 0.0693, "lr": 4.558099477013288e-06, "epoch": 1.056338028169014, "percentage": 52.82, "elapsed_time": "0:02:25", "remaining_time": "0:02:10"}
227
+ {"current_steps": 226, "total_steps": 426, "loss": 0.0825, "lr": 4.5213829642926635e-06, "epoch": 1.0610328638497653, "percentage": 53.05, "elapsed_time": "0:02:26", "remaining_time": "0:02:09"}
228
+ {"current_steps": 227, "total_steps": 426, "loss": 0.0748, "lr": 4.484692481126323e-06, "epoch": 1.0657276995305165, "percentage": 53.29, "elapsed_time": "0:02:26", "remaining_time": "0:02:08"}
229
+ {"current_steps": 228, "total_steps": 426, "loss": 0.0675, "lr": 4.4480300229236525e-06, "epoch": 1.0704225352112675, "percentage": 53.52, "elapsed_time": "0:02:27", "remaining_time": "0:02:08"}
230
+ {"current_steps": 229, "total_steps": 426, "loss": 0.072, "lr": 4.411397583569894e-06, "epoch": 1.0751173708920188, "percentage": 53.76, "elapsed_time": "0:02:28", "remaining_time": "0:02:07"}
231
+ {"current_steps": 230, "total_steps": 426, "loss": 0.0793, "lr": 4.374797155317721e-06, "epoch": 1.07981220657277, "percentage": 53.99, "elapsed_time": "0:02:28", "remaining_time": "0:02:06"}
232
+ {"current_steps": 231, "total_steps": 426, "loss": 0.069, "lr": 4.338230728678888e-06, "epoch": 1.084507042253521, "percentage": 54.23, "elapsed_time": "0:02:29", "remaining_time": "0:02:06"}
233
+ {"current_steps": 232, "total_steps": 426, "loss": 0.0757, "lr": 4.30170029231597e-06, "epoch": 1.0892018779342723, "percentage": 54.46, "elapsed_time": "0:02:29", "remaining_time": "0:02:05"}
234
+ {"current_steps": 233, "total_steps": 426, "loss": 0.0742, "lr": 4.265207832934212e-06, "epoch": 1.0938967136150235, "percentage": 54.69, "elapsed_time": "0:02:30", "remaining_time": "0:02:04"}
235
+ {"current_steps": 234, "total_steps": 426, "loss": 0.0897, "lr": 4.228755335173488e-06, "epoch": 1.0985915492957747, "percentage": 54.93, "elapsed_time": "0:02:31", "remaining_time": "0:02:04"}
236
+ {"current_steps": 235, "total_steps": 426, "loss": 0.0712, "lr": 4.192344781500362e-06, "epoch": 1.1032863849765258, "percentage": 55.16, "elapsed_time": "0:02:31", "remaining_time": "0:02:03"}
237
+ {"current_steps": 236, "total_steps": 426, "loss": 0.0779, "lr": 4.155978152100266e-06, "epoch": 1.107981220657277, "percentage": 55.4, "elapsed_time": "0:02:32", "remaining_time": "0:02:02"}
238
+ {"current_steps": 237, "total_steps": 426, "loss": 0.0705, "lr": 4.119657424769819e-06, "epoch": 1.1126760563380282, "percentage": 55.63, "elapsed_time": "0:02:32", "remaining_time": "0:02:02"}
239
+ {"current_steps": 238, "total_steps": 426, "loss": 0.0792, "lr": 4.0833845748092586e-06, "epoch": 1.1173708920187793, "percentage": 55.87, "elapsed_time": "0:02:33", "remaining_time": "0:02:01"}
240
+ {"current_steps": 239, "total_steps": 426, "loss": 0.0701, "lr": 4.047161574915012e-06, "epoch": 1.1220657276995305, "percentage": 56.1, "elapsed_time": "0:02:34", "remaining_time": "0:02:00"}
241
+ {"current_steps": 240, "total_steps": 426, "loss": 0.0842, "lr": 4.010990395072414e-06, "epoch": 1.1267605633802817, "percentage": 56.34, "elapsed_time": "0:02:34", "remaining_time": "0:01:59"}
242
+ {"current_steps": 241, "total_steps": 426, "loss": 0.0942, "lr": 3.974873002448575e-06, "epoch": 1.131455399061033, "percentage": 56.57, "elapsed_time": "0:02:35", "remaining_time": "0:01:59"}
243
+ {"current_steps": 242, "total_steps": 426, "loss": 0.0623, "lr": 3.938811361285386e-06, "epoch": 1.136150234741784, "percentage": 56.81, "elapsed_time": "0:02:36", "remaining_time": "0:01:58"}
244
+ {"current_steps": 243, "total_steps": 426, "loss": 0.0686, "lr": 3.902807432792698e-06, "epoch": 1.1408450704225352, "percentage": 57.04, "elapsed_time": "0:02:36", "remaining_time": "0:01:57"}
245
+ {"current_steps": 244, "total_steps": 426, "loss": 0.0688, "lr": 3.866863175041666e-06, "epoch": 1.1455399061032865, "percentage": 57.28, "elapsed_time": "0:02:37", "remaining_time": "0:01:57"}
246
+ {"current_steps": 245, "total_steps": 426, "loss": 0.0824, "lr": 3.830980542858256e-06, "epoch": 1.1502347417840375, "percentage": 57.51, "elapsed_time": "0:02:37", "remaining_time": "0:01:56"}
247
+ {"current_steps": 246, "total_steps": 426, "loss": 0.0751, "lr": 3.7951614877169285e-06, "epoch": 1.1549295774647887, "percentage": 57.75, "elapsed_time": "0:02:38", "remaining_time": "0:01:55"}
248
+ {"current_steps": 247, "total_steps": 426, "loss": 0.0686, "lr": 3.7594079576345123e-06, "epoch": 1.15962441314554, "percentage": 57.98, "elapsed_time": "0:02:39", "remaining_time": "0:01:55"}
249
+ {"current_steps": 248, "total_steps": 426, "loss": 0.0592, "lr": 3.7237218970642624e-06, "epoch": 1.164319248826291, "percentage": 58.22, "elapsed_time": "0:02:39", "remaining_time": "0:01:54"}
250
+ {"current_steps": 249, "total_steps": 426, "loss": 0.0716, "lr": 3.6881052467901056e-06, "epoch": 1.1690140845070423, "percentage": 58.45, "elapsed_time": "0:02:40", "remaining_time": "0:01:53"}
251
+ {"current_steps": 250, "total_steps": 426, "loss": 0.0689, "lr": 3.6525599438210956e-06, "epoch": 1.1737089201877935, "percentage": 58.69, "elapsed_time": "0:02:40", "remaining_time": "0:01:53"}
252
+ {"current_steps": 251, "total_steps": 426, "loss": 0.0697, "lr": 3.617087921286073e-06, "epoch": 1.1784037558685445, "percentage": 58.92, "elapsed_time": "0:02:41", "remaining_time": "0:01:52"}
253
+ {"current_steps": 252, "total_steps": 426, "loss": 0.0654, "lr": 3.5816911083285165e-06, "epoch": 1.1830985915492958, "percentage": 59.15, "elapsed_time": "0:02:42", "remaining_time": "0:01:52"}
254
+ {"current_steps": 253, "total_steps": 426, "loss": 0.0662, "lr": 3.5463714300016483e-06, "epoch": 1.187793427230047, "percentage": 59.39, "elapsed_time": "0:02:42", "remaining_time": "0:01:51"}
255
+ {"current_steps": 254, "total_steps": 426, "loss": 0.0628, "lr": 3.511130807163724e-06, "epoch": 1.192488262910798, "percentage": 59.62, "elapsed_time": "0:02:43", "remaining_time": "0:01:50"}
256
+ {"current_steps": 255, "total_steps": 426, "loss": 0.0659, "lr": 3.4759711563735676e-06, "epoch": 1.1971830985915493, "percentage": 59.86, "elapsed_time": "0:02:44", "remaining_time": "0:01:50"}
257
+ {"current_steps": 256, "total_steps": 426, "loss": 0.0561, "lr": 3.440894389786352e-06, "epoch": 1.2018779342723005, "percentage": 60.09, "elapsed_time": "0:02:44", "remaining_time": "0:01:49"}
258
+ {"current_steps": 257, "total_steps": 426, "loss": 0.061, "lr": 3.405902415049593e-06, "epoch": 1.2065727699530517, "percentage": 60.33, "elapsed_time": "0:02:45", "remaining_time": "0:01:48"}
259
+ {"current_steps": 258, "total_steps": 426, "loss": 0.0628, "lr": 3.370997135199413e-06, "epoch": 1.2112676056338028, "percentage": 60.56, "elapsed_time": "0:02:45", "remaining_time": "0:01:48"}
260
+ {"current_steps": 259, "total_steps": 426, "loss": 0.0821, "lr": 3.3361804485570315e-06, "epoch": 1.215962441314554, "percentage": 60.8, "elapsed_time": "0:02:46", "remaining_time": "0:01:47"}
261
+ {"current_steps": 260, "total_steps": 426, "loss": 0.0733, "lr": 3.3014542486255365e-06, "epoch": 1.2206572769953052, "percentage": 61.03, "elapsed_time": "0:02:47", "remaining_time": "0:01:46"}
262
+ {"current_steps": 261, "total_steps": 426, "loss": 0.0776, "lr": 3.2668204239869046e-06, "epoch": 1.2253521126760563, "percentage": 61.27, "elapsed_time": "0:02:47", "remaining_time": "0:01:46"}
263
+ {"current_steps": 262, "total_steps": 426, "loss": 0.0744, "lr": 3.2322808581992825e-06, "epoch": 1.2300469483568075, "percentage": 61.5, "elapsed_time": "0:02:48", "remaining_time": "0:01:45"}
264
+ {"current_steps": 263, "total_steps": 426, "loss": 0.0688, "lr": 3.1978374296945635e-06, "epoch": 1.2347417840375587, "percentage": 61.74, "elapsed_time": "0:02:49", "remaining_time": "0:01:44"}
265
+ {"current_steps": 264, "total_steps": 426, "loss": 0.0638, "lr": 3.1634920116762175e-06, "epoch": 1.2394366197183098, "percentage": 61.97, "elapsed_time": "0:02:49", "remaining_time": "0:01:44"}
266
+ {"current_steps": 265, "total_steps": 426, "loss": 0.0758, "lr": 3.1292464720174163e-06, "epoch": 1.244131455399061, "percentage": 62.21, "elapsed_time": "0:02:50", "remaining_time": "0:01:43"}
267
+ {"current_steps": 266, "total_steps": 426, "loss": 0.0584, "lr": 3.0951026731594634e-06, "epoch": 1.2488262910798122, "percentage": 62.44, "elapsed_time": "0:02:51", "remaining_time": "0:01:42"}
268
+ {"current_steps": 267, "total_steps": 426, "loss": 0.0778, "lr": 3.061062472010489e-06, "epoch": 1.2535211267605635, "percentage": 62.68, "elapsed_time": "0:02:51", "remaining_time": "0:01:42"}
269
+ {"current_steps": 268, "total_steps": 426, "loss": 0.08, "lr": 3.0271277198444737e-06, "epoch": 1.2582159624413145, "percentage": 62.91, "elapsed_time": "0:02:52", "remaining_time": "0:01:41"}
270
+ {"current_steps": 269, "total_steps": 426, "loss": 0.0639, "lr": 2.9933002622005563e-06, "epoch": 1.2629107981220657, "percentage": 63.15, "elapsed_time": "0:02:52", "remaining_time": "0:01:40"}
271
+ {"current_steps": 270, "total_steps": 426, "loss": 0.0796, "lr": 2.9595819387826753e-06, "epoch": 1.267605633802817, "percentage": 63.38, "elapsed_time": "0:02:53", "remaining_time": "0:01:40"}
272
+ {"current_steps": 271, "total_steps": 426, "loss": 0.0512, "lr": 2.9259745833595132e-06, "epoch": 1.272300469483568, "percentage": 63.62, "elapsed_time": "0:02:54", "remaining_time": "0:01:39"}
273
+ {"current_steps": 272, "total_steps": 426, "loss": 0.06, "lr": 2.89248002366476e-06, "epoch": 1.2769953051643192, "percentage": 63.85, "elapsed_time": "0:02:54", "remaining_time": "0:01:38"}
274
+ {"current_steps": 273, "total_steps": 426, "loss": 0.0708, "lr": 2.8591000812977245e-06, "epoch": 1.2816901408450705, "percentage": 64.08, "elapsed_time": "0:02:55", "remaining_time": "0:01:38"}
275
+ {"current_steps": 274, "total_steps": 426, "loss": 0.0737, "lr": 2.8258365716242543e-06, "epoch": 1.2863849765258215, "percentage": 64.32, "elapsed_time": "0:02:55", "remaining_time": "0:01:37"}
276
+ {"current_steps": 275, "total_steps": 426, "loss": 0.0576, "lr": 2.792691303678016e-06, "epoch": 1.2910798122065728, "percentage": 64.55, "elapsed_time": "0:02:56", "remaining_time": "0:01:36"}
277
+ {"current_steps": 276, "total_steps": 426, "loss": 0.0627, "lr": 2.7596660800621076e-06, "epoch": 1.295774647887324, "percentage": 64.79, "elapsed_time": "0:02:57", "remaining_time": "0:01:36"}
278
+ {"current_steps": 277, "total_steps": 426, "loss": 0.0633, "lr": 2.7267626968510264e-06, "epoch": 1.300469483568075, "percentage": 65.02, "elapsed_time": "0:02:57", "remaining_time": "0:01:35"}
279
+ {"current_steps": 278, "total_steps": 426, "loss": 0.061, "lr": 2.6939829434929834e-06, "epoch": 1.3051643192488263, "percentage": 65.26, "elapsed_time": "0:02:58", "remaining_time": "0:01:34"}
280
+ {"current_steps": 279, "total_steps": 426, "loss": 0.0773, "lr": 2.661328602712592e-06, "epoch": 1.3098591549295775, "percentage": 65.49, "elapsed_time": "0:02:59", "remaining_time": "0:01:34"}
281
+ {"current_steps": 280, "total_steps": 426, "loss": 0.0615, "lr": 2.6288014504139104e-06, "epoch": 1.3145539906103285, "percentage": 65.73, "elapsed_time": "0:02:59", "remaining_time": "0:01:33"}
282
+ {"current_steps": 281, "total_steps": 426, "loss": 0.0744, "lr": 2.5964032555838593e-06, "epoch": 1.3192488262910798, "percentage": 65.96, "elapsed_time": "0:03:00", "remaining_time": "0:01:33"}
283
+ {"current_steps": 282, "total_steps": 426, "loss": 0.0676, "lr": 2.5641357801960186e-06, "epoch": 1.323943661971831, "percentage": 66.2, "elapsed_time": "0:03:00", "remaining_time": "0:01:32"}
284
+ {"current_steps": 283, "total_steps": 426, "loss": 0.0684, "lr": 2.5320007791147954e-06, "epoch": 1.3286384976525822, "percentage": 66.43, "elapsed_time": "0:03:01", "remaining_time": "0:01:31"}
285
+ {"current_steps": 284, "total_steps": 426, "loss": 0.0632, "lr": 2.5000000000000015e-06, "epoch": 1.3333333333333333, "percentage": 66.67, "elapsed_time": "0:03:02", "remaining_time": "0:01:31"}
286
+ {"current_steps": 285, "total_steps": 426, "loss": 0.0536, "lr": 2.4681351832117815e-06, "epoch": 1.3380281690140845, "percentage": 66.9, "elapsed_time": "0:03:02", "remaining_time": "0:01:30"}
287
+ {"current_steps": 286, "total_steps": 426, "loss": 0.0647, "lr": 2.4364080617159885e-06, "epoch": 1.3427230046948357, "percentage": 67.14, "elapsed_time": "0:03:03", "remaining_time": "0:01:29"}
288
+ {"current_steps": 287, "total_steps": 426, "loss": 0.0701, "lr": 2.404820360989928e-06, "epoch": 1.347417840375587, "percentage": 67.37, "elapsed_time": "0:03:04", "remaining_time": "0:01:29"}
289
+ {"current_steps": 288, "total_steps": 426, "loss": 0.0736, "lr": 2.373373798928507e-06, "epoch": 1.352112676056338, "percentage": 67.61, "elapsed_time": "0:03:04", "remaining_time": "0:01:28"}
290
+ {"current_steps": 289, "total_steps": 426, "loss": 0.0769, "lr": 2.3420700857508233e-06, "epoch": 1.3568075117370892, "percentage": 67.84, "elapsed_time": "0:03:05", "remaining_time": "0:01:27"}
291
+ {"current_steps": 290, "total_steps": 426, "loss": 0.0653, "lr": 2.310910923907149e-06, "epoch": 1.3615023474178405, "percentage": 68.08, "elapsed_time": "0:03:05", "remaining_time": "0:01:27"}
292
+ {"current_steps": 291, "total_steps": 426, "loss": 0.0675, "lr": 2.2798980079863386e-06, "epoch": 1.3661971830985915, "percentage": 68.31, "elapsed_time": "0:03:06", "remaining_time": "0:01:26"}
293
+ {"current_steps": 292, "total_steps": 426, "loss": 0.0574, "lr": 2.249033024623672e-06, "epoch": 1.3708920187793427, "percentage": 68.54, "elapsed_time": "0:03:07", "remaining_time": "0:01:25"}
294
+ {"current_steps": 293, "total_steps": 426, "loss": 0.0622, "lr": 2.2183176524091293e-06, "epoch": 1.375586854460094, "percentage": 68.78, "elapsed_time": "0:03:07", "remaining_time": "0:01:25"}
295
+ {"current_steps": 294, "total_steps": 426, "loss": 0.0679, "lr": 2.187753561796097e-06, "epoch": 1.380281690140845, "percentage": 69.01, "elapsed_time": "0:03:08", "remaining_time": "0:01:24"}
296
+ {"current_steps": 295, "total_steps": 426, "loss": 0.0874, "lr": 2.1573424150105234e-06, "epoch": 1.3849765258215962, "percentage": 69.25, "elapsed_time": "0:03:09", "remaining_time": "0:01:23"}
297
+ {"current_steps": 296, "total_steps": 426, "loss": 0.0593, "lr": 2.127085865960516e-06, "epoch": 1.3896713615023475, "percentage": 69.48, "elapsed_time": "0:03:09", "remaining_time": "0:01:23"}
298
+ {"current_steps": 297, "total_steps": 426, "loss": 0.0862, "lr": 2.0969855601463966e-06, "epoch": 1.3943661971830985, "percentage": 69.72, "elapsed_time": "0:03:10", "remaining_time": "0:01:22"}
299
+ {"current_steps": 298, "total_steps": 426, "loss": 0.0667, "lr": 2.0670431345712092e-06, "epoch": 1.3990610328638498, "percentage": 69.95, "elapsed_time": "0:03:10", "remaining_time": "0:01:22"}
300
+ {"current_steps": 299, "total_steps": 426, "loss": 0.0649, "lr": 2.0372602176516914e-06, "epoch": 1.403755868544601, "percentage": 70.19, "elapsed_time": "0:03:11", "remaining_time": "0:01:21"}
301
+ {"current_steps": 300, "total_steps": 426, "loss": 0.0646, "lr": 2.0076384291297134e-06, "epoch": 1.408450704225352, "percentage": 70.42, "elapsed_time": "0:03:12", "remaining_time": "0:01:20"}
302
+ {"current_steps": 301, "total_steps": 426, "loss": 0.0698, "lr": 1.97817937998419e-06, "epoch": 1.4131455399061033, "percentage": 70.66, "elapsed_time": "0:03:12", "remaining_time": "0:01:20"}
303
+ {"current_steps": 302, "total_steps": 426, "loss": 0.0582, "lr": 1.9488846723434646e-06, "epoch": 1.4178403755868545, "percentage": 70.89, "elapsed_time": "0:03:13", "remaining_time": "0:01:19"}
304
+ {"current_steps": 303, "total_steps": 426, "loss": 0.0755, "lr": 1.9197558993981784e-06, "epoch": 1.4225352112676055, "percentage": 71.13, "elapsed_time": "0:03:14", "remaining_time": "0:01:18"}
305
+ {"current_steps": 304, "total_steps": 426, "loss": 0.0751, "lr": 1.890794645314633e-06, "epoch": 1.4272300469483568, "percentage": 71.36, "elapsed_time": "0:03:14", "remaining_time": "0:01:18"}
306
+ {"current_steps": 305, "total_steps": 426, "loss": 0.0726, "lr": 1.8620024851486174e-06, "epoch": 1.431924882629108, "percentage": 71.6, "elapsed_time": "0:03:15", "remaining_time": "0:01:17"}
307
+ {"current_steps": 306, "total_steps": 426, "loss": 0.0684, "lr": 1.8333809847597644e-06, "epoch": 1.436619718309859, "percentage": 71.83, "elapsed_time": "0:03:15", "remaining_time": "0:01:16"}
308
+ {"current_steps": 307, "total_steps": 426, "loss": 0.0614, "lr": 1.8049317007263933e-06, "epoch": 1.4413145539906103, "percentage": 72.07, "elapsed_time": "0:03:16", "remaining_time": "0:01:16"}
309
+ {"current_steps": 308, "total_steps": 426, "loss": 0.0713, "lr": 1.7766561802608374e-06, "epoch": 1.4460093896713615, "percentage": 72.3, "elapsed_time": "0:03:17", "remaining_time": "0:01:15"}
310
+ {"current_steps": 309, "total_steps": 426, "loss": 0.0562, "lr": 1.748555961125315e-06, "epoch": 1.4507042253521127, "percentage": 72.54, "elapsed_time": "0:03:17", "remaining_time": "0:01:14"}
311
+ {"current_steps": 310, "total_steps": 426, "loss": 0.0681, "lr": 1.7206325715483003e-06, "epoch": 1.455399061032864, "percentage": 72.77, "elapsed_time": "0:03:18", "remaining_time": "0:01:14"}
312
+ {"current_steps": 311, "total_steps": 426, "loss": 0.0619, "lr": 1.6928875301413916e-06, "epoch": 1.460093896713615, "percentage": 73.0, "elapsed_time": "0:03:18", "remaining_time": "0:01:13"}
313
+ {"current_steps": 312, "total_steps": 426, "loss": 0.061, "lr": 1.665322345816746e-06, "epoch": 1.4647887323943662, "percentage": 73.24, "elapsed_time": "0:03:19", "remaining_time": "0:01:12"}
314
+ {"current_steps": 313, "total_steps": 426, "loss": 0.0572, "lr": 1.637938517705001e-06, "epoch": 1.4694835680751175, "percentage": 73.47, "elapsed_time": "0:03:20", "remaining_time": "0:01:12"}
315
+ {"current_steps": 314, "total_steps": 426, "loss": 0.0604, "lr": 1.6107375350737437e-06, "epoch": 1.4741784037558685, "percentage": 73.71, "elapsed_time": "0:03:20", "remaining_time": "0:01:11"}
316
+ {"current_steps": 315, "total_steps": 426, "loss": 0.0588, "lr": 1.583720877246533e-06, "epoch": 1.4788732394366197, "percentage": 73.94, "elapsed_time": "0:03:21", "remaining_time": "0:01:10"}
317
+ {"current_steps": 316, "total_steps": 426, "loss": 0.0732, "lr": 1.556890013522428e-06, "epoch": 1.483568075117371, "percentage": 74.18, "elapsed_time": "0:03:22", "remaining_time": "0:01:10"}
318
+ {"current_steps": 317, "total_steps": 426, "loss": 0.076, "lr": 1.5302464030960924e-06, "epoch": 1.488262910798122, "percentage": 74.41, "elapsed_time": "0:03:22", "remaining_time": "0:01:09"}
319
+ {"current_steps": 318, "total_steps": 426, "loss": 0.0625, "lr": 1.50379149497843e-06, "epoch": 1.4929577464788732, "percentage": 74.65, "elapsed_time": "0:03:23", "remaining_time": "0:01:09"}
320
+ {"current_steps": 319, "total_steps": 426, "loss": 0.0523, "lr": 1.477526727917784e-06, "epoch": 1.4976525821596245, "percentage": 74.88, "elapsed_time": "0:03:23", "remaining_time": "0:01:08"}
321
+ {"current_steps": 320, "total_steps": 426, "loss": 0.0579, "lr": 1.4514535303216893e-06, "epoch": 1.5023474178403755, "percentage": 75.12, "elapsed_time": "0:03:24", "remaining_time": "0:01:07"}
322
+ {"current_steps": 321, "total_steps": 426, "loss": 0.0698, "lr": 1.4255733201791883e-06, "epoch": 1.5070422535211268, "percentage": 75.35, "elapsed_time": "0:03:25", "remaining_time": "0:01:07"}
323
+ {"current_steps": 322, "total_steps": 426, "loss": 0.0452, "lr": 1.3998875049837141e-06, "epoch": 1.511737089201878, "percentage": 75.59, "elapsed_time": "0:03:25", "remaining_time": "0:01:06"}
324
+ {"current_steps": 323, "total_steps": 426, "loss": 0.0631, "lr": 1.3743974816565441e-06, "epoch": 1.516431924882629, "percentage": 75.82, "elapsed_time": "0:03:26", "remaining_time": "0:01:05"}
325
+ {"current_steps": 324, "total_steps": 426, "loss": 0.0618, "lr": 1.3491046364708294e-06, "epoch": 1.5211267605633803, "percentage": 76.06, "elapsed_time": "0:03:27", "remaining_time": "0:01:05"}
326
+ {"current_steps": 325, "total_steps": 426, "loss": 0.0681, "lr": 1.3240103449762004e-06, "epoch": 1.5258215962441315, "percentage": 76.29, "elapsed_time": "0:03:27", "remaining_time": "0:01:04"}
327
+ {"current_steps": 326, "total_steps": 426, "loss": 0.0617, "lr": 1.2991159719239581e-06, "epoch": 1.5305164319248825, "percentage": 76.53, "elapsed_time": "0:03:28", "remaining_time": "0:01:03"}
328
+ {"current_steps": 327, "total_steps": 426, "loss": 0.059, "lr": 1.2744228711928585e-06, "epoch": 1.5352112676056338, "percentage": 76.76, "elapsed_time": "0:03:29", "remaining_time": "0:01:03"}
329
+ {"current_steps": 328, "total_steps": 426, "loss": 0.0717, "lr": 1.249932385715467e-06, "epoch": 1.539906103286385, "percentage": 77.0, "elapsed_time": "0:03:29", "remaining_time": "0:01:02"}
330
+ {"current_steps": 329, "total_steps": 426, "loss": 0.0672, "lr": 1.2256458474051375e-06, "epoch": 1.544600938967136, "percentage": 77.23, "elapsed_time": "0:03:30", "remaining_time": "0:01:02"}
331
+ {"current_steps": 330, "total_steps": 426, "loss": 0.0633, "lr": 1.2015645770835765e-06, "epoch": 1.5492957746478875, "percentage": 77.46, "elapsed_time": "0:03:30", "remaining_time": "0:01:01"}
332
+ {"current_steps": 331, "total_steps": 426, "loss": 0.0541, "lr": 1.177689884408993e-06, "epoch": 1.5539906103286385, "percentage": 77.7, "elapsed_time": "0:03:31", "remaining_time": "0:01:00"}
333
+ {"current_steps": 332, "total_steps": 426, "loss": 0.0655, "lr": 1.1540230678048969e-06, "epoch": 1.5586854460093895, "percentage": 77.93, "elapsed_time": "0:03:32", "remaining_time": "0:01:00"}
334
+ {"current_steps": 333, "total_steps": 426, "loss": 0.0601, "lr": 1.1305654143894674e-06, "epoch": 1.563380281690141, "percentage": 78.17, "elapsed_time": "0:03:32", "remaining_time": "0:00:59"}
335
+ {"current_steps": 334, "total_steps": 426, "loss": 0.0686, "lr": 1.1073181999055538e-06, "epoch": 1.568075117370892, "percentage": 78.4, "elapsed_time": "0:03:33", "remaining_time": "0:00:58"}
336
+ {"current_steps": 335, "total_steps": 426, "loss": 0.0814, "lr": 1.0842826886513074e-06, "epoch": 1.5727699530516432, "percentage": 78.64, "elapsed_time": "0:03:34", "remaining_time": "0:00:58"}
337
+ {"current_steps": 336, "total_steps": 426, "loss": 0.069, "lr": 1.0614601334114099e-06, "epoch": 1.5774647887323945, "percentage": 78.87, "elapsed_time": "0:03:34", "remaining_time": "0:00:57"}
338
+ {"current_steps": 337, "total_steps": 426, "loss": 0.0631, "lr": 1.038851775388941e-06, "epoch": 1.5821596244131455, "percentage": 79.11, "elapsed_time": "0:03:35", "remaining_time": "0:00:56"}
339
+ {"current_steps": 338, "total_steps": 426, "loss": 0.0578, "lr": 1.016458844137887e-06, "epoch": 1.5868544600938967, "percentage": 79.34, "elapsed_time": "0:03:35", "remaining_time": "0:00:56"}
340
+ {"current_steps": 339, "total_steps": 426, "loss": 0.0528, "lr": 9.942825574962595e-07, "epoch": 1.591549295774648, "percentage": 79.58, "elapsed_time": "0:03:36", "remaining_time": "0:00:55"}
341
+ {"current_steps": 340, "total_steps": 426, "loss": 0.0711, "lr": 9.723241215198692e-07, "epoch": 1.596244131455399, "percentage": 79.81, "elapsed_time": "0:03:37", "remaining_time": "0:00:54"}
342
+ {"current_steps": 341, "total_steps": 426, "loss": 0.0617, "lr": 9.505847304167337e-07, "epoch": 1.6009389671361502, "percentage": 80.05, "elapsed_time": "0:03:37", "remaining_time": "0:00:54"}
343
+ {"current_steps": 342, "total_steps": 426, "loss": 0.0576, "lr": 9.290655664821296e-07, "epoch": 1.6056338028169015, "percentage": 80.28, "elapsed_time": "0:03:38", "remaining_time": "0:00:53"}
344
+ {"current_steps": 343, "total_steps": 426, "loss": 0.0816, "lr": 9.077678000342949e-07, "epoch": 1.6103286384976525, "percentage": 80.52, "elapsed_time": "0:03:39", "remaining_time": "0:00:53"}
345
+ {"current_steps": 344, "total_steps": 426, "loss": 0.0533, "lr": 8.866925893507805e-07, "epoch": 1.6150234741784038, "percentage": 80.75, "elapsed_time": "0:03:39", "remaining_time": "0:00:52"}
346
+ {"current_steps": 345, "total_steps": 426, "loss": 0.0487, "lr": 8.658410806054568e-07, "epoch": 1.619718309859155, "percentage": 80.99, "elapsed_time": "0:03:40", "remaining_time": "0:00:51"}
347
+ {"current_steps": 346, "total_steps": 426, "loss": 0.0642, "lr": 8.45214407806182e-07, "epoch": 1.624413145539906, "percentage": 81.22, "elapsed_time": "0:03:40", "remaining_time": "0:00:51"}
348
+ {"current_steps": 347, "total_steps": 426, "loss": 0.0654, "lr": 8.248136927331241e-07, "epoch": 1.6291079812206573, "percentage": 81.46, "elapsed_time": "0:03:41", "remaining_time": "0:00:50"}
349
+ {"current_steps": 348, "total_steps": 426, "loss": 0.0649, "lr": 8.046400448777575e-07, "epoch": 1.6338028169014085, "percentage": 81.69, "elapsed_time": "0:03:42", "remaining_time": "0:00:49"}
350
+ {"current_steps": 349, "total_steps": 426, "loss": 0.077, "lr": 7.846945613825213e-07, "epoch": 1.6384976525821595, "percentage": 81.92, "elapsed_time": "0:03:42", "remaining_time": "0:00:49"}
351
+ {"current_steps": 350, "total_steps": 426, "loss": 0.059, "lr": 7.649783269811523e-07, "epoch": 1.6431924882629108, "percentage": 82.16, "elapsed_time": "0:03:43", "remaining_time": "0:00:48"}
352
+ {"current_steps": 351, "total_steps": 426, "loss": 0.064, "lr": 7.45492413939689e-07, "epoch": 1.647887323943662, "percentage": 82.39, "elapsed_time": "0:03:44", "remaining_time": "0:00:47"}
353
+ {"current_steps": 352, "total_steps": 426, "loss": 0.0577, "lr": 7.26237881998163e-07, "epoch": 1.652582159624413, "percentage": 82.63, "elapsed_time": "0:03:44", "remaining_time": "0:00:47"}
354
+ {"current_steps": 353, "total_steps": 426, "loss": 0.0637, "lr": 7.072157783129585e-07, "epoch": 1.6572769953051645, "percentage": 82.86, "elapsed_time": "0:03:45", "remaining_time": "0:00:46"}
355
+ {"current_steps": 354, "total_steps": 426, "loss": 0.0552, "lr": 6.884271373998608e-07, "epoch": 1.6619718309859155, "percentage": 83.1, "elapsed_time": "0:03:45", "remaining_time": "0:00:45"}
356
+ {"current_steps": 355, "total_steps": 426, "loss": 0.054, "lr": 6.698729810778065e-07, "epoch": 1.6666666666666665, "percentage": 83.33, "elapsed_time": "0:03:46", "remaining_time": "0:00:45"}
357
+ {"current_steps": 356, "total_steps": 426, "loss": 0.0591, "lr": 6.515543184133e-07, "epoch": 1.671361502347418, "percentage": 83.57, "elapsed_time": "0:03:47", "remaining_time": "0:00:44"}
358
+ {"current_steps": 357, "total_steps": 426, "loss": 0.0517, "lr": 6.334721456655363e-07, "epoch": 1.676056338028169, "percentage": 83.8, "elapsed_time": "0:03:48", "remaining_time": "0:00:44"}
359
+ {"current_steps": 358, "total_steps": 426, "loss": 0.0589, "lr": 6.156274462322292e-07, "epoch": 1.6807511737089202, "percentage": 84.04, "elapsed_time": "0:03:48", "remaining_time": "0:00:43"}
360
+ {"current_steps": 359, "total_steps": 426, "loss": 0.0618, "lr": 5.980211905961181e-07, "epoch": 1.6854460093896715, "percentage": 84.27, "elapsed_time": "0:03:49", "remaining_time": "0:00:42"}
361
+ {"current_steps": 360, "total_steps": 426, "loss": 0.0708, "lr": 5.806543362721945e-07, "epoch": 1.6901408450704225, "percentage": 84.51, "elapsed_time": "0:03:49", "remaining_time": "0:00:42"}
362
+ {"current_steps": 361, "total_steps": 426, "loss": 0.0571, "lr": 5.635278277556267e-07, "epoch": 1.6948356807511737, "percentage": 84.74, "elapsed_time": "0:03:50", "remaining_time": "0:00:41"}
363
+ {"current_steps": 362, "total_steps": 426, "loss": 0.0516, "lr": 5.466425964703914e-07, "epoch": 1.699530516431925, "percentage": 84.98, "elapsed_time": "0:03:51", "remaining_time": "0:00:40"}
364
+ {"current_steps": 363, "total_steps": 426, "loss": 0.0769, "lr": 5.29999560718622e-07, "epoch": 1.704225352112676, "percentage": 85.21, "elapsed_time": "0:03:51", "remaining_time": "0:00:40"}
365
+ {"current_steps": 364, "total_steps": 426, "loss": 0.049, "lr": 5.135996256306619e-07, "epoch": 1.7089201877934272, "percentage": 85.45, "elapsed_time": "0:03:52", "remaining_time": "0:00:39"}
366
+ {"current_steps": 365, "total_steps": 426, "loss": 0.0537, "lr": 4.974436831158441e-07, "epoch": 1.7136150234741785, "percentage": 85.68, "elapsed_time": "0:03:52", "remaining_time": "0:00:38"}
367
+ {"current_steps": 366, "total_steps": 426, "loss": 0.0451, "lr": 4.815326118139813e-07, "epoch": 1.7183098591549295, "percentage": 85.92, "elapsed_time": "0:03:53", "remaining_time": "0:00:38"}
368
+ {"current_steps": 367, "total_steps": 426, "loss": 0.0653, "lr": 4.658672770475825e-07, "epoch": 1.7230046948356808, "percentage": 86.15, "elapsed_time": "0:03:54", "remaining_time": "0:00:37"}
369
+ {"current_steps": 368, "total_steps": 426, "loss": 0.0619, "lr": 4.5044853077479134e-07, "epoch": 1.727699530516432, "percentage": 86.38, "elapsed_time": "0:03:54", "remaining_time": "0:00:37"}
370
+ {"current_steps": 369, "total_steps": 426, "loss": 0.0536, "lr": 4.3527721154305703e-07, "epoch": 1.732394366197183, "percentage": 86.62, "elapsed_time": "0:03:55", "remaining_time": "0:00:36"}
371
+ {"current_steps": 370, "total_steps": 426, "loss": 0.0697, "lr": 4.203541444435211e-07, "epoch": 1.7370892018779343, "percentage": 86.85, "elapsed_time": "0:03:56", "remaining_time": "0:00:35"}
372
+ {"current_steps": 371, "total_steps": 426, "loss": 0.0513, "lr": 4.0568014106615205e-07, "epoch": 1.7417840375586855, "percentage": 87.09, "elapsed_time": "0:03:56", "remaining_time": "0:00:35"}
373
+ {"current_steps": 372, "total_steps": 426, "loss": 0.0663, "lr": 3.9125599945560866e-07, "epoch": 1.7464788732394365, "percentage": 87.32, "elapsed_time": "0:03:57", "remaining_time": "0:00:34"}
374
+ {"current_steps": 373, "total_steps": 426, "loss": 0.0589, "lr": 3.770825040678294e-07, "epoch": 1.7511737089201878, "percentage": 87.56, "elapsed_time": "0:03:57", "remaining_time": "0:00:33"}
375
+ {"current_steps": 374, "total_steps": 426, "loss": 0.0655, "lr": 3.631604257273774e-07, "epoch": 1.755868544600939, "percentage": 87.79, "elapsed_time": "0:03:58", "remaining_time": "0:00:33"}
376
+ {"current_steps": 375, "total_steps": 426, "loss": 0.0503, "lr": 3.4949052158551875e-07, "epoch": 1.76056338028169, "percentage": 88.03, "elapsed_time": "0:03:59", "remaining_time": "0:00:32"}
377
+ {"current_steps": 376, "total_steps": 426, "loss": 0.0528, "lr": 3.360735350790428e-07, "epoch": 1.7652582159624415, "percentage": 88.26, "elapsed_time": "0:03:59", "remaining_time": "0:00:31"}
378
+ {"current_steps": 377, "total_steps": 426, "loss": 0.0565, "lr": 3.229101958898273e-07, "epoch": 1.7699530516431925, "percentage": 88.5, "elapsed_time": "0:04:00", "remaining_time": "0:00:31"}
379
+ {"current_steps": 378, "total_steps": 426, "loss": 0.0451, "lr": 3.100012199051627e-07, "epoch": 1.7746478873239435, "percentage": 88.73, "elapsed_time": "0:04:01", "remaining_time": "0:00:30"}
380
+ {"current_steps": 379, "total_steps": 426, "loss": 0.0742, "lr": 2.973473091788121e-07, "epoch": 1.779342723004695, "percentage": 88.97, "elapsed_time": "0:04:01", "remaining_time": "0:00:29"}
381
+ {"current_steps": 380, "total_steps": 426, "loss": 0.0604, "lr": 2.8494915189283325e-07, "epoch": 1.784037558685446, "percentage": 89.2, "elapsed_time": "0:04:02", "remaining_time": "0:00:29"}
382
+ {"current_steps": 381, "total_steps": 426, "loss": 0.065, "lr": 2.728074223201488e-07, "epoch": 1.788732394366197, "percentage": 89.44, "elapsed_time": "0:04:02", "remaining_time": "0:00:28"}
383
+ {"current_steps": 382, "total_steps": 426, "loss": 0.0586, "lr": 2.6092278078788004e-07, "epoch": 1.7934272300469485, "percentage": 89.67, "elapsed_time": "0:04:03", "remaining_time": "0:00:28"}
384
+ {"current_steps": 383, "total_steps": 426, "loss": 0.0562, "lr": 2.4929587364143195e-07, "epoch": 1.7981220657276995, "percentage": 89.91, "elapsed_time": "0:04:04", "remaining_time": "0:00:27"}
385
+ {"current_steps": 384, "total_steps": 426, "loss": 0.0538, "lr": 2.3792733320934348e-07, "epoch": 1.8028169014084507, "percentage": 90.14, "elapsed_time": "0:04:04", "remaining_time": "0:00:26"}
386
+ {"current_steps": 385, "total_steps": 426, "loss": 0.0556, "lr": 2.2681777776889736e-07, "epoch": 1.807511737089202, "percentage": 90.38, "elapsed_time": "0:04:05", "remaining_time": "0:00:26"}
387
+ {"current_steps": 386, "total_steps": 426, "loss": 0.058, "lr": 2.1596781151249524e-07, "epoch": 1.812206572769953, "percentage": 90.61, "elapsed_time": "0:04:05", "remaining_time": "0:00:25"}
388
+ {"current_steps": 387, "total_steps": 426, "loss": 0.0545, "lr": 2.053780245147996e-07, "epoch": 1.8169014084507042, "percentage": 90.85, "elapsed_time": "0:04:06", "remaining_time": "0:00:24"}
389
+ {"current_steps": 388, "total_steps": 426, "loss": 0.0589, "lr": 1.9504899270064105e-07, "epoch": 1.8215962441314555, "percentage": 91.08, "elapsed_time": "0:04:07", "remaining_time": "0:00:24"}
390
+ {"current_steps": 389, "total_steps": 426, "loss": 0.0512, "lr": 1.849812778137e-07, "epoch": 1.8262910798122065, "percentage": 91.31, "elapsed_time": "0:04:07", "remaining_time": "0:00:23"}
391
+ {"current_steps": 390, "total_steps": 426, "loss": 0.0513, "lr": 1.7517542738595071e-07, "epoch": 1.8309859154929577, "percentage": 91.55, "elapsed_time": "0:04:08", "remaining_time": "0:00:22"}
392
+ {"current_steps": 391, "total_steps": 426, "loss": 0.0491, "lr": 1.6563197470788827e-07, "epoch": 1.835680751173709, "percentage": 91.78, "elapsed_time": "0:04:09", "remaining_time": "0:00:22"}
393
+ {"current_steps": 392, "total_steps": 426, "loss": 0.057, "lr": 1.5635143879952575e-07, "epoch": 1.84037558685446, "percentage": 92.02, "elapsed_time": "0:04:09", "remaining_time": "0:00:21"}
394
+ {"current_steps": 393, "total_steps": 426, "loss": 0.0702, "lr": 1.47334324382164e-07, "epoch": 1.8450704225352113, "percentage": 92.25, "elapsed_time": "0:04:10", "remaining_time": "0:00:21"}
395
+ {"current_steps": 394, "total_steps": 426, "loss": 0.0613, "lr": 1.3858112185094418e-07, "epoch": 1.8497652582159625, "percentage": 92.49, "elapsed_time": "0:04:10", "remaining_time": "0:00:20"}
396
+ {"current_steps": 395, "total_steps": 426, "loss": 0.053, "lr": 1.3009230724818134e-07, "epoch": 1.8544600938967135, "percentage": 92.72, "elapsed_time": "0:04:11", "remaining_time": "0:00:19"}
397
+ {"current_steps": 396, "total_steps": 426, "loss": 0.0605, "lr": 1.2186834223746612e-07, "epoch": 1.8591549295774648, "percentage": 92.96, "elapsed_time": "0:04:12", "remaining_time": "0:00:19"}
398
+ {"current_steps": 397, "total_steps": 426, "loss": 0.0462, "lr": 1.1390967407856612e-07, "epoch": 1.863849765258216, "percentage": 93.19, "elapsed_time": "0:04:12", "remaining_time": "0:00:18"}
399
+ {"current_steps": 398, "total_steps": 426, "loss": 0.0635, "lr": 1.0621673560309798e-07, "epoch": 1.868544600938967, "percentage": 93.43, "elapsed_time": "0:04:13", "remaining_time": "0:00:17"}
400
+ {"current_steps": 399, "total_steps": 426, "loss": 0.0699, "lr": 9.878994519098573e-08, "epoch": 1.8732394366197183, "percentage": 93.66, "elapsed_time": "0:04:14", "remaining_time": "0:00:17"}
401
+ {"current_steps": 400, "total_steps": 426, "loss": 0.0539, "lr": 9.162970674771177e-08, "epoch": 1.8779342723004695, "percentage": 93.9, "elapsed_time": "0:04:14", "remaining_time": "0:00:16"}
402
+ {"current_steps": 400, "total_steps": 426, "eval_loss": 0.12246008962392807, "epoch": 1.8779342723004695, "percentage": 93.9, "elapsed_time": "0:04:15", "remaining_time": "0:00:16"}
403
+ {"current_steps": 401, "total_steps": 426, "loss": 0.0637, "lr": 8.473640968234609e-08, "epoch": 1.8826291079812205, "percentage": 94.13, "elapsed_time": "0:04:15", "remaining_time": "0:00:15"}
404
+ {"current_steps": 402, "total_steps": 426, "loss": 0.0621, "lr": 7.81104288863721e-08, "epoch": 1.887323943661972, "percentage": 94.37, "elapsed_time": "0:04:16", "remaining_time": "0:00:15"}
405
+ {"current_steps": 403, "total_steps": 426, "loss": 0.0556, "lr": 7.175212471329573e-08, "epoch": 1.892018779342723, "percentage": 94.6, "elapsed_time": "0:04:17", "remaining_time": "0:00:14"}
406
+ {"current_steps": 404, "total_steps": 426, "loss": 0.055, "lr": 6.566184295904777e-08, "epoch": 1.896713615023474, "percentage": 94.84, "elapsed_time": "0:04:17", "remaining_time": "0:00:14"}
407
+ {"current_steps": 405, "total_steps": 426, "loss": 0.0557, "lr": 5.983991484317997e-08, "epoch": 1.9014084507042255, "percentage": 95.07, "elapsed_time": "0:04:18", "remaining_time": "0:00:13"}
408
+ {"current_steps": 406, "total_steps": 426, "loss": 0.0665, "lr": 5.4286656990847897e-08, "epoch": 1.9061032863849765, "percentage": 95.31, "elapsed_time": "0:04:19", "remaining_time": "0:00:12"}
409
+ {"current_steps": 407, "total_steps": 426, "loss": 0.0536, "lr": 4.9002371415595716e-08, "epoch": 1.9107981220657277, "percentage": 95.54, "elapsed_time": "0:04:19", "remaining_time": "0:00:12"}
410
+ {"current_steps": 408, "total_steps": 426, "loss": 0.0735, "lr": 4.398734550292716e-08, "epoch": 1.915492957746479, "percentage": 95.77, "elapsed_time": "0:04:20", "remaining_time": "0:00:11"}
411
+ {"current_steps": 409, "total_steps": 426, "loss": 0.057, "lr": 3.9241851994678556e-08, "epoch": 1.92018779342723, "percentage": 96.01, "elapsed_time": "0:04:21", "remaining_time": "0:00:10"}
412
+ {"current_steps": 410, "total_steps": 426, "loss": 0.0543, "lr": 3.476614897418573e-08, "epoch": 1.9248826291079812, "percentage": 96.24, "elapsed_time": "0:04:21", "remaining_time": "0:00:10"}
413
+ {"current_steps": 411, "total_steps": 426, "loss": 0.0499, "lr": 3.0560479852246304e-08, "epoch": 1.9295774647887325, "percentage": 96.48, "elapsed_time": "0:04:22", "remaining_time": "0:00:09"}
414
+ {"current_steps": 412, "total_steps": 426, "loss": 0.0582, "lr": 2.6625073353884756e-08, "epoch": 1.9342723004694835, "percentage": 96.71, "elapsed_time": "0:04:23", "remaining_time": "0:00:08"}
415
+ {"current_steps": 413, "total_steps": 426, "loss": 0.0481, "lr": 2.2960143505909027e-08, "epoch": 1.9389671361502347, "percentage": 96.95, "elapsed_time": "0:04:23", "remaining_time": "0:00:08"}
416
+ {"current_steps": 414, "total_steps": 426, "loss": 0.0632, "lr": 1.9565889625275945e-08, "epoch": 1.943661971830986, "percentage": 97.18, "elapsed_time": "0:04:24", "remaining_time": "0:00:07"}
417
+ {"current_steps": 415, "total_steps": 426, "loss": 0.0583, "lr": 1.644249630824657e-08, "epoch": 1.948356807511737, "percentage": 97.42, "elapsed_time": "0:04:24", "remaining_time": "0:00:07"}
418
+ {"current_steps": 416, "total_steps": 426, "loss": 0.0774, "lr": 1.3590133420350315e-08, "epoch": 1.9530516431924883, "percentage": 97.65, "elapsed_time": "0:04:25", "remaining_time": "0:00:06"}
419
+ {"current_steps": 417, "total_steps": 426, "loss": 0.0681, "lr": 1.1008956087144585e-08, "epoch": 1.9577464788732395, "percentage": 97.89, "elapsed_time": "0:04:26", "remaining_time": "0:00:05"}
420
+ {"current_steps": 418, "total_steps": 426, "loss": 0.0617, "lr": 8.699104685779835e-09, "epoch": 1.9624413145539905, "percentage": 98.12, "elapsed_time": "0:04:26", "remaining_time": "0:00:05"}
421
+ {"current_steps": 419, "total_steps": 426, "loss": 0.0639, "lr": 6.660704837364029e-09, "epoch": 1.9671361502347418, "percentage": 98.36, "elapsed_time": "0:04:27", "remaining_time": "0:00:04"}
422
+ {"current_steps": 420, "total_steps": 426, "loss": 0.0527, "lr": 4.89386740013198e-09, "epoch": 1.971830985915493, "percentage": 98.59, "elapsed_time": "0:04:27", "remaining_time": "0:00:03"}
423
+ {"current_steps": 421, "total_steps": 426, "loss": 0.0587, "lr": 3.3986884634146232e-09, "epoch": 1.976525821596244, "percentage": 98.83, "elapsed_time": "0:04:28", "remaining_time": "0:00:03"}
424
+ {"current_steps": 422, "total_steps": 426, "loss": 0.0523, "lr": 2.1752493424148647e-09, "epoch": 1.9812206572769953, "percentage": 99.06, "elapsed_time": "0:04:29", "remaining_time": "0:00:02"}
425
+ {"current_steps": 423, "total_steps": 426, "loss": 0.0587, "lr": 1.2236165737850025e-09, "epoch": 1.9859154929577465, "percentage": 99.3, "elapsed_time": "0:04:29", "remaining_time": "0:00:01"}
426
+ {"current_steps": 424, "total_steps": 426, "loss": 0.0628, "lr": 5.438419120062933e-10, "epoch": 1.9906103286384975, "percentage": 99.53, "elapsed_time": "0:04:30", "remaining_time": "0:00:01"}
427
+ {"current_steps": 425, "total_steps": 426, "loss": 0.0638, "lr": 1.3596232657675512e-10, "epoch": 1.995305164319249, "percentage": 99.77, "elapsed_time": "0:04:30", "remaining_time": "0:00:00"}
428
+ {"current_steps": 426, "total_steps": 426, "loss": 0.0422, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:04:31", "remaining_time": "0:00:00"}
429
+ {"current_steps": 426, "total_steps": 426, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:04:35", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,3040 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 200,
6
+ "global_step": 426,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004694835680751174,
13
+ "grad_norm": 4.795204374719416,
14
+ "learning_rate": 9.999864037673424e-06,
15
+ "loss": 0.5112,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.009389671361502348,
20
+ "grad_norm": 6.671091528449369,
21
+ "learning_rate": 9.999456158087994e-06,
22
+ "loss": 0.5814,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.014084507042253521,
27
+ "grad_norm": 4.659415777664479,
28
+ "learning_rate": 9.998776383426217e-06,
29
+ "loss": 0.479,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.018779342723004695,
34
+ "grad_norm": 5.583672872687822,
35
+ "learning_rate": 9.997824750657586e-06,
36
+ "loss": 0.5216,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.023474178403755867,
41
+ "grad_norm": 5.08059978162162,
42
+ "learning_rate": 9.996601311536586e-06,
43
+ "loss": 0.4186,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.028169014084507043,
48
+ "grad_norm": 4.898857020085729,
49
+ "learning_rate": 9.995106132599869e-06,
50
+ "loss": 0.3469,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.03286384976525822,
55
+ "grad_norm": 5.611044165670074,
56
+ "learning_rate": 9.993339295162637e-06,
57
+ "loss": 0.3785,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.03755868544600939,
62
+ "grad_norm": 4.459429257689431,
63
+ "learning_rate": 9.99130089531422e-06,
64
+ "loss": 0.3432,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.04225352112676056,
69
+ "grad_norm": 4.908780848178339,
70
+ "learning_rate": 9.988991043912857e-06,
71
+ "loss": 0.3235,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.046948356807511735,
76
+ "grad_norm": 5.048960769795611,
77
+ "learning_rate": 9.98640986657965e-06,
78
+ "loss": 0.3698,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.051643192488262914,
83
+ "grad_norm": 4.619982734539293,
84
+ "learning_rate": 9.983557503691755e-06,
85
+ "loss": 0.2923,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.056338028169014086,
90
+ "grad_norm": 4.12973548135526,
91
+ "learning_rate": 9.980434110374725e-06,
92
+ "loss": 0.3107,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.06103286384976526,
97
+ "grad_norm": 3.9677289618540543,
98
+ "learning_rate": 9.977039856494091e-06,
99
+ "loss": 0.2975,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.06572769953051644,
104
+ "grad_norm": 4.603594193640064,
105
+ "learning_rate": 9.973374926646117e-06,
106
+ "loss": 0.3518,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.07042253521126761,
111
+ "grad_norm": 4.061204527861547,
112
+ "learning_rate": 9.969439520147754e-06,
113
+ "loss": 0.2697,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.07511737089201878,
118
+ "grad_norm": 3.769691610605157,
119
+ "learning_rate": 9.965233851025816e-06,
120
+ "loss": 0.2818,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.07981220657276995,
125
+ "grad_norm": 3.8781678633472576,
126
+ "learning_rate": 9.960758148005323e-06,
127
+ "loss": 0.2619,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.08450704225352113,
132
+ "grad_norm": 4.190415068667403,
133
+ "learning_rate": 9.956012654497073e-06,
134
+ "loss": 0.2755,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.0892018779342723,
139
+ "grad_norm": 3.8093127033843888,
140
+ "learning_rate": 9.950997628584404e-06,
141
+ "loss": 0.2486,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.09389671361502347,
146
+ "grad_norm": 3.545564020776135,
147
+ "learning_rate": 9.945713343009154e-06,
148
+ "loss": 0.2501,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.09859154929577464,
153
+ "grad_norm": 3.9525326696536793,
154
+ "learning_rate": 9.94016008515682e-06,
155
+ "loss": 0.2854,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.10328638497652583,
160
+ "grad_norm": 3.6138981079617007,
161
+ "learning_rate": 9.934338157040953e-06,
162
+ "loss": 0.2531,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.107981220657277,
167
+ "grad_norm": 3.891292972336178,
168
+ "learning_rate": 9.928247875286705e-06,
169
+ "loss": 0.2523,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.11267605633802817,
174
+ "grad_norm": 3.244579382155417,
175
+ "learning_rate": 9.921889571113629e-06,
176
+ "loss": 0.2434,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.11737089201877934,
181
+ "grad_norm": 4.137132814439194,
182
+ "learning_rate": 9.915263590317654e-06,
183
+ "loss": 0.2718,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.12206572769953052,
188
+ "grad_norm": 4.9163221796982475,
189
+ "learning_rate": 9.90837029325229e-06,
190
+ "loss": 0.2921,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.1267605633802817,
195
+ "grad_norm": 3.3260959787723037,
196
+ "learning_rate": 9.901210054809015e-06,
197
+ "loss": 0.2147,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.13145539906103287,
202
+ "grad_norm": 4.065082755860131,
203
+ "learning_rate": 9.893783264396903e-06,
204
+ "loss": 0.2637,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.13615023474178403,
209
+ "grad_norm": 4.174162434813742,
210
+ "learning_rate": 9.886090325921435e-06,
211
+ "loss": 0.2321,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.14084507042253522,
216
+ "grad_norm": 4.693347721123008,
217
+ "learning_rate": 9.878131657762535e-06,
218
+ "loss": 0.3077,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.14553990610328638,
223
+ "grad_norm": 4.266608402876341,
224
+ "learning_rate": 9.86990769275182e-06,
225
+ "loss": 0.2806,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.15023474178403756,
230
+ "grad_norm": 4.475943347006578,
231
+ "learning_rate": 9.861418878149056e-06,
232
+ "loss": 0.2824,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.15492957746478872,
237
+ "grad_norm": 3.817410688787844,
238
+ "learning_rate": 9.852665675617837e-06,
239
+ "loss": 0.2407,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.1596244131455399,
244
+ "grad_norm": 4.029518865324446,
245
+ "learning_rate": 9.843648561200476e-06,
246
+ "loss": 0.2418,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.1643192488262911,
251
+ "grad_norm": 4.050089313329657,
252
+ "learning_rate": 9.834368025292112e-06,
253
+ "loss": 0.2238,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.16901408450704225,
258
+ "grad_norm": 3.2465811282121284,
259
+ "learning_rate": 9.82482457261405e-06,
260
+ "loss": 0.1777,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.17370892018779344,
265
+ "grad_norm": 4.085550059024563,
266
+ "learning_rate": 9.8150187221863e-06,
267
+ "loss": 0.2386,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.1784037558685446,
272
+ "grad_norm": 3.8228602004618915,
273
+ "learning_rate": 9.80495100729936e-06,
274
+ "loss": 0.2047,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.18309859154929578,
279
+ "grad_norm": 3.5173239554573104,
280
+ "learning_rate": 9.7946219754852e-06,
281
+ "loss": 0.1926,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.18779342723004694,
286
+ "grad_norm": 4.042996140064424,
287
+ "learning_rate": 9.784032188487507e-06,
288
+ "loss": 0.215,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.19248826291079812,
293
+ "grad_norm": 3.7747228674253095,
294
+ "learning_rate": 9.773182222231104e-06,
295
+ "loss": 0.2514,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.19718309859154928,
300
+ "grad_norm": 3.413189150344936,
301
+ "learning_rate": 9.762072666790658e-06,
302
+ "loss": 0.1938,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.20187793427230047,
307
+ "grad_norm": 3.323095711089638,
308
+ "learning_rate": 9.750704126358568e-06,
309
+ "loss": 0.1956,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.20657276995305165,
314
+ "grad_norm": 4.202877582031939,
315
+ "learning_rate": 9.73907721921212e-06,
316
+ "loss": 0.2453,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.2112676056338028,
321
+ "grad_norm": 3.894408184592951,
322
+ "learning_rate": 9.727192577679852e-06,
323
+ "loss": 0.2213,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.215962441314554,
328
+ "grad_norm": 3.197362377698984,
329
+ "learning_rate": 9.715050848107167e-06,
330
+ "loss": 0.1572,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.22065727699530516,
335
+ "grad_norm": 3.2809579008926235,
336
+ "learning_rate": 9.702652690821188e-06,
337
+ "loss": 0.197,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.22535211267605634,
342
+ "grad_norm": 3.2137474221256785,
343
+ "learning_rate": 9.689998780094839e-06,
344
+ "loss": 0.1852,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.2300469483568075,
349
+ "grad_norm": 3.991542444769107,
350
+ "learning_rate": 9.677089804110173e-06,
351
+ "loss": 0.2511,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.2347417840375587,
356
+ "grad_norm": 4.174811745124501,
357
+ "learning_rate": 9.663926464920959e-06,
358
+ "loss": 0.2268,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.23943661971830985,
363
+ "grad_norm": 3.7474767500546773,
364
+ "learning_rate": 9.650509478414483e-06,
365
+ "loss": 0.2202,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.24413145539906103,
370
+ "grad_norm": 3.574569223751201,
371
+ "learning_rate": 9.636839574272623e-06,
372
+ "loss": 0.2327,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.24882629107981222,
377
+ "grad_norm": 4.105006674014343,
378
+ "learning_rate": 9.622917495932172e-06,
379
+ "loss": 0.1751,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.2535211267605634,
384
+ "grad_norm": 3.625037822332638,
385
+ "learning_rate": 9.608744000544392e-06,
386
+ "loss": 0.1788,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.25821596244131456,
391
+ "grad_norm": 4.7379084130057745,
392
+ "learning_rate": 9.594319858933847e-06,
393
+ "loss": 0.2295,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.26291079812206575,
398
+ "grad_norm": 3.3484314858035686,
399
+ "learning_rate": 9.579645855556481e-06,
400
+ "loss": 0.1806,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.2676056338028169,
405
+ "grad_norm": 3.5038203232986227,
406
+ "learning_rate": 9.564722788456943e-06,
407
+ "loss": 0.1775,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.27230046948356806,
412
+ "grad_norm": 3.871688553348583,
413
+ "learning_rate": 9.54955146922521e-06,
414
+ "loss": 0.1939,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.27699530516431925,
419
+ "grad_norm": 3.5582803403614616,
420
+ "learning_rate": 9.534132722952419e-06,
421
+ "loss": 0.1721,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.28169014084507044,
426
+ "grad_norm": 3.941136846971122,
427
+ "learning_rate": 9.51846738818602e-06,
428
+ "loss": 0.184,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.2863849765258216,
433
+ "grad_norm": 3.8189227978944564,
434
+ "learning_rate": 9.502556316884157e-06,
435
+ "loss": 0.1849,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.29107981220657275,
440
+ "grad_norm": 4.281787668463841,
441
+ "learning_rate": 9.48640037436934e-06,
442
+ "loss": 0.2188,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.29577464788732394,
447
+ "grad_norm": 4.1870166781411005,
448
+ "learning_rate": 9.470000439281379e-06,
449
+ "loss": 0.2013,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.3004694835680751,
454
+ "grad_norm": 3.6542900239467215,
455
+ "learning_rate": 9.453357403529609e-06,
456
+ "loss": 0.1902,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.3051643192488263,
461
+ "grad_norm": 4.048087435082514,
462
+ "learning_rate": 9.436472172244374e-06,
463
+ "loss": 0.1958,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.30985915492957744,
468
+ "grad_norm": 3.2012779839143595,
469
+ "learning_rate": 9.419345663727805e-06,
470
+ "loss": 0.1856,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.3145539906103286,
475
+ "grad_norm": 3.463585644365661,
476
+ "learning_rate": 9.401978809403882e-06,
477
+ "loss": 0.1556,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.3192488262910798,
482
+ "grad_norm": 4.6341173177324135,
483
+ "learning_rate": 9.38437255376777e-06,
484
+ "loss": 0.2187,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.323943661971831,
489
+ "grad_norm": 3.985278135671177,
490
+ "learning_rate": 9.366527854334464e-06,
491
+ "loss": 0.2231,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.3286384976525822,
496
+ "grad_norm": 2.850329563186479,
497
+ "learning_rate": 9.348445681586703e-06,
498
+ "loss": 0.1569,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.3333333333333333,
503
+ "grad_norm": 3.044468275425822,
504
+ "learning_rate": 9.330127018922195e-06,
505
+ "loss": 0.1597,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.3380281690140845,
510
+ "grad_norm": 4.456904752370724,
511
+ "learning_rate": 9.31157286260014e-06,
512
+ "loss": 0.2194,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.3427230046948357,
517
+ "grad_norm": 3.389050972417507,
518
+ "learning_rate": 9.292784221687043e-06,
519
+ "loss": 0.1803,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.3474178403755869,
524
+ "grad_norm": 3.9110108508571257,
525
+ "learning_rate": 9.273762118001837e-06,
526
+ "loss": 0.2177,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.352112676056338,
531
+ "grad_norm": 3.13042301627468,
532
+ "learning_rate": 9.25450758606031e-06,
533
+ "loss": 0.1675,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.3568075117370892,
538
+ "grad_norm": 4.129010737841615,
539
+ "learning_rate": 9.235021673018849e-06,
540
+ "loss": 0.2049,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.3615023474178404,
545
+ "grad_norm": 3.807813561235126,
546
+ "learning_rate": 9.21530543861748e-06,
547
+ "loss": 0.174,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.36619718309859156,
552
+ "grad_norm": 4.125811030900892,
553
+ "learning_rate": 9.195359955122244e-06,
554
+ "loss": 0.1986,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.37089201877934275,
559
+ "grad_norm": 3.7854067565828298,
560
+ "learning_rate": 9.175186307266877e-06,
561
+ "loss": 0.1991,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.3755868544600939,
566
+ "grad_norm": 4.170476576769826,
567
+ "learning_rate": 9.15478559219382e-06,
568
+ "loss": 0.1914,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.38028169014084506,
573
+ "grad_norm": 3.890159653894575,
574
+ "learning_rate": 9.134158919394545e-06,
575
+ "loss": 0.1921,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.38497652582159625,
580
+ "grad_norm": 4.2357930988312,
581
+ "learning_rate": 9.113307410649222e-06,
582
+ "loss": 0.2081,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.38967136150234744,
587
+ "grad_norm": 4.040758215123453,
588
+ "learning_rate": 9.092232199965707e-06,
589
+ "loss": 0.1836,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.39436619718309857,
594
+ "grad_norm": 3.980705387886667,
595
+ "learning_rate": 9.070934433517872e-06,
596
+ "loss": 0.1781,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.39906103286384975,
601
+ "grad_norm": 4.335971265689919,
602
+ "learning_rate": 9.049415269583268e-06,
603
+ "loss": 0.1924,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.40375586854460094,
608
+ "grad_norm": 4.382100810714692,
609
+ "learning_rate": 9.027675878480131e-06,
610
+ "loss": 0.2079,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.4084507042253521,
615
+ "grad_norm": 4.5130875707678015,
616
+ "learning_rate": 9.005717442503741e-06,
617
+ "loss": 0.2016,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.4131455399061033,
622
+ "grad_norm": 4.601983373249001,
623
+ "learning_rate": 8.983541155862114e-06,
624
+ "loss": 0.2229,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.41784037558685444,
629
+ "grad_norm": 3.934340537790252,
630
+ "learning_rate": 8.96114822461106e-06,
631
+ "loss": 0.1736,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.4225352112676056,
636
+ "grad_norm": 3.4666148131597723,
637
+ "learning_rate": 8.938539866588593e-06,
638
+ "loss": 0.1647,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.4272300469483568,
643
+ "grad_norm": 4.147994111662615,
644
+ "learning_rate": 8.915717311348693e-06,
645
+ "loss": 0.1854,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.431924882629108,
650
+ "grad_norm": 4.028813272613093,
651
+ "learning_rate": 8.892681800094447e-06,
652
+ "loss": 0.1802,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.43661971830985913,
657
+ "grad_norm": 4.39999158423739,
658
+ "learning_rate": 8.869434585610534e-06,
659
+ "loss": 0.1934,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.4413145539906103,
664
+ "grad_norm": 4.223582086678747,
665
+ "learning_rate": 8.845976932195104e-06,
666
+ "loss": 0.1899,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.4460093896713615,
671
+ "grad_norm": 4.071436760079734,
672
+ "learning_rate": 8.822310115591008e-06,
673
+ "loss": 0.1997,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.4507042253521127,
678
+ "grad_norm": 3.9657472714155655,
679
+ "learning_rate": 8.798435422916425e-06,
680
+ "loss": 0.185,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.45539906103286387,
685
+ "grad_norm": 4.095809344671023,
686
+ "learning_rate": 8.774354152594862e-06,
687
+ "loss": 0.1785,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.460093896713615,
692
+ "grad_norm": 3.3516880714576636,
693
+ "learning_rate": 8.750067614284534e-06,
694
+ "loss": 0.1791,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.4647887323943662,
699
+ "grad_norm": 4.2003458933177455,
700
+ "learning_rate": 8.725577128807144e-06,
701
+ "loss": 0.1845,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.4694835680751174,
706
+ "grad_norm": 4.019353944901272,
707
+ "learning_rate": 8.700884028076042e-06,
708
+ "loss": 0.1769,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.47417840375586856,
713
+ "grad_norm": 3.9313808946183664,
714
+ "learning_rate": 8.675989655023802e-06,
715
+ "loss": 0.162,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.4788732394366197,
720
+ "grad_norm": 3.7273553247097784,
721
+ "learning_rate": 8.650895363529172e-06,
722
+ "loss": 0.155,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.4835680751173709,
727
+ "grad_norm": 3.860027505973743,
728
+ "learning_rate": 8.625602518343457e-06,
729
+ "loss": 0.191,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.48826291079812206,
734
+ "grad_norm": 4.063169661001865,
735
+ "learning_rate": 8.600112495016289e-06,
736
+ "loss": 0.1921,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.49295774647887325,
741
+ "grad_norm": 4.433076480175269,
742
+ "learning_rate": 8.574426679820813e-06,
743
+ "loss": 0.2151,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.49765258215962443,
748
+ "grad_norm": 4.644458717501688,
749
+ "learning_rate": 8.548546469678311e-06,
750
+ "loss": 0.2053,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.5023474178403756,
755
+ "grad_norm": 3.8686095531900793,
756
+ "learning_rate": 8.522473272082217e-06,
757
+ "loss": 0.1923,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.5070422535211268,
762
+ "grad_norm": 3.6370636790935316,
763
+ "learning_rate": 8.496208505021572e-06,
764
+ "loss": 0.1732,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.5117370892018779,
769
+ "grad_norm": 3.931100768718882,
770
+ "learning_rate": 8.469753596903909e-06,
771
+ "loss": 0.215,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.5164319248826291,
776
+ "grad_norm": 3.222160406728147,
777
+ "learning_rate": 8.443109986477574e-06,
778
+ "loss": 0.1535,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.5211267605633803,
783
+ "grad_norm": 3.1687669945021026,
784
+ "learning_rate": 8.416279122753468e-06,
785
+ "loss": 0.1688,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.5258215962441315,
790
+ "grad_norm": 4.034798717378171,
791
+ "learning_rate": 8.389262464926256e-06,
792
+ "loss": 0.2148,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.5305164319248826,
797
+ "grad_norm": 4.2590091916898345,
798
+ "learning_rate": 8.362061482295001e-06,
799
+ "loss": 0.201,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.5352112676056338,
804
+ "grad_norm": 3.6419107281885403,
805
+ "learning_rate": 8.334677654183254e-06,
806
+ "loss": 0.1751,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.539906103286385,
811
+ "grad_norm": 3.6510949138745934,
812
+ "learning_rate": 8.307112469858608e-06,
813
+ "loss": 0.1623,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.5446009389671361,
818
+ "grad_norm": 3.9107430715007148,
819
+ "learning_rate": 8.279367428451703e-06,
820
+ "loss": 0.1709,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.5492957746478874,
825
+ "grad_norm": 3.900306484150481,
826
+ "learning_rate": 8.251444038874685e-06,
827
+ "loss": 0.1662,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.5539906103286385,
832
+ "grad_norm": 4.479886889874258,
833
+ "learning_rate": 8.223343819739164e-06,
834
+ "loss": 0.2016,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.5586854460093896,
839
+ "grad_norm": 4.320007211036499,
840
+ "learning_rate": 8.19506829927361e-06,
841
+ "loss": 0.2096,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.5633802816901409,
846
+ "grad_norm": 3.32707857447822,
847
+ "learning_rate": 8.166619015240236e-06,
848
+ "loss": 0.1666,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.568075117370892,
853
+ "grad_norm": 2.843970779549723,
854
+ "learning_rate": 8.137997514851385e-06,
855
+ "loss": 0.1522,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.5727699530516432,
860
+ "grad_norm": 4.346534605577487,
861
+ "learning_rate": 8.109205354685367e-06,
862
+ "loss": 0.1927,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.5774647887323944,
867
+ "grad_norm": 3.88372486514076,
868
+ "learning_rate": 8.080244100601822e-06,
869
+ "loss": 0.1589,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.5821596244131455,
874
+ "grad_norm": 3.631870325678664,
875
+ "learning_rate": 8.051115327656538e-06,
876
+ "loss": 0.1462,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.5868544600938967,
881
+ "grad_norm": 4.065792275969599,
882
+ "learning_rate": 8.021820620015811e-06,
883
+ "loss": 0.1604,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.5915492957746479,
888
+ "grad_norm": 4.197122693766938,
889
+ "learning_rate": 7.992361570870289e-06,
890
+ "loss": 0.2352,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.596244131455399,
895
+ "grad_norm": 4.016831160352165,
896
+ "learning_rate": 7.96273978234831e-06,
897
+ "loss": 0.1765,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.6009389671361502,
902
+ "grad_norm": 4.170326120071254,
903
+ "learning_rate": 7.932956865428792e-06,
904
+ "loss": 0.1899,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.6056338028169014,
909
+ "grad_norm": 3.652423631205711,
910
+ "learning_rate": 7.903014439853605e-06,
911
+ "loss": 0.1652,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.6103286384976526,
916
+ "grad_norm": 4.255257946934246,
917
+ "learning_rate": 7.872914134039485e-06,
918
+ "loss": 0.1878,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.6150234741784038,
923
+ "grad_norm": 4.248016621946989,
924
+ "learning_rate": 7.842657584989477e-06,
925
+ "loss": 0.1676,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.6197183098591549,
930
+ "grad_norm": 4.048534079722626,
931
+ "learning_rate": 7.812246438203905e-06,
932
+ "loss": 0.174,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.6244131455399061,
937
+ "grad_norm": 4.032618733921642,
938
+ "learning_rate": 7.78168234759087e-06,
939
+ "loss": 0.1498,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.6291079812206573,
944
+ "grad_norm": 3.5014943886648044,
945
+ "learning_rate": 7.750966975376328e-06,
946
+ "loss": 0.1531,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.6338028169014085,
951
+ "grad_norm": 3.630724763160065,
952
+ "learning_rate": 7.720101992013661e-06,
953
+ "loss": 0.1548,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.6384976525821596,
958
+ "grad_norm": 3.938445162927457,
959
+ "learning_rate": 7.689089076092851e-06,
960
+ "loss": 0.1724,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.6431924882629108,
965
+ "grad_norm": 3.575845041441881,
966
+ "learning_rate": 7.657929914249177e-06,
967
+ "loss": 0.1757,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.647887323943662,
972
+ "grad_norm": 3.678347641314121,
973
+ "learning_rate": 7.626626201071494e-06,
974
+ "loss": 0.1584,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.6525821596244131,
979
+ "grad_norm": 4.211878828367982,
980
+ "learning_rate": 7.5951796390100755e-06,
981
+ "loss": 0.2042,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.6572769953051644,
986
+ "grad_norm": 3.7731909368198973,
987
+ "learning_rate": 7.563591938284012e-06,
988
+ "loss": 0.1726,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.6619718309859155,
993
+ "grad_norm": 3.791961955439014,
994
+ "learning_rate": 7.53186481678822e-06,
995
+ "loss": 0.1674,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.6666666666666666,
1000
+ "grad_norm": 4.010497588006458,
1001
+ "learning_rate": 7.500000000000001e-06,
1002
+ "loss": 0.175,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.6713615023474179,
1007
+ "grad_norm": 4.341307070452301,
1008
+ "learning_rate": 7.467999220885204e-06,
1009
+ "loss": 0.1697,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.676056338028169,
1014
+ "grad_norm": 4.511074930877239,
1015
+ "learning_rate": 7.4358642198039835e-06,
1016
+ "loss": 0.1817,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.6807511737089202,
1021
+ "grad_norm": 3.7801909041528554,
1022
+ "learning_rate": 7.403596744416142e-06,
1023
+ "loss": 0.1518,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.6854460093896714,
1028
+ "grad_norm": 3.568798084454868,
1029
+ "learning_rate": 7.371198549586091e-06,
1030
+ "loss": 0.1529,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.6901408450704225,
1035
+ "grad_norm": 4.190472637446197,
1036
+ "learning_rate": 7.338671397287409e-06,
1037
+ "loss": 0.1713,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.6948356807511737,
1042
+ "grad_norm": 4.399405719639844,
1043
+ "learning_rate": 7.306017056507018e-06,
1044
+ "loss": 0.1774,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.6995305164319249,
1049
+ "grad_norm": 4.341913847305131,
1050
+ "learning_rate": 7.273237303148976e-06,
1051
+ "loss": 0.1697,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.704225352112676,
1056
+ "grad_norm": 3.661657149489898,
1057
+ "learning_rate": 7.240333919937893e-06,
1058
+ "loss": 0.167,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.7089201877934272,
1063
+ "grad_norm": 3.6710552151881015,
1064
+ "learning_rate": 7.207308696321985e-06,
1065
+ "loss": 0.1681,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.7136150234741784,
1070
+ "grad_norm": 3.9835723574451354,
1071
+ "learning_rate": 7.174163428375748e-06,
1072
+ "loss": 0.1763,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.7183098591549296,
1077
+ "grad_norm": 4.3173265257350595,
1078
+ "learning_rate": 7.140899918702276e-06,
1079
+ "loss": 0.1756,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.7230046948356808,
1084
+ "grad_norm": 4.156822867069766,
1085
+ "learning_rate": 7.107519976335241e-06,
1086
+ "loss": 0.123,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.7276995305164319,
1091
+ "grad_norm": 4.3882806884162955,
1092
+ "learning_rate": 7.0740254166404884e-06,
1093
+ "loss": 0.195,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.7323943661971831,
1098
+ "grad_norm": 4.008796537630938,
1099
+ "learning_rate": 7.040418061217325e-06,
1100
+ "loss": 0.1509,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.7370892018779343,
1105
+ "grad_norm": 3.2355440667888256,
1106
+ "learning_rate": 7.006699737799445e-06,
1107
+ "loss": 0.1627,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.7417840375586855,
1112
+ "grad_norm": 3.831946914512411,
1113
+ "learning_rate": 6.972872280155528e-06,
1114
+ "loss": 0.1739,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.7464788732394366,
1119
+ "grad_norm": 4.099923330425261,
1120
+ "learning_rate": 6.938937527989511e-06,
1121
+ "loss": 0.1743,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.7511737089201878,
1126
+ "grad_norm": 3.5859028894643834,
1127
+ "learning_rate": 6.9048973268405375e-06,
1128
+ "loss": 0.1718,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.755868544600939,
1133
+ "grad_norm": 3.731415848676003,
1134
+ "learning_rate": 6.8707535279825845e-06,
1135
+ "loss": 0.1419,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.7605633802816901,
1140
+ "grad_norm": 3.7787919208216043,
1141
+ "learning_rate": 6.836507988323785e-06,
1142
+ "loss": 0.1626,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.7652582159624414,
1147
+ "grad_norm": 4.152969444426624,
1148
+ "learning_rate": 6.802162570305436e-06,
1149
+ "loss": 0.1537,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.7699530516431925,
1154
+ "grad_norm": 3.84703555318092,
1155
+ "learning_rate": 6.767719141800718e-06,
1156
+ "loss": 0.1735,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.7746478873239436,
1161
+ "grad_norm": 3.9643045102797654,
1162
+ "learning_rate": 6.733179576013098e-06,
1163
+ "loss": 0.1637,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.7793427230046949,
1168
+ "grad_norm": 3.7275425500623034,
1169
+ "learning_rate": 6.698545751374465e-06,
1170
+ "loss": 0.1501,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.784037558685446,
1175
+ "grad_norm": 3.3002519083185,
1176
+ "learning_rate": 6.663819551442969e-06,
1177
+ "loss": 0.1354,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.7887323943661971,
1182
+ "grad_norm": 3.657657708799669,
1183
+ "learning_rate": 6.629002864800589e-06,
1184
+ "loss": 0.1609,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.7934272300469484,
1189
+ "grad_norm": 3.8851214014226847,
1190
+ "learning_rate": 6.594097584950406e-06,
1191
+ "loss": 0.1688,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.7981220657276995,
1196
+ "grad_norm": 3.698748549659436,
1197
+ "learning_rate": 6.55910561021365e-06,
1198
+ "loss": 0.1425,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.8028169014084507,
1203
+ "grad_norm": 4.509235312817185,
1204
+ "learning_rate": 6.524028843626433e-06,
1205
+ "loss": 0.1737,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.8075117370892019,
1210
+ "grad_norm": 3.836573705410599,
1211
+ "learning_rate": 6.488869192836279e-06,
1212
+ "loss": 0.1404,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.812206572769953,
1217
+ "grad_norm": 4.29566042099674,
1218
+ "learning_rate": 6.453628569998352e-06,
1219
+ "loss": 0.1594,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.8169014084507042,
1224
+ "grad_norm": 3.438270946115778,
1225
+ "learning_rate": 6.418308891671484e-06,
1226
+ "loss": 0.1098,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.8215962441314554,
1231
+ "grad_norm": 3.871618753539285,
1232
+ "learning_rate": 6.38291207871393e-06,
1233
+ "loss": 0.1621,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.8262910798122066,
1238
+ "grad_norm": 4.577752714781617,
1239
+ "learning_rate": 6.347440056178904e-06,
1240
+ "loss": 0.1683,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.8309859154929577,
1245
+ "grad_norm": 4.216863880007683,
1246
+ "learning_rate": 6.311894753209896e-06,
1247
+ "loss": 0.1517,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.8356807511737089,
1252
+ "grad_norm": 3.043573924671583,
1253
+ "learning_rate": 6.27627810293574e-06,
1254
+ "loss": 0.1289,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.8403755868544601,
1259
+ "grad_norm": 3.527160739315952,
1260
+ "learning_rate": 6.2405920423654885e-06,
1261
+ "loss": 0.134,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.8450704225352113,
1266
+ "grad_norm": 3.7066736612021685,
1267
+ "learning_rate": 6.204838512283073e-06,
1268
+ "loss": 0.1452,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.8497652582159625,
1273
+ "grad_norm": 3.603977634656601,
1274
+ "learning_rate": 6.169019457141745e-06,
1275
+ "loss": 0.1566,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.8544600938967136,
1280
+ "grad_norm": 3.937075495705898,
1281
+ "learning_rate": 6.133136824958334e-06,
1282
+ "loss": 0.1419,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.8591549295774648,
1287
+ "grad_norm": 3.492364551161864,
1288
+ "learning_rate": 6.097192567207304e-06,
1289
+ "loss": 0.1692,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.863849765258216,
1294
+ "grad_norm": 4.141470946913356,
1295
+ "learning_rate": 6.061188638714616e-06,
1296
+ "loss": 0.1647,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.8685446009389671,
1301
+ "grad_norm": 3.3218959604383578,
1302
+ "learning_rate": 6.0251269975514275e-06,
1303
+ "loss": 0.1516,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.8732394366197183,
1308
+ "grad_norm": 3.7214562944778753,
1309
+ "learning_rate": 5.989009604927587e-06,
1310
+ "loss": 0.1532,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.8779342723004695,
1315
+ "grad_norm": 3.918123431215504,
1316
+ "learning_rate": 5.95283842508499e-06,
1317
+ "loss": 0.1517,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.8826291079812206,
1322
+ "grad_norm": 4.200241291576511,
1323
+ "learning_rate": 5.916615425190744e-06,
1324
+ "loss": 0.1388,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.8873239436619719,
1329
+ "grad_norm": 3.578546132642782,
1330
+ "learning_rate": 5.8803425752301814e-06,
1331
+ "loss": 0.1336,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.892018779342723,
1336
+ "grad_norm": 3.8896406411659568,
1337
+ "learning_rate": 5.844021847899735e-06,
1338
+ "loss": 0.1678,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.8967136150234741,
1343
+ "grad_norm": 3.923157229296463,
1344
+ "learning_rate": 5.80765521849964e-06,
1345
+ "loss": 0.1588,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.9014084507042254,
1350
+ "grad_norm": 4.887462190776199,
1351
+ "learning_rate": 5.771244664826512e-06,
1352
+ "loss": 0.1862,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.9061032863849765,
1357
+ "grad_norm": 3.892899910946184,
1358
+ "learning_rate": 5.734792167065789e-06,
1359
+ "loss": 0.1583,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.9107981220657277,
1364
+ "grad_norm": 3.875646212259954,
1365
+ "learning_rate": 5.698299707684031e-06,
1366
+ "loss": 0.1606,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.9154929577464789,
1371
+ "grad_norm": 4.159885168843491,
1372
+ "learning_rate": 5.661769271321113e-06,
1373
+ "loss": 0.1522,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.92018779342723,
1378
+ "grad_norm": 4.879886251274869,
1379
+ "learning_rate": 5.6252028446822805e-06,
1380
+ "loss": 0.1488,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.9248826291079812,
1385
+ "grad_norm": 3.9547190533041063,
1386
+ "learning_rate": 5.588602416430107e-06,
1387
+ "loss": 0.1571,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.9295774647887324,
1392
+ "grad_norm": 4.277238571530009,
1393
+ "learning_rate": 5.55196997707635e-06,
1394
+ "loss": 0.1739,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.9342723004694836,
1399
+ "grad_norm": 3.9869584184219726,
1400
+ "learning_rate": 5.515307518873677e-06,
1401
+ "loss": 0.1507,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.9389671361502347,
1406
+ "grad_norm": 3.68770864813949,
1407
+ "learning_rate": 5.478617035707337e-06,
1408
+ "loss": 0.1647,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.9389671361502347,
1413
+ "eval_loss": 0.13491584360599518,
1414
+ "eval_runtime": 0.7117,
1415
+ "eval_samples_per_second": 25.292,
1416
+ "eval_steps_per_second": 7.026,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.9436619718309859,
1421
+ "grad_norm": 3.510035840216914,
1422
+ "learning_rate": 5.441900522986712e-06,
1423
+ "loss": 0.1237,
1424
+ "step": 201
1425
+ },
1426
+ {
1427
+ "epoch": 0.9483568075117371,
1428
+ "grad_norm": 3.9036745854615296,
1429
+ "learning_rate": 5.4051599775368e-06,
1430
+ "loss": 0.1671,
1431
+ "step": 202
1432
+ },
1433
+ {
1434
+ "epoch": 0.9530516431924883,
1435
+ "grad_norm": 3.848422877317892,
1436
+ "learning_rate": 5.368397397489615e-06,
1437
+ "loss": 0.1563,
1438
+ "step": 203
1439
+ },
1440
+ {
1441
+ "epoch": 0.9577464788732394,
1442
+ "grad_norm": 4.271946732870076,
1443
+ "learning_rate": 5.33161478217552e-06,
1444
+ "loss": 0.1635,
1445
+ "step": 204
1446
+ },
1447
+ {
1448
+ "epoch": 0.9624413145539906,
1449
+ "grad_norm": 3.914833373577505,
1450
+ "learning_rate": 5.294814132014503e-06,
1451
+ "loss": 0.1431,
1452
+ "step": 205
1453
+ },
1454
+ {
1455
+ "epoch": 0.9671361502347418,
1456
+ "grad_norm": 4.482214207355883,
1457
+ "learning_rate": 5.257997448407366e-06,
1458
+ "loss": 0.1683,
1459
+ "step": 206
1460
+ },
1461
+ {
1462
+ "epoch": 0.971830985915493,
1463
+ "grad_norm": 3.6338742689711157,
1464
+ "learning_rate": 5.221166733626895e-06,
1465
+ "loss": 0.1525,
1466
+ "step": 207
1467
+ },
1468
+ {
1469
+ "epoch": 0.9765258215962441,
1470
+ "grad_norm": 3.484086395047381,
1471
+ "learning_rate": 5.184323990708959e-06,
1472
+ "loss": 0.1339,
1473
+ "step": 208
1474
+ },
1475
+ {
1476
+ "epoch": 0.9812206572769953,
1477
+ "grad_norm": 4.143271752012906,
1478
+ "learning_rate": 5.147471223343573e-06,
1479
+ "loss": 0.169,
1480
+ "step": 209
1481
+ },
1482
+ {
1483
+ "epoch": 0.9859154929577465,
1484
+ "grad_norm": 3.426834701225127,
1485
+ "learning_rate": 5.110610435765935e-06,
1486
+ "loss": 0.1405,
1487
+ "step": 210
1488
+ },
1489
+ {
1490
+ "epoch": 0.9906103286384976,
1491
+ "grad_norm": 3.6850642867289496,
1492
+ "learning_rate": 5.073743632647422e-06,
1493
+ "loss": 0.1378,
1494
+ "step": 211
1495
+ },
1496
+ {
1497
+ "epoch": 0.9953051643192489,
1498
+ "grad_norm": 3.5440812097360403,
1499
+ "learning_rate": 5.0368728189865624e-06,
1500
+ "loss": 0.1598,
1501
+ "step": 212
1502
+ },
1503
+ {
1504
+ "epoch": 1.0,
1505
+ "grad_norm": 2.6450454475529668,
1506
+ "learning_rate": 5e-06,
1507
+ "loss": 0.1034,
1508
+ "step": 213
1509
+ },
1510
+ {
1511
+ "epoch": 1.0046948356807512,
1512
+ "grad_norm": 3.0640065668586396,
1513
+ "learning_rate": 4.9631271810134375e-06,
1514
+ "loss": 0.0972,
1515
+ "step": 214
1516
+ },
1517
+ {
1518
+ "epoch": 1.0093896713615023,
1519
+ "grad_norm": 3.1394702975706537,
1520
+ "learning_rate": 4.9262563673525795e-06,
1521
+ "loss": 0.0888,
1522
+ "step": 215
1523
+ },
1524
+ {
1525
+ "epoch": 1.0140845070422535,
1526
+ "grad_norm": 3.167224106896483,
1527
+ "learning_rate": 4.8893895642340665e-06,
1528
+ "loss": 0.0834,
1529
+ "step": 216
1530
+ },
1531
+ {
1532
+ "epoch": 1.0187793427230047,
1533
+ "grad_norm": 2.3333205452853267,
1534
+ "learning_rate": 4.852528776656428e-06,
1535
+ "loss": 0.074,
1536
+ "step": 217
1537
+ },
1538
+ {
1539
+ "epoch": 1.0234741784037558,
1540
+ "grad_norm": 2.782266383936839,
1541
+ "learning_rate": 4.815676009291044e-06,
1542
+ "loss": 0.0773,
1543
+ "step": 218
1544
+ },
1545
+ {
1546
+ "epoch": 1.028169014084507,
1547
+ "grad_norm": 2.602376417670595,
1548
+ "learning_rate": 4.778833266373107e-06,
1549
+ "loss": 0.0815,
1550
+ "step": 219
1551
+ },
1552
+ {
1553
+ "epoch": 1.0328638497652582,
1554
+ "grad_norm": 2.9420428534406375,
1555
+ "learning_rate": 4.742002551592635e-06,
1556
+ "loss": 0.0716,
1557
+ "step": 220
1558
+ },
1559
+ {
1560
+ "epoch": 1.0375586854460095,
1561
+ "grad_norm": 3.203435221751088,
1562
+ "learning_rate": 4.705185867985498e-06,
1563
+ "loss": 0.0807,
1564
+ "step": 221
1565
+ },
1566
+ {
1567
+ "epoch": 1.0422535211267605,
1568
+ "grad_norm": 3.0517466566506313,
1569
+ "learning_rate": 4.668385217824482e-06,
1570
+ "loss": 0.09,
1571
+ "step": 222
1572
+ },
1573
+ {
1574
+ "epoch": 1.0469483568075117,
1575
+ "grad_norm": 3.396434458065312,
1576
+ "learning_rate": 4.631602602510388e-06,
1577
+ "loss": 0.0694,
1578
+ "step": 223
1579
+ },
1580
+ {
1581
+ "epoch": 1.051643192488263,
1582
+ "grad_norm": 2.8316530077839825,
1583
+ "learning_rate": 4.594840022463201e-06,
1584
+ "loss": 0.0764,
1585
+ "step": 224
1586
+ },
1587
+ {
1588
+ "epoch": 1.056338028169014,
1589
+ "grad_norm": 2.93952235820806,
1590
+ "learning_rate": 4.558099477013288e-06,
1591
+ "loss": 0.0693,
1592
+ "step": 225
1593
+ },
1594
+ {
1595
+ "epoch": 1.0610328638497653,
1596
+ "grad_norm": 3.6220656106046327,
1597
+ "learning_rate": 4.5213829642926635e-06,
1598
+ "loss": 0.0825,
1599
+ "step": 226
1600
+ },
1601
+ {
1602
+ "epoch": 1.0657276995305165,
1603
+ "grad_norm": 3.187067652820305,
1604
+ "learning_rate": 4.484692481126323e-06,
1605
+ "loss": 0.0748,
1606
+ "step": 227
1607
+ },
1608
+ {
1609
+ "epoch": 1.0704225352112675,
1610
+ "grad_norm": 3.3250313971491465,
1611
+ "learning_rate": 4.4480300229236525e-06,
1612
+ "loss": 0.0675,
1613
+ "step": 228
1614
+ },
1615
+ {
1616
+ "epoch": 1.0751173708920188,
1617
+ "grad_norm": 3.3046625737744715,
1618
+ "learning_rate": 4.411397583569894e-06,
1619
+ "loss": 0.072,
1620
+ "step": 229
1621
+ },
1622
+ {
1623
+ "epoch": 1.07981220657277,
1624
+ "grad_norm": 3.5194513327792634,
1625
+ "learning_rate": 4.374797155317721e-06,
1626
+ "loss": 0.0793,
1627
+ "step": 230
1628
+ },
1629
+ {
1630
+ "epoch": 1.084507042253521,
1631
+ "grad_norm": 3.028301470503519,
1632
+ "learning_rate": 4.338230728678888e-06,
1633
+ "loss": 0.069,
1634
+ "step": 231
1635
+ },
1636
+ {
1637
+ "epoch": 1.0892018779342723,
1638
+ "grad_norm": 3.0829418530310426,
1639
+ "learning_rate": 4.30170029231597e-06,
1640
+ "loss": 0.0757,
1641
+ "step": 232
1642
+ },
1643
+ {
1644
+ "epoch": 1.0938967136150235,
1645
+ "grad_norm": 2.977410939944313,
1646
+ "learning_rate": 4.265207832934212e-06,
1647
+ "loss": 0.0742,
1648
+ "step": 233
1649
+ },
1650
+ {
1651
+ "epoch": 1.0985915492957747,
1652
+ "grad_norm": 3.8289001527160718,
1653
+ "learning_rate": 4.228755335173488e-06,
1654
+ "loss": 0.0897,
1655
+ "step": 234
1656
+ },
1657
+ {
1658
+ "epoch": 1.1032863849765258,
1659
+ "grad_norm": 3.3617924153179928,
1660
+ "learning_rate": 4.192344781500362e-06,
1661
+ "loss": 0.0712,
1662
+ "step": 235
1663
+ },
1664
+ {
1665
+ "epoch": 1.107981220657277,
1666
+ "grad_norm": 3.686821301487297,
1667
+ "learning_rate": 4.155978152100266e-06,
1668
+ "loss": 0.0779,
1669
+ "step": 236
1670
+ },
1671
+ {
1672
+ "epoch": 1.1126760563380282,
1673
+ "grad_norm": 3.1088066953258906,
1674
+ "learning_rate": 4.119657424769819e-06,
1675
+ "loss": 0.0705,
1676
+ "step": 237
1677
+ },
1678
+ {
1679
+ "epoch": 1.1173708920187793,
1680
+ "grad_norm": 3.38972188941091,
1681
+ "learning_rate": 4.0833845748092586e-06,
1682
+ "loss": 0.0792,
1683
+ "step": 238
1684
+ },
1685
+ {
1686
+ "epoch": 1.1220657276995305,
1687
+ "grad_norm": 3.0692560777778723,
1688
+ "learning_rate": 4.047161574915012e-06,
1689
+ "loss": 0.0701,
1690
+ "step": 239
1691
+ },
1692
+ {
1693
+ "epoch": 1.1267605633802817,
1694
+ "grad_norm": 3.2818080025715384,
1695
+ "learning_rate": 4.010990395072414e-06,
1696
+ "loss": 0.0842,
1697
+ "step": 240
1698
+ },
1699
+ {
1700
+ "epoch": 1.131455399061033,
1701
+ "grad_norm": 3.8988971065644766,
1702
+ "learning_rate": 3.974873002448575e-06,
1703
+ "loss": 0.0942,
1704
+ "step": 241
1705
+ },
1706
+ {
1707
+ "epoch": 1.136150234741784,
1708
+ "grad_norm": 2.934017427407112,
1709
+ "learning_rate": 3.938811361285386e-06,
1710
+ "loss": 0.0623,
1711
+ "step": 242
1712
+ },
1713
+ {
1714
+ "epoch": 1.1408450704225352,
1715
+ "grad_norm": 3.334408203824069,
1716
+ "learning_rate": 3.902807432792698e-06,
1717
+ "loss": 0.0686,
1718
+ "step": 243
1719
+ },
1720
+ {
1721
+ "epoch": 1.1455399061032865,
1722
+ "grad_norm": 2.9836283442913034,
1723
+ "learning_rate": 3.866863175041666e-06,
1724
+ "loss": 0.0688,
1725
+ "step": 244
1726
+ },
1727
+ {
1728
+ "epoch": 1.1502347417840375,
1729
+ "grad_norm": 3.505788056577321,
1730
+ "learning_rate": 3.830980542858256e-06,
1731
+ "loss": 0.0824,
1732
+ "step": 245
1733
+ },
1734
+ {
1735
+ "epoch": 1.1549295774647887,
1736
+ "grad_norm": 3.1617099032634,
1737
+ "learning_rate": 3.7951614877169285e-06,
1738
+ "loss": 0.0751,
1739
+ "step": 246
1740
+ },
1741
+ {
1742
+ "epoch": 1.15962441314554,
1743
+ "grad_norm": 3.4236656518990176,
1744
+ "learning_rate": 3.7594079576345123e-06,
1745
+ "loss": 0.0686,
1746
+ "step": 247
1747
+ },
1748
+ {
1749
+ "epoch": 1.164319248826291,
1750
+ "grad_norm": 3.176431715899578,
1751
+ "learning_rate": 3.7237218970642624e-06,
1752
+ "loss": 0.0592,
1753
+ "step": 248
1754
+ },
1755
+ {
1756
+ "epoch": 1.1690140845070423,
1757
+ "grad_norm": 3.099580380881821,
1758
+ "learning_rate": 3.6881052467901056e-06,
1759
+ "loss": 0.0716,
1760
+ "step": 249
1761
+ },
1762
+ {
1763
+ "epoch": 1.1737089201877935,
1764
+ "grad_norm": 3.0967208333457075,
1765
+ "learning_rate": 3.6525599438210956e-06,
1766
+ "loss": 0.0689,
1767
+ "step": 250
1768
+ },
1769
+ {
1770
+ "epoch": 1.1784037558685445,
1771
+ "grad_norm": 3.008440635349803,
1772
+ "learning_rate": 3.617087921286073e-06,
1773
+ "loss": 0.0697,
1774
+ "step": 251
1775
+ },
1776
+ {
1777
+ "epoch": 1.1830985915492958,
1778
+ "grad_norm": 3.4620103981622328,
1779
+ "learning_rate": 3.5816911083285165e-06,
1780
+ "loss": 0.0654,
1781
+ "step": 252
1782
+ },
1783
+ {
1784
+ "epoch": 1.187793427230047,
1785
+ "grad_norm": 3.3909304259214523,
1786
+ "learning_rate": 3.5463714300016483e-06,
1787
+ "loss": 0.0662,
1788
+ "step": 253
1789
+ },
1790
+ {
1791
+ "epoch": 1.192488262910798,
1792
+ "grad_norm": 2.6178631981639255,
1793
+ "learning_rate": 3.511130807163724e-06,
1794
+ "loss": 0.0628,
1795
+ "step": 254
1796
+ },
1797
+ {
1798
+ "epoch": 1.1971830985915493,
1799
+ "grad_norm": 2.8881354533865475,
1800
+ "learning_rate": 3.4759711563735676e-06,
1801
+ "loss": 0.0659,
1802
+ "step": 255
1803
+ },
1804
+ {
1805
+ "epoch": 1.2018779342723005,
1806
+ "grad_norm": 2.62325831247376,
1807
+ "learning_rate": 3.440894389786352e-06,
1808
+ "loss": 0.0561,
1809
+ "step": 256
1810
+ },
1811
+ {
1812
+ "epoch": 1.2065727699530517,
1813
+ "grad_norm": 2.9418772360228393,
1814
+ "learning_rate": 3.405902415049593e-06,
1815
+ "loss": 0.061,
1816
+ "step": 257
1817
+ },
1818
+ {
1819
+ "epoch": 1.2112676056338028,
1820
+ "grad_norm": 3.4581329998441417,
1821
+ "learning_rate": 3.370997135199413e-06,
1822
+ "loss": 0.0628,
1823
+ "step": 258
1824
+ },
1825
+ {
1826
+ "epoch": 1.215962441314554,
1827
+ "grad_norm": 3.5503748470931424,
1828
+ "learning_rate": 3.3361804485570315e-06,
1829
+ "loss": 0.0821,
1830
+ "step": 259
1831
+ },
1832
+ {
1833
+ "epoch": 1.2206572769953052,
1834
+ "grad_norm": 3.302725061517345,
1835
+ "learning_rate": 3.3014542486255365e-06,
1836
+ "loss": 0.0733,
1837
+ "step": 260
1838
+ },
1839
+ {
1840
+ "epoch": 1.2253521126760563,
1841
+ "grad_norm": 4.045018515872984,
1842
+ "learning_rate": 3.2668204239869046e-06,
1843
+ "loss": 0.0776,
1844
+ "step": 261
1845
+ },
1846
+ {
1847
+ "epoch": 1.2300469483568075,
1848
+ "grad_norm": 3.2141304628680176,
1849
+ "learning_rate": 3.2322808581992825e-06,
1850
+ "loss": 0.0744,
1851
+ "step": 262
1852
+ },
1853
+ {
1854
+ "epoch": 1.2347417840375587,
1855
+ "grad_norm": 2.9881598927254664,
1856
+ "learning_rate": 3.1978374296945635e-06,
1857
+ "loss": 0.0688,
1858
+ "step": 263
1859
+ },
1860
+ {
1861
+ "epoch": 1.2394366197183098,
1862
+ "grad_norm": 3.139790761073445,
1863
+ "learning_rate": 3.1634920116762175e-06,
1864
+ "loss": 0.0638,
1865
+ "step": 264
1866
+ },
1867
+ {
1868
+ "epoch": 1.244131455399061,
1869
+ "grad_norm": 3.9357909534554794,
1870
+ "learning_rate": 3.1292464720174163e-06,
1871
+ "loss": 0.0758,
1872
+ "step": 265
1873
+ },
1874
+ {
1875
+ "epoch": 1.2488262910798122,
1876
+ "grad_norm": 3.1864403476892926,
1877
+ "learning_rate": 3.0951026731594634e-06,
1878
+ "loss": 0.0584,
1879
+ "step": 266
1880
+ },
1881
+ {
1882
+ "epoch": 1.2535211267605635,
1883
+ "grad_norm": 3.1957512926501592,
1884
+ "learning_rate": 3.061062472010489e-06,
1885
+ "loss": 0.0778,
1886
+ "step": 267
1887
+ },
1888
+ {
1889
+ "epoch": 1.2582159624413145,
1890
+ "grad_norm": 3.035126432338683,
1891
+ "learning_rate": 3.0271277198444737e-06,
1892
+ "loss": 0.08,
1893
+ "step": 268
1894
+ },
1895
+ {
1896
+ "epoch": 1.2629107981220657,
1897
+ "grad_norm": 2.9002169641506184,
1898
+ "learning_rate": 2.9933002622005563e-06,
1899
+ "loss": 0.0639,
1900
+ "step": 269
1901
+ },
1902
+ {
1903
+ "epoch": 1.267605633802817,
1904
+ "grad_norm": 3.8857704071522794,
1905
+ "learning_rate": 2.9595819387826753e-06,
1906
+ "loss": 0.0796,
1907
+ "step": 270
1908
+ },
1909
+ {
1910
+ "epoch": 1.272300469483568,
1911
+ "grad_norm": 2.9183886458613286,
1912
+ "learning_rate": 2.9259745833595132e-06,
1913
+ "loss": 0.0512,
1914
+ "step": 271
1915
+ },
1916
+ {
1917
+ "epoch": 1.2769953051643192,
1918
+ "grad_norm": 2.7426214567232208,
1919
+ "learning_rate": 2.89248002366476e-06,
1920
+ "loss": 0.06,
1921
+ "step": 272
1922
+ },
1923
+ {
1924
+ "epoch": 1.2816901408450705,
1925
+ "grad_norm": 3.380274644016965,
1926
+ "learning_rate": 2.8591000812977245e-06,
1927
+ "loss": 0.0708,
1928
+ "step": 273
1929
+ },
1930
+ {
1931
+ "epoch": 1.2863849765258215,
1932
+ "grad_norm": 2.757229395688675,
1933
+ "learning_rate": 2.8258365716242543e-06,
1934
+ "loss": 0.0737,
1935
+ "step": 274
1936
+ },
1937
+ {
1938
+ "epoch": 1.2910798122065728,
1939
+ "grad_norm": 2.7653621401197093,
1940
+ "learning_rate": 2.792691303678016e-06,
1941
+ "loss": 0.0576,
1942
+ "step": 275
1943
+ },
1944
+ {
1945
+ "epoch": 1.295774647887324,
1946
+ "grad_norm": 3.453656353347679,
1947
+ "learning_rate": 2.7596660800621076e-06,
1948
+ "loss": 0.0627,
1949
+ "step": 276
1950
+ },
1951
+ {
1952
+ "epoch": 1.300469483568075,
1953
+ "grad_norm": 2.8529993808118648,
1954
+ "learning_rate": 2.7267626968510264e-06,
1955
+ "loss": 0.0633,
1956
+ "step": 277
1957
+ },
1958
+ {
1959
+ "epoch": 1.3051643192488263,
1960
+ "grad_norm": 2.9547910427609474,
1961
+ "learning_rate": 2.6939829434929834e-06,
1962
+ "loss": 0.061,
1963
+ "step": 278
1964
+ },
1965
+ {
1966
+ "epoch": 1.3098591549295775,
1967
+ "grad_norm": 2.942958970826166,
1968
+ "learning_rate": 2.661328602712592e-06,
1969
+ "loss": 0.0773,
1970
+ "step": 279
1971
+ },
1972
+ {
1973
+ "epoch": 1.3145539906103285,
1974
+ "grad_norm": 3.332191035671694,
1975
+ "learning_rate": 2.6288014504139104e-06,
1976
+ "loss": 0.0615,
1977
+ "step": 280
1978
+ },
1979
+ {
1980
+ "epoch": 1.3192488262910798,
1981
+ "grad_norm": 3.6679803671451525,
1982
+ "learning_rate": 2.5964032555838593e-06,
1983
+ "loss": 0.0744,
1984
+ "step": 281
1985
+ },
1986
+ {
1987
+ "epoch": 1.323943661971831,
1988
+ "grad_norm": 3.1040924660718443,
1989
+ "learning_rate": 2.5641357801960186e-06,
1990
+ "loss": 0.0676,
1991
+ "step": 282
1992
+ },
1993
+ {
1994
+ "epoch": 1.3286384976525822,
1995
+ "grad_norm": 3.878865964680938,
1996
+ "learning_rate": 2.5320007791147954e-06,
1997
+ "loss": 0.0684,
1998
+ "step": 283
1999
+ },
2000
+ {
2001
+ "epoch": 1.3333333333333333,
2002
+ "grad_norm": 3.270058460501866,
2003
+ "learning_rate": 2.5000000000000015e-06,
2004
+ "loss": 0.0632,
2005
+ "step": 284
2006
+ },
2007
+ {
2008
+ "epoch": 1.3380281690140845,
2009
+ "grad_norm": 3.072881487564358,
2010
+ "learning_rate": 2.4681351832117815e-06,
2011
+ "loss": 0.0536,
2012
+ "step": 285
2013
+ },
2014
+ {
2015
+ "epoch": 1.3427230046948357,
2016
+ "grad_norm": 2.6619665373165273,
2017
+ "learning_rate": 2.4364080617159885e-06,
2018
+ "loss": 0.0647,
2019
+ "step": 286
2020
+ },
2021
+ {
2022
+ "epoch": 1.347417840375587,
2023
+ "grad_norm": 3.0294315401160365,
2024
+ "learning_rate": 2.404820360989928e-06,
2025
+ "loss": 0.0701,
2026
+ "step": 287
2027
+ },
2028
+ {
2029
+ "epoch": 1.352112676056338,
2030
+ "grad_norm": 3.0933476030085116,
2031
+ "learning_rate": 2.373373798928507e-06,
2032
+ "loss": 0.0736,
2033
+ "step": 288
2034
+ },
2035
+ {
2036
+ "epoch": 1.3568075117370892,
2037
+ "grad_norm": 3.8718454799643025,
2038
+ "learning_rate": 2.3420700857508233e-06,
2039
+ "loss": 0.0769,
2040
+ "step": 289
2041
+ },
2042
+ {
2043
+ "epoch": 1.3615023474178405,
2044
+ "grad_norm": 3.046334334976069,
2045
+ "learning_rate": 2.310910923907149e-06,
2046
+ "loss": 0.0653,
2047
+ "step": 290
2048
+ },
2049
+ {
2050
+ "epoch": 1.3661971830985915,
2051
+ "grad_norm": 2.7618071701287144,
2052
+ "learning_rate": 2.2798980079863386e-06,
2053
+ "loss": 0.0675,
2054
+ "step": 291
2055
+ },
2056
+ {
2057
+ "epoch": 1.3708920187793427,
2058
+ "grad_norm": 2.505332456791594,
2059
+ "learning_rate": 2.249033024623672e-06,
2060
+ "loss": 0.0574,
2061
+ "step": 292
2062
+ },
2063
+ {
2064
+ "epoch": 1.375586854460094,
2065
+ "grad_norm": 3.149079722149451,
2066
+ "learning_rate": 2.2183176524091293e-06,
2067
+ "loss": 0.0622,
2068
+ "step": 293
2069
+ },
2070
+ {
2071
+ "epoch": 1.380281690140845,
2072
+ "grad_norm": 3.306440815612311,
2073
+ "learning_rate": 2.187753561796097e-06,
2074
+ "loss": 0.0679,
2075
+ "step": 294
2076
+ },
2077
+ {
2078
+ "epoch": 1.3849765258215962,
2079
+ "grad_norm": 3.4664457393542314,
2080
+ "learning_rate": 2.1573424150105234e-06,
2081
+ "loss": 0.0874,
2082
+ "step": 295
2083
+ },
2084
+ {
2085
+ "epoch": 1.3896713615023475,
2086
+ "grad_norm": 2.864420723191411,
2087
+ "learning_rate": 2.127085865960516e-06,
2088
+ "loss": 0.0593,
2089
+ "step": 296
2090
+ },
2091
+ {
2092
+ "epoch": 1.3943661971830985,
2093
+ "grad_norm": 3.265921239453905,
2094
+ "learning_rate": 2.0969855601463966e-06,
2095
+ "loss": 0.0862,
2096
+ "step": 297
2097
+ },
2098
+ {
2099
+ "epoch": 1.3990610328638498,
2100
+ "grad_norm": 3.1972561463638796,
2101
+ "learning_rate": 2.0670431345712092e-06,
2102
+ "loss": 0.0667,
2103
+ "step": 298
2104
+ },
2105
+ {
2106
+ "epoch": 1.403755868544601,
2107
+ "grad_norm": 3.178077845399186,
2108
+ "learning_rate": 2.0372602176516914e-06,
2109
+ "loss": 0.0649,
2110
+ "step": 299
2111
+ },
2112
+ {
2113
+ "epoch": 1.408450704225352,
2114
+ "grad_norm": 3.0828376978324816,
2115
+ "learning_rate": 2.0076384291297134e-06,
2116
+ "loss": 0.0646,
2117
+ "step": 300
2118
+ },
2119
+ {
2120
+ "epoch": 1.4131455399061033,
2121
+ "grad_norm": 3.781415924698528,
2122
+ "learning_rate": 1.97817937998419e-06,
2123
+ "loss": 0.0698,
2124
+ "step": 301
2125
+ },
2126
+ {
2127
+ "epoch": 1.4178403755868545,
2128
+ "grad_norm": 2.9270678876378473,
2129
+ "learning_rate": 1.9488846723434646e-06,
2130
+ "loss": 0.0582,
2131
+ "step": 302
2132
+ },
2133
+ {
2134
+ "epoch": 1.4225352112676055,
2135
+ "grad_norm": 3.182754883711226,
2136
+ "learning_rate": 1.9197558993981784e-06,
2137
+ "loss": 0.0755,
2138
+ "step": 303
2139
+ },
2140
+ {
2141
+ "epoch": 1.4272300469483568,
2142
+ "grad_norm": 4.347876050700364,
2143
+ "learning_rate": 1.890794645314633e-06,
2144
+ "loss": 0.0751,
2145
+ "step": 304
2146
+ },
2147
+ {
2148
+ "epoch": 1.431924882629108,
2149
+ "grad_norm": 3.4170291073721986,
2150
+ "learning_rate": 1.8620024851486174e-06,
2151
+ "loss": 0.0726,
2152
+ "step": 305
2153
+ },
2154
+ {
2155
+ "epoch": 1.436619718309859,
2156
+ "grad_norm": 3.0339897056805314,
2157
+ "learning_rate": 1.8333809847597644e-06,
2158
+ "loss": 0.0684,
2159
+ "step": 306
2160
+ },
2161
+ {
2162
+ "epoch": 1.4413145539906103,
2163
+ "grad_norm": 2.954379101389434,
2164
+ "learning_rate": 1.8049317007263933e-06,
2165
+ "loss": 0.0614,
2166
+ "step": 307
2167
+ },
2168
+ {
2169
+ "epoch": 1.4460093896713615,
2170
+ "grad_norm": 3.3042418964602422,
2171
+ "learning_rate": 1.7766561802608374e-06,
2172
+ "loss": 0.0713,
2173
+ "step": 308
2174
+ },
2175
+ {
2176
+ "epoch": 1.4507042253521127,
2177
+ "grad_norm": 2.824370246827801,
2178
+ "learning_rate": 1.748555961125315e-06,
2179
+ "loss": 0.0562,
2180
+ "step": 309
2181
+ },
2182
+ {
2183
+ "epoch": 1.455399061032864,
2184
+ "grad_norm": 2.9122471995759733,
2185
+ "learning_rate": 1.7206325715483003e-06,
2186
+ "loss": 0.0681,
2187
+ "step": 310
2188
+ },
2189
+ {
2190
+ "epoch": 1.460093896713615,
2191
+ "grad_norm": 2.8367517326893235,
2192
+ "learning_rate": 1.6928875301413916e-06,
2193
+ "loss": 0.0619,
2194
+ "step": 311
2195
+ },
2196
+ {
2197
+ "epoch": 1.4647887323943662,
2198
+ "grad_norm": 2.791143086178845,
2199
+ "learning_rate": 1.665322345816746e-06,
2200
+ "loss": 0.061,
2201
+ "step": 312
2202
+ },
2203
+ {
2204
+ "epoch": 1.4694835680751175,
2205
+ "grad_norm": 2.727958957886574,
2206
+ "learning_rate": 1.637938517705001e-06,
2207
+ "loss": 0.0572,
2208
+ "step": 313
2209
+ },
2210
+ {
2211
+ "epoch": 1.4741784037558685,
2212
+ "grad_norm": 2.9497575661742546,
2213
+ "learning_rate": 1.6107375350737437e-06,
2214
+ "loss": 0.0604,
2215
+ "step": 314
2216
+ },
2217
+ {
2218
+ "epoch": 1.4788732394366197,
2219
+ "grad_norm": 2.834121188274959,
2220
+ "learning_rate": 1.583720877246533e-06,
2221
+ "loss": 0.0588,
2222
+ "step": 315
2223
+ },
2224
+ {
2225
+ "epoch": 1.483568075117371,
2226
+ "grad_norm": 3.3311893313167977,
2227
+ "learning_rate": 1.556890013522428e-06,
2228
+ "loss": 0.0732,
2229
+ "step": 316
2230
+ },
2231
+ {
2232
+ "epoch": 1.488262910798122,
2233
+ "grad_norm": 3.6505753284732756,
2234
+ "learning_rate": 1.5302464030960924e-06,
2235
+ "loss": 0.076,
2236
+ "step": 317
2237
+ },
2238
+ {
2239
+ "epoch": 1.4929577464788732,
2240
+ "grad_norm": 3.20221336162175,
2241
+ "learning_rate": 1.50379149497843e-06,
2242
+ "loss": 0.0625,
2243
+ "step": 318
2244
+ },
2245
+ {
2246
+ "epoch": 1.4976525821596245,
2247
+ "grad_norm": 3.0957037845154427,
2248
+ "learning_rate": 1.477526727917784e-06,
2249
+ "loss": 0.0523,
2250
+ "step": 319
2251
+ },
2252
+ {
2253
+ "epoch": 1.5023474178403755,
2254
+ "grad_norm": 2.9117820797728333,
2255
+ "learning_rate": 1.4514535303216893e-06,
2256
+ "loss": 0.0579,
2257
+ "step": 320
2258
+ },
2259
+ {
2260
+ "epoch": 1.5070422535211268,
2261
+ "grad_norm": 3.642282551587516,
2262
+ "learning_rate": 1.4255733201791883e-06,
2263
+ "loss": 0.0698,
2264
+ "step": 321
2265
+ },
2266
+ {
2267
+ "epoch": 1.511737089201878,
2268
+ "grad_norm": 2.804152827109322,
2269
+ "learning_rate": 1.3998875049837141e-06,
2270
+ "loss": 0.0452,
2271
+ "step": 322
2272
+ },
2273
+ {
2274
+ "epoch": 1.516431924882629,
2275
+ "grad_norm": 3.308554659285574,
2276
+ "learning_rate": 1.3743974816565441e-06,
2277
+ "loss": 0.0631,
2278
+ "step": 323
2279
+ },
2280
+ {
2281
+ "epoch": 1.5211267605633803,
2282
+ "grad_norm": 2.962797268596488,
2283
+ "learning_rate": 1.3491046364708294e-06,
2284
+ "loss": 0.0618,
2285
+ "step": 324
2286
+ },
2287
+ {
2288
+ "epoch": 1.5258215962441315,
2289
+ "grad_norm": 3.4552837438460413,
2290
+ "learning_rate": 1.3240103449762004e-06,
2291
+ "loss": 0.0681,
2292
+ "step": 325
2293
+ },
2294
+ {
2295
+ "epoch": 1.5305164319248825,
2296
+ "grad_norm": 2.9767738403092343,
2297
+ "learning_rate": 1.2991159719239581e-06,
2298
+ "loss": 0.0617,
2299
+ "step": 326
2300
+ },
2301
+ {
2302
+ "epoch": 1.5352112676056338,
2303
+ "grad_norm": 2.6804049886596895,
2304
+ "learning_rate": 1.2744228711928585e-06,
2305
+ "loss": 0.059,
2306
+ "step": 327
2307
+ },
2308
+ {
2309
+ "epoch": 1.539906103286385,
2310
+ "grad_norm": 3.3222243056999994,
2311
+ "learning_rate": 1.249932385715467e-06,
2312
+ "loss": 0.0717,
2313
+ "step": 328
2314
+ },
2315
+ {
2316
+ "epoch": 1.544600938967136,
2317
+ "grad_norm": 3.2024170392370577,
2318
+ "learning_rate": 1.2256458474051375e-06,
2319
+ "loss": 0.0672,
2320
+ "step": 329
2321
+ },
2322
+ {
2323
+ "epoch": 1.5492957746478875,
2324
+ "grad_norm": 3.1135706020377474,
2325
+ "learning_rate": 1.2015645770835765e-06,
2326
+ "loss": 0.0633,
2327
+ "step": 330
2328
+ },
2329
+ {
2330
+ "epoch": 1.5539906103286385,
2331
+ "grad_norm": 2.7519192765221674,
2332
+ "learning_rate": 1.177689884408993e-06,
2333
+ "loss": 0.0541,
2334
+ "step": 331
2335
+ },
2336
+ {
2337
+ "epoch": 1.5586854460093895,
2338
+ "grad_norm": 3.7908372452425683,
2339
+ "learning_rate": 1.1540230678048969e-06,
2340
+ "loss": 0.0655,
2341
+ "step": 332
2342
+ },
2343
+ {
2344
+ "epoch": 1.563380281690141,
2345
+ "grad_norm": 2.866079908216172,
2346
+ "learning_rate": 1.1305654143894674e-06,
2347
+ "loss": 0.0601,
2348
+ "step": 333
2349
+ },
2350
+ {
2351
+ "epoch": 1.568075117370892,
2352
+ "grad_norm": 3.482298719501922,
2353
+ "learning_rate": 1.1073181999055538e-06,
2354
+ "loss": 0.0686,
2355
+ "step": 334
2356
+ },
2357
+ {
2358
+ "epoch": 1.5727699530516432,
2359
+ "grad_norm": 3.6693057526405344,
2360
+ "learning_rate": 1.0842826886513074e-06,
2361
+ "loss": 0.0814,
2362
+ "step": 335
2363
+ },
2364
+ {
2365
+ "epoch": 1.5774647887323945,
2366
+ "grad_norm": 2.778508919631583,
2367
+ "learning_rate": 1.0614601334114099e-06,
2368
+ "loss": 0.069,
2369
+ "step": 336
2370
+ },
2371
+ {
2372
+ "epoch": 1.5821596244131455,
2373
+ "grad_norm": 3.6537227782570025,
2374
+ "learning_rate": 1.038851775388941e-06,
2375
+ "loss": 0.0631,
2376
+ "step": 337
2377
+ },
2378
+ {
2379
+ "epoch": 1.5868544600938967,
2380
+ "grad_norm": 3.0964574567282592,
2381
+ "learning_rate": 1.016458844137887e-06,
2382
+ "loss": 0.0578,
2383
+ "step": 338
2384
+ },
2385
+ {
2386
+ "epoch": 1.591549295774648,
2387
+ "grad_norm": 3.4001361932505594,
2388
+ "learning_rate": 9.942825574962595e-07,
2389
+ "loss": 0.0528,
2390
+ "step": 339
2391
+ },
2392
+ {
2393
+ "epoch": 1.596244131455399,
2394
+ "grad_norm": 3.323166525021157,
2395
+ "learning_rate": 9.723241215198692e-07,
2396
+ "loss": 0.0711,
2397
+ "step": 340
2398
+ },
2399
+ {
2400
+ "epoch": 1.6009389671361502,
2401
+ "grad_norm": 3.1159737219680586,
2402
+ "learning_rate": 9.505847304167337e-07,
2403
+ "loss": 0.0617,
2404
+ "step": 341
2405
+ },
2406
+ {
2407
+ "epoch": 1.6056338028169015,
2408
+ "grad_norm": 2.958823464080263,
2409
+ "learning_rate": 9.290655664821296e-07,
2410
+ "loss": 0.0576,
2411
+ "step": 342
2412
+ },
2413
+ {
2414
+ "epoch": 1.6103286384976525,
2415
+ "grad_norm": 4.238880488341955,
2416
+ "learning_rate": 9.077678000342949e-07,
2417
+ "loss": 0.0816,
2418
+ "step": 343
2419
+ },
2420
+ {
2421
+ "epoch": 1.6150234741784038,
2422
+ "grad_norm": 3.054086397600406,
2423
+ "learning_rate": 8.866925893507805e-07,
2424
+ "loss": 0.0533,
2425
+ "step": 344
2426
+ },
2427
+ {
2428
+ "epoch": 1.619718309859155,
2429
+ "grad_norm": 2.611673361544413,
2430
+ "learning_rate": 8.658410806054568e-07,
2431
+ "loss": 0.0487,
2432
+ "step": 345
2433
+ },
2434
+ {
2435
+ "epoch": 1.624413145539906,
2436
+ "grad_norm": 3.149887311923902,
2437
+ "learning_rate": 8.45214407806182e-07,
2438
+ "loss": 0.0642,
2439
+ "step": 346
2440
+ },
2441
+ {
2442
+ "epoch": 1.6291079812206573,
2443
+ "grad_norm": 3.414783689958213,
2444
+ "learning_rate": 8.248136927331241e-07,
2445
+ "loss": 0.0654,
2446
+ "step": 347
2447
+ },
2448
+ {
2449
+ "epoch": 1.6338028169014085,
2450
+ "grad_norm": 3.4584245742879367,
2451
+ "learning_rate": 8.046400448777575e-07,
2452
+ "loss": 0.0649,
2453
+ "step": 348
2454
+ },
2455
+ {
2456
+ "epoch": 1.6384976525821595,
2457
+ "grad_norm": 3.7974172096004137,
2458
+ "learning_rate": 7.846945613825213e-07,
2459
+ "loss": 0.077,
2460
+ "step": 349
2461
+ },
2462
+ {
2463
+ "epoch": 1.6431924882629108,
2464
+ "grad_norm": 2.7548845295160502,
2465
+ "learning_rate": 7.649783269811523e-07,
2466
+ "loss": 0.059,
2467
+ "step": 350
2468
+ },
2469
+ {
2470
+ "epoch": 1.647887323943662,
2471
+ "grad_norm": 3.0522336424937837,
2472
+ "learning_rate": 7.45492413939689e-07,
2473
+ "loss": 0.064,
2474
+ "step": 351
2475
+ },
2476
+ {
2477
+ "epoch": 1.652582159624413,
2478
+ "grad_norm": 3.1272534601494537,
2479
+ "learning_rate": 7.26237881998163e-07,
2480
+ "loss": 0.0577,
2481
+ "step": 352
2482
+ },
2483
+ {
2484
+ "epoch": 1.6572769953051645,
2485
+ "grad_norm": 3.4716200804112836,
2486
+ "learning_rate": 7.072157783129585e-07,
2487
+ "loss": 0.0637,
2488
+ "step": 353
2489
+ },
2490
+ {
2491
+ "epoch": 1.6619718309859155,
2492
+ "grad_norm": 3.189006297689155,
2493
+ "learning_rate": 6.884271373998608e-07,
2494
+ "loss": 0.0552,
2495
+ "step": 354
2496
+ },
2497
+ {
2498
+ "epoch": 1.6666666666666665,
2499
+ "grad_norm": 3.275855039152132,
2500
+ "learning_rate": 6.698729810778065e-07,
2501
+ "loss": 0.054,
2502
+ "step": 355
2503
+ },
2504
+ {
2505
+ "epoch": 1.671361502347418,
2506
+ "grad_norm": 2.844460478298155,
2507
+ "learning_rate": 6.515543184133e-07,
2508
+ "loss": 0.0591,
2509
+ "step": 356
2510
+ },
2511
+ {
2512
+ "epoch": 1.676056338028169,
2513
+ "grad_norm": 2.6166726631454895,
2514
+ "learning_rate": 6.334721456655363e-07,
2515
+ "loss": 0.0517,
2516
+ "step": 357
2517
+ },
2518
+ {
2519
+ "epoch": 1.6807511737089202,
2520
+ "grad_norm": 2.788931539872924,
2521
+ "learning_rate": 6.156274462322292e-07,
2522
+ "loss": 0.0589,
2523
+ "step": 358
2524
+ },
2525
+ {
2526
+ "epoch": 1.6854460093896715,
2527
+ "grad_norm": 2.873926732805073,
2528
+ "learning_rate": 5.980211905961181e-07,
2529
+ "loss": 0.0618,
2530
+ "step": 359
2531
+ },
2532
+ {
2533
+ "epoch": 1.6901408450704225,
2534
+ "grad_norm": 3.740023513632287,
2535
+ "learning_rate": 5.806543362721945e-07,
2536
+ "loss": 0.0708,
2537
+ "step": 360
2538
+ },
2539
+ {
2540
+ "epoch": 1.6948356807511737,
2541
+ "grad_norm": 2.7500566126341597,
2542
+ "learning_rate": 5.635278277556267e-07,
2543
+ "loss": 0.0571,
2544
+ "step": 361
2545
+ },
2546
+ {
2547
+ "epoch": 1.699530516431925,
2548
+ "grad_norm": 2.6085828247320335,
2549
+ "learning_rate": 5.466425964703914e-07,
2550
+ "loss": 0.0516,
2551
+ "step": 362
2552
+ },
2553
+ {
2554
+ "epoch": 1.704225352112676,
2555
+ "grad_norm": 3.8172023034551454,
2556
+ "learning_rate": 5.29999560718622e-07,
2557
+ "loss": 0.0769,
2558
+ "step": 363
2559
+ },
2560
+ {
2561
+ "epoch": 1.7089201877934272,
2562
+ "grad_norm": 3.063560281770235,
2563
+ "learning_rate": 5.135996256306619e-07,
2564
+ "loss": 0.049,
2565
+ "step": 364
2566
+ },
2567
+ {
2568
+ "epoch": 1.7136150234741785,
2569
+ "grad_norm": 2.8086570365980226,
2570
+ "learning_rate": 4.974436831158441e-07,
2571
+ "loss": 0.0537,
2572
+ "step": 365
2573
+ },
2574
+ {
2575
+ "epoch": 1.7183098591549295,
2576
+ "grad_norm": 2.3760205601645352,
2577
+ "learning_rate": 4.815326118139813e-07,
2578
+ "loss": 0.0451,
2579
+ "step": 366
2580
+ },
2581
+ {
2582
+ "epoch": 1.7230046948356808,
2583
+ "grad_norm": 3.2029887484388375,
2584
+ "learning_rate": 4.658672770475825e-07,
2585
+ "loss": 0.0653,
2586
+ "step": 367
2587
+ },
2588
+ {
2589
+ "epoch": 1.727699530516432,
2590
+ "grad_norm": 2.7949060118197697,
2591
+ "learning_rate": 4.5044853077479134e-07,
2592
+ "loss": 0.0619,
2593
+ "step": 368
2594
+ },
2595
+ {
2596
+ "epoch": 1.732394366197183,
2597
+ "grad_norm": 3.3885949882085633,
2598
+ "learning_rate": 4.3527721154305703e-07,
2599
+ "loss": 0.0536,
2600
+ "step": 369
2601
+ },
2602
+ {
2603
+ "epoch": 1.7370892018779343,
2604
+ "grad_norm": 4.081611903327972,
2605
+ "learning_rate": 4.203541444435211e-07,
2606
+ "loss": 0.0697,
2607
+ "step": 370
2608
+ },
2609
+ {
2610
+ "epoch": 1.7417840375586855,
2611
+ "grad_norm": 2.4729147024249056,
2612
+ "learning_rate": 4.0568014106615205e-07,
2613
+ "loss": 0.0513,
2614
+ "step": 371
2615
+ },
2616
+ {
2617
+ "epoch": 1.7464788732394365,
2618
+ "grad_norm": 2.925317632089207,
2619
+ "learning_rate": 3.9125599945560866e-07,
2620
+ "loss": 0.0663,
2621
+ "step": 372
2622
+ },
2623
+ {
2624
+ "epoch": 1.7511737089201878,
2625
+ "grad_norm": 2.569501928815174,
2626
+ "learning_rate": 3.770825040678294e-07,
2627
+ "loss": 0.0589,
2628
+ "step": 373
2629
+ },
2630
+ {
2631
+ "epoch": 1.755868544600939,
2632
+ "grad_norm": 3.8728187651614587,
2633
+ "learning_rate": 3.631604257273774e-07,
2634
+ "loss": 0.0655,
2635
+ "step": 374
2636
+ },
2637
+ {
2638
+ "epoch": 1.76056338028169,
2639
+ "grad_norm": 2.8933948309587767,
2640
+ "learning_rate": 3.4949052158551875e-07,
2641
+ "loss": 0.0503,
2642
+ "step": 375
2643
+ },
2644
+ {
2645
+ "epoch": 1.7652582159624415,
2646
+ "grad_norm": 2.860650778052901,
2647
+ "learning_rate": 3.360735350790428e-07,
2648
+ "loss": 0.0528,
2649
+ "step": 376
2650
+ },
2651
+ {
2652
+ "epoch": 1.7699530516431925,
2653
+ "grad_norm": 2.859160518799869,
2654
+ "learning_rate": 3.229101958898273e-07,
2655
+ "loss": 0.0565,
2656
+ "step": 377
2657
+ },
2658
+ {
2659
+ "epoch": 1.7746478873239435,
2660
+ "grad_norm": 2.42945289968454,
2661
+ "learning_rate": 3.100012199051627e-07,
2662
+ "loss": 0.0451,
2663
+ "step": 378
2664
+ },
2665
+ {
2666
+ "epoch": 1.779342723004695,
2667
+ "grad_norm": 3.754828586419858,
2668
+ "learning_rate": 2.973473091788121e-07,
2669
+ "loss": 0.0742,
2670
+ "step": 379
2671
+ },
2672
+ {
2673
+ "epoch": 1.784037558685446,
2674
+ "grad_norm": 3.147608019903321,
2675
+ "learning_rate": 2.8494915189283325e-07,
2676
+ "loss": 0.0604,
2677
+ "step": 380
2678
+ },
2679
+ {
2680
+ "epoch": 1.788732394366197,
2681
+ "grad_norm": 3.237069552431269,
2682
+ "learning_rate": 2.728074223201488e-07,
2683
+ "loss": 0.065,
2684
+ "step": 381
2685
+ },
2686
+ {
2687
+ "epoch": 1.7934272300469485,
2688
+ "grad_norm": 2.6000683404369807,
2689
+ "learning_rate": 2.6092278078788004e-07,
2690
+ "loss": 0.0586,
2691
+ "step": 382
2692
+ },
2693
+ {
2694
+ "epoch": 1.7981220657276995,
2695
+ "grad_norm": 3.468636771445419,
2696
+ "learning_rate": 2.4929587364143195e-07,
2697
+ "loss": 0.0562,
2698
+ "step": 383
2699
+ },
2700
+ {
2701
+ "epoch": 1.8028169014084507,
2702
+ "grad_norm": 3.161220355885942,
2703
+ "learning_rate": 2.3792733320934348e-07,
2704
+ "loss": 0.0538,
2705
+ "step": 384
2706
+ },
2707
+ {
2708
+ "epoch": 1.807511737089202,
2709
+ "grad_norm": 2.9327006638853854,
2710
+ "learning_rate": 2.2681777776889736e-07,
2711
+ "loss": 0.0556,
2712
+ "step": 385
2713
+ },
2714
+ {
2715
+ "epoch": 1.812206572769953,
2716
+ "grad_norm": 3.3689952712099287,
2717
+ "learning_rate": 2.1596781151249524e-07,
2718
+ "loss": 0.058,
2719
+ "step": 386
2720
+ },
2721
+ {
2722
+ "epoch": 1.8169014084507042,
2723
+ "grad_norm": 2.7335112128080254,
2724
+ "learning_rate": 2.053780245147996e-07,
2725
+ "loss": 0.0545,
2726
+ "step": 387
2727
+ },
2728
+ {
2729
+ "epoch": 1.8215962441314555,
2730
+ "grad_norm": 2.4667590914238575,
2731
+ "learning_rate": 1.9504899270064105e-07,
2732
+ "loss": 0.0589,
2733
+ "step": 388
2734
+ },
2735
+ {
2736
+ "epoch": 1.8262910798122065,
2737
+ "grad_norm": 3.0307874039496405,
2738
+ "learning_rate": 1.849812778137e-07,
2739
+ "loss": 0.0512,
2740
+ "step": 389
2741
+ },
2742
+ {
2743
+ "epoch": 1.8309859154929577,
2744
+ "grad_norm": 3.032909890271892,
2745
+ "learning_rate": 1.7517542738595071e-07,
2746
+ "loss": 0.0513,
2747
+ "step": 390
2748
+ },
2749
+ {
2750
+ "epoch": 1.835680751173709,
2751
+ "grad_norm": 2.62000849899143,
2752
+ "learning_rate": 1.6563197470788827e-07,
2753
+ "loss": 0.0491,
2754
+ "step": 391
2755
+ },
2756
+ {
2757
+ "epoch": 1.84037558685446,
2758
+ "grad_norm": 2.4318299093894993,
2759
+ "learning_rate": 1.5635143879952575e-07,
2760
+ "loss": 0.057,
2761
+ "step": 392
2762
+ },
2763
+ {
2764
+ "epoch": 1.8450704225352113,
2765
+ "grad_norm": 3.773873807239743,
2766
+ "learning_rate": 1.47334324382164e-07,
2767
+ "loss": 0.0702,
2768
+ "step": 393
2769
+ },
2770
+ {
2771
+ "epoch": 1.8497652582159625,
2772
+ "grad_norm": 3.263553650207675,
2773
+ "learning_rate": 1.3858112185094418e-07,
2774
+ "loss": 0.0613,
2775
+ "step": 394
2776
+ },
2777
+ {
2778
+ "epoch": 1.8544600938967135,
2779
+ "grad_norm": 2.9363138071346375,
2780
+ "learning_rate": 1.3009230724818134e-07,
2781
+ "loss": 0.053,
2782
+ "step": 395
2783
+ },
2784
+ {
2785
+ "epoch": 1.8591549295774648,
2786
+ "grad_norm": 2.673827204626592,
2787
+ "learning_rate": 1.2186834223746612e-07,
2788
+ "loss": 0.0605,
2789
+ "step": 396
2790
+ },
2791
+ {
2792
+ "epoch": 1.863849765258216,
2793
+ "grad_norm": 2.506335617990487,
2794
+ "learning_rate": 1.1390967407856612e-07,
2795
+ "loss": 0.0462,
2796
+ "step": 397
2797
+ },
2798
+ {
2799
+ "epoch": 1.868544600938967,
2800
+ "grad_norm": 3.1980347503602706,
2801
+ "learning_rate": 1.0621673560309798e-07,
2802
+ "loss": 0.0635,
2803
+ "step": 398
2804
+ },
2805
+ {
2806
+ "epoch": 1.8732394366197183,
2807
+ "grad_norm": 3.182050122354943,
2808
+ "learning_rate": 9.878994519098573e-08,
2809
+ "loss": 0.0699,
2810
+ "step": 399
2811
+ },
2812
+ {
2813
+ "epoch": 1.8779342723004695,
2814
+ "grad_norm": 2.7086168446256567,
2815
+ "learning_rate": 9.162970674771177e-08,
2816
+ "loss": 0.0539,
2817
+ "step": 400
2818
+ },
2819
+ {
2820
+ "epoch": 1.8779342723004695,
2821
+ "eval_loss": 0.12246008962392807,
2822
+ "eval_runtime": 0.7074,
2823
+ "eval_samples_per_second": 25.446,
2824
+ "eval_steps_per_second": 7.068,
2825
+ "step": 400
2826
+ },
2827
+ {
2828
+ "epoch": 1.8826291079812205,
2829
+ "grad_norm": 3.1713191051591076,
2830
+ "learning_rate": 8.473640968234609e-08,
2831
+ "loss": 0.0637,
2832
+ "step": 401
2833
+ },
2834
+ {
2835
+ "epoch": 1.887323943661972,
2836
+ "grad_norm": 3.0631100542384613,
2837
+ "learning_rate": 7.81104288863721e-08,
2838
+ "loss": 0.0621,
2839
+ "step": 402
2840
+ },
2841
+ {
2842
+ "epoch": 1.892018779342723,
2843
+ "grad_norm": 2.8917048206418716,
2844
+ "learning_rate": 7.175212471329573e-08,
2845
+ "loss": 0.0556,
2846
+ "step": 403
2847
+ },
2848
+ {
2849
+ "epoch": 1.896713615023474,
2850
+ "grad_norm": 2.761898269195093,
2851
+ "learning_rate": 6.566184295904777e-08,
2852
+ "loss": 0.055,
2853
+ "step": 404
2854
+ },
2855
+ {
2856
+ "epoch": 1.9014084507042255,
2857
+ "grad_norm": 3.434964857446632,
2858
+ "learning_rate": 5.983991484317997e-08,
2859
+ "loss": 0.0557,
2860
+ "step": 405
2861
+ },
2862
+ {
2863
+ "epoch": 1.9061032863849765,
2864
+ "grad_norm": 3.186765875351621,
2865
+ "learning_rate": 5.4286656990847897e-08,
2866
+ "loss": 0.0665,
2867
+ "step": 406
2868
+ },
2869
+ {
2870
+ "epoch": 1.9107981220657277,
2871
+ "grad_norm": 3.066717104478485,
2872
+ "learning_rate": 4.9002371415595716e-08,
2873
+ "loss": 0.0536,
2874
+ "step": 407
2875
+ },
2876
+ {
2877
+ "epoch": 1.915492957746479,
2878
+ "grad_norm": 3.5649654031909477,
2879
+ "learning_rate": 4.398734550292716e-08,
2880
+ "loss": 0.0735,
2881
+ "step": 408
2882
+ },
2883
+ {
2884
+ "epoch": 1.92018779342723,
2885
+ "grad_norm": 2.940337067946803,
2886
+ "learning_rate": 3.9241851994678556e-08,
2887
+ "loss": 0.057,
2888
+ "step": 409
2889
+ },
2890
+ {
2891
+ "epoch": 1.9248826291079812,
2892
+ "grad_norm": 2.7003970471399215,
2893
+ "learning_rate": 3.476614897418573e-08,
2894
+ "loss": 0.0543,
2895
+ "step": 410
2896
+ },
2897
+ {
2898
+ "epoch": 1.9295774647887325,
2899
+ "grad_norm": 2.824853133769705,
2900
+ "learning_rate": 3.0560479852246304e-08,
2901
+ "loss": 0.0499,
2902
+ "step": 411
2903
+ },
2904
+ {
2905
+ "epoch": 1.9342723004694835,
2906
+ "grad_norm": 2.551580294352127,
2907
+ "learning_rate": 2.6625073353884756e-08,
2908
+ "loss": 0.0582,
2909
+ "step": 412
2910
+ },
2911
+ {
2912
+ "epoch": 1.9389671361502347,
2913
+ "grad_norm": 3.1358852738186695,
2914
+ "learning_rate": 2.2960143505909027e-08,
2915
+ "loss": 0.0481,
2916
+ "step": 413
2917
+ },
2918
+ {
2919
+ "epoch": 1.943661971830986,
2920
+ "grad_norm": 3.618275161279335,
2921
+ "learning_rate": 1.9565889625275945e-08,
2922
+ "loss": 0.0632,
2923
+ "step": 414
2924
+ },
2925
+ {
2926
+ "epoch": 1.948356807511737,
2927
+ "grad_norm": 2.947508817832676,
2928
+ "learning_rate": 1.644249630824657e-08,
2929
+ "loss": 0.0583,
2930
+ "step": 415
2931
+ },
2932
+ {
2933
+ "epoch": 1.9530516431924883,
2934
+ "grad_norm": 3.3076990571760456,
2935
+ "learning_rate": 1.3590133420350315e-08,
2936
+ "loss": 0.0774,
2937
+ "step": 416
2938
+ },
2939
+ {
2940
+ "epoch": 1.9577464788732395,
2941
+ "grad_norm": 3.1708502937148753,
2942
+ "learning_rate": 1.1008956087144585e-08,
2943
+ "loss": 0.0681,
2944
+ "step": 417
2945
+ },
2946
+ {
2947
+ "epoch": 1.9624413145539905,
2948
+ "grad_norm": 2.93798757319245,
2949
+ "learning_rate": 8.699104685779835e-09,
2950
+ "loss": 0.0617,
2951
+ "step": 418
2952
+ },
2953
+ {
2954
+ "epoch": 1.9671361502347418,
2955
+ "grad_norm": 3.640329339145807,
2956
+ "learning_rate": 6.660704837364029e-09,
2957
+ "loss": 0.0639,
2958
+ "step": 419
2959
+ },
2960
+ {
2961
+ "epoch": 1.971830985915493,
2962
+ "grad_norm": 2.683257620228897,
2963
+ "learning_rate": 4.89386740013198e-09,
2964
+ "loss": 0.0527,
2965
+ "step": 420
2966
+ },
2967
+ {
2968
+ "epoch": 1.976525821596244,
2969
+ "grad_norm": 3.036848828270319,
2970
+ "learning_rate": 3.3986884634146232e-09,
2971
+ "loss": 0.0587,
2972
+ "step": 421
2973
+ },
2974
+ {
2975
+ "epoch": 1.9812206572769953,
2976
+ "grad_norm": 2.698642495311718,
2977
+ "learning_rate": 2.1752493424148647e-09,
2978
+ "loss": 0.0523,
2979
+ "step": 422
2980
+ },
2981
+ {
2982
+ "epoch": 1.9859154929577465,
2983
+ "grad_norm": 2.6732902544483363,
2984
+ "learning_rate": 1.2236165737850025e-09,
2985
+ "loss": 0.0587,
2986
+ "step": 423
2987
+ },
2988
+ {
2989
+ "epoch": 1.9906103286384975,
2990
+ "grad_norm": 2.9233181677697897,
2991
+ "learning_rate": 5.438419120062933e-10,
2992
+ "loss": 0.0628,
2993
+ "step": 424
2994
+ },
2995
+ {
2996
+ "epoch": 1.995305164319249,
2997
+ "grad_norm": 3.2089865905600052,
2998
+ "learning_rate": 1.3596232657675512e-10,
2999
+ "loss": 0.0638,
3000
+ "step": 425
3001
+ },
3002
+ {
3003
+ "epoch": 2.0,
3004
+ "grad_norm": 2.7939164330811934,
3005
+ "learning_rate": 0.0,
3006
+ "loss": 0.0422,
3007
+ "step": 426
3008
+ },
3009
+ {
3010
+ "epoch": 2.0,
3011
+ "step": 426,
3012
+ "total_flos": 1768470073344.0,
3013
+ "train_loss": 0.13181914092684296,
3014
+ "train_runtime": 275.8873,
3015
+ "train_samples_per_second": 12.317,
3016
+ "train_steps_per_second": 1.544
3017
+ }
3018
+ ],
3019
+ "logging_steps": 1,
3020
+ "max_steps": 426,
3021
+ "num_input_tokens_seen": 0,
3022
+ "num_train_epochs": 2,
3023
+ "save_steps": 5000,
3024
+ "stateful_callbacks": {
3025
+ "TrainerControl": {
3026
+ "args": {
3027
+ "should_epoch_stop": false,
3028
+ "should_evaluate": false,
3029
+ "should_log": false,
3030
+ "should_save": true,
3031
+ "should_training_stop": true
3032
+ },
3033
+ "attributes": {}
3034
+ }
3035
+ },
3036
+ "total_flos": 1768470073344.0,
3037
+ "train_batch_size": 2,
3038
+ "trial_name": null,
3039
+ "trial_params": null
3040
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:997c48652b8e33e3de5b370ea30930c8cc5c6da18622ce23e58892a9948d0d43
3
+ size 7224
training_eval_loss.png ADDED
training_loss.png ADDED
vocab.json ADDED
The diff for this file is too large to render. See raw diff