cutelemonlili commited on
Commit
6884d79
·
verified ·
1 Parent(s): e13b85b

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 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-14B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: MATH_training_response_Qwen2.5_32B
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_response_Qwen2.5_32B
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the MATH_training_response_Qwen2.5_32B dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0584
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: 0.0001
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - total_train_batch_size: 4
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
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 2.0
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:------:|:----:|:---------------:|
57
+ | 0.0558 | 1.5038 | 200 | 0.0589 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - PEFT 0.12.0
63
+ - Transformers 4.46.1
64
+ - Pytorch 2.5.1+cu124
65
+ - Datasets 3.1.0
66
+ - Tokenizers 0.20.3
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "gate_proj",
25
+ "k_proj",
26
+ "down_proj",
27
+ "o_proj",
28
+ "up_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c39ca6ff9dff9f982c90fd7482ebc4fb0c95b652b62588946895e52840791633
3
+ size 68902296
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": 0.05842316150665283,
4
+ "eval_runtime": 2.8784,
5
+ "eval_samples_per_second": 2.084,
6
+ "eval_steps_per_second": 0.695,
7
+ "total_flos": 505244584771584.0,
8
+ "train_loss": 0.0657289699980415,
9
+ "train_runtime": 994.4218,
10
+ "train_samples_per_second": 1.064,
11
+ "train_steps_per_second": 0.267
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.05842316150665283,
4
+ "eval_runtime": 2.8784,
5
+ "eval_samples_per_second": 2.084,
6
+ "eval_steps_per_second": 0.695
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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": 505244584771584.0,
4
+ "train_loss": 0.0657289699980415,
5
+ "train_runtime": 994.4218,
6
+ "train_samples_per_second": 1.064,
7
+ "train_steps_per_second": 0.267
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 266, "loss": 0.2155, "lr": 3.7037037037037037e-06, "epoch": 0.007518796992481203, "percentage": 0.38, "elapsed_time": "0:00:06", "remaining_time": "0:29:44"}
2
+ {"current_steps": 2, "total_steps": 266, "loss": 0.1179, "lr": 7.4074074074074075e-06, "epoch": 0.015037593984962405, "percentage": 0.75, "elapsed_time": "0:00:16", "remaining_time": "0:37:01"}
3
+ {"current_steps": 3, "total_steps": 266, "loss": 0.1368, "lr": 1.1111111111111112e-05, "epoch": 0.022556390977443608, "percentage": 1.13, "elapsed_time": "0:00:20", "remaining_time": "0:29:52"}
4
+ {"current_steps": 4, "total_steps": 266, "loss": 0.1401, "lr": 1.4814814814814815e-05, "epoch": 0.03007518796992481, "percentage": 1.5, "elapsed_time": "0:00:24", "remaining_time": "0:26:15"}
5
+ {"current_steps": 5, "total_steps": 266, "loss": 0.1562, "lr": 1.8518518518518518e-05, "epoch": 0.03759398496240601, "percentage": 1.88, "elapsed_time": "0:00:27", "remaining_time": "0:24:02"}
6
+ {"current_steps": 6, "total_steps": 266, "loss": 0.2811, "lr": 2.2222222222222223e-05, "epoch": 0.045112781954887216, "percentage": 2.26, "elapsed_time": "0:00:31", "remaining_time": "0:22:32"}
7
+ {"current_steps": 7, "total_steps": 266, "loss": 0.1378, "lr": 2.5925925925925925e-05, "epoch": 0.05263157894736842, "percentage": 2.63, "elapsed_time": "0:00:34", "remaining_time": "0:21:28"}
8
+ {"current_steps": 8, "total_steps": 266, "loss": 0.1329, "lr": 2.962962962962963e-05, "epoch": 0.06015037593984962, "percentage": 3.01, "elapsed_time": "0:00:38", "remaining_time": "0:20:40"}
9
+ {"current_steps": 9, "total_steps": 266, "loss": 0.0993, "lr": 3.3333333333333335e-05, "epoch": 0.06766917293233082, "percentage": 3.38, "elapsed_time": "0:00:42", "remaining_time": "0:20:01"}
10
+ {"current_steps": 10, "total_steps": 266, "loss": 0.1078, "lr": 3.7037037037037037e-05, "epoch": 0.07518796992481203, "percentage": 3.76, "elapsed_time": "0:00:45", "remaining_time": "0:19:28"}
11
+ {"current_steps": 11, "total_steps": 266, "loss": 0.2271, "lr": 4.074074074074074e-05, "epoch": 0.08270676691729323, "percentage": 4.14, "elapsed_time": "0:00:49", "remaining_time": "0:19:02"}
12
+ {"current_steps": 12, "total_steps": 266, "loss": 0.1553, "lr": 4.4444444444444447e-05, "epoch": 0.09022556390977443, "percentage": 4.51, "elapsed_time": "0:00:52", "remaining_time": "0:18:39"}
13
+ {"current_steps": 13, "total_steps": 266, "loss": 0.1876, "lr": 4.814814814814815e-05, "epoch": 0.09774436090225563, "percentage": 4.89, "elapsed_time": "0:00:56", "remaining_time": "0:18:19"}
14
+ {"current_steps": 14, "total_steps": 266, "loss": 0.1678, "lr": 5.185185185185185e-05, "epoch": 0.10526315789473684, "percentage": 5.26, "elapsed_time": "0:01:00", "remaining_time": "0:18:01"}
15
+ {"current_steps": 15, "total_steps": 266, "loss": 0.1741, "lr": 5.555555555555556e-05, "epoch": 0.11278195488721804, "percentage": 5.64, "elapsed_time": "0:01:03", "remaining_time": "0:17:46"}
16
+ {"current_steps": 16, "total_steps": 266, "loss": 0.1011, "lr": 5.925925925925926e-05, "epoch": 0.12030075187969924, "percentage": 6.02, "elapsed_time": "0:01:07", "remaining_time": "0:17:32"}
17
+ {"current_steps": 17, "total_steps": 266, "loss": 0.1249, "lr": 6.296296296296296e-05, "epoch": 0.12781954887218044, "percentage": 6.39, "elapsed_time": "0:01:10", "remaining_time": "0:17:19"}
18
+ {"current_steps": 18, "total_steps": 266, "loss": 0.1049, "lr": 6.666666666666667e-05, "epoch": 0.13533834586466165, "percentage": 6.77, "elapsed_time": "0:01:14", "remaining_time": "0:17:07"}
19
+ {"current_steps": 19, "total_steps": 266, "loss": 0.1105, "lr": 7.037037037037038e-05, "epoch": 0.14285714285714285, "percentage": 7.14, "elapsed_time": "0:01:18", "remaining_time": "0:16:56"}
20
+ {"current_steps": 20, "total_steps": 266, "loss": 0.1015, "lr": 7.407407407407407e-05, "epoch": 0.15037593984962405, "percentage": 7.52, "elapsed_time": "0:01:21", "remaining_time": "0:16:46"}
21
+ {"current_steps": 21, "total_steps": 266, "loss": 0.1023, "lr": 7.777777777777778e-05, "epoch": 0.15789473684210525, "percentage": 7.89, "elapsed_time": "0:01:25", "remaining_time": "0:16:36"}
22
+ {"current_steps": 22, "total_steps": 266, "loss": 0.0852, "lr": 8.148148148148148e-05, "epoch": 0.16541353383458646, "percentage": 8.27, "elapsed_time": "0:01:29", "remaining_time": "0:16:27"}
23
+ {"current_steps": 23, "total_steps": 266, "loss": 0.0795, "lr": 8.518518518518518e-05, "epoch": 0.17293233082706766, "percentage": 8.65, "elapsed_time": "0:01:32", "remaining_time": "0:16:19"}
24
+ {"current_steps": 24, "total_steps": 266, "loss": 0.0859, "lr": 8.888888888888889e-05, "epoch": 0.18045112781954886, "percentage": 9.02, "elapsed_time": "0:01:36", "remaining_time": "0:16:11"}
25
+ {"current_steps": 25, "total_steps": 266, "loss": 0.1168, "lr": 9.25925925925926e-05, "epoch": 0.18796992481203006, "percentage": 9.4, "elapsed_time": "0:01:39", "remaining_time": "0:16:03"}
26
+ {"current_steps": 26, "total_steps": 266, "loss": 0.0767, "lr": 9.62962962962963e-05, "epoch": 0.19548872180451127, "percentage": 9.77, "elapsed_time": "0:01:43", "remaining_time": "0:15:55"}
27
+ {"current_steps": 27, "total_steps": 266, "loss": 0.0943, "lr": 0.0001, "epoch": 0.20300751879699247, "percentage": 10.15, "elapsed_time": "0:01:47", "remaining_time": "0:15:48"}
28
+ {"current_steps": 28, "total_steps": 266, "loss": 0.0816, "lr": 9.999568045802217e-05, "epoch": 0.21052631578947367, "percentage": 10.53, "elapsed_time": "0:01:50", "remaining_time": "0:15:42"}
29
+ {"current_steps": 29, "total_steps": 266, "loss": 0.0915, "lr": 9.998272257842641e-05, "epoch": 0.21804511278195488, "percentage": 10.9, "elapsed_time": "0:01:54", "remaining_time": "0:15:35"}
30
+ {"current_steps": 30, "total_steps": 266, "loss": 0.0735, "lr": 9.996112860009688e-05, "epoch": 0.22556390977443608, "percentage": 11.28, "elapsed_time": "0:01:58", "remaining_time": "0:15:28"}
31
+ {"current_steps": 31, "total_steps": 266, "loss": 0.0833, "lr": 9.993090225407743e-05, "epoch": 0.23308270676691728, "percentage": 11.65, "elapsed_time": "0:02:01", "remaining_time": "0:15:22"}
32
+ {"current_steps": 32, "total_steps": 266, "loss": 0.0763, "lr": 9.989204876292688e-05, "epoch": 0.24060150375939848, "percentage": 12.03, "elapsed_time": "0:02:05", "remaining_time": "0:15:16"}
33
+ {"current_steps": 33, "total_steps": 266, "loss": 0.0727, "lr": 9.984457483981669e-05, "epoch": 0.24812030075187969, "percentage": 12.41, "elapsed_time": "0:02:08", "remaining_time": "0:15:10"}
34
+ {"current_steps": 34, "total_steps": 266, "loss": 0.0619, "lr": 9.978848868737098e-05, "epoch": 0.2556390977443609, "percentage": 12.78, "elapsed_time": "0:02:12", "remaining_time": "0:15:04"}
35
+ {"current_steps": 35, "total_steps": 266, "loss": 0.0667, "lr": 9.972379999624936e-05, "epoch": 0.2631578947368421, "percentage": 13.16, "elapsed_time": "0:02:16", "remaining_time": "0:14:58"}
36
+ {"current_steps": 36, "total_steps": 266, "loss": 0.0549, "lr": 9.96505199434725e-05, "epoch": 0.2706766917293233, "percentage": 13.53, "elapsed_time": "0:02:19", "remaining_time": "0:14:53"}
37
+ {"current_steps": 37, "total_steps": 266, "loss": 0.0717, "lr": 9.956866119049095e-05, "epoch": 0.2781954887218045, "percentage": 13.91, "elapsed_time": "0:02:23", "remaining_time": "0:14:47"}
38
+ {"current_steps": 38, "total_steps": 266, "loss": 0.0688, "lr": 9.947823788099753e-05, "epoch": 0.2857142857142857, "percentage": 14.29, "elapsed_time": "0:02:27", "remaining_time": "0:14:42"}
39
+ {"current_steps": 39, "total_steps": 266, "loss": 0.0589, "lr": 9.937926563848346e-05, "epoch": 0.2932330827067669, "percentage": 14.66, "elapsed_time": "0:02:30", "remaining_time": "0:14:36"}
40
+ {"current_steps": 40, "total_steps": 266, "loss": 0.0608, "lr": 9.927176156353899e-05, "epoch": 0.3007518796992481, "percentage": 15.04, "elapsed_time": "0:02:34", "remaining_time": "0:14:31"}
41
+ {"current_steps": 41, "total_steps": 266, "loss": 0.0772, "lr": 9.91557442308987e-05, "epoch": 0.3082706766917293, "percentage": 15.41, "elapsed_time": "0:02:37", "remaining_time": "0:14:26"}
42
+ {"current_steps": 42, "total_steps": 266, "loss": 0.0584, "lr": 9.903123368623216e-05, "epoch": 0.3157894736842105, "percentage": 15.79, "elapsed_time": "0:02:41", "remaining_time": "0:14:21"}
43
+ {"current_steps": 43, "total_steps": 266, "loss": 0.0626, "lr": 9.889825144268029e-05, "epoch": 0.3233082706766917, "percentage": 16.17, "elapsed_time": "0:02:45", "remaining_time": "0:14:16"}
44
+ {"current_steps": 44, "total_steps": 266, "loss": 0.0809, "lr": 9.875682047713846e-05, "epoch": 0.3308270676691729, "percentage": 16.54, "elapsed_time": "0:02:48", "remaining_time": "0:14:11"}
45
+ {"current_steps": 45, "total_steps": 266, "loss": 0.0509, "lr": 9.860696522628639e-05, "epoch": 0.3383458646616541, "percentage": 16.92, "elapsed_time": "0:02:52", "remaining_time": "0:14:06"}
46
+ {"current_steps": 46, "total_steps": 266, "loss": 0.068, "lr": 9.844871158236591e-05, "epoch": 0.3458646616541353, "percentage": 17.29, "elapsed_time": "0:02:56", "remaining_time": "0:14:01"}
47
+ {"current_steps": 47, "total_steps": 266, "loss": 0.0639, "lr": 9.828208688870735e-05, "epoch": 0.3533834586466165, "percentage": 17.67, "elapsed_time": "0:02:59", "remaining_time": "0:13:57"}
48
+ {"current_steps": 48, "total_steps": 266, "loss": 0.069, "lr": 9.810711993500507e-05, "epoch": 0.3609022556390977, "percentage": 18.05, "elapsed_time": "0:03:03", "remaining_time": "0:13:52"}
49
+ {"current_steps": 49, "total_steps": 266, "loss": 0.0622, "lr": 9.792384095234313e-05, "epoch": 0.3684210526315789, "percentage": 18.42, "elapsed_time": "0:03:06", "remaining_time": "0:13:47"}
50
+ {"current_steps": 50, "total_steps": 266, "loss": 0.049, "lr": 9.773228160797188e-05, "epoch": 0.37593984962406013, "percentage": 18.8, "elapsed_time": "0:03:10", "remaining_time": "0:13:43"}
51
+ {"current_steps": 51, "total_steps": 266, "loss": 0.0606, "lr": 9.753247499983649e-05, "epoch": 0.38345864661654133, "percentage": 19.17, "elapsed_time": "0:03:14", "remaining_time": "0:13:38"}
52
+ {"current_steps": 52, "total_steps": 266, "loss": 0.0724, "lr": 9.732445565085824e-05, "epoch": 0.39097744360902253, "percentage": 19.55, "elapsed_time": "0:03:18", "remaining_time": "0:13:36"}
53
+ {"current_steps": 53, "total_steps": 266, "loss": 0.0743, "lr": 9.71082595029695e-05, "epoch": 0.39849624060150374, "percentage": 19.92, "elapsed_time": "0:03:21", "remaining_time": "0:13:31"}
54
+ {"current_steps": 54, "total_steps": 266, "loss": 0.068, "lr": 9.688392391090373e-05, "epoch": 0.40601503759398494, "percentage": 20.3, "elapsed_time": "0:03:25", "remaining_time": "0:13:26"}
55
+ {"current_steps": 55, "total_steps": 266, "loss": 0.0697, "lr": 9.665148763574123e-05, "epoch": 0.41353383458646614, "percentage": 20.68, "elapsed_time": "0:03:29", "remaining_time": "0:13:23"}
56
+ {"current_steps": 56, "total_steps": 266, "loss": 0.0596, "lr": 9.64109908382119e-05, "epoch": 0.42105263157894735, "percentage": 21.05, "elapsed_time": "0:03:32", "remaining_time": "0:13:18"}
57
+ {"current_steps": 57, "total_steps": 266, "loss": 0.0559, "lr": 9.616247507175623e-05, "epoch": 0.42857142857142855, "percentage": 21.43, "elapsed_time": "0:03:36", "remaining_time": "0:13:14"}
58
+ {"current_steps": 58, "total_steps": 266, "loss": 0.0608, "lr": 9.590598327534564e-05, "epoch": 0.43609022556390975, "percentage": 21.8, "elapsed_time": "0:03:40", "remaining_time": "0:13:10"}
59
+ {"current_steps": 59, "total_steps": 266, "loss": 0.0728, "lr": 9.564155976606339e-05, "epoch": 0.44360902255639095, "percentage": 22.18, "elapsed_time": "0:03:44", "remaining_time": "0:13:06"}
60
+ {"current_steps": 60, "total_steps": 266, "loss": 0.0769, "lr": 9.536925023144742e-05, "epoch": 0.45112781954887216, "percentage": 22.56, "elapsed_time": "0:03:47", "remaining_time": "0:13:01"}
61
+ {"current_steps": 61, "total_steps": 266, "loss": 0.0807, "lr": 9.508910172159635e-05, "epoch": 0.45864661654135336, "percentage": 22.93, "elapsed_time": "0:03:51", "remaining_time": "0:12:57"}
62
+ {"current_steps": 62, "total_steps": 266, "loss": 0.0688, "lr": 9.480116264104011e-05, "epoch": 0.46616541353383456, "percentage": 23.31, "elapsed_time": "0:03:54", "remaining_time": "0:12:52"}
63
+ {"current_steps": 63, "total_steps": 266, "loss": 0.0718, "lr": 9.450548274037653e-05, "epoch": 0.47368421052631576, "percentage": 23.68, "elapsed_time": "0:03:58", "remaining_time": "0:12:48"}
64
+ {"current_steps": 64, "total_steps": 266, "loss": 0.0597, "lr": 9.420211310767533e-05, "epoch": 0.48120300751879697, "percentage": 24.06, "elapsed_time": "0:04:02", "remaining_time": "0:12:44"}
65
+ {"current_steps": 65, "total_steps": 266, "loss": 0.0543, "lr": 9.389110615965102e-05, "epoch": 0.48872180451127817, "percentage": 24.44, "elapsed_time": "0:04:05", "remaining_time": "0:12:39"}
66
+ {"current_steps": 66, "total_steps": 266, "loss": 0.0664, "lr": 9.35725156326063e-05, "epoch": 0.49624060150375937, "percentage": 24.81, "elapsed_time": "0:04:09", "remaining_time": "0:12:35"}
67
+ {"current_steps": 67, "total_steps": 266, "loss": 0.0664, "lr": 9.324639657314742e-05, "epoch": 0.5037593984962406, "percentage": 25.19, "elapsed_time": "0:04:12", "remaining_time": "0:12:31"}
68
+ {"current_steps": 68, "total_steps": 266, "loss": 0.0724, "lr": 9.291280532867302e-05, "epoch": 0.5112781954887218, "percentage": 25.56, "elapsed_time": "0:04:16", "remaining_time": "0:12:27"}
69
+ {"current_steps": 69, "total_steps": 266, "loss": 0.0604, "lr": 9.257179953763845e-05, "epoch": 0.518796992481203, "percentage": 25.94, "elapsed_time": "0:04:20", "remaining_time": "0:12:22"}
70
+ {"current_steps": 70, "total_steps": 266, "loss": 0.0646, "lr": 9.222343811959693e-05, "epoch": 0.5263157894736842, "percentage": 26.32, "elapsed_time": "0:04:23", "remaining_time": "0:12:18"}
71
+ {"current_steps": 71, "total_steps": 266, "loss": 0.067, "lr": 9.186778126501916e-05, "epoch": 0.5338345864661654, "percentage": 26.69, "elapsed_time": "0:04:27", "remaining_time": "0:12:14"}
72
+ {"current_steps": 72, "total_steps": 266, "loss": 0.0612, "lr": 9.150489042489367e-05, "epoch": 0.5413533834586466, "percentage": 27.07, "elapsed_time": "0:04:31", "remaining_time": "0:12:10"}
73
+ {"current_steps": 73, "total_steps": 266, "loss": 0.0696, "lr": 9.113482830010918e-05, "epoch": 0.5488721804511278, "percentage": 27.44, "elapsed_time": "0:04:34", "remaining_time": "0:12:06"}
74
+ {"current_steps": 74, "total_steps": 266, "loss": 0.0591, "lr": 9.075765883062093e-05, "epoch": 0.556390977443609, "percentage": 27.82, "elapsed_time": "0:04:38", "remaining_time": "0:12:01"}
75
+ {"current_steps": 75, "total_steps": 266, "loss": 0.0669, "lr": 9.037344718440322e-05, "epoch": 0.5639097744360902, "percentage": 28.2, "elapsed_time": "0:04:41", "remaining_time": "0:11:57"}
76
+ {"current_steps": 76, "total_steps": 266, "loss": 0.073, "lr": 8.99822597461894e-05, "epoch": 0.5714285714285714, "percentage": 28.57, "elapsed_time": "0:04:45", "remaining_time": "0:11:53"}
77
+ {"current_steps": 77, "total_steps": 266, "loss": 0.0593, "lr": 8.958416410600187e-05, "epoch": 0.5789473684210527, "percentage": 28.95, "elapsed_time": "0:04:49", "remaining_time": "0:11:49"}
78
+ {"current_steps": 78, "total_steps": 266, "loss": 0.0747, "lr": 8.917922904747384e-05, "epoch": 0.5864661654135338, "percentage": 29.32, "elapsed_time": "0:04:52", "remaining_time": "0:11:45"}
79
+ {"current_steps": 79, "total_steps": 266, "loss": 0.0575, "lr": 8.876752453596462e-05, "epoch": 0.5939849624060151, "percentage": 29.7, "elapsed_time": "0:04:56", "remaining_time": "0:11:41"}
80
+ {"current_steps": 80, "total_steps": 266, "loss": 0.0738, "lr": 8.834912170647101e-05, "epoch": 0.6015037593984962, "percentage": 30.08, "elapsed_time": "0:04:59", "remaining_time": "0:11:37"}
81
+ {"current_steps": 81, "total_steps": 266, "loss": 0.0772, "lr": 8.792409285133642e-05, "epoch": 0.6090225563909775, "percentage": 30.45, "elapsed_time": "0:05:03", "remaining_time": "0:11:33"}
82
+ {"current_steps": 82, "total_steps": 266, "loss": 0.0632, "lr": 8.749251140776016e-05, "epoch": 0.6165413533834586, "percentage": 30.83, "elapsed_time": "0:05:07", "remaining_time": "0:11:29"}
83
+ {"current_steps": 83, "total_steps": 266, "loss": 0.0571, "lr": 8.705445194510868e-05, "epoch": 0.6240601503759399, "percentage": 31.2, "elapsed_time": "0:05:10", "remaining_time": "0:11:25"}
84
+ {"current_steps": 84, "total_steps": 266, "loss": 0.068, "lr": 8.66099901520315e-05, "epoch": 0.631578947368421, "percentage": 31.58, "elapsed_time": "0:05:14", "remaining_time": "0:11:21"}
85
+ {"current_steps": 85, "total_steps": 266, "loss": 0.0655, "lr": 8.615920282338355e-05, "epoch": 0.6390977443609023, "percentage": 31.95, "elapsed_time": "0:05:17", "remaining_time": "0:11:17"}
86
+ {"current_steps": 86, "total_steps": 266, "loss": 0.0542, "lr": 8.570216784695637e-05, "epoch": 0.6466165413533834, "percentage": 32.33, "elapsed_time": "0:05:21", "remaining_time": "0:11:13"}
87
+ {"current_steps": 87, "total_steps": 266, "loss": 0.069, "lr": 8.52389641900206e-05, "epoch": 0.6541353383458647, "percentage": 32.71, "elapsed_time": "0:05:25", "remaining_time": "0:11:09"}
88
+ {"current_steps": 88, "total_steps": 266, "loss": 0.05, "lr": 8.476967188568188e-05, "epoch": 0.6616541353383458, "percentage": 33.08, "elapsed_time": "0:05:28", "remaining_time": "0:11:05"}
89
+ {"current_steps": 89, "total_steps": 266, "loss": 0.0492, "lr": 8.429437201905254e-05, "epoch": 0.6691729323308271, "percentage": 33.46, "elapsed_time": "0:05:32", "remaining_time": "0:11:01"}
90
+ {"current_steps": 90, "total_steps": 266, "loss": 0.0645, "lr": 8.381314671324159e-05, "epoch": 0.6766917293233082, "percentage": 33.83, "elapsed_time": "0:05:36", "remaining_time": "0:10:57"}
91
+ {"current_steps": 91, "total_steps": 266, "loss": 0.0727, "lr": 8.332607911516545e-05, "epoch": 0.6842105263157895, "percentage": 34.21, "elapsed_time": "0:05:39", "remaining_time": "0:10:53"}
92
+ {"current_steps": 92, "total_steps": 266, "loss": 0.0563, "lr": 8.283325338118153e-05, "epoch": 0.6917293233082706, "percentage": 34.59, "elapsed_time": "0:05:43", "remaining_time": "0:10:49"}
93
+ {"current_steps": 93, "total_steps": 266, "loss": 0.0641, "lr": 8.233475466254765e-05, "epoch": 0.6992481203007519, "percentage": 34.96, "elapsed_time": "0:05:46", "remaining_time": "0:10:45"}
94
+ {"current_steps": 94, "total_steps": 266, "loss": 0.0729, "lr": 8.183066909070947e-05, "epoch": 0.706766917293233, "percentage": 35.34, "elapsed_time": "0:05:50", "remaining_time": "0:10:41"}
95
+ {"current_steps": 95, "total_steps": 266, "loss": 0.0609, "lr": 8.132108376241849e-05, "epoch": 0.7142857142857143, "percentage": 35.71, "elapsed_time": "0:05:54", "remaining_time": "0:10:37"}
96
+ {"current_steps": 96, "total_steps": 266, "loss": 0.0754, "lr": 8.08060867246834e-05, "epoch": 0.7218045112781954, "percentage": 36.09, "elapsed_time": "0:05:57", "remaining_time": "0:10:33"}
97
+ {"current_steps": 97, "total_steps": 266, "loss": 0.0567, "lr": 8.028576695955711e-05, "epoch": 0.7293233082706767, "percentage": 36.47, "elapsed_time": "0:06:01", "remaining_time": "0:10:29"}
98
+ {"current_steps": 98, "total_steps": 266, "loss": 0.0581, "lr": 7.97602143687623e-05, "epoch": 0.7368421052631579, "percentage": 36.84, "elapsed_time": "0:06:04", "remaining_time": "0:10:25"}
99
+ {"current_steps": 99, "total_steps": 266, "loss": 0.0547, "lr": 7.922951975815811e-05, "epoch": 0.7443609022556391, "percentage": 37.22, "elapsed_time": "0:06:08", "remaining_time": "0:10:21"}
100
+ {"current_steps": 100, "total_steps": 266, "loss": 0.0585, "lr": 7.869377482205042e-05, "epoch": 0.7518796992481203, "percentage": 37.59, "elapsed_time": "0:06:12", "remaining_time": "0:10:17"}
101
+ {"current_steps": 101, "total_steps": 266, "loss": 0.0525, "lr": 7.815307212734888e-05, "epoch": 0.7593984962406015, "percentage": 37.97, "elapsed_time": "0:06:15", "remaining_time": "0:10:14"}
102
+ {"current_steps": 102, "total_steps": 266, "loss": 0.0664, "lr": 7.760750509757298e-05, "epoch": 0.7669172932330827, "percentage": 38.35, "elapsed_time": "0:06:19", "remaining_time": "0:10:10"}
103
+ {"current_steps": 103, "total_steps": 266, "loss": 0.0464, "lr": 7.705716799671019e-05, "epoch": 0.7744360902255639, "percentage": 38.72, "elapsed_time": "0:06:23", "remaining_time": "0:10:06"}
104
+ {"current_steps": 104, "total_steps": 266, "loss": 0.0617, "lr": 7.650215591292888e-05, "epoch": 0.7819548872180451, "percentage": 39.1, "elapsed_time": "0:06:26", "remaining_time": "0:10:02"}
105
+ {"current_steps": 105, "total_steps": 266, "loss": 0.0544, "lr": 7.594256474214882e-05, "epoch": 0.7894736842105263, "percentage": 39.47, "elapsed_time": "0:06:30", "remaining_time": "0:09:58"}
106
+ {"current_steps": 106, "total_steps": 266, "loss": 0.0743, "lr": 7.537849117147212e-05, "epoch": 0.7969924812030075, "percentage": 39.85, "elapsed_time": "0:06:33", "remaining_time": "0:09:54"}
107
+ {"current_steps": 107, "total_steps": 266, "loss": 0.07, "lr": 7.481003266247744e-05, "epoch": 0.8045112781954887, "percentage": 40.23, "elapsed_time": "0:06:37", "remaining_time": "0:09:50"}
108
+ {"current_steps": 108, "total_steps": 266, "loss": 0.0664, "lr": 7.423728743438048e-05, "epoch": 0.8120300751879699, "percentage": 40.6, "elapsed_time": "0:06:41", "remaining_time": "0:09:46"}
109
+ {"current_steps": 109, "total_steps": 266, "loss": 0.0648, "lr": 7.366035444706347e-05, "epoch": 0.8195488721804511, "percentage": 40.98, "elapsed_time": "0:06:44", "remaining_time": "0:09:43"}
110
+ {"current_steps": 110, "total_steps": 266, "loss": 0.0679, "lr": 7.307933338397667e-05, "epoch": 0.8270676691729323, "percentage": 41.35, "elapsed_time": "0:06:48", "remaining_time": "0:09:39"}
111
+ {"current_steps": 111, "total_steps": 266, "loss": 0.0601, "lr": 7.249432463491498e-05, "epoch": 0.8345864661654135, "percentage": 41.73, "elapsed_time": "0:06:51", "remaining_time": "0:09:35"}
112
+ {"current_steps": 112, "total_steps": 266, "loss": 0.0498, "lr": 7.190542927867234e-05, "epoch": 0.8421052631578947, "percentage": 42.11, "elapsed_time": "0:06:55", "remaining_time": "0:09:31"}
113
+ {"current_steps": 113, "total_steps": 266, "loss": 0.0546, "lr": 7.131274906557725e-05, "epoch": 0.849624060150376, "percentage": 42.48, "elapsed_time": "0:06:59", "remaining_time": "0:09:27"}
114
+ {"current_steps": 114, "total_steps": 266, "loss": 0.054, "lr": 7.071638639991207e-05, "epoch": 0.8571428571428571, "percentage": 42.86, "elapsed_time": "0:07:02", "remaining_time": "0:09:23"}
115
+ {"current_steps": 115, "total_steps": 266, "loss": 0.0599, "lr": 7.011644432221958e-05, "epoch": 0.8646616541353384, "percentage": 43.23, "elapsed_time": "0:07:06", "remaining_time": "0:09:19"}
116
+ {"current_steps": 116, "total_steps": 266, "loss": 0.0776, "lr": 6.95130264914993e-05, "epoch": 0.8721804511278195, "percentage": 43.61, "elapsed_time": "0:07:10", "remaining_time": "0:09:16"}
117
+ {"current_steps": 117, "total_steps": 266, "loss": 0.0519, "lr": 6.890623716729724e-05, "epoch": 0.8796992481203008, "percentage": 43.98, "elapsed_time": "0:07:13", "remaining_time": "0:09:12"}
118
+ {"current_steps": 118, "total_steps": 266, "loss": 0.0565, "lr": 6.82961811916917e-05, "epoch": 0.8872180451127819, "percentage": 44.36, "elapsed_time": "0:07:17", "remaining_time": "0:09:08"}
119
+ {"current_steps": 119, "total_steps": 266, "loss": 0.0485, "lr": 6.768296397117848e-05, "epoch": 0.8947368421052632, "percentage": 44.74, "elapsed_time": "0:07:20", "remaining_time": "0:09:04"}
120
+ {"current_steps": 120, "total_steps": 266, "loss": 0.0639, "lr": 6.706669145845863e-05, "epoch": 0.9022556390977443, "percentage": 45.11, "elapsed_time": "0:07:24", "remaining_time": "0:09:00"}
121
+ {"current_steps": 121, "total_steps": 266, "loss": 0.0583, "lr": 6.644747013413168e-05, "epoch": 0.9097744360902256, "percentage": 45.49, "elapsed_time": "0:07:28", "remaining_time": "0:08:57"}
122
+ {"current_steps": 122, "total_steps": 266, "loss": 0.0643, "lr": 6.582540698829781e-05, "epoch": 0.9172932330827067, "percentage": 45.86, "elapsed_time": "0:07:31", "remaining_time": "0:08:53"}
123
+ {"current_steps": 123, "total_steps": 266, "loss": 0.0729, "lr": 6.520060950207185e-05, "epoch": 0.924812030075188, "percentage": 46.24, "elapsed_time": "0:07:35", "remaining_time": "0:08:49"}
124
+ {"current_steps": 124, "total_steps": 266, "loss": 0.0561, "lr": 6.457318562901256e-05, "epoch": 0.9323308270676691, "percentage": 46.62, "elapsed_time": "0:07:39", "remaining_time": "0:08:45"}
125
+ {"current_steps": 125, "total_steps": 266, "loss": 0.0657, "lr": 6.394324377647028e-05, "epoch": 0.9398496240601504, "percentage": 46.99, "elapsed_time": "0:07:42", "remaining_time": "0:08:41"}
126
+ {"current_steps": 126, "total_steps": 266, "loss": 0.0591, "lr": 6.331089278685599e-05, "epoch": 0.9473684210526315, "percentage": 47.37, "elapsed_time": "0:07:46", "remaining_time": "0:08:37"}
127
+ {"current_steps": 127, "total_steps": 266, "loss": 0.0483, "lr": 6.26762419188355e-05, "epoch": 0.9548872180451128, "percentage": 47.74, "elapsed_time": "0:07:49", "remaining_time": "0:08:34"}
128
+ {"current_steps": 128, "total_steps": 266, "loss": 0.0811, "lr": 6.203940082845144e-05, "epoch": 0.9624060150375939, "percentage": 48.12, "elapsed_time": "0:07:53", "remaining_time": "0:08:30"}
129
+ {"current_steps": 129, "total_steps": 266, "loss": 0.0708, "lr": 6.140047955017671e-05, "epoch": 0.9699248120300752, "percentage": 48.5, "elapsed_time": "0:07:57", "remaining_time": "0:08:26"}
130
+ {"current_steps": 130, "total_steps": 266, "loss": 0.0687, "lr": 6.075958847790262e-05, "epoch": 0.9774436090225563, "percentage": 48.87, "elapsed_time": "0:08:00", "remaining_time": "0:08:22"}
131
+ {"current_steps": 131, "total_steps": 266, "loss": 0.0507, "lr": 6.011683834586473e-05, "epoch": 0.9849624060150376, "percentage": 49.25, "elapsed_time": "0:08:04", "remaining_time": "0:08:19"}
132
+ {"current_steps": 132, "total_steps": 266, "loss": 0.0463, "lr": 5.947234020951015e-05, "epoch": 0.9924812030075187, "percentage": 49.62, "elapsed_time": "0:08:07", "remaining_time": "0:08:15"}
133
+ {"current_steps": 133, "total_steps": 266, "loss": 0.0591, "lr": 5.882620542630901e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:08:11", "remaining_time": "0:08:11"}
134
+ {"current_steps": 134, "total_steps": 266, "loss": 0.053, "lr": 5.8178545636514145e-05, "epoch": 1.0075187969924813, "percentage": 50.38, "elapsed_time": "0:08:15", "remaining_time": "0:08:07"}
135
+ {"current_steps": 135, "total_steps": 266, "loss": 0.0505, "lr": 5.752947274387147e-05, "epoch": 1.0150375939849625, "percentage": 50.75, "elapsed_time": "0:08:18", "remaining_time": "0:08:03"}
136
+ {"current_steps": 136, "total_steps": 266, "loss": 0.0675, "lr": 5.687909889628529e-05, "epoch": 1.0225563909774436, "percentage": 51.13, "elapsed_time": "0:08:22", "remaining_time": "0:08:00"}
137
+ {"current_steps": 137, "total_steps": 266, "loss": 0.054, "lr": 5.622753646644102e-05, "epoch": 1.0300751879699248, "percentage": 51.5, "elapsed_time": "0:08:25", "remaining_time": "0:07:56"}
138
+ {"current_steps": 138, "total_steps": 266, "loss": 0.0548, "lr": 5.557489803238933e-05, "epoch": 1.037593984962406, "percentage": 51.88, "elapsed_time": "0:08:29", "remaining_time": "0:07:52"}
139
+ {"current_steps": 139, "total_steps": 266, "loss": 0.0475, "lr": 5.492129635809473e-05, "epoch": 1.045112781954887, "percentage": 52.26, "elapsed_time": "0:08:33", "remaining_time": "0:07:48"}
140
+ {"current_steps": 140, "total_steps": 266, "loss": 0.0457, "lr": 5.426684437395196e-05, "epoch": 1.0526315789473684, "percentage": 52.63, "elapsed_time": "0:08:36", "remaining_time": "0:07:45"}
141
+ {"current_steps": 141, "total_steps": 266, "loss": 0.0488, "lr": 5.361165515727374e-05, "epoch": 1.0601503759398496, "percentage": 53.01, "elapsed_time": "0:08:40", "remaining_time": "0:07:41"}
142
+ {"current_steps": 142, "total_steps": 266, "loss": 0.0557, "lr": 5.295584191275308e-05, "epoch": 1.0676691729323309, "percentage": 53.38, "elapsed_time": "0:08:44", "remaining_time": "0:07:37"}
143
+ {"current_steps": 143, "total_steps": 266, "loss": 0.0602, "lr": 5.229951795290353e-05, "epoch": 1.0751879699248121, "percentage": 53.76, "elapsed_time": "0:08:47", "remaining_time": "0:07:33"}
144
+ {"current_steps": 144, "total_steps": 266, "loss": 0.0458, "lr": 5.164279667848094e-05, "epoch": 1.0827067669172932, "percentage": 54.14, "elapsed_time": "0:08:51", "remaining_time": "0:07:30"}
145
+ {"current_steps": 145, "total_steps": 266, "loss": 0.0489, "lr": 5.0985791558889785e-05, "epoch": 1.0902255639097744, "percentage": 54.51, "elapsed_time": "0:08:54", "remaining_time": "0:07:26"}
146
+ {"current_steps": 146, "total_steps": 266, "loss": 0.0582, "lr": 5.032861611257783e-05, "epoch": 1.0977443609022557, "percentage": 54.89, "elapsed_time": "0:08:58", "remaining_time": "0:07:22"}
147
+ {"current_steps": 147, "total_steps": 266, "loss": 0.0468, "lr": 4.967138388742218e-05, "epoch": 1.1052631578947367, "percentage": 55.26, "elapsed_time": "0:09:02", "remaining_time": "0:07:18"}
148
+ {"current_steps": 148, "total_steps": 266, "loss": 0.065, "lr": 4.901420844111021e-05, "epoch": 1.112781954887218, "percentage": 55.64, "elapsed_time": "0:09:05", "remaining_time": "0:07:15"}
149
+ {"current_steps": 149, "total_steps": 266, "loss": 0.0663, "lr": 4.835720332151907e-05, "epoch": 1.1203007518796992, "percentage": 56.02, "elapsed_time": "0:09:09", "remaining_time": "0:07:11"}
150
+ {"current_steps": 150, "total_steps": 266, "loss": 0.0557, "lr": 4.770048204709648e-05, "epoch": 1.1278195488721805, "percentage": 56.39, "elapsed_time": "0:09:12", "remaining_time": "0:07:07"}
151
+ {"current_steps": 151, "total_steps": 266, "loss": 0.0659, "lr": 4.7044158087246926e-05, "epoch": 1.1353383458646618, "percentage": 56.77, "elapsed_time": "0:09:16", "remaining_time": "0:07:03"}
152
+ {"current_steps": 152, "total_steps": 266, "loss": 0.0477, "lr": 4.6388344842726264e-05, "epoch": 1.1428571428571428, "percentage": 57.14, "elapsed_time": "0:09:20", "remaining_time": "0:07:00"}
153
+ {"current_steps": 153, "total_steps": 266, "loss": 0.0569, "lr": 4.5733155626048036e-05, "epoch": 1.150375939849624, "percentage": 57.52, "elapsed_time": "0:09:23", "remaining_time": "0:06:56"}
154
+ {"current_steps": 154, "total_steps": 266, "loss": 0.0578, "lr": 4.507870364190527e-05, "epoch": 1.1578947368421053, "percentage": 57.89, "elapsed_time": "0:09:27", "remaining_time": "0:06:52"}
155
+ {"current_steps": 155, "total_steps": 266, "loss": 0.0537, "lr": 4.4425101967610674e-05, "epoch": 1.1654135338345863, "percentage": 58.27, "elapsed_time": "0:09:31", "remaining_time": "0:06:48"}
156
+ {"current_steps": 156, "total_steps": 266, "loss": 0.0582, "lr": 4.377246353355899e-05, "epoch": 1.1729323308270676, "percentage": 58.65, "elapsed_time": "0:09:34", "remaining_time": "0:06:45"}
157
+ {"current_steps": 157, "total_steps": 266, "loss": 0.056, "lr": 4.312090110371473e-05, "epoch": 1.1804511278195489, "percentage": 59.02, "elapsed_time": "0:09:38", "remaining_time": "0:06:41"}
158
+ {"current_steps": 158, "total_steps": 266, "loss": 0.0682, "lr": 4.247052725612852e-05, "epoch": 1.1879699248120301, "percentage": 59.4, "elapsed_time": "0:09:41", "remaining_time": "0:06:37"}
159
+ {"current_steps": 159, "total_steps": 266, "loss": 0.0507, "lr": 4.1821454363485866e-05, "epoch": 1.1954887218045114, "percentage": 59.77, "elapsed_time": "0:09:45", "remaining_time": "0:06:34"}
160
+ {"current_steps": 160, "total_steps": 266, "loss": 0.0499, "lr": 4.1173794573690996e-05, "epoch": 1.2030075187969924, "percentage": 60.15, "elapsed_time": "0:09:49", "remaining_time": "0:06:30"}
161
+ {"current_steps": 161, "total_steps": 266, "loss": 0.06, "lr": 4.052765979048986e-05, "epoch": 1.2105263157894737, "percentage": 60.53, "elapsed_time": "0:09:52", "remaining_time": "0:06:26"}
162
+ {"current_steps": 162, "total_steps": 266, "loss": 0.0465, "lr": 3.988316165413528e-05, "epoch": 1.218045112781955, "percentage": 60.9, "elapsed_time": "0:09:56", "remaining_time": "0:06:22"}
163
+ {"current_steps": 163, "total_steps": 266, "loss": 0.0546, "lr": 3.924041152209739e-05, "epoch": 1.225563909774436, "percentage": 61.28, "elapsed_time": "0:09:59", "remaining_time": "0:06:19"}
164
+ {"current_steps": 164, "total_steps": 266, "loss": 0.0583, "lr": 3.859952044982329e-05, "epoch": 1.2330827067669172, "percentage": 61.65, "elapsed_time": "0:10:03", "remaining_time": "0:06:15"}
165
+ {"current_steps": 165, "total_steps": 266, "loss": 0.0485, "lr": 3.7960599171548574e-05, "epoch": 1.2406015037593985, "percentage": 62.03, "elapsed_time": "0:10:07", "remaining_time": "0:06:11"}
166
+ {"current_steps": 166, "total_steps": 266, "loss": 0.0549, "lr": 3.732375808116451e-05, "epoch": 1.2481203007518797, "percentage": 62.41, "elapsed_time": "0:10:10", "remaining_time": "0:06:07"}
167
+ {"current_steps": 167, "total_steps": 266, "loss": 0.0465, "lr": 3.668910721314402e-05, "epoch": 1.255639097744361, "percentage": 62.78, "elapsed_time": "0:10:14", "remaining_time": "0:06:04"}
168
+ {"current_steps": 168, "total_steps": 266, "loss": 0.0542, "lr": 3.605675622352973e-05, "epoch": 1.263157894736842, "percentage": 63.16, "elapsed_time": "0:10:18", "remaining_time": "0:06:00"}
169
+ {"current_steps": 169, "total_steps": 266, "loss": 0.0583, "lr": 3.542681437098745e-05, "epoch": 1.2706766917293233, "percentage": 63.53, "elapsed_time": "0:10:21", "remaining_time": "0:05:56"}
170
+ {"current_steps": 170, "total_steps": 266, "loss": 0.0457, "lr": 3.479939049792817e-05, "epoch": 1.2781954887218046, "percentage": 63.91, "elapsed_time": "0:10:25", "remaining_time": "0:05:53"}
171
+ {"current_steps": 171, "total_steps": 266, "loss": 0.0557, "lr": 3.417459301170219e-05, "epoch": 1.2857142857142856, "percentage": 64.29, "elapsed_time": "0:10:28", "remaining_time": "0:05:49"}
172
+ {"current_steps": 172, "total_steps": 266, "loss": 0.0448, "lr": 3.355252986586832e-05, "epoch": 1.2932330827067668, "percentage": 64.66, "elapsed_time": "0:10:32", "remaining_time": "0:05:45"}
173
+ {"current_steps": 173, "total_steps": 266, "loss": 0.057, "lr": 3.293330854154136e-05, "epoch": 1.300751879699248, "percentage": 65.04, "elapsed_time": "0:10:36", "remaining_time": "0:05:41"}
174
+ {"current_steps": 174, "total_steps": 266, "loss": 0.0359, "lr": 3.2317036028821523e-05, "epoch": 1.3082706766917294, "percentage": 65.41, "elapsed_time": "0:10:39", "remaining_time": "0:05:38"}
175
+ {"current_steps": 175, "total_steps": 266, "loss": 0.0465, "lr": 3.1703818808308324e-05, "epoch": 1.3157894736842106, "percentage": 65.79, "elapsed_time": "0:10:43", "remaining_time": "0:05:34"}
176
+ {"current_steps": 176, "total_steps": 266, "loss": 0.0516, "lr": 3.109376283270277e-05, "epoch": 1.3233082706766917, "percentage": 66.17, "elapsed_time": "0:10:46", "remaining_time": "0:05:30"}
177
+ {"current_steps": 177, "total_steps": 266, "loss": 0.0565, "lr": 3.0486973508500727e-05, "epoch": 1.330827067669173, "percentage": 66.54, "elapsed_time": "0:10:50", "remaining_time": "0:05:27"}
178
+ {"current_steps": 178, "total_steps": 266, "loss": 0.0586, "lr": 2.988355567778043e-05, "epoch": 1.3383458646616542, "percentage": 66.92, "elapsed_time": "0:10:54", "remaining_time": "0:05:23"}
179
+ {"current_steps": 179, "total_steps": 266, "loss": 0.0565, "lr": 2.9283613600087933e-05, "epoch": 1.3458646616541352, "percentage": 67.29, "elapsed_time": "0:10:57", "remaining_time": "0:05:19"}
180
+ {"current_steps": 180, "total_steps": 266, "loss": 0.0424, "lr": 2.8687250934422772e-05, "epoch": 1.3533834586466165, "percentage": 67.67, "elapsed_time": "0:11:01", "remaining_time": "0:05:16"}
181
+ {"current_steps": 181, "total_steps": 266, "loss": 0.0415, "lr": 2.8094570721327662e-05, "epoch": 1.3609022556390977, "percentage": 68.05, "elapsed_time": "0:11:05", "remaining_time": "0:05:12"}
182
+ {"current_steps": 182, "total_steps": 266, "loss": 0.0505, "lr": 2.750567536508504e-05, "epoch": 1.368421052631579, "percentage": 68.42, "elapsed_time": "0:11:08", "remaining_time": "0:05:08"}
183
+ {"current_steps": 183, "total_steps": 266, "loss": 0.06, "lr": 2.6920666616023327e-05, "epoch": 1.3759398496240602, "percentage": 68.8, "elapsed_time": "0:11:12", "remaining_time": "0:05:04"}
184
+ {"current_steps": 184, "total_steps": 266, "loss": 0.0602, "lr": 2.6339645552936536e-05, "epoch": 1.3834586466165413, "percentage": 69.17, "elapsed_time": "0:11:15", "remaining_time": "0:05:01"}
185
+ {"current_steps": 185, "total_steps": 266, "loss": 0.0497, "lr": 2.5762712565619528e-05, "epoch": 1.3909774436090225, "percentage": 69.55, "elapsed_time": "0:11:19", "remaining_time": "0:04:57"}
186
+ {"current_steps": 186, "total_steps": 266, "loss": 0.0452, "lr": 2.5189967337522573e-05, "epoch": 1.3984962406015038, "percentage": 69.92, "elapsed_time": "0:11:23", "remaining_time": "0:04:53"}
187
+ {"current_steps": 187, "total_steps": 266, "loss": 0.0518, "lr": 2.46215088285279e-05, "epoch": 1.4060150375939848, "percentage": 70.3, "elapsed_time": "0:11:26", "remaining_time": "0:04:50"}
188
+ {"current_steps": 188, "total_steps": 266, "loss": 0.044, "lr": 2.4057435257851175e-05, "epoch": 1.413533834586466, "percentage": 70.68, "elapsed_time": "0:11:30", "remaining_time": "0:04:46"}
189
+ {"current_steps": 189, "total_steps": 266, "loss": 0.0566, "lr": 2.349784408707112e-05, "epoch": 1.4210526315789473, "percentage": 71.05, "elapsed_time": "0:11:33", "remaining_time": "0:04:42"}
190
+ {"current_steps": 190, "total_steps": 266, "loss": 0.0543, "lr": 2.2942832003289823e-05, "epoch": 1.4285714285714286, "percentage": 71.43, "elapsed_time": "0:11:37", "remaining_time": "0:04:39"}
191
+ {"current_steps": 191, "total_steps": 266, "loss": 0.0571, "lr": 2.2392494902427025e-05, "epoch": 1.4360902255639099, "percentage": 71.8, "elapsed_time": "0:11:41", "remaining_time": "0:04:35"}
192
+ {"current_steps": 192, "total_steps": 266, "loss": 0.0482, "lr": 2.1846927872651137e-05, "epoch": 1.443609022556391, "percentage": 72.18, "elapsed_time": "0:11:44", "remaining_time": "0:04:31"}
193
+ {"current_steps": 193, "total_steps": 266, "loss": 0.0568, "lr": 2.1306225177949585e-05, "epoch": 1.4511278195488722, "percentage": 72.56, "elapsed_time": "0:11:48", "remaining_time": "0:04:27"}
194
+ {"current_steps": 194, "total_steps": 266, "loss": 0.0603, "lr": 2.07704802418419e-05, "epoch": 1.4586466165413534, "percentage": 72.93, "elapsed_time": "0:11:52", "remaining_time": "0:04:24"}
195
+ {"current_steps": 195, "total_steps": 266, "loss": 0.0584, "lr": 2.0239785631237705e-05, "epoch": 1.4661654135338344, "percentage": 73.31, "elapsed_time": "0:11:55", "remaining_time": "0:04:20"}
196
+ {"current_steps": 196, "total_steps": 266, "loss": 0.0458, "lr": 1.9714233040442915e-05, "epoch": 1.4736842105263157, "percentage": 73.68, "elapsed_time": "0:11:59", "remaining_time": "0:04:17"}
197
+ {"current_steps": 197, "total_steps": 266, "loss": 0.0484, "lr": 1.9193913275316626e-05, "epoch": 1.481203007518797, "percentage": 74.06, "elapsed_time": "0:12:03", "remaining_time": "0:04:13"}
198
+ {"current_steps": 198, "total_steps": 266, "loss": 0.0467, "lr": 1.8678916237581522e-05, "epoch": 1.4887218045112782, "percentage": 74.44, "elapsed_time": "0:12:07", "remaining_time": "0:04:09"}
199
+ {"current_steps": 199, "total_steps": 266, "loss": 0.0408, "lr": 1.816933090929055e-05, "epoch": 1.4962406015037595, "percentage": 74.81, "elapsed_time": "0:12:10", "remaining_time": "0:04:06"}
200
+ {"current_steps": 200, "total_steps": 266, "loss": 0.0558, "lr": 1.7665245337452368e-05, "epoch": 1.5037593984962405, "percentage": 75.19, "elapsed_time": "0:12:14", "remaining_time": "0:04:02"}
201
+ {"current_steps": 200, "total_steps": 266, "eval_loss": 0.05888579785823822, "epoch": 1.5037593984962405, "percentage": 75.19, "elapsed_time": "0:12:17", "remaining_time": "0:04:03"}
202
+ {"current_steps": 201, "total_steps": 266, "loss": 0.0515, "lr": 1.716674661881848e-05, "epoch": 1.5112781954887218, "percentage": 75.56, "elapsed_time": "0:12:20", "remaining_time": "0:03:59"}
203
+ {"current_steps": 202, "total_steps": 266, "loss": 0.0487, "lr": 1.667392088483456e-05, "epoch": 1.518796992481203, "percentage": 75.94, "elapsed_time": "0:12:24", "remaining_time": "0:03:55"}
204
+ {"current_steps": 203, "total_steps": 266, "loss": 0.0562, "lr": 1.6186853286758397e-05, "epoch": 1.526315789473684, "percentage": 76.32, "elapsed_time": "0:12:28", "remaining_time": "0:03:52"}
205
+ {"current_steps": 204, "total_steps": 266, "loss": 0.0537, "lr": 1.570562798094747e-05, "epoch": 1.5338345864661656, "percentage": 76.69, "elapsed_time": "0:12:32", "remaining_time": "0:03:48"}
206
+ {"current_steps": 205, "total_steps": 266, "loss": 0.069, "lr": 1.5230328114318127e-05, "epoch": 1.5413533834586466, "percentage": 77.07, "elapsed_time": "0:12:35", "remaining_time": "0:03:44"}
207
+ {"current_steps": 206, "total_steps": 266, "loss": 0.05, "lr": 1.4761035809979395e-05, "epoch": 1.5488721804511278, "percentage": 77.44, "elapsed_time": "0:12:39", "remaining_time": "0:03:41"}
208
+ {"current_steps": 207, "total_steps": 266, "loss": 0.0495, "lr": 1.4297832153043656e-05, "epoch": 1.556390977443609, "percentage": 77.82, "elapsed_time": "0:12:42", "remaining_time": "0:03:37"}
209
+ {"current_steps": 208, "total_steps": 266, "loss": 0.0608, "lr": 1.3840797176616466e-05, "epoch": 1.5639097744360901, "percentage": 78.2, "elapsed_time": "0:12:46", "remaining_time": "0:03:33"}
210
+ {"current_steps": 209, "total_steps": 266, "loss": 0.0509, "lr": 1.3390009847968504e-05, "epoch": 1.5714285714285714, "percentage": 78.57, "elapsed_time": "0:12:50", "remaining_time": "0:03:30"}
211
+ {"current_steps": 210, "total_steps": 266, "loss": 0.0578, "lr": 1.2945548054891321e-05, "epoch": 1.5789473684210527, "percentage": 78.95, "elapsed_time": "0:12:53", "remaining_time": "0:03:26"}
212
+ {"current_steps": 211, "total_steps": 266, "loss": 0.0519, "lr": 1.2507488592239847e-05, "epoch": 1.5864661654135337, "percentage": 79.32, "elapsed_time": "0:12:57", "remaining_time": "0:03:22"}
213
+ {"current_steps": 212, "total_steps": 266, "loss": 0.0559, "lr": 1.2075907148663579e-05, "epoch": 1.5939849624060152, "percentage": 79.7, "elapsed_time": "0:13:01", "remaining_time": "0:03:18"}
214
+ {"current_steps": 213, "total_steps": 266, "loss": 0.0548, "lr": 1.1650878293528994e-05, "epoch": 1.6015037593984962, "percentage": 80.08, "elapsed_time": "0:13:04", "remaining_time": "0:03:15"}
215
+ {"current_steps": 214, "total_steps": 266, "loss": 0.0456, "lr": 1.1232475464035385e-05, "epoch": 1.6090225563909775, "percentage": 80.45, "elapsed_time": "0:13:08", "remaining_time": "0:03:11"}
216
+ {"current_steps": 215, "total_steps": 266, "loss": 0.0512, "lr": 1.0820770952526155e-05, "epoch": 1.6165413533834587, "percentage": 80.83, "elapsed_time": "0:13:11", "remaining_time": "0:03:07"}
217
+ {"current_steps": 216, "total_steps": 266, "loss": 0.058, "lr": 1.0415835893998116e-05, "epoch": 1.6240601503759398, "percentage": 81.2, "elapsed_time": "0:13:15", "remaining_time": "0:03:04"}
218
+ {"current_steps": 217, "total_steps": 266, "loss": 0.0543, "lr": 1.0017740253810609e-05, "epoch": 1.631578947368421, "percentage": 81.58, "elapsed_time": "0:13:19", "remaining_time": "0:03:00"}
219
+ {"current_steps": 218, "total_steps": 266, "loss": 0.0527, "lr": 9.62655281559679e-06, "epoch": 1.6390977443609023, "percentage": 81.95, "elapsed_time": "0:13:22", "remaining_time": "0:02:56"}
220
+ {"current_steps": 219, "total_steps": 266, "loss": 0.0522, "lr": 9.242341169379076e-06, "epoch": 1.6466165413533833, "percentage": 82.33, "elapsed_time": "0:13:26", "remaining_time": "0:02:53"}
221
+ {"current_steps": 220, "total_steps": 266, "loss": 0.0577, "lr": 8.865171699890834e-06, "epoch": 1.6541353383458648, "percentage": 82.71, "elapsed_time": "0:13:29", "remaining_time": "0:02:49"}
222
+ {"current_steps": 221, "total_steps": 266, "loss": 0.0626, "lr": 8.49510957510633e-06, "epoch": 1.6616541353383458, "percentage": 83.08, "elapsed_time": "0:13:33", "remaining_time": "0:02:45"}
223
+ {"current_steps": 222, "total_steps": 266, "loss": 0.0429, "lr": 8.132218734980852e-06, "epoch": 1.669172932330827, "percentage": 83.46, "elapsed_time": "0:13:37", "remaining_time": "0:02:41"}
224
+ {"current_steps": 223, "total_steps": 266, "loss": 0.0461, "lr": 7.776561880403072e-06, "epoch": 1.6766917293233083, "percentage": 83.83, "elapsed_time": "0:13:40", "remaining_time": "0:02:38"}
225
+ {"current_steps": 224, "total_steps": 266, "loss": 0.0524, "lr": 7.4282004623615396e-06, "epoch": 1.6842105263157894, "percentage": 84.21, "elapsed_time": "0:13:44", "remaining_time": "0:02:34"}
226
+ {"current_steps": 225, "total_steps": 266, "loss": 0.0435, "lr": 7.0871946713269856e-06, "epoch": 1.6917293233082706, "percentage": 84.59, "elapsed_time": "0:13:48", "remaining_time": "0:02:30"}
227
+ {"current_steps": 226, "total_steps": 266, "loss": 0.0457, "lr": 6.753603426852589e-06, "epoch": 1.699248120300752, "percentage": 84.96, "elapsed_time": "0:13:51", "remaining_time": "0:02:27"}
228
+ {"current_steps": 227, "total_steps": 266, "loss": 0.0539, "lr": 6.427484367393699e-06, "epoch": 1.706766917293233, "percentage": 85.34, "elapsed_time": "0:13:55", "remaining_time": "0:02:23"}
229
+ {"current_steps": 228, "total_steps": 266, "loss": 0.055, "lr": 6.108893840348995e-06, "epoch": 1.7142857142857144, "percentage": 85.71, "elapsed_time": "0:13:58", "remaining_time": "0:02:19"}
230
+ {"current_steps": 229, "total_steps": 266, "loss": 0.0542, "lr": 5.797886892324694e-06, "epoch": 1.7218045112781954, "percentage": 86.09, "elapsed_time": "0:14:02", "remaining_time": "0:02:16"}
231
+ {"current_steps": 230, "total_steps": 266, "loss": 0.0502, "lr": 5.494517259623477e-06, "epoch": 1.7293233082706767, "percentage": 86.47, "elapsed_time": "0:14:06", "remaining_time": "0:02:12"}
232
+ {"current_steps": 231, "total_steps": 266, "loss": 0.0548, "lr": 5.198837358959901e-06, "epoch": 1.736842105263158, "percentage": 86.84, "elapsed_time": "0:14:09", "remaining_time": "0:02:08"}
233
+ {"current_steps": 232, "total_steps": 266, "loss": 0.0616, "lr": 4.910898278403669e-06, "epoch": 1.744360902255639, "percentage": 87.22, "elapsed_time": "0:14:13", "remaining_time": "0:02:05"}
234
+ {"current_steps": 233, "total_steps": 266, "loss": 0.0572, "lr": 4.630749768552589e-06, "epoch": 1.7518796992481203, "percentage": 87.59, "elapsed_time": "0:14:16", "remaining_time": "0:02:01"}
235
+ {"current_steps": 234, "total_steps": 266, "loss": 0.0463, "lr": 4.358440233936617e-06, "epoch": 1.7593984962406015, "percentage": 87.97, "elapsed_time": "0:14:20", "remaining_time": "0:01:57"}
236
+ {"current_steps": 235, "total_steps": 266, "loss": 0.0563, "lr": 4.094016724654359e-06, "epoch": 1.7669172932330826, "percentage": 88.35, "elapsed_time": "0:14:24", "remaining_time": "0:01:54"}
237
+ {"current_steps": 236, "total_steps": 266, "loss": 0.0514, "lr": 3.837524928243774e-06, "epoch": 1.774436090225564, "percentage": 88.72, "elapsed_time": "0:14:27", "remaining_time": "0:01:50"}
238
+ {"current_steps": 237, "total_steps": 266, "loss": 0.0614, "lr": 3.589009161788104e-06, "epoch": 1.781954887218045, "percentage": 89.1, "elapsed_time": "0:14:31", "remaining_time": "0:01:46"}
239
+ {"current_steps": 238, "total_steps": 266, "loss": 0.0581, "lr": 3.3485123642587658e-06, "epoch": 1.7894736842105263, "percentage": 89.47, "elapsed_time": "0:14:35", "remaining_time": "0:01:42"}
240
+ {"current_steps": 239, "total_steps": 266, "loss": 0.0612, "lr": 3.116076089096265e-06, "epoch": 1.7969924812030076, "percentage": 89.85, "elapsed_time": "0:14:38", "remaining_time": "0:01:39"}
241
+ {"current_steps": 240, "total_steps": 266, "loss": 0.0664, "lr": 2.8917404970305097e-06, "epoch": 1.8045112781954886, "percentage": 90.23, "elapsed_time": "0:14:42", "remaining_time": "0:01:35"}
242
+ {"current_steps": 241, "total_steps": 266, "loss": 0.0542, "lr": 2.675544349141779e-06, "epoch": 1.8120300751879699, "percentage": 90.6, "elapsed_time": "0:14:45", "remaining_time": "0:01:31"}
243
+ {"current_steps": 242, "total_steps": 266, "loss": 0.0571, "lr": 2.4675250001635232e-06, "epoch": 1.8195488721804511, "percentage": 90.98, "elapsed_time": "0:14:49", "remaining_time": "0:01:28"}
244
+ {"current_steps": 243, "total_steps": 266, "loss": 0.0437, "lr": 2.2677183920281343e-06, "epoch": 1.8270676691729322, "percentage": 91.35, "elapsed_time": "0:14:53", "remaining_time": "0:01:24"}
245
+ {"current_steps": 244, "total_steps": 266, "loss": 0.0497, "lr": 2.076159047656889e-06, "epoch": 1.8345864661654137, "percentage": 91.73, "elapsed_time": "0:14:56", "remaining_time": "0:01:20"}
246
+ {"current_steps": 245, "total_steps": 266, "loss": 0.0581, "lr": 1.892880064994934e-06, "epoch": 1.8421052631578947, "percentage": 92.11, "elapsed_time": "0:15:00", "remaining_time": "0:01:17"}
247
+ {"current_steps": 246, "total_steps": 266, "loss": 0.0488, "lr": 1.7179131112926627e-06, "epoch": 1.849624060150376, "percentage": 92.48, "elapsed_time": "0:15:03", "remaining_time": "0:01:13"}
248
+ {"current_steps": 247, "total_steps": 266, "loss": 0.0366, "lr": 1.551288417634106e-06, "epoch": 1.8571428571428572, "percentage": 92.86, "elapsed_time": "0:15:07", "remaining_time": "0:01:09"}
249
+ {"current_steps": 248, "total_steps": 266, "loss": 0.0456, "lr": 1.3930347737136196e-06, "epoch": 1.8646616541353382, "percentage": 93.23, "elapsed_time": "0:15:11", "remaining_time": "0:01:06"}
250
+ {"current_steps": 249, "total_steps": 266, "loss": 0.0512, "lr": 1.2431795228615372e-06, "epoch": 1.8721804511278195, "percentage": 93.61, "elapsed_time": "0:15:14", "remaining_time": "0:01:02"}
251
+ {"current_steps": 250, "total_steps": 266, "loss": 0.0665, "lr": 1.101748557319715e-06, "epoch": 1.8796992481203008, "percentage": 93.98, "elapsed_time": "0:15:18", "remaining_time": "0:00:58"}
252
+ {"current_steps": 251, "total_steps": 266, "loss": 0.0469, "lr": 9.687663137678604e-07, "epoch": 1.8872180451127818, "percentage": 94.36, "elapsed_time": "0:15:22", "remaining_time": "0:00:55"}
253
+ {"current_steps": 252, "total_steps": 266, "loss": 0.0537, "lr": 8.442557691013043e-07, "epoch": 1.8947368421052633, "percentage": 94.74, "elapsed_time": "0:15:25", "remaining_time": "0:00:51"}
254
+ {"current_steps": 253, "total_steps": 266, "loss": 0.0565, "lr": 7.282384364610206e-07, "epoch": 1.9022556390977443, "percentage": 95.11, "elapsed_time": "0:15:29", "remaining_time": "0:00:47"}
255
+ {"current_steps": 254, "total_steps": 266, "loss": 0.0448, "lr": 6.207343615165561e-07, "epoch": 1.9097744360902256, "percentage": 95.49, "elapsed_time": "0:15:32", "remaining_time": "0:00:44"}
256
+ {"current_steps": 255, "total_steps": 266, "loss": 0.0589, "lr": 5.217621190024779e-07, "epoch": 1.9172932330827068, "percentage": 95.86, "elapsed_time": "0:15:36", "remaining_time": "0:00:40"}
257
+ {"current_steps": 256, "total_steps": 266, "loss": 0.0481, "lr": 4.3133880950905205e-07, "epoch": 1.9248120300751879, "percentage": 96.24, "elapsed_time": "0:15:40", "remaining_time": "0:00:36"}
258
+ {"current_steps": 257, "total_steps": 266, "loss": 0.0529, "lr": 3.494800565275125e-07, "epoch": 1.9323308270676691, "percentage": 96.62, "elapsed_time": "0:15:43", "remaining_time": "0:00:33"}
259
+ {"current_steps": 258, "total_steps": 266, "loss": 0.0509, "lr": 2.762000037506485e-07, "epoch": 1.9398496240601504, "percentage": 96.99, "elapsed_time": "0:15:47", "remaining_time": "0:00:29"}
260
+ {"current_steps": 259, "total_steps": 266, "loss": 0.0487, "lr": 2.115113126290258e-07, "epoch": 1.9473684210526314, "percentage": 97.37, "elapsed_time": "0:15:50", "remaining_time": "0:00:25"}
261
+ {"current_steps": 260, "total_steps": 266, "loss": 0.0514, "lr": 1.554251601833201e-07, "epoch": 1.954887218045113, "percentage": 97.74, "elapsed_time": "0:15:54", "remaining_time": "0:00:22"}
262
+ {"current_steps": 261, "total_steps": 266, "loss": 0.0492, "lr": 1.0795123707312283e-07, "epoch": 1.962406015037594, "percentage": 98.12, "elapsed_time": "0:15:58", "remaining_time": "0:00:18"}
263
+ {"current_steps": 262, "total_steps": 266, "loss": 0.0495, "lr": 6.909774592258056e-08, "epoch": 1.9699248120300752, "percentage": 98.5, "elapsed_time": "0:16:01", "remaining_time": "0:00:14"}
264
+ {"current_steps": 263, "total_steps": 266, "loss": 0.0537, "lr": 3.8871399903134265e-08, "epoch": 1.9774436090225564, "percentage": 98.87, "elapsed_time": "0:16:05", "remaining_time": "0:00:11"}
265
+ {"current_steps": 264, "total_steps": 266, "loss": 0.0583, "lr": 1.7277421573608232e-08, "epoch": 1.9849624060150375, "percentage": 99.25, "elapsed_time": "0:16:09", "remaining_time": "0:00:07"}
266
+ {"current_steps": 265, "total_steps": 266, "loss": 0.0431, "lr": 4.319541977831909e-09, "epoch": 1.9924812030075187, "percentage": 99.62, "elapsed_time": "0:16:12", "remaining_time": "0:00:03"}
267
+ {"current_steps": 266, "total_steps": 266, "loss": 0.0523, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:16:16", "remaining_time": "0:00:00"}
268
+ {"current_steps": 266, "total_steps": 266, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:16:34", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,1912 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 200,
6
+ "global_step": 266,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.007518796992481203,
13
+ "grad_norm": 0.11732577645825801,
14
+ "learning_rate": 3.7037037037037037e-06,
15
+ "loss": 0.2155,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.015037593984962405,
20
+ "grad_norm": 0.05305452355379764,
21
+ "learning_rate": 7.4074074074074075e-06,
22
+ "loss": 0.1179,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.022556390977443608,
27
+ "grad_norm": 0.07056205250715394,
28
+ "learning_rate": 1.1111111111111112e-05,
29
+ "loss": 0.1368,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03007518796992481,
34
+ "grad_norm": 0.0700691302254581,
35
+ "learning_rate": 1.4814814814814815e-05,
36
+ "loss": 0.1401,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.03759398496240601,
41
+ "grad_norm": 0.08565830143081989,
42
+ "learning_rate": 1.8518518518518518e-05,
43
+ "loss": 0.1562,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.045112781954887216,
48
+ "grad_norm": 0.30651952600873233,
49
+ "learning_rate": 2.2222222222222223e-05,
50
+ "loss": 0.2811,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.05263157894736842,
55
+ "grad_norm": 0.07240084960667219,
56
+ "learning_rate": 2.5925925925925925e-05,
57
+ "loss": 0.1378,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.06015037593984962,
62
+ "grad_norm": 0.07568164648001585,
63
+ "learning_rate": 2.962962962962963e-05,
64
+ "loss": 0.1329,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.06766917293233082,
69
+ "grad_norm": 0.05994893391950599,
70
+ "learning_rate": 3.3333333333333335e-05,
71
+ "loss": 0.0993,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.07518796992481203,
76
+ "grad_norm": 0.05644813323984804,
77
+ "learning_rate": 3.7037037037037037e-05,
78
+ "loss": 0.1078,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.08270676691729323,
83
+ "grad_norm": 0.18351086574979253,
84
+ "learning_rate": 4.074074074074074e-05,
85
+ "loss": 0.2271,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.09022556390977443,
90
+ "grad_norm": 0.12343563992543348,
91
+ "learning_rate": 4.4444444444444447e-05,
92
+ "loss": 0.1553,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.09774436090225563,
97
+ "grad_norm": 0.19403392901884683,
98
+ "learning_rate": 4.814814814814815e-05,
99
+ "loss": 0.1876,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.10526315789473684,
104
+ "grad_norm": 0.1698635404915775,
105
+ "learning_rate": 5.185185185185185e-05,
106
+ "loss": 0.1678,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.11278195488721804,
111
+ "grad_norm": 0.18636555926386134,
112
+ "learning_rate": 5.555555555555556e-05,
113
+ "loss": 0.1741,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.12030075187969924,
118
+ "grad_norm": 0.08056187660671005,
119
+ "learning_rate": 5.925925925925926e-05,
120
+ "loss": 0.1011,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.12781954887218044,
125
+ "grad_norm": 0.10287340868237937,
126
+ "learning_rate": 6.296296296296296e-05,
127
+ "loss": 0.1249,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.13533834586466165,
132
+ "grad_norm": 0.08292601423227217,
133
+ "learning_rate": 6.666666666666667e-05,
134
+ "loss": 0.1049,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.14285714285714285,
139
+ "grad_norm": 0.12062052347791452,
140
+ "learning_rate": 7.037037037037038e-05,
141
+ "loss": 0.1105,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.15037593984962405,
146
+ "grad_norm": 0.11203988601268791,
147
+ "learning_rate": 7.407407407407407e-05,
148
+ "loss": 0.1015,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.15789473684210525,
153
+ "grad_norm": 0.10736435956481093,
154
+ "learning_rate": 7.777777777777778e-05,
155
+ "loss": 0.1023,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.16541353383458646,
160
+ "grad_norm": 0.11602245680744329,
161
+ "learning_rate": 8.148148148148148e-05,
162
+ "loss": 0.0852,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.17293233082706766,
167
+ "grad_norm": 0.10825490419856049,
168
+ "learning_rate": 8.518518518518518e-05,
169
+ "loss": 0.0795,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.18045112781954886,
174
+ "grad_norm": 0.10319023121857403,
175
+ "learning_rate": 8.888888888888889e-05,
176
+ "loss": 0.0859,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.18796992481203006,
181
+ "grad_norm": 0.15337743955651192,
182
+ "learning_rate": 9.25925925925926e-05,
183
+ "loss": 0.1168,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.19548872180451127,
188
+ "grad_norm": 0.10056410123379396,
189
+ "learning_rate": 9.62962962962963e-05,
190
+ "loss": 0.0767,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.20300751879699247,
195
+ "grad_norm": 0.07740925049230485,
196
+ "learning_rate": 0.0001,
197
+ "loss": 0.0943,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.21052631578947367,
202
+ "grad_norm": 0.07583550448236821,
203
+ "learning_rate": 9.999568045802217e-05,
204
+ "loss": 0.0816,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.21804511278195488,
209
+ "grad_norm": 0.0878707363058605,
210
+ "learning_rate": 9.998272257842641e-05,
211
+ "loss": 0.0915,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.22556390977443608,
216
+ "grad_norm": 0.06644634793224094,
217
+ "learning_rate": 9.996112860009688e-05,
218
+ "loss": 0.0735,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.23308270676691728,
223
+ "grad_norm": 0.06726254004833397,
224
+ "learning_rate": 9.993090225407743e-05,
225
+ "loss": 0.0833,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.24060150375939848,
230
+ "grad_norm": 0.07745911457398465,
231
+ "learning_rate": 9.989204876292688e-05,
232
+ "loss": 0.0763,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.24812030075187969,
237
+ "grad_norm": 0.07933782861569086,
238
+ "learning_rate": 9.984457483981669e-05,
239
+ "loss": 0.0727,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.2556390977443609,
244
+ "grad_norm": 0.05352514919025439,
245
+ "learning_rate": 9.978848868737098e-05,
246
+ "loss": 0.0619,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.2631578947368421,
251
+ "grad_norm": 0.057275981805351865,
252
+ "learning_rate": 9.972379999624936e-05,
253
+ "loss": 0.0667,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.2706766917293233,
258
+ "grad_norm": 0.047899291547381255,
259
+ "learning_rate": 9.96505199434725e-05,
260
+ "loss": 0.0549,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.2781954887218045,
265
+ "grad_norm": 0.07041433718375159,
266
+ "learning_rate": 9.956866119049095e-05,
267
+ "loss": 0.0717,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.2857142857142857,
272
+ "grad_norm": 0.06067132800315734,
273
+ "learning_rate": 9.947823788099753e-05,
274
+ "loss": 0.0688,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.2932330827067669,
279
+ "grad_norm": 0.07050604575217402,
280
+ "learning_rate": 9.937926563848346e-05,
281
+ "loss": 0.0589,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.3007518796992481,
286
+ "grad_norm": 0.06909437372282598,
287
+ "learning_rate": 9.927176156353899e-05,
288
+ "loss": 0.0608,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.3082706766917293,
293
+ "grad_norm": 0.06460236823173392,
294
+ "learning_rate": 9.91557442308987e-05,
295
+ "loss": 0.0772,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.3157894736842105,
300
+ "grad_norm": 0.06578421481078767,
301
+ "learning_rate": 9.903123368623216e-05,
302
+ "loss": 0.0584,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.3233082706766917,
307
+ "grad_norm": 0.056411479719996896,
308
+ "learning_rate": 9.889825144268029e-05,
309
+ "loss": 0.0626,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.3308270676691729,
314
+ "grad_norm": 0.08604040079464503,
315
+ "learning_rate": 9.875682047713846e-05,
316
+ "loss": 0.0809,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.3383458646616541,
321
+ "grad_norm": 0.04025901149889958,
322
+ "learning_rate": 9.860696522628639e-05,
323
+ "loss": 0.0509,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.3458646616541353,
328
+ "grad_norm": 0.06109559327644354,
329
+ "learning_rate": 9.844871158236591e-05,
330
+ "loss": 0.068,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.3533834586466165,
335
+ "grad_norm": 0.05027383429552543,
336
+ "learning_rate": 9.828208688870735e-05,
337
+ "loss": 0.0639,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.3609022556390977,
342
+ "grad_norm": 0.06541436928843007,
343
+ "learning_rate": 9.810711993500507e-05,
344
+ "loss": 0.069,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.3684210526315789,
349
+ "grad_norm": 0.04816635749010927,
350
+ "learning_rate": 9.792384095234313e-05,
351
+ "loss": 0.0622,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.37593984962406013,
356
+ "grad_norm": 0.04291709569711796,
357
+ "learning_rate": 9.773228160797188e-05,
358
+ "loss": 0.049,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.38345864661654133,
363
+ "grad_norm": 0.050992018473701675,
364
+ "learning_rate": 9.753247499983649e-05,
365
+ "loss": 0.0606,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.39097744360902253,
370
+ "grad_norm": 0.06311298942479784,
371
+ "learning_rate": 9.732445565085824e-05,
372
+ "loss": 0.0724,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.39849624060150374,
377
+ "grad_norm": 0.05417998623796329,
378
+ "learning_rate": 9.71082595029695e-05,
379
+ "loss": 0.0743,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.40601503759398494,
384
+ "grad_norm": 0.10500108704036493,
385
+ "learning_rate": 9.688392391090373e-05,
386
+ "loss": 0.068,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.41353383458646614,
391
+ "grad_norm": 0.0886767782153305,
392
+ "learning_rate": 9.665148763574123e-05,
393
+ "loss": 0.0697,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.42105263157894735,
398
+ "grad_norm": 0.0439165386707066,
399
+ "learning_rate": 9.64109908382119e-05,
400
+ "loss": 0.0596,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.42857142857142855,
405
+ "grad_norm": 0.054934555532877516,
406
+ "learning_rate": 9.616247507175623e-05,
407
+ "loss": 0.0559,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.43609022556390975,
412
+ "grad_norm": 0.05011430875402478,
413
+ "learning_rate": 9.590598327534564e-05,
414
+ "loss": 0.0608,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.44360902255639095,
419
+ "grad_norm": 0.08164222581806205,
420
+ "learning_rate": 9.564155976606339e-05,
421
+ "loss": 0.0728,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.45112781954887216,
426
+ "grad_norm": 0.068249029412382,
427
+ "learning_rate": 9.536925023144742e-05,
428
+ "loss": 0.0769,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.45864661654135336,
433
+ "grad_norm": 0.08766128533878917,
434
+ "learning_rate": 9.508910172159635e-05,
435
+ "loss": 0.0807,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.46616541353383456,
440
+ "grad_norm": 0.08267380913496714,
441
+ "learning_rate": 9.480116264104011e-05,
442
+ "loss": 0.0688,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.47368421052631576,
447
+ "grad_norm": 0.056304693308065895,
448
+ "learning_rate": 9.450548274037653e-05,
449
+ "loss": 0.0718,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.48120300751879697,
454
+ "grad_norm": 0.046549935161625186,
455
+ "learning_rate": 9.420211310767533e-05,
456
+ "loss": 0.0597,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.48872180451127817,
461
+ "grad_norm": 0.051003421704534715,
462
+ "learning_rate": 9.389110615965102e-05,
463
+ "loss": 0.0543,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.49624060150375937,
468
+ "grad_norm": 0.056229605749365814,
469
+ "learning_rate": 9.35725156326063e-05,
470
+ "loss": 0.0664,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.5037593984962406,
475
+ "grad_norm": 0.05192766124616745,
476
+ "learning_rate": 9.324639657314742e-05,
477
+ "loss": 0.0664,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.5112781954887218,
482
+ "grad_norm": 0.05663307303512644,
483
+ "learning_rate": 9.291280532867302e-05,
484
+ "loss": 0.0724,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.518796992481203,
489
+ "grad_norm": 0.04788394804790932,
490
+ "learning_rate": 9.257179953763845e-05,
491
+ "loss": 0.0604,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.5263157894736842,
496
+ "grad_norm": 0.05896579606266624,
497
+ "learning_rate": 9.222343811959693e-05,
498
+ "loss": 0.0646,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.5338345864661654,
503
+ "grad_norm": 0.05629065110150116,
504
+ "learning_rate": 9.186778126501916e-05,
505
+ "loss": 0.067,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.5413533834586466,
510
+ "grad_norm": 0.04584833961975404,
511
+ "learning_rate": 9.150489042489367e-05,
512
+ "loss": 0.0612,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.5488721804511278,
517
+ "grad_norm": 0.09187351768006502,
518
+ "learning_rate": 9.113482830010918e-05,
519
+ "loss": 0.0696,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.556390977443609,
524
+ "grad_norm": 0.04979123048456232,
525
+ "learning_rate": 9.075765883062093e-05,
526
+ "loss": 0.0591,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.5639097744360902,
531
+ "grad_norm": 0.17951533461958985,
532
+ "learning_rate": 9.037344718440322e-05,
533
+ "loss": 0.0669,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.5714285714285714,
538
+ "grad_norm": 0.0598867711914895,
539
+ "learning_rate": 8.99822597461894e-05,
540
+ "loss": 0.073,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.5789473684210527,
545
+ "grad_norm": 0.061301068751050965,
546
+ "learning_rate": 8.958416410600187e-05,
547
+ "loss": 0.0593,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.5864661654135338,
552
+ "grad_norm": 0.07718039287956263,
553
+ "learning_rate": 8.917922904747384e-05,
554
+ "loss": 0.0747,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.5939849624060151,
559
+ "grad_norm": 0.08031913391827475,
560
+ "learning_rate": 8.876752453596462e-05,
561
+ "loss": 0.0575,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.6015037593984962,
566
+ "grad_norm": 0.09187557284156139,
567
+ "learning_rate": 8.834912170647101e-05,
568
+ "loss": 0.0738,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.6090225563909775,
573
+ "grad_norm": 0.06469130411192654,
574
+ "learning_rate": 8.792409285133642e-05,
575
+ "loss": 0.0772,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.6165413533834586,
580
+ "grad_norm": 0.059958610675886856,
581
+ "learning_rate": 8.749251140776016e-05,
582
+ "loss": 0.0632,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.6240601503759399,
587
+ "grad_norm": 0.053104489982768004,
588
+ "learning_rate": 8.705445194510868e-05,
589
+ "loss": 0.0571,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.631578947368421,
594
+ "grad_norm": 0.05506977920080928,
595
+ "learning_rate": 8.66099901520315e-05,
596
+ "loss": 0.068,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.6390977443609023,
601
+ "grad_norm": 0.05061868141802937,
602
+ "learning_rate": 8.615920282338355e-05,
603
+ "loss": 0.0655,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.6466165413533834,
608
+ "grad_norm": 0.04542060285450703,
609
+ "learning_rate": 8.570216784695637e-05,
610
+ "loss": 0.0542,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.6541353383458647,
615
+ "grad_norm": 0.06619278409184891,
616
+ "learning_rate": 8.52389641900206e-05,
617
+ "loss": 0.069,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.6616541353383458,
622
+ "grad_norm": 0.046648382294451465,
623
+ "learning_rate": 8.476967188568188e-05,
624
+ "loss": 0.05,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.6691729323308271,
629
+ "grad_norm": 0.04903241517184936,
630
+ "learning_rate": 8.429437201905254e-05,
631
+ "loss": 0.0492,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.6766917293233082,
636
+ "grad_norm": 0.054401413965596515,
637
+ "learning_rate": 8.381314671324159e-05,
638
+ "loss": 0.0645,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.6842105263157895,
643
+ "grad_norm": 0.07665192699881623,
644
+ "learning_rate": 8.332607911516545e-05,
645
+ "loss": 0.0727,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.6917293233082706,
650
+ "grad_norm": 0.04614115034705018,
651
+ "learning_rate": 8.283325338118153e-05,
652
+ "loss": 0.0563,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.6992481203007519,
657
+ "grad_norm": 0.048721192197202036,
658
+ "learning_rate": 8.233475466254765e-05,
659
+ "loss": 0.0641,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.706766917293233,
664
+ "grad_norm": 0.09689687696289023,
665
+ "learning_rate": 8.183066909070947e-05,
666
+ "loss": 0.0729,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.7142857142857143,
671
+ "grad_norm": 0.04898235088121123,
672
+ "learning_rate": 8.132108376241849e-05,
673
+ "loss": 0.0609,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.7218045112781954,
678
+ "grad_norm": 0.062476539893748746,
679
+ "learning_rate": 8.08060867246834e-05,
680
+ "loss": 0.0754,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.7293233082706767,
685
+ "grad_norm": 0.048842336871983916,
686
+ "learning_rate": 8.028576695955711e-05,
687
+ "loss": 0.0567,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.7368421052631579,
692
+ "grad_norm": 0.05091154083494744,
693
+ "learning_rate": 7.97602143687623e-05,
694
+ "loss": 0.0581,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.7443609022556391,
699
+ "grad_norm": 0.05277857543999218,
700
+ "learning_rate": 7.922951975815811e-05,
701
+ "loss": 0.0547,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.7518796992481203,
706
+ "grad_norm": 0.04995056636669834,
707
+ "learning_rate": 7.869377482205042e-05,
708
+ "loss": 0.0585,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.7593984962406015,
713
+ "grad_norm": 0.048863116813669935,
714
+ "learning_rate": 7.815307212734888e-05,
715
+ "loss": 0.0525,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.7669172932330827,
720
+ "grad_norm": 0.05363054356558151,
721
+ "learning_rate": 7.760750509757298e-05,
722
+ "loss": 0.0664,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.7744360902255639,
727
+ "grad_norm": 0.0419800232132696,
728
+ "learning_rate": 7.705716799671019e-05,
729
+ "loss": 0.0464,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.7819548872180451,
734
+ "grad_norm": 0.0621701703495248,
735
+ "learning_rate": 7.650215591292888e-05,
736
+ "loss": 0.0617,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.7894736842105263,
741
+ "grad_norm": 0.053222448281503805,
742
+ "learning_rate": 7.594256474214882e-05,
743
+ "loss": 0.0544,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.7969924812030075,
748
+ "grad_norm": 0.17520046998525754,
749
+ "learning_rate": 7.537849117147212e-05,
750
+ "loss": 0.0743,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.8045112781954887,
755
+ "grad_norm": 0.06071964383569251,
756
+ "learning_rate": 7.481003266247744e-05,
757
+ "loss": 0.07,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.8120300751879699,
762
+ "grad_norm": 0.06585274207722815,
763
+ "learning_rate": 7.423728743438048e-05,
764
+ "loss": 0.0664,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.8195488721804511,
769
+ "grad_norm": 0.053702064082499425,
770
+ "learning_rate": 7.366035444706347e-05,
771
+ "loss": 0.0648,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.8270676691729323,
776
+ "grad_norm": 0.06732634646621387,
777
+ "learning_rate": 7.307933338397667e-05,
778
+ "loss": 0.0679,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.8345864661654135,
783
+ "grad_norm": 0.07087978228058076,
784
+ "learning_rate": 7.249432463491498e-05,
785
+ "loss": 0.0601,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.8421052631578947,
790
+ "grad_norm": 0.048864453734589225,
791
+ "learning_rate": 7.190542927867234e-05,
792
+ "loss": 0.0498,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.849624060150376,
797
+ "grad_norm": 0.05567999935512773,
798
+ "learning_rate": 7.131274906557725e-05,
799
+ "loss": 0.0546,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.8571428571428571,
804
+ "grad_norm": 0.059648830514490166,
805
+ "learning_rate": 7.071638639991207e-05,
806
+ "loss": 0.054,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.8646616541353384,
811
+ "grad_norm": 0.06108153656181792,
812
+ "learning_rate": 7.011644432221958e-05,
813
+ "loss": 0.0599,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.8721804511278195,
818
+ "grad_norm": 0.06266956242565164,
819
+ "learning_rate": 6.95130264914993e-05,
820
+ "loss": 0.0776,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.8796992481203008,
825
+ "grad_norm": 0.06408453590394719,
826
+ "learning_rate": 6.890623716729724e-05,
827
+ "loss": 0.0519,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.8872180451127819,
832
+ "grad_norm": 0.0530662143868006,
833
+ "learning_rate": 6.82961811916917e-05,
834
+ "loss": 0.0565,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.8947368421052632,
839
+ "grad_norm": 0.04982487689350046,
840
+ "learning_rate": 6.768296397117848e-05,
841
+ "loss": 0.0485,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.9022556390977443,
846
+ "grad_norm": 0.05447809635854366,
847
+ "learning_rate": 6.706669145845863e-05,
848
+ "loss": 0.0639,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.9097744360902256,
853
+ "grad_norm": 0.05549903762455599,
854
+ "learning_rate": 6.644747013413168e-05,
855
+ "loss": 0.0583,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.9172932330827067,
860
+ "grad_norm": 0.05498533914312949,
861
+ "learning_rate": 6.582540698829781e-05,
862
+ "loss": 0.0643,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.924812030075188,
867
+ "grad_norm": 0.061216429868395664,
868
+ "learning_rate": 6.520060950207185e-05,
869
+ "loss": 0.0729,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.9323308270676691,
874
+ "grad_norm": 0.04913486061307017,
875
+ "learning_rate": 6.457318562901256e-05,
876
+ "loss": 0.0561,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.9398496240601504,
881
+ "grad_norm": 0.05187115501206559,
882
+ "learning_rate": 6.394324377647028e-05,
883
+ "loss": 0.0657,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.9473684210526315,
888
+ "grad_norm": 0.062441560969921664,
889
+ "learning_rate": 6.331089278685599e-05,
890
+ "loss": 0.0591,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.9548872180451128,
895
+ "grad_norm": 0.049315583568074056,
896
+ "learning_rate": 6.26762419188355e-05,
897
+ "loss": 0.0483,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.9624060150375939,
902
+ "grad_norm": 0.0692504928064921,
903
+ "learning_rate": 6.203940082845144e-05,
904
+ "loss": 0.0811,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.9699248120300752,
909
+ "grad_norm": 0.06962571966408558,
910
+ "learning_rate": 6.140047955017671e-05,
911
+ "loss": 0.0708,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.9774436090225563,
916
+ "grad_norm": 0.0696227047140056,
917
+ "learning_rate": 6.075958847790262e-05,
918
+ "loss": 0.0687,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.9849624060150376,
923
+ "grad_norm": 0.0707387356212119,
924
+ "learning_rate": 6.011683834586473e-05,
925
+ "loss": 0.0507,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.9924812030075187,
930
+ "grad_norm": 0.04646244901827649,
931
+ "learning_rate": 5.947234020951015e-05,
932
+ "loss": 0.0463,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 1.0,
937
+ "grad_norm": 0.05536559616639241,
938
+ "learning_rate": 5.882620542630901e-05,
939
+ "loss": 0.0591,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 1.0075187969924813,
944
+ "grad_norm": 0.07973973145414537,
945
+ "learning_rate": 5.8178545636514145e-05,
946
+ "loss": 0.053,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 1.0150375939849625,
951
+ "grad_norm": 0.0717315767711819,
952
+ "learning_rate": 5.752947274387147e-05,
953
+ "loss": 0.0505,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 1.0225563909774436,
958
+ "grad_norm": 0.05613937499913696,
959
+ "learning_rate": 5.687909889628529e-05,
960
+ "loss": 0.0675,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 1.0300751879699248,
965
+ "grad_norm": 0.054366295788576144,
966
+ "learning_rate": 5.622753646644102e-05,
967
+ "loss": 0.054,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 1.037593984962406,
972
+ "grad_norm": 0.05668284327984812,
973
+ "learning_rate": 5.557489803238933e-05,
974
+ "loss": 0.0548,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 1.045112781954887,
979
+ "grad_norm": 0.0891727938743713,
980
+ "learning_rate": 5.492129635809473e-05,
981
+ "loss": 0.0475,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 1.0526315789473684,
986
+ "grad_norm": 0.06656022952521709,
987
+ "learning_rate": 5.426684437395196e-05,
988
+ "loss": 0.0457,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 1.0601503759398496,
993
+ "grad_norm": 0.05558545326947945,
994
+ "learning_rate": 5.361165515727374e-05,
995
+ "loss": 0.0488,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 1.0676691729323309,
1000
+ "grad_norm": 0.09105926777317562,
1001
+ "learning_rate": 5.295584191275308e-05,
1002
+ "loss": 0.0557,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 1.0751879699248121,
1007
+ "grad_norm": 0.07164287847259117,
1008
+ "learning_rate": 5.229951795290353e-05,
1009
+ "loss": 0.0602,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 1.0827067669172932,
1014
+ "grad_norm": 0.049157639401816514,
1015
+ "learning_rate": 5.164279667848094e-05,
1016
+ "loss": 0.0458,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 1.0902255639097744,
1021
+ "grad_norm": 0.06265164380965654,
1022
+ "learning_rate": 5.0985791558889785e-05,
1023
+ "loss": 0.0489,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 1.0977443609022557,
1028
+ "grad_norm": 0.0939217508789768,
1029
+ "learning_rate": 5.032861611257783e-05,
1030
+ "loss": 0.0582,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 1.1052631578947367,
1035
+ "grad_norm": 0.0700349034994235,
1036
+ "learning_rate": 4.967138388742218e-05,
1037
+ "loss": 0.0468,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 1.112781954887218,
1042
+ "grad_norm": 0.0728519582319508,
1043
+ "learning_rate": 4.901420844111021e-05,
1044
+ "loss": 0.065,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 1.1203007518796992,
1049
+ "grad_norm": 0.07663131138150972,
1050
+ "learning_rate": 4.835720332151907e-05,
1051
+ "loss": 0.0663,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 1.1278195488721805,
1056
+ "grad_norm": 0.0570893195865412,
1057
+ "learning_rate": 4.770048204709648e-05,
1058
+ "loss": 0.0557,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 1.1353383458646618,
1063
+ "grad_norm": 0.0639577359352655,
1064
+ "learning_rate": 4.7044158087246926e-05,
1065
+ "loss": 0.0659,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 1.1428571428571428,
1070
+ "grad_norm": 0.06865878867133068,
1071
+ "learning_rate": 4.6388344842726264e-05,
1072
+ "loss": 0.0477,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 1.150375939849624,
1077
+ "grad_norm": 0.06027852120270197,
1078
+ "learning_rate": 4.5733155626048036e-05,
1079
+ "loss": 0.0569,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 1.1578947368421053,
1084
+ "grad_norm": 0.060736614265756404,
1085
+ "learning_rate": 4.507870364190527e-05,
1086
+ "loss": 0.0578,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.1654135338345863,
1091
+ "grad_norm": 0.05655861834499769,
1092
+ "learning_rate": 4.4425101967610674e-05,
1093
+ "loss": 0.0537,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.1729323308270676,
1098
+ "grad_norm": 0.08128771365109748,
1099
+ "learning_rate": 4.377246353355899e-05,
1100
+ "loss": 0.0582,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.1804511278195489,
1105
+ "grad_norm": 0.061292647571849164,
1106
+ "learning_rate": 4.312090110371473e-05,
1107
+ "loss": 0.056,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.1879699248120301,
1112
+ "grad_norm": 0.07064990537024936,
1113
+ "learning_rate": 4.247052725612852e-05,
1114
+ "loss": 0.0682,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.1954887218045114,
1119
+ "grad_norm": 0.06773157054753728,
1120
+ "learning_rate": 4.1821454363485866e-05,
1121
+ "loss": 0.0507,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.2030075187969924,
1126
+ "grad_norm": 0.05759838937841694,
1127
+ "learning_rate": 4.1173794573690996e-05,
1128
+ "loss": 0.0499,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.2105263157894737,
1133
+ "grad_norm": 0.05684766471772889,
1134
+ "learning_rate": 4.052765979048986e-05,
1135
+ "loss": 0.06,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.218045112781955,
1140
+ "grad_norm": 0.05627811122291738,
1141
+ "learning_rate": 3.988316165413528e-05,
1142
+ "loss": 0.0465,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.225563909774436,
1147
+ "grad_norm": 0.0634447313672517,
1148
+ "learning_rate": 3.924041152209739e-05,
1149
+ "loss": 0.0546,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.2330827067669172,
1154
+ "grad_norm": 0.06129516733509535,
1155
+ "learning_rate": 3.859952044982329e-05,
1156
+ "loss": 0.0583,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.2406015037593985,
1161
+ "grad_norm": 0.0556690200442891,
1162
+ "learning_rate": 3.7960599171548574e-05,
1163
+ "loss": 0.0485,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.2481203007518797,
1168
+ "grad_norm": 0.05909797088448607,
1169
+ "learning_rate": 3.732375808116451e-05,
1170
+ "loss": 0.0549,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.255639097744361,
1175
+ "grad_norm": 0.0584647942308342,
1176
+ "learning_rate": 3.668910721314402e-05,
1177
+ "loss": 0.0465,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.263157894736842,
1182
+ "grad_norm": 0.06616801896130901,
1183
+ "learning_rate": 3.605675622352973e-05,
1184
+ "loss": 0.0542,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.2706766917293233,
1189
+ "grad_norm": 0.0610415449148621,
1190
+ "learning_rate": 3.542681437098745e-05,
1191
+ "loss": 0.0583,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.2781954887218046,
1196
+ "grad_norm": 0.06164991136935588,
1197
+ "learning_rate": 3.479939049792817e-05,
1198
+ "loss": 0.0457,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.2857142857142856,
1203
+ "grad_norm": 0.06976263090026703,
1204
+ "learning_rate": 3.417459301170219e-05,
1205
+ "loss": 0.0557,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.2932330827067668,
1210
+ "grad_norm": 0.08609184464570446,
1211
+ "learning_rate": 3.355252986586832e-05,
1212
+ "loss": 0.0448,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.300751879699248,
1217
+ "grad_norm": 0.0679124684070907,
1218
+ "learning_rate": 3.293330854154136e-05,
1219
+ "loss": 0.057,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.3082706766917294,
1224
+ "grad_norm": 0.054159879855348425,
1225
+ "learning_rate": 3.2317036028821523e-05,
1226
+ "loss": 0.0359,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.3157894736842106,
1231
+ "grad_norm": 0.06546859720273018,
1232
+ "learning_rate": 3.1703818808308324e-05,
1233
+ "loss": 0.0465,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.3233082706766917,
1238
+ "grad_norm": 0.06090228684811805,
1239
+ "learning_rate": 3.109376283270277e-05,
1240
+ "loss": 0.0516,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.330827067669173,
1245
+ "grad_norm": 0.06348664345535836,
1246
+ "learning_rate": 3.0486973508500727e-05,
1247
+ "loss": 0.0565,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.3383458646616542,
1252
+ "grad_norm": 0.06726956159455097,
1253
+ "learning_rate": 2.988355567778043e-05,
1254
+ "loss": 0.0586,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.3458646616541352,
1259
+ "grad_norm": 0.06665459570295906,
1260
+ "learning_rate": 2.9283613600087933e-05,
1261
+ "loss": 0.0565,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.3533834586466165,
1266
+ "grad_norm": 0.06544040767443535,
1267
+ "learning_rate": 2.8687250934422772e-05,
1268
+ "loss": 0.0424,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.3609022556390977,
1273
+ "grad_norm": 0.05554025930164869,
1274
+ "learning_rate": 2.8094570721327662e-05,
1275
+ "loss": 0.0415,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.368421052631579,
1280
+ "grad_norm": 0.0634605881917348,
1281
+ "learning_rate": 2.750567536508504e-05,
1282
+ "loss": 0.0505,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.3759398496240602,
1287
+ "grad_norm": 0.06956419288103331,
1288
+ "learning_rate": 2.6920666616023327e-05,
1289
+ "loss": 0.06,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.3834586466165413,
1294
+ "grad_norm": 0.06376462019500133,
1295
+ "learning_rate": 2.6339645552936536e-05,
1296
+ "loss": 0.0602,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.3909774436090225,
1301
+ "grad_norm": 0.06679763262814233,
1302
+ "learning_rate": 2.5762712565619528e-05,
1303
+ "loss": 0.0497,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.3984962406015038,
1308
+ "grad_norm": 0.053421734602639936,
1309
+ "learning_rate": 2.5189967337522573e-05,
1310
+ "loss": 0.0452,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.4060150375939848,
1315
+ "grad_norm": 0.0643654223637289,
1316
+ "learning_rate": 2.46215088285279e-05,
1317
+ "loss": 0.0518,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.413533834586466,
1322
+ "grad_norm": 0.056212251452042714,
1323
+ "learning_rate": 2.4057435257851175e-05,
1324
+ "loss": 0.044,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.4210526315789473,
1329
+ "grad_norm": 0.07011435146976071,
1330
+ "learning_rate": 2.349784408707112e-05,
1331
+ "loss": 0.0566,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.4285714285714286,
1336
+ "grad_norm": 0.06302928445269088,
1337
+ "learning_rate": 2.2942832003289823e-05,
1338
+ "loss": 0.0543,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.4360902255639099,
1343
+ "grad_norm": 0.06769161277611331,
1344
+ "learning_rate": 2.2392494902427025e-05,
1345
+ "loss": 0.0571,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.443609022556391,
1350
+ "grad_norm": 0.058764427988578866,
1351
+ "learning_rate": 2.1846927872651137e-05,
1352
+ "loss": 0.0482,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.4511278195488722,
1357
+ "grad_norm": 0.06462419466731671,
1358
+ "learning_rate": 2.1306225177949585e-05,
1359
+ "loss": 0.0568,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.4586466165413534,
1364
+ "grad_norm": 0.07227950771449271,
1365
+ "learning_rate": 2.07704802418419e-05,
1366
+ "loss": 0.0603,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.4661654135338344,
1371
+ "grad_norm": 0.06636932716724628,
1372
+ "learning_rate": 2.0239785631237705e-05,
1373
+ "loss": 0.0584,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.4736842105263157,
1378
+ "grad_norm": 0.056385340594049246,
1379
+ "learning_rate": 1.9714233040442915e-05,
1380
+ "loss": 0.0458,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.481203007518797,
1385
+ "grad_norm": 0.06237719152557535,
1386
+ "learning_rate": 1.9193913275316626e-05,
1387
+ "loss": 0.0484,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.4887218045112782,
1392
+ "grad_norm": 0.0729466042662235,
1393
+ "learning_rate": 1.8678916237581522e-05,
1394
+ "loss": 0.0467,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.4962406015037595,
1399
+ "grad_norm": 0.059334240343210554,
1400
+ "learning_rate": 1.816933090929055e-05,
1401
+ "loss": 0.0408,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.5037593984962405,
1406
+ "grad_norm": 0.07236922556022596,
1407
+ "learning_rate": 1.7665245337452368e-05,
1408
+ "loss": 0.0558,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.5037593984962405,
1413
+ "eval_loss": 0.05888579785823822,
1414
+ "eval_runtime": 2.9139,
1415
+ "eval_samples_per_second": 2.059,
1416
+ "eval_steps_per_second": 0.686,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 1.5112781954887218,
1421
+ "grad_norm": 0.06362440611633548,
1422
+ "learning_rate": 1.716674661881848e-05,
1423
+ "loss": 0.0515,
1424
+ "step": 201
1425
+ },
1426
+ {
1427
+ "epoch": 1.518796992481203,
1428
+ "grad_norm": 0.07191386409954059,
1429
+ "learning_rate": 1.667392088483456e-05,
1430
+ "loss": 0.0487,
1431
+ "step": 202
1432
+ },
1433
+ {
1434
+ "epoch": 1.526315789473684,
1435
+ "grad_norm": 0.0704482597934987,
1436
+ "learning_rate": 1.6186853286758397e-05,
1437
+ "loss": 0.0562,
1438
+ "step": 203
1439
+ },
1440
+ {
1441
+ "epoch": 1.5338345864661656,
1442
+ "grad_norm": 0.0641485568233754,
1443
+ "learning_rate": 1.570562798094747e-05,
1444
+ "loss": 0.0537,
1445
+ "step": 204
1446
+ },
1447
+ {
1448
+ "epoch": 1.5413533834586466,
1449
+ "grad_norm": 0.2476858058227162,
1450
+ "learning_rate": 1.5230328114318127e-05,
1451
+ "loss": 0.069,
1452
+ "step": 205
1453
+ },
1454
+ {
1455
+ "epoch": 1.5488721804511278,
1456
+ "grad_norm": 0.07165648268834594,
1457
+ "learning_rate": 1.4761035809979395e-05,
1458
+ "loss": 0.05,
1459
+ "step": 206
1460
+ },
1461
+ {
1462
+ "epoch": 1.556390977443609,
1463
+ "grad_norm": 0.07136700845895734,
1464
+ "learning_rate": 1.4297832153043656e-05,
1465
+ "loss": 0.0495,
1466
+ "step": 207
1467
+ },
1468
+ {
1469
+ "epoch": 1.5639097744360901,
1470
+ "grad_norm": 0.06970939624439716,
1471
+ "learning_rate": 1.3840797176616466e-05,
1472
+ "loss": 0.0608,
1473
+ "step": 208
1474
+ },
1475
+ {
1476
+ "epoch": 1.5714285714285714,
1477
+ "grad_norm": 0.07183753275895223,
1478
+ "learning_rate": 1.3390009847968504e-05,
1479
+ "loss": 0.0509,
1480
+ "step": 209
1481
+ },
1482
+ {
1483
+ "epoch": 1.5789473684210527,
1484
+ "grad_norm": 0.06789564902473792,
1485
+ "learning_rate": 1.2945548054891321e-05,
1486
+ "loss": 0.0578,
1487
+ "step": 210
1488
+ },
1489
+ {
1490
+ "epoch": 1.5864661654135337,
1491
+ "grad_norm": 0.07783704991244755,
1492
+ "learning_rate": 1.2507488592239847e-05,
1493
+ "loss": 0.0519,
1494
+ "step": 211
1495
+ },
1496
+ {
1497
+ "epoch": 1.5939849624060152,
1498
+ "grad_norm": 0.07869926070204697,
1499
+ "learning_rate": 1.2075907148663579e-05,
1500
+ "loss": 0.0559,
1501
+ "step": 212
1502
+ },
1503
+ {
1504
+ "epoch": 1.6015037593984962,
1505
+ "grad_norm": 0.06124945988811601,
1506
+ "learning_rate": 1.1650878293528994e-05,
1507
+ "loss": 0.0548,
1508
+ "step": 213
1509
+ },
1510
+ {
1511
+ "epoch": 1.6090225563909775,
1512
+ "grad_norm": 0.0714026383572265,
1513
+ "learning_rate": 1.1232475464035385e-05,
1514
+ "loss": 0.0456,
1515
+ "step": 214
1516
+ },
1517
+ {
1518
+ "epoch": 1.6165413533834587,
1519
+ "grad_norm": 0.09052491852044252,
1520
+ "learning_rate": 1.0820770952526155e-05,
1521
+ "loss": 0.0512,
1522
+ "step": 215
1523
+ },
1524
+ {
1525
+ "epoch": 1.6240601503759398,
1526
+ "grad_norm": 0.07556514721607528,
1527
+ "learning_rate": 1.0415835893998116e-05,
1528
+ "loss": 0.058,
1529
+ "step": 216
1530
+ },
1531
+ {
1532
+ "epoch": 1.631578947368421,
1533
+ "grad_norm": 0.08293706337595592,
1534
+ "learning_rate": 1.0017740253810609e-05,
1535
+ "loss": 0.0543,
1536
+ "step": 217
1537
+ },
1538
+ {
1539
+ "epoch": 1.6390977443609023,
1540
+ "grad_norm": 0.08293716749347428,
1541
+ "learning_rate": 9.62655281559679e-06,
1542
+ "loss": 0.0527,
1543
+ "step": 218
1544
+ },
1545
+ {
1546
+ "epoch": 1.6466165413533833,
1547
+ "grad_norm": 0.06528865403508805,
1548
+ "learning_rate": 9.242341169379076e-06,
1549
+ "loss": 0.0522,
1550
+ "step": 219
1551
+ },
1552
+ {
1553
+ "epoch": 1.6541353383458648,
1554
+ "grad_norm": 0.08214994733323353,
1555
+ "learning_rate": 8.865171699890834e-06,
1556
+ "loss": 0.0577,
1557
+ "step": 220
1558
+ },
1559
+ {
1560
+ "epoch": 1.6616541353383458,
1561
+ "grad_norm": 0.07469570260905062,
1562
+ "learning_rate": 8.49510957510633e-06,
1563
+ "loss": 0.0626,
1564
+ "step": 221
1565
+ },
1566
+ {
1567
+ "epoch": 1.669172932330827,
1568
+ "grad_norm": 0.0779710894409375,
1569
+ "learning_rate": 8.132218734980852e-06,
1570
+ "loss": 0.0429,
1571
+ "step": 222
1572
+ },
1573
+ {
1574
+ "epoch": 1.6766917293233083,
1575
+ "grad_norm": 0.06025824332971454,
1576
+ "learning_rate": 7.776561880403072e-06,
1577
+ "loss": 0.0461,
1578
+ "step": 223
1579
+ },
1580
+ {
1581
+ "epoch": 1.6842105263157894,
1582
+ "grad_norm": 0.07160415901272407,
1583
+ "learning_rate": 7.4282004623615396e-06,
1584
+ "loss": 0.0524,
1585
+ "step": 224
1586
+ },
1587
+ {
1588
+ "epoch": 1.6917293233082706,
1589
+ "grad_norm": 0.06093918594696831,
1590
+ "learning_rate": 7.0871946713269856e-06,
1591
+ "loss": 0.0435,
1592
+ "step": 225
1593
+ },
1594
+ {
1595
+ "epoch": 1.699248120300752,
1596
+ "grad_norm": 0.06202821639579326,
1597
+ "learning_rate": 6.753603426852589e-06,
1598
+ "loss": 0.0457,
1599
+ "step": 226
1600
+ },
1601
+ {
1602
+ "epoch": 1.706766917293233,
1603
+ "grad_norm": 0.06995303102929186,
1604
+ "learning_rate": 6.427484367393699e-06,
1605
+ "loss": 0.0539,
1606
+ "step": 227
1607
+ },
1608
+ {
1609
+ "epoch": 1.7142857142857144,
1610
+ "grad_norm": 0.06659469820778222,
1611
+ "learning_rate": 6.108893840348995e-06,
1612
+ "loss": 0.055,
1613
+ "step": 228
1614
+ },
1615
+ {
1616
+ "epoch": 1.7218045112781954,
1617
+ "grad_norm": 0.06908634964367481,
1618
+ "learning_rate": 5.797886892324694e-06,
1619
+ "loss": 0.0542,
1620
+ "step": 229
1621
+ },
1622
+ {
1623
+ "epoch": 1.7293233082706767,
1624
+ "grad_norm": 0.06616826334511514,
1625
+ "learning_rate": 5.494517259623477e-06,
1626
+ "loss": 0.0502,
1627
+ "step": 230
1628
+ },
1629
+ {
1630
+ "epoch": 1.736842105263158,
1631
+ "grad_norm": 0.06876777218997701,
1632
+ "learning_rate": 5.198837358959901e-06,
1633
+ "loss": 0.0548,
1634
+ "step": 231
1635
+ },
1636
+ {
1637
+ "epoch": 1.744360902255639,
1638
+ "grad_norm": 0.07834360233609336,
1639
+ "learning_rate": 4.910898278403669e-06,
1640
+ "loss": 0.0616,
1641
+ "step": 232
1642
+ },
1643
+ {
1644
+ "epoch": 1.7518796992481203,
1645
+ "grad_norm": 0.07465093867859447,
1646
+ "learning_rate": 4.630749768552589e-06,
1647
+ "loss": 0.0572,
1648
+ "step": 233
1649
+ },
1650
+ {
1651
+ "epoch": 1.7593984962406015,
1652
+ "grad_norm": 0.06530867011066181,
1653
+ "learning_rate": 4.358440233936617e-06,
1654
+ "loss": 0.0463,
1655
+ "step": 234
1656
+ },
1657
+ {
1658
+ "epoch": 1.7669172932330826,
1659
+ "grad_norm": 0.09329860109695949,
1660
+ "learning_rate": 4.094016724654359e-06,
1661
+ "loss": 0.0563,
1662
+ "step": 235
1663
+ },
1664
+ {
1665
+ "epoch": 1.774436090225564,
1666
+ "grad_norm": 0.06576003650403141,
1667
+ "learning_rate": 3.837524928243774e-06,
1668
+ "loss": 0.0514,
1669
+ "step": 236
1670
+ },
1671
+ {
1672
+ "epoch": 1.781954887218045,
1673
+ "grad_norm": 0.06889410337817259,
1674
+ "learning_rate": 3.589009161788104e-06,
1675
+ "loss": 0.0614,
1676
+ "step": 237
1677
+ },
1678
+ {
1679
+ "epoch": 1.7894736842105263,
1680
+ "grad_norm": 0.07328907327992419,
1681
+ "learning_rate": 3.3485123642587658e-06,
1682
+ "loss": 0.0581,
1683
+ "step": 238
1684
+ },
1685
+ {
1686
+ "epoch": 1.7969924812030076,
1687
+ "grad_norm": 0.0799744075197541,
1688
+ "learning_rate": 3.116076089096265e-06,
1689
+ "loss": 0.0612,
1690
+ "step": 239
1691
+ },
1692
+ {
1693
+ "epoch": 1.8045112781954886,
1694
+ "grad_norm": 0.0692766811110033,
1695
+ "learning_rate": 2.8917404970305097e-06,
1696
+ "loss": 0.0664,
1697
+ "step": 240
1698
+ },
1699
+ {
1700
+ "epoch": 1.8120300751879699,
1701
+ "grad_norm": 0.09315535739949427,
1702
+ "learning_rate": 2.675544349141779e-06,
1703
+ "loss": 0.0542,
1704
+ "step": 241
1705
+ },
1706
+ {
1707
+ "epoch": 1.8195488721804511,
1708
+ "grad_norm": 0.07045512960614121,
1709
+ "learning_rate": 2.4675250001635232e-06,
1710
+ "loss": 0.0571,
1711
+ "step": 242
1712
+ },
1713
+ {
1714
+ "epoch": 1.8270676691729322,
1715
+ "grad_norm": 0.06416431699975886,
1716
+ "learning_rate": 2.2677183920281343e-06,
1717
+ "loss": 0.0437,
1718
+ "step": 243
1719
+ },
1720
+ {
1721
+ "epoch": 1.8345864661654137,
1722
+ "grad_norm": 0.07900619401755478,
1723
+ "learning_rate": 2.076159047656889e-06,
1724
+ "loss": 0.0497,
1725
+ "step": 244
1726
+ },
1727
+ {
1728
+ "epoch": 1.8421052631578947,
1729
+ "grad_norm": 0.06818090463377556,
1730
+ "learning_rate": 1.892880064994934e-06,
1731
+ "loss": 0.0581,
1732
+ "step": 245
1733
+ },
1734
+ {
1735
+ "epoch": 1.849624060150376,
1736
+ "grad_norm": 0.061208976982830766,
1737
+ "learning_rate": 1.7179131112926627e-06,
1738
+ "loss": 0.0488,
1739
+ "step": 246
1740
+ },
1741
+ {
1742
+ "epoch": 1.8571428571428572,
1743
+ "grad_norm": 0.05975396469345226,
1744
+ "learning_rate": 1.551288417634106e-06,
1745
+ "loss": 0.0366,
1746
+ "step": 247
1747
+ },
1748
+ {
1749
+ "epoch": 1.8646616541353382,
1750
+ "grad_norm": 0.060287054649790124,
1751
+ "learning_rate": 1.3930347737136196e-06,
1752
+ "loss": 0.0456,
1753
+ "step": 248
1754
+ },
1755
+ {
1756
+ "epoch": 1.8721804511278195,
1757
+ "grad_norm": 0.06949859076738091,
1758
+ "learning_rate": 1.2431795228615372e-06,
1759
+ "loss": 0.0512,
1760
+ "step": 249
1761
+ },
1762
+ {
1763
+ "epoch": 1.8796992481203008,
1764
+ "grad_norm": 0.08459802709762443,
1765
+ "learning_rate": 1.101748557319715e-06,
1766
+ "loss": 0.0665,
1767
+ "step": 250
1768
+ },
1769
+ {
1770
+ "epoch": 1.8872180451127818,
1771
+ "grad_norm": 0.06720551802143489,
1772
+ "learning_rate": 9.687663137678604e-07,
1773
+ "loss": 0.0469,
1774
+ "step": 251
1775
+ },
1776
+ {
1777
+ "epoch": 1.8947368421052633,
1778
+ "grad_norm": 0.06624697456947008,
1779
+ "learning_rate": 8.442557691013043e-07,
1780
+ "loss": 0.0537,
1781
+ "step": 252
1782
+ },
1783
+ {
1784
+ "epoch": 1.9022556390977443,
1785
+ "grad_norm": 0.06860794314118437,
1786
+ "learning_rate": 7.282384364610206e-07,
1787
+ "loss": 0.0565,
1788
+ "step": 253
1789
+ },
1790
+ {
1791
+ "epoch": 1.9097744360902256,
1792
+ "grad_norm": 0.05821083299642523,
1793
+ "learning_rate": 6.207343615165561e-07,
1794
+ "loss": 0.0448,
1795
+ "step": 254
1796
+ },
1797
+ {
1798
+ "epoch": 1.9172932330827068,
1799
+ "grad_norm": 0.06867399486094057,
1800
+ "learning_rate": 5.217621190024779e-07,
1801
+ "loss": 0.0589,
1802
+ "step": 255
1803
+ },
1804
+ {
1805
+ "epoch": 1.9248120300751879,
1806
+ "grad_norm": 0.07349776193267195,
1807
+ "learning_rate": 4.3133880950905205e-07,
1808
+ "loss": 0.0481,
1809
+ "step": 256
1810
+ },
1811
+ {
1812
+ "epoch": 1.9323308270676691,
1813
+ "grad_norm": 0.06778653354714559,
1814
+ "learning_rate": 3.494800565275125e-07,
1815
+ "loss": 0.0529,
1816
+ "step": 257
1817
+ },
1818
+ {
1819
+ "epoch": 1.9398496240601504,
1820
+ "grad_norm": 0.06505781250894338,
1821
+ "learning_rate": 2.762000037506485e-07,
1822
+ "loss": 0.0509,
1823
+ "step": 258
1824
+ },
1825
+ {
1826
+ "epoch": 1.9473684210526314,
1827
+ "grad_norm": 0.0663839326111524,
1828
+ "learning_rate": 2.115113126290258e-07,
1829
+ "loss": 0.0487,
1830
+ "step": 259
1831
+ },
1832
+ {
1833
+ "epoch": 1.954887218045113,
1834
+ "grad_norm": 0.06716745984670522,
1835
+ "learning_rate": 1.554251601833201e-07,
1836
+ "loss": 0.0514,
1837
+ "step": 260
1838
+ },
1839
+ {
1840
+ "epoch": 1.962406015037594,
1841
+ "grad_norm": 0.06435180661512399,
1842
+ "learning_rate": 1.0795123707312283e-07,
1843
+ "loss": 0.0492,
1844
+ "step": 261
1845
+ },
1846
+ {
1847
+ "epoch": 1.9699248120300752,
1848
+ "grad_norm": 0.07170714274542285,
1849
+ "learning_rate": 6.909774592258056e-08,
1850
+ "loss": 0.0495,
1851
+ "step": 262
1852
+ },
1853
+ {
1854
+ "epoch": 1.9774436090225564,
1855
+ "grad_norm": 0.07191186181372972,
1856
+ "learning_rate": 3.8871399903134265e-08,
1857
+ "loss": 0.0537,
1858
+ "step": 263
1859
+ },
1860
+ {
1861
+ "epoch": 1.9849624060150375,
1862
+ "grad_norm": 0.06577649105544005,
1863
+ "learning_rate": 1.7277421573608232e-08,
1864
+ "loss": 0.0583,
1865
+ "step": 264
1866
+ },
1867
+ {
1868
+ "epoch": 1.9924812030075187,
1869
+ "grad_norm": 0.06050970727730994,
1870
+ "learning_rate": 4.319541977831909e-09,
1871
+ "loss": 0.0431,
1872
+ "step": 265
1873
+ },
1874
+ {
1875
+ "epoch": 2.0,
1876
+ "grad_norm": 0.0737013160449602,
1877
+ "learning_rate": 0.0,
1878
+ "loss": 0.0523,
1879
+ "step": 266
1880
+ },
1881
+ {
1882
+ "epoch": 2.0,
1883
+ "step": 266,
1884
+ "total_flos": 505244584771584.0,
1885
+ "train_loss": 0.0657289699980415,
1886
+ "train_runtime": 994.4218,
1887
+ "train_samples_per_second": 1.064,
1888
+ "train_steps_per_second": 0.267
1889
+ }
1890
+ ],
1891
+ "logging_steps": 1,
1892
+ "max_steps": 266,
1893
+ "num_input_tokens_seen": 0,
1894
+ "num_train_epochs": 2,
1895
+ "save_steps": 300,
1896
+ "stateful_callbacks": {
1897
+ "TrainerControl": {
1898
+ "args": {
1899
+ "should_epoch_stop": false,
1900
+ "should_evaluate": false,
1901
+ "should_log": false,
1902
+ "should_save": true,
1903
+ "should_training_stop": true
1904
+ },
1905
+ "attributes": {}
1906
+ }
1907
+ },
1908
+ "total_flos": 505244584771584.0,
1909
+ "train_batch_size": 1,
1910
+ "trial_name": null,
1911
+ "trial_params": null
1912
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c301ab149ef7c3d6e0e84295b28ff9ceb35e3833587817b4340c35b645c01a
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