cutelemonlili commited on
Commit
fe4d85f
·
verified ·
1 Parent(s): 458a1d3

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 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-32B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: MATH_training_Qwen_QwQ_32B_Preview
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_Qwen_QwQ_32B_Preview
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the MATH_training_Qwen_QwQ_32B_Preview dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1138
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: 2
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - total_train_batch_size: 8
47
+ - total_eval_batch_size: 4
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - 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
+ | 0.1143 | 0.8197 | 200 | 0.1309 |
58
+ | 0.0814 | 1.6393 | 400 | 0.1139 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - PEFT 0.12.0
64
+ - Transformers 4.46.1
65
+ - Pytorch 2.5.1+cu124
66
+ - Datasets 3.1.0
67
+ - 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/Qwen2.5-32B-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
+ "down_proj",
24
+ "gate_proj",
25
+ "k_proj",
26
+ "o_proj",
27
+ "v_proj",
28
+ "q_proj",
29
+ "up_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 sha256:034d4677206a331462f298f75b2c7dbfb2db0deb58e247acbb7fadf7f9b3841b
3
+ size 134337704
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": 0.1137932687997818,
4
+ "eval_runtime": 15.7746,
5
+ "eval_samples_per_second": 1.268,
6
+ "eval_steps_per_second": 0.317,
7
+ "total_flos": 2471609260572672.0,
8
+ "train_loss": 0.1494467844423212,
9
+ "train_runtime": 5820.7005,
10
+ "train_samples_per_second": 0.671,
11
+ "train_steps_per_second": 0.084
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.1137932687997818,
4
+ "eval_runtime": 15.7746,
5
+ "eval_samples_per_second": 1.268,
6
+ "eval_steps_per_second": 0.317
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": 2471609260572672.0,
4
+ "train_loss": 0.1494467844423212,
5
+ "train_runtime": 5820.7005,
6
+ "train_samples_per_second": 0.671,
7
+ "train_steps_per_second": 0.084
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,491 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 488, "loss": 0.5811, "lr": 2.040816326530612e-06, "epoch": 0.004098360655737705, "percentage": 0.2, "elapsed_time": "0:00:16", "remaining_time": "2:14:00"}
2
+ {"current_steps": 2, "total_steps": 488, "loss": 0.5563, "lr": 4.081632653061224e-06, "epoch": 0.00819672131147541, "percentage": 0.41, "elapsed_time": "0:00:28", "remaining_time": "1:54:15"}
3
+ {"current_steps": 3, "total_steps": 488, "loss": 0.6131, "lr": 6.122448979591837e-06, "epoch": 0.012295081967213115, "percentage": 0.61, "elapsed_time": "0:00:39", "remaining_time": "1:47:25"}
4
+ {"current_steps": 4, "total_steps": 488, "loss": 0.5505, "lr": 8.163265306122448e-06, "epoch": 0.01639344262295082, "percentage": 0.82, "elapsed_time": "0:00:51", "remaining_time": "1:43:56"}
5
+ {"current_steps": 5, "total_steps": 488, "loss": 0.6017, "lr": 1.0204081632653061e-05, "epoch": 0.020491803278688523, "percentage": 1.02, "elapsed_time": "0:01:03", "remaining_time": "1:41:40"}
6
+ {"current_steps": 6, "total_steps": 488, "loss": 0.5789, "lr": 1.2244897959183674e-05, "epoch": 0.02459016393442623, "percentage": 1.23, "elapsed_time": "0:01:14", "remaining_time": "1:40:18"}
7
+ {"current_steps": 7, "total_steps": 488, "loss": 0.5539, "lr": 1.4285714285714285e-05, "epoch": 0.028688524590163935, "percentage": 1.43, "elapsed_time": "0:01:26", "remaining_time": "1:39:18"}
8
+ {"current_steps": 8, "total_steps": 488, "loss": 0.5965, "lr": 1.6326530612244897e-05, "epoch": 0.03278688524590164, "percentage": 1.64, "elapsed_time": "0:01:38", "remaining_time": "1:38:24"}
9
+ {"current_steps": 9, "total_steps": 488, "loss": 0.4591, "lr": 1.836734693877551e-05, "epoch": 0.036885245901639344, "percentage": 1.84, "elapsed_time": "0:01:50", "remaining_time": "1:37:51"}
10
+ {"current_steps": 10, "total_steps": 488, "loss": 0.5436, "lr": 2.0408163265306123e-05, "epoch": 0.040983606557377046, "percentage": 2.05, "elapsed_time": "0:02:02", "remaining_time": "1:37:13"}
11
+ {"current_steps": 11, "total_steps": 488, "loss": 0.5932, "lr": 2.2448979591836737e-05, "epoch": 0.045081967213114756, "percentage": 2.25, "elapsed_time": "0:02:13", "remaining_time": "1:36:43"}
12
+ {"current_steps": 12, "total_steps": 488, "loss": 0.6225, "lr": 2.448979591836735e-05, "epoch": 0.04918032786885246, "percentage": 2.46, "elapsed_time": "0:02:25", "remaining_time": "1:36:16"}
13
+ {"current_steps": 13, "total_steps": 488, "loss": 0.5069, "lr": 2.6530612244897963e-05, "epoch": 0.05327868852459016, "percentage": 2.66, "elapsed_time": "0:02:37", "remaining_time": "1:35:53"}
14
+ {"current_steps": 14, "total_steps": 488, "loss": 0.5482, "lr": 2.857142857142857e-05, "epoch": 0.05737704918032787, "percentage": 2.87, "elapsed_time": "0:02:49", "remaining_time": "1:35:29"}
15
+ {"current_steps": 15, "total_steps": 488, "loss": 0.5687, "lr": 3.061224489795919e-05, "epoch": 0.06147540983606557, "percentage": 3.07, "elapsed_time": "0:03:00", "remaining_time": "1:35:06"}
16
+ {"current_steps": 16, "total_steps": 488, "loss": 0.5238, "lr": 3.265306122448979e-05, "epoch": 0.06557377049180328, "percentage": 3.28, "elapsed_time": "0:03:12", "remaining_time": "1:34:44"}
17
+ {"current_steps": 17, "total_steps": 488, "loss": 0.5037, "lr": 3.469387755102041e-05, "epoch": 0.06967213114754098, "percentage": 3.48, "elapsed_time": "0:03:24", "remaining_time": "1:34:27"}
18
+ {"current_steps": 18, "total_steps": 488, "loss": 0.5432, "lr": 3.673469387755102e-05, "epoch": 0.07377049180327869, "percentage": 3.69, "elapsed_time": "0:03:36", "remaining_time": "1:34:08"}
19
+ {"current_steps": 19, "total_steps": 488, "loss": 0.539, "lr": 3.8775510204081634e-05, "epoch": 0.0778688524590164, "percentage": 3.89, "elapsed_time": "0:03:48", "remaining_time": "1:33:52"}
20
+ {"current_steps": 20, "total_steps": 488, "loss": 0.424, "lr": 4.0816326530612245e-05, "epoch": 0.08196721311475409, "percentage": 4.1, "elapsed_time": "0:04:00", "remaining_time": "1:33:36"}
21
+ {"current_steps": 21, "total_steps": 488, "loss": 0.4999, "lr": 4.2857142857142856e-05, "epoch": 0.0860655737704918, "percentage": 4.3, "elapsed_time": "0:04:11", "remaining_time": "1:33:18"}
22
+ {"current_steps": 22, "total_steps": 488, "loss": 0.4599, "lr": 4.4897959183673474e-05, "epoch": 0.09016393442622951, "percentage": 4.51, "elapsed_time": "0:04:23", "remaining_time": "1:33:02"}
23
+ {"current_steps": 23, "total_steps": 488, "loss": 0.4769, "lr": 4.6938775510204086e-05, "epoch": 0.0942622950819672, "percentage": 4.71, "elapsed_time": "0:04:35", "remaining_time": "1:32:46"}
24
+ {"current_steps": 24, "total_steps": 488, "loss": 0.524, "lr": 4.89795918367347e-05, "epoch": 0.09836065573770492, "percentage": 4.92, "elapsed_time": "0:04:47", "remaining_time": "1:32:29"}
25
+ {"current_steps": 25, "total_steps": 488, "loss": 0.4415, "lr": 5.102040816326531e-05, "epoch": 0.10245901639344263, "percentage": 5.12, "elapsed_time": "0:04:58", "remaining_time": "1:32:14"}
26
+ {"current_steps": 26, "total_steps": 488, "loss": 0.4785, "lr": 5.3061224489795926e-05, "epoch": 0.10655737704918032, "percentage": 5.33, "elapsed_time": "0:05:10", "remaining_time": "1:31:56"}
27
+ {"current_steps": 27, "total_steps": 488, "loss": 0.4654, "lr": 5.510204081632653e-05, "epoch": 0.11065573770491803, "percentage": 5.53, "elapsed_time": "0:05:22", "remaining_time": "1:31:42"}
28
+ {"current_steps": 28, "total_steps": 488, "loss": 0.3948, "lr": 5.714285714285714e-05, "epoch": 0.11475409836065574, "percentage": 5.74, "elapsed_time": "0:05:34", "remaining_time": "1:31:27"}
29
+ {"current_steps": 29, "total_steps": 488, "loss": 0.3919, "lr": 5.918367346938776e-05, "epoch": 0.11885245901639344, "percentage": 5.94, "elapsed_time": "0:05:45", "remaining_time": "1:31:13"}
30
+ {"current_steps": 30, "total_steps": 488, "loss": 0.3686, "lr": 6.122448979591838e-05, "epoch": 0.12295081967213115, "percentage": 6.15, "elapsed_time": "0:05:57", "remaining_time": "1:30:57"}
31
+ {"current_steps": 31, "total_steps": 488, "loss": 0.3657, "lr": 6.326530612244899e-05, "epoch": 0.12704918032786885, "percentage": 6.35, "elapsed_time": "0:06:09", "remaining_time": "1:30:43"}
32
+ {"current_steps": 32, "total_steps": 488, "loss": 0.3603, "lr": 6.530612244897959e-05, "epoch": 0.13114754098360656, "percentage": 6.56, "elapsed_time": "0:06:21", "remaining_time": "1:30:33"}
33
+ {"current_steps": 33, "total_steps": 488, "loss": 0.3936, "lr": 6.73469387755102e-05, "epoch": 0.13524590163934427, "percentage": 6.76, "elapsed_time": "0:06:33", "remaining_time": "1:30:19"}
34
+ {"current_steps": 34, "total_steps": 488, "loss": 0.3886, "lr": 6.938775510204082e-05, "epoch": 0.13934426229508196, "percentage": 6.97, "elapsed_time": "0:06:44", "remaining_time": "1:30:07"}
35
+ {"current_steps": 35, "total_steps": 488, "loss": 0.3437, "lr": 7.142857142857143e-05, "epoch": 0.14344262295081966, "percentage": 7.17, "elapsed_time": "0:06:56", "remaining_time": "1:29:53"}
36
+ {"current_steps": 36, "total_steps": 488, "loss": 0.3732, "lr": 7.346938775510205e-05, "epoch": 0.14754098360655737, "percentage": 7.38, "elapsed_time": "0:07:08", "remaining_time": "1:29:40"}
37
+ {"current_steps": 37, "total_steps": 488, "loss": 0.3843, "lr": 7.551020408163266e-05, "epoch": 0.15163934426229508, "percentage": 7.58, "elapsed_time": "0:07:20", "remaining_time": "1:29:27"}
38
+ {"current_steps": 38, "total_steps": 488, "loss": 0.3499, "lr": 7.755102040816327e-05, "epoch": 0.1557377049180328, "percentage": 7.79, "elapsed_time": "0:07:32", "remaining_time": "1:29:14"}
39
+ {"current_steps": 39, "total_steps": 488, "loss": 0.3199, "lr": 7.959183673469388e-05, "epoch": 0.1598360655737705, "percentage": 7.99, "elapsed_time": "0:07:44", "remaining_time": "1:29:04"}
40
+ {"current_steps": 40, "total_steps": 488, "loss": 0.3394, "lr": 8.163265306122449e-05, "epoch": 0.16393442622950818, "percentage": 8.2, "elapsed_time": "0:07:55", "remaining_time": "1:28:50"}
41
+ {"current_steps": 41, "total_steps": 488, "loss": 0.3431, "lr": 8.367346938775511e-05, "epoch": 0.1680327868852459, "percentage": 8.4, "elapsed_time": "0:08:07", "remaining_time": "1:28:36"}
42
+ {"current_steps": 42, "total_steps": 488, "loss": 0.3199, "lr": 8.571428571428571e-05, "epoch": 0.1721311475409836, "percentage": 8.61, "elapsed_time": "0:08:19", "remaining_time": "1:28:23"}
43
+ {"current_steps": 43, "total_steps": 488, "loss": 0.2775, "lr": 8.775510204081632e-05, "epoch": 0.1762295081967213, "percentage": 8.81, "elapsed_time": "0:08:31", "remaining_time": "1:28:10"}
44
+ {"current_steps": 44, "total_steps": 488, "loss": 0.3086, "lr": 8.979591836734695e-05, "epoch": 0.18032786885245902, "percentage": 9.02, "elapsed_time": "0:08:43", "remaining_time": "1:27:57"}
45
+ {"current_steps": 45, "total_steps": 488, "loss": 0.2814, "lr": 9.183673469387756e-05, "epoch": 0.18442622950819673, "percentage": 9.22, "elapsed_time": "0:08:54", "remaining_time": "1:27:44"}
46
+ {"current_steps": 46, "total_steps": 488, "loss": 0.3394, "lr": 9.387755102040817e-05, "epoch": 0.1885245901639344, "percentage": 9.43, "elapsed_time": "0:09:06", "remaining_time": "1:27:31"}
47
+ {"current_steps": 47, "total_steps": 488, "loss": 0.2795, "lr": 9.591836734693878e-05, "epoch": 0.19262295081967212, "percentage": 9.63, "elapsed_time": "0:09:18", "remaining_time": "1:27:18"}
48
+ {"current_steps": 48, "total_steps": 488, "loss": 0.2901, "lr": 9.79591836734694e-05, "epoch": 0.19672131147540983, "percentage": 9.84, "elapsed_time": "0:09:30", "remaining_time": "1:27:07"}
49
+ {"current_steps": 49, "total_steps": 488, "loss": 0.2772, "lr": 0.0001, "epoch": 0.20081967213114754, "percentage": 10.04, "elapsed_time": "0:09:42", "remaining_time": "1:26:54"}
50
+ {"current_steps": 50, "total_steps": 488, "loss": 0.2801, "lr": 9.999871970850594e-05, "epoch": 0.20491803278688525, "percentage": 10.25, "elapsed_time": "0:09:53", "remaining_time": "1:26:42"}
51
+ {"current_steps": 51, "total_steps": 488, "loss": 0.2908, "lr": 9.99948788995896e-05, "epoch": 0.20901639344262296, "percentage": 10.45, "elapsed_time": "0:10:05", "remaining_time": "1:26:30"}
52
+ {"current_steps": 52, "total_steps": 488, "loss": 0.2662, "lr": 9.998847776994521e-05, "epoch": 0.21311475409836064, "percentage": 10.66, "elapsed_time": "0:10:17", "remaining_time": "1:26:17"}
53
+ {"current_steps": 53, "total_steps": 488, "loss": 0.3133, "lr": 9.99795166473852e-05, "epoch": 0.21721311475409835, "percentage": 10.86, "elapsed_time": "0:10:29", "remaining_time": "1:26:03"}
54
+ {"current_steps": 54, "total_steps": 488, "loss": 0.2974, "lr": 9.996799599082358e-05, "epoch": 0.22131147540983606, "percentage": 11.07, "elapsed_time": "0:10:40", "remaining_time": "1:25:50"}
55
+ {"current_steps": 55, "total_steps": 488, "loss": 0.251, "lr": 9.995391639025224e-05, "epoch": 0.22540983606557377, "percentage": 11.27, "elapsed_time": "0:10:52", "remaining_time": "1:25:38"}
56
+ {"current_steps": 56, "total_steps": 488, "loss": 0.2477, "lr": 9.993727856671093e-05, "epoch": 0.22950819672131148, "percentage": 11.48, "elapsed_time": "0:11:04", "remaining_time": "1:25:26"}
57
+ {"current_steps": 57, "total_steps": 488, "loss": 0.2493, "lr": 9.99180833722502e-05, "epoch": 0.2336065573770492, "percentage": 11.68, "elapsed_time": "0:11:16", "remaining_time": "1:25:13"}
58
+ {"current_steps": 58, "total_steps": 488, "loss": 0.263, "lr": 9.989633178988782e-05, "epoch": 0.23770491803278687, "percentage": 11.89, "elapsed_time": "0:11:28", "remaining_time": "1:25:01"}
59
+ {"current_steps": 59, "total_steps": 488, "loss": 0.2326, "lr": 9.98720249335584e-05, "epoch": 0.24180327868852458, "percentage": 12.09, "elapsed_time": "0:11:39", "remaining_time": "1:24:48"}
60
+ {"current_steps": 60, "total_steps": 488, "loss": 0.2696, "lr": 9.984516404805643e-05, "epoch": 0.2459016393442623, "percentage": 12.3, "elapsed_time": "0:11:51", "remaining_time": "1:24:35"}
61
+ {"current_steps": 61, "total_steps": 488, "loss": 0.2272, "lr": 9.981575050897245e-05, "epoch": 0.25, "percentage": 12.5, "elapsed_time": "0:12:03", "remaining_time": "1:24:23"}
62
+ {"current_steps": 62, "total_steps": 488, "loss": 0.2277, "lr": 9.978378582262258e-05, "epoch": 0.2540983606557377, "percentage": 12.7, "elapsed_time": "0:12:14", "remaining_time": "1:24:10"}
63
+ {"current_steps": 63, "total_steps": 488, "loss": 0.2222, "lr": 9.974927162597147e-05, "epoch": 0.2581967213114754, "percentage": 12.91, "elapsed_time": "0:12:26", "remaining_time": "1:23:57"}
64
+ {"current_steps": 64, "total_steps": 488, "loss": 0.2147, "lr": 9.971220968654842e-05, "epoch": 0.26229508196721313, "percentage": 13.11, "elapsed_time": "0:12:38", "remaining_time": "1:23:44"}
65
+ {"current_steps": 65, "total_steps": 488, "loss": 0.2395, "lr": 9.967260190235686e-05, "epoch": 0.26639344262295084, "percentage": 13.32, "elapsed_time": "0:12:50", "remaining_time": "1:23:32"}
66
+ {"current_steps": 66, "total_steps": 488, "loss": 0.191, "lr": 9.963045030177716e-05, "epoch": 0.27049180327868855, "percentage": 13.52, "elapsed_time": "0:13:02", "remaining_time": "1:23:20"}
67
+ {"current_steps": 67, "total_steps": 488, "loss": 0.2106, "lr": 9.958575704346275e-05, "epoch": 0.27459016393442626, "percentage": 13.73, "elapsed_time": "0:13:13", "remaining_time": "1:23:07"}
68
+ {"current_steps": 68, "total_steps": 488, "loss": 0.2045, "lr": 9.953852441622958e-05, "epoch": 0.2786885245901639, "percentage": 13.93, "elapsed_time": "0:13:25", "remaining_time": "1:22:55"}
69
+ {"current_steps": 69, "total_steps": 488, "loss": 0.2129, "lr": 9.948875483893885e-05, "epoch": 0.2827868852459016, "percentage": 14.14, "elapsed_time": "0:13:37", "remaining_time": "1:22:43"}
70
+ {"current_steps": 70, "total_steps": 488, "loss": 0.2115, "lr": 9.943645086037325e-05, "epoch": 0.28688524590163933, "percentage": 14.34, "elapsed_time": "0:13:49", "remaining_time": "1:22:30"}
71
+ {"current_steps": 71, "total_steps": 488, "loss": 0.2481, "lr": 9.938161515910633e-05, "epoch": 0.29098360655737704, "percentage": 14.55, "elapsed_time": "0:14:00", "remaining_time": "1:22:18"}
72
+ {"current_steps": 72, "total_steps": 488, "loss": 0.2177, "lr": 9.932425054336536e-05, "epoch": 0.29508196721311475, "percentage": 14.75, "elapsed_time": "0:14:12", "remaining_time": "1:22:06"}
73
+ {"current_steps": 73, "total_steps": 488, "loss": 0.1893, "lr": 9.926435995088751e-05, "epoch": 0.29918032786885246, "percentage": 14.96, "elapsed_time": "0:14:24", "remaining_time": "1:21:54"}
74
+ {"current_steps": 74, "total_steps": 488, "loss": 0.2272, "lr": 9.920194644876948e-05, "epoch": 0.30327868852459017, "percentage": 15.16, "elapsed_time": "0:14:36", "remaining_time": "1:21:42"}
75
+ {"current_steps": 75, "total_steps": 488, "loss": 0.1853, "lr": 9.913701323331024e-05, "epoch": 0.3073770491803279, "percentage": 15.37, "elapsed_time": "0:14:47", "remaining_time": "1:21:29"}
76
+ {"current_steps": 76, "total_steps": 488, "loss": 0.1728, "lr": 9.906956362984754e-05, "epoch": 0.3114754098360656, "percentage": 15.57, "elapsed_time": "0:14:59", "remaining_time": "1:21:17"}
77
+ {"current_steps": 77, "total_steps": 488, "loss": 0.1731, "lr": 9.899960109258755e-05, "epoch": 0.3155737704918033, "percentage": 15.78, "elapsed_time": "0:15:11", "remaining_time": "1:21:05"}
78
+ {"current_steps": 78, "total_steps": 488, "loss": 0.2246, "lr": 9.89271292044279e-05, "epoch": 0.319672131147541, "percentage": 15.98, "elapsed_time": "0:15:23", "remaining_time": "1:20:53"}
79
+ {"current_steps": 79, "total_steps": 488, "loss": 0.2027, "lr": 9.88521516767743e-05, "epoch": 0.3237704918032787, "percentage": 16.19, "elapsed_time": "0:15:34", "remaining_time": "1:20:40"}
80
+ {"current_steps": 80, "total_steps": 488, "loss": 0.2154, "lr": 9.877467234935035e-05, "epoch": 0.32786885245901637, "percentage": 16.39, "elapsed_time": "0:15:46", "remaining_time": "1:20:27"}
81
+ {"current_steps": 81, "total_steps": 488, "loss": 0.178, "lr": 9.869469519000103e-05, "epoch": 0.3319672131147541, "percentage": 16.6, "elapsed_time": "0:15:58", "remaining_time": "1:20:15"}
82
+ {"current_steps": 82, "total_steps": 488, "loss": 0.1973, "lr": 9.861222429448939e-05, "epoch": 0.3360655737704918, "percentage": 16.8, "elapsed_time": "0:16:10", "remaining_time": "1:20:03"}
83
+ {"current_steps": 83, "total_steps": 488, "loss": 0.1611, "lr": 9.852726388628689e-05, "epoch": 0.3401639344262295, "percentage": 17.01, "elapsed_time": "0:16:21", "remaining_time": "1:19:51"}
84
+ {"current_steps": 84, "total_steps": 488, "loss": 0.1885, "lr": 9.843981831635704e-05, "epoch": 0.3442622950819672, "percentage": 17.21, "elapsed_time": "0:16:33", "remaining_time": "1:19:39"}
85
+ {"current_steps": 85, "total_steps": 488, "loss": 0.1896, "lr": 9.834989206293264e-05, "epoch": 0.3483606557377049, "percentage": 17.42, "elapsed_time": "0:16:45", "remaining_time": "1:19:27"}
86
+ {"current_steps": 86, "total_steps": 488, "loss": 0.1811, "lr": 9.825748973128633e-05, "epoch": 0.3524590163934426, "percentage": 17.62, "elapsed_time": "0:16:57", "remaining_time": "1:19:15"}
87
+ {"current_steps": 87, "total_steps": 488, "loss": 0.1992, "lr": 9.816261605349493e-05, "epoch": 0.35655737704918034, "percentage": 17.83, "elapsed_time": "0:17:09", "remaining_time": "1:19:03"}
88
+ {"current_steps": 88, "total_steps": 488, "loss": 0.1956, "lr": 9.806527588819692e-05, "epoch": 0.36065573770491804, "percentage": 18.03, "elapsed_time": "0:17:20", "remaining_time": "1:18:51"}
89
+ {"current_steps": 89, "total_steps": 488, "loss": 0.1825, "lr": 9.796547422034374e-05, "epoch": 0.36475409836065575, "percentage": 18.24, "elapsed_time": "0:17:32", "remaining_time": "1:18:39"}
90
+ {"current_steps": 90, "total_steps": 488, "loss": 0.1749, "lr": 9.786321616094444e-05, "epoch": 0.36885245901639346, "percentage": 18.44, "elapsed_time": "0:17:44", "remaining_time": "1:18:27"}
91
+ {"current_steps": 91, "total_steps": 488, "loss": 0.1944, "lr": 9.775850694680397e-05, "epoch": 0.3729508196721312, "percentage": 18.65, "elapsed_time": "0:17:56", "remaining_time": "1:18:15"}
92
+ {"current_steps": 92, "total_steps": 488, "loss": 0.1771, "lr": 9.765135194025499e-05, "epoch": 0.3770491803278688, "percentage": 18.85, "elapsed_time": "0:18:07", "remaining_time": "1:18:02"}
93
+ {"current_steps": 93, "total_steps": 488, "loss": 0.1661, "lr": 9.754175662888321e-05, "epoch": 0.38114754098360654, "percentage": 19.06, "elapsed_time": "0:18:19", "remaining_time": "1:17:50"}
94
+ {"current_steps": 94, "total_steps": 488, "loss": 0.1981, "lr": 9.742972662524644e-05, "epoch": 0.38524590163934425, "percentage": 19.26, "elapsed_time": "0:18:31", "remaining_time": "1:17:38"}
95
+ {"current_steps": 95, "total_steps": 488, "loss": 0.1735, "lr": 9.731526766658712e-05, "epoch": 0.38934426229508196, "percentage": 19.47, "elapsed_time": "0:18:43", "remaining_time": "1:17:25"}
96
+ {"current_steps": 96, "total_steps": 488, "loss": 0.1582, "lr": 9.719838561453848e-05, "epoch": 0.39344262295081966, "percentage": 19.67, "elapsed_time": "0:18:54", "remaining_time": "1:17:13"}
97
+ {"current_steps": 97, "total_steps": 488, "loss": 0.18, "lr": 9.707908645482442e-05, "epoch": 0.3975409836065574, "percentage": 19.88, "elapsed_time": "0:19:06", "remaining_time": "1:17:01"}
98
+ {"current_steps": 98, "total_steps": 488, "loss": 0.158, "lr": 9.695737629695292e-05, "epoch": 0.4016393442622951, "percentage": 20.08, "elapsed_time": "0:19:18", "remaining_time": "1:16:49"}
99
+ {"current_steps": 99, "total_steps": 488, "loss": 0.1829, "lr": 9.683326137390314e-05, "epoch": 0.4057377049180328, "percentage": 20.29, "elapsed_time": "0:19:29", "remaining_time": "1:16:36"}
100
+ {"current_steps": 100, "total_steps": 488, "loss": 0.158, "lr": 9.670674804180633e-05, "epoch": 0.4098360655737705, "percentage": 20.49, "elapsed_time": "0:19:41", "remaining_time": "1:16:25"}
101
+ {"current_steps": 101, "total_steps": 488, "loss": 0.1912, "lr": 9.657784277962017e-05, "epoch": 0.4139344262295082, "percentage": 20.7, "elapsed_time": "0:19:53", "remaining_time": "1:16:12"}
102
+ {"current_steps": 102, "total_steps": 488, "loss": 0.1585, "lr": 9.644655218879713e-05, "epoch": 0.4180327868852459, "percentage": 20.9, "elapsed_time": "0:20:05", "remaining_time": "1:16:00"}
103
+ {"current_steps": 103, "total_steps": 488, "loss": 0.1642, "lr": 9.631288299294625e-05, "epoch": 0.42213114754098363, "percentage": 21.11, "elapsed_time": "0:20:16", "remaining_time": "1:15:48"}
104
+ {"current_steps": 104, "total_steps": 488, "loss": 0.1719, "lr": 9.617684203748894e-05, "epoch": 0.4262295081967213, "percentage": 21.31, "elapsed_time": "0:20:28", "remaining_time": "1:15:36"}
105
+ {"current_steps": 105, "total_steps": 488, "loss": 0.1366, "lr": 9.603843628930827e-05, "epoch": 0.430327868852459, "percentage": 21.52, "elapsed_time": "0:20:40", "remaining_time": "1:15:24"}
106
+ {"current_steps": 106, "total_steps": 488, "loss": 0.1484, "lr": 9.589767283639238e-05, "epoch": 0.4344262295081967, "percentage": 21.72, "elapsed_time": "0:20:52", "remaining_time": "1:15:13"}
107
+ {"current_steps": 107, "total_steps": 488, "loss": 0.1426, "lr": 9.575455888747129e-05, "epoch": 0.4385245901639344, "percentage": 21.93, "elapsed_time": "0:21:04", "remaining_time": "1:15:01"}
108
+ {"current_steps": 108, "total_steps": 488, "loss": 0.1442, "lr": 9.560910177164788e-05, "epoch": 0.4426229508196721, "percentage": 22.13, "elapsed_time": "0:21:15", "remaining_time": "1:14:49"}
109
+ {"current_steps": 109, "total_steps": 488, "loss": 0.1495, "lr": 9.546130893802246e-05, "epoch": 0.44672131147540983, "percentage": 22.34, "elapsed_time": "0:21:27", "remaining_time": "1:14:37"}
110
+ {"current_steps": 110, "total_steps": 488, "loss": 0.1395, "lr": 9.531118795531136e-05, "epoch": 0.45081967213114754, "percentage": 22.54, "elapsed_time": "0:21:39", "remaining_time": "1:14:25"}
111
+ {"current_steps": 111, "total_steps": 488, "loss": 0.1871, "lr": 9.515874651145926e-05, "epoch": 0.45491803278688525, "percentage": 22.75, "elapsed_time": "0:21:51", "remaining_time": "1:14:13"}
112
+ {"current_steps": 112, "total_steps": 488, "loss": 0.1634, "lr": 9.50039924132455e-05, "epoch": 0.45901639344262296, "percentage": 22.95, "elapsed_time": "0:22:02", "remaining_time": "1:14:01"}
113
+ {"current_steps": 113, "total_steps": 488, "loss": 0.1819, "lr": 9.484693358588435e-05, "epoch": 0.46311475409836067, "percentage": 23.16, "elapsed_time": "0:22:14", "remaining_time": "1:13:49"}
114
+ {"current_steps": 114, "total_steps": 488, "loss": 0.1749, "lr": 9.468757807261899e-05, "epoch": 0.4672131147540984, "percentage": 23.36, "elapsed_time": "0:22:26", "remaining_time": "1:13:37"}
115
+ {"current_steps": 115, "total_steps": 488, "loss": 0.1856, "lr": 9.452593403430978e-05, "epoch": 0.4713114754098361, "percentage": 23.57, "elapsed_time": "0:22:38", "remaining_time": "1:13:25"}
116
+ {"current_steps": 116, "total_steps": 488, "loss": 0.1723, "lr": 9.436200974901619e-05, "epoch": 0.47540983606557374, "percentage": 23.77, "elapsed_time": "0:22:50", "remaining_time": "1:13:14"}
117
+ {"current_steps": 117, "total_steps": 488, "loss": 0.1927, "lr": 9.419581361157295e-05, "epoch": 0.47950819672131145, "percentage": 23.98, "elapsed_time": "0:23:02", "remaining_time": "1:13:02"}
118
+ {"current_steps": 118, "total_steps": 488, "loss": 0.1593, "lr": 9.402735413316012e-05, "epoch": 0.48360655737704916, "percentage": 24.18, "elapsed_time": "0:23:13", "remaining_time": "1:12:50"}
119
+ {"current_steps": 119, "total_steps": 488, "loss": 0.1463, "lr": 9.385663994086717e-05, "epoch": 0.48770491803278687, "percentage": 24.39, "elapsed_time": "0:23:25", "remaining_time": "1:12:38"}
120
+ {"current_steps": 120, "total_steps": 488, "loss": 0.1757, "lr": 9.368367977725126e-05, "epoch": 0.4918032786885246, "percentage": 24.59, "elapsed_time": "0:23:37", "remaining_time": "1:12:26"}
121
+ {"current_steps": 121, "total_steps": 488, "loss": 0.1488, "lr": 9.350848249988942e-05, "epoch": 0.4959016393442623, "percentage": 24.8, "elapsed_time": "0:23:49", "remaining_time": "1:12:14"}
122
+ {"current_steps": 122, "total_steps": 488, "loss": 0.1689, "lr": 9.333105708092499e-05, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:24:01", "remaining_time": "1:12:03"}
123
+ {"current_steps": 123, "total_steps": 488, "loss": 0.1389, "lr": 9.315141260660823e-05, "epoch": 0.5040983606557377, "percentage": 25.2, "elapsed_time": "0:24:12", "remaining_time": "1:11:51"}
124
+ {"current_steps": 124, "total_steps": 488, "loss": 0.1521, "lr": 9.296955827683075e-05, "epoch": 0.5081967213114754, "percentage": 25.41, "elapsed_time": "0:24:24", "remaining_time": "1:11:39"}
125
+ {"current_steps": 125, "total_steps": 488, "loss": 0.1717, "lr": 9.278550340465469e-05, "epoch": 0.5122950819672131, "percentage": 25.61, "elapsed_time": "0:24:36", "remaining_time": "1:11:27"}
126
+ {"current_steps": 126, "total_steps": 488, "loss": 0.1347, "lr": 9.259925741583549e-05, "epoch": 0.5163934426229508, "percentage": 25.82, "elapsed_time": "0:24:48", "remaining_time": "1:11:15"}
127
+ {"current_steps": 127, "total_steps": 488, "loss": 0.1378, "lr": 9.241082984833937e-05, "epoch": 0.5204918032786885, "percentage": 26.02, "elapsed_time": "0:25:00", "remaining_time": "1:11:04"}
128
+ {"current_steps": 128, "total_steps": 488, "loss": 0.1545, "lr": 9.222023035185481e-05, "epoch": 0.5245901639344263, "percentage": 26.23, "elapsed_time": "0:25:11", "remaining_time": "1:10:52"}
129
+ {"current_steps": 129, "total_steps": 488, "loss": 0.1502, "lr": 9.20274686872984e-05, "epoch": 0.5286885245901639, "percentage": 26.43, "elapsed_time": "0:25:23", "remaining_time": "1:10:40"}
130
+ {"current_steps": 130, "total_steps": 488, "loss": 0.1338, "lr": 9.183255472631486e-05, "epoch": 0.5327868852459017, "percentage": 26.64, "elapsed_time": "0:25:35", "remaining_time": "1:10:28"}
131
+ {"current_steps": 131, "total_steps": 488, "loss": 0.1671, "lr": 9.163549845077172e-05, "epoch": 0.5368852459016393, "percentage": 26.84, "elapsed_time": "0:25:47", "remaining_time": "1:10:16"}
132
+ {"current_steps": 132, "total_steps": 488, "loss": 0.1512, "lr": 9.143630995224785e-05, "epoch": 0.5409836065573771, "percentage": 27.05, "elapsed_time": "0:25:58", "remaining_time": "1:10:03"}
133
+ {"current_steps": 133, "total_steps": 488, "loss": 0.1565, "lr": 9.123499943151692e-05, "epoch": 0.5450819672131147, "percentage": 27.25, "elapsed_time": "0:26:10", "remaining_time": "1:09:52"}
134
+ {"current_steps": 134, "total_steps": 488, "loss": 0.153, "lr": 9.10315771980248e-05, "epoch": 0.5491803278688525, "percentage": 27.46, "elapsed_time": "0:26:22", "remaining_time": "1:09:40"}
135
+ {"current_steps": 135, "total_steps": 488, "loss": 0.1392, "lr": 9.082605366936168e-05, "epoch": 0.5532786885245902, "percentage": 27.66, "elapsed_time": "0:26:34", "remaining_time": "1:09:28"}
136
+ {"current_steps": 136, "total_steps": 488, "loss": 0.1677, "lr": 9.061843937072861e-05, "epoch": 0.5573770491803278, "percentage": 27.87, "elapsed_time": "0:26:45", "remaining_time": "1:09:16"}
137
+ {"current_steps": 137, "total_steps": 488, "loss": 0.1383, "lr": 9.040874493439839e-05, "epoch": 0.5614754098360656, "percentage": 28.07, "elapsed_time": "0:26:57", "remaining_time": "1:09:04"}
138
+ {"current_steps": 138, "total_steps": 488, "loss": 0.1668, "lr": 9.019698109917119e-05, "epoch": 0.5655737704918032, "percentage": 28.28, "elapsed_time": "0:27:09", "remaining_time": "1:08:52"}
139
+ {"current_steps": 139, "total_steps": 488, "loss": 0.1218, "lr": 8.998315870982444e-05, "epoch": 0.569672131147541, "percentage": 28.48, "elapsed_time": "0:27:21", "remaining_time": "1:08:41"}
140
+ {"current_steps": 140, "total_steps": 488, "loss": 0.1676, "lr": 8.976728871655762e-05, "epoch": 0.5737704918032787, "percentage": 28.69, "elapsed_time": "0:27:33", "remaining_time": "1:08:29"}
141
+ {"current_steps": 141, "total_steps": 488, "loss": 0.1437, "lr": 8.954938217443136e-05, "epoch": 0.5778688524590164, "percentage": 28.89, "elapsed_time": "0:27:44", "remaining_time": "1:08:17"}
142
+ {"current_steps": 142, "total_steps": 488, "loss": 0.1739, "lr": 8.932945024280139e-05, "epoch": 0.5819672131147541, "percentage": 29.1, "elapsed_time": "0:27:56", "remaining_time": "1:08:05"}
143
+ {"current_steps": 143, "total_steps": 488, "loss": 0.1537, "lr": 8.910750418474693e-05, "epoch": 0.5860655737704918, "percentage": 29.3, "elapsed_time": "0:28:08", "remaining_time": "1:07:53"}
144
+ {"current_steps": 144, "total_steps": 488, "loss": 0.1475, "lr": 8.8883555366494e-05, "epoch": 0.5901639344262295, "percentage": 29.51, "elapsed_time": "0:28:20", "remaining_time": "1:07:41"}
145
+ {"current_steps": 145, "total_steps": 488, "loss": 0.1733, "lr": 8.865761525683329e-05, "epoch": 0.5942622950819673, "percentage": 29.71, "elapsed_time": "0:28:32", "remaining_time": "1:07:29"}
146
+ {"current_steps": 146, "total_steps": 488, "loss": 0.1416, "lr": 8.842969542653281e-05, "epoch": 0.5983606557377049, "percentage": 29.92, "elapsed_time": "0:28:43", "remaining_time": "1:07:18"}
147
+ {"current_steps": 147, "total_steps": 488, "loss": 0.1408, "lr": 8.819980754774539e-05, "epoch": 0.6024590163934426, "percentage": 30.12, "elapsed_time": "0:28:55", "remaining_time": "1:07:06"}
148
+ {"current_steps": 148, "total_steps": 488, "loss": 0.1404, "lr": 8.796796339341083e-05, "epoch": 0.6065573770491803, "percentage": 30.33, "elapsed_time": "0:29:07", "remaining_time": "1:06:54"}
149
+ {"current_steps": 149, "total_steps": 488, "loss": 0.1442, "lr": 8.773417483665309e-05, "epoch": 0.610655737704918, "percentage": 30.53, "elapsed_time": "0:29:19", "remaining_time": "1:06:42"}
150
+ {"current_steps": 150, "total_steps": 488, "loss": 0.1373, "lr": 8.749845385017221e-05, "epoch": 0.6147540983606558, "percentage": 30.74, "elapsed_time": "0:29:30", "remaining_time": "1:06:30"}
151
+ {"current_steps": 151, "total_steps": 488, "loss": 0.1386, "lr": 8.726081250563114e-05, "epoch": 0.6188524590163934, "percentage": 30.94, "elapsed_time": "0:29:42", "remaining_time": "1:06:18"}
152
+ {"current_steps": 152, "total_steps": 488, "loss": 0.1563, "lr": 8.702126297303754e-05, "epoch": 0.6229508196721312, "percentage": 31.15, "elapsed_time": "0:29:54", "remaining_time": "1:06:06"}
153
+ {"current_steps": 153, "total_steps": 488, "loss": 0.1457, "lr": 8.677981752012061e-05, "epoch": 0.6270491803278688, "percentage": 31.35, "elapsed_time": "0:30:06", "remaining_time": "1:05:54"}
154
+ {"current_steps": 154, "total_steps": 488, "loss": 0.1451, "lr": 8.65364885117027e-05, "epoch": 0.6311475409836066, "percentage": 31.56, "elapsed_time": "0:30:18", "remaining_time": "1:05:43"}
155
+ {"current_steps": 155, "total_steps": 488, "loss": 0.1346, "lr": 8.629128840906622e-05, "epoch": 0.6352459016393442, "percentage": 31.76, "elapsed_time": "0:30:29", "remaining_time": "1:05:31"}
156
+ {"current_steps": 156, "total_steps": 488, "loss": 0.1447, "lr": 8.604422976931538e-05, "epoch": 0.639344262295082, "percentage": 31.97, "elapsed_time": "0:30:41", "remaining_time": "1:05:19"}
157
+ {"current_steps": 157, "total_steps": 488, "loss": 0.1274, "lr": 8.579532524473322e-05, "epoch": 0.6434426229508197, "percentage": 32.17, "elapsed_time": "0:30:53", "remaining_time": "1:05:07"}
158
+ {"current_steps": 158, "total_steps": 488, "loss": 0.1329, "lr": 8.554458758213352e-05, "epoch": 0.6475409836065574, "percentage": 32.38, "elapsed_time": "0:31:04", "remaining_time": "1:04:55"}
159
+ {"current_steps": 159, "total_steps": 488, "loss": 0.1361, "lr": 8.529202962220818e-05, "epoch": 0.6516393442622951, "percentage": 32.58, "elapsed_time": "0:31:16", "remaining_time": "1:04:43"}
160
+ {"current_steps": 160, "total_steps": 488, "loss": 0.1197, "lr": 8.50376642988695e-05, "epoch": 0.6557377049180327, "percentage": 32.79, "elapsed_time": "0:31:28", "remaining_time": "1:04:32"}
161
+ {"current_steps": 161, "total_steps": 488, "loss": 0.1593, "lr": 8.478150463858788e-05, "epoch": 0.6598360655737705, "percentage": 32.99, "elapsed_time": "0:31:40", "remaining_time": "1:04:20"}
162
+ {"current_steps": 162, "total_steps": 488, "loss": 0.1339, "lr": 8.452356375972466e-05, "epoch": 0.6639344262295082, "percentage": 33.2, "elapsed_time": "0:31:52", "remaining_time": "1:04:08"}
163
+ {"current_steps": 163, "total_steps": 488, "loss": 0.1658, "lr": 8.42638548718604e-05, "epoch": 0.6680327868852459, "percentage": 33.4, "elapsed_time": "0:32:04", "remaining_time": "1:03:56"}
164
+ {"current_steps": 164, "total_steps": 488, "loss": 0.1391, "lr": 8.40023912751183e-05, "epoch": 0.6721311475409836, "percentage": 33.61, "elapsed_time": "0:32:15", "remaining_time": "1:03:44"}
165
+ {"current_steps": 165, "total_steps": 488, "loss": 0.1332, "lr": 8.373918635948311e-05, "epoch": 0.6762295081967213, "percentage": 33.81, "elapsed_time": "0:32:27", "remaining_time": "1:03:32"}
166
+ {"current_steps": 166, "total_steps": 488, "loss": 0.1263, "lr": 8.34742536041154e-05, "epoch": 0.680327868852459, "percentage": 34.02, "elapsed_time": "0:32:39", "remaining_time": "1:03:21"}
167
+ {"current_steps": 167, "total_steps": 488, "loss": 0.1278, "lr": 8.320760657666133e-05, "epoch": 0.6844262295081968, "percentage": 34.22, "elapsed_time": "0:32:51", "remaining_time": "1:03:09"}
168
+ {"current_steps": 168, "total_steps": 488, "loss": 0.1336, "lr": 8.293925893255771e-05, "epoch": 0.6885245901639344, "percentage": 34.43, "elapsed_time": "0:33:03", "remaining_time": "1:02:57"}
169
+ {"current_steps": 169, "total_steps": 488, "loss": 0.1453, "lr": 8.266922441433284e-05, "epoch": 0.6926229508196722, "percentage": 34.63, "elapsed_time": "0:33:14", "remaining_time": "1:02:45"}
170
+ {"current_steps": 170, "total_steps": 488, "loss": 0.1139, "lr": 8.239751685090253e-05, "epoch": 0.6967213114754098, "percentage": 34.84, "elapsed_time": "0:33:26", "remaining_time": "1:02:33"}
171
+ {"current_steps": 171, "total_steps": 488, "loss": 0.1251, "lr": 8.212415015686213e-05, "epoch": 0.7008196721311475, "percentage": 35.04, "elapsed_time": "0:33:38", "remaining_time": "1:02:21"}
172
+ {"current_steps": 172, "total_steps": 488, "loss": 0.1569, "lr": 8.184913833177372e-05, "epoch": 0.7049180327868853, "percentage": 35.25, "elapsed_time": "0:33:50", "remaining_time": "1:02:10"}
173
+ {"current_steps": 173, "total_steps": 488, "loss": 0.1519, "lr": 8.157249545944934e-05, "epoch": 0.7090163934426229, "percentage": 35.45, "elapsed_time": "0:34:02", "remaining_time": "1:01:58"}
174
+ {"current_steps": 174, "total_steps": 488, "loss": 0.1338, "lr": 8.129423570722964e-05, "epoch": 0.7131147540983607, "percentage": 35.66, "elapsed_time": "0:34:13", "remaining_time": "1:01:46"}
175
+ {"current_steps": 175, "total_steps": 488, "loss": 0.1359, "lr": 8.101437332525837e-05, "epoch": 0.7172131147540983, "percentage": 35.86, "elapsed_time": "0:34:25", "remaining_time": "1:01:34"}
176
+ {"current_steps": 176, "total_steps": 488, "loss": 0.1197, "lr": 8.073292264575263e-05, "epoch": 0.7213114754098361, "percentage": 36.07, "elapsed_time": "0:34:37", "remaining_time": "1:01:22"}
177
+ {"current_steps": 177, "total_steps": 488, "loss": 0.1183, "lr": 8.044989808226885e-05, "epoch": 0.7254098360655737, "percentage": 36.27, "elapsed_time": "0:34:49", "remaining_time": "1:01:10"}
178
+ {"current_steps": 178, "total_steps": 488, "loss": 0.1372, "lr": 8.016531412896468e-05, "epoch": 0.7295081967213115, "percentage": 36.48, "elapsed_time": "0:35:00", "remaining_time": "1:00:58"}
179
+ {"current_steps": 179, "total_steps": 488, "loss": 0.1214, "lr": 7.98791853598567e-05, "epoch": 0.7336065573770492, "percentage": 36.68, "elapsed_time": "0:35:12", "remaining_time": "1:00:46"}
180
+ {"current_steps": 180, "total_steps": 488, "loss": 0.1364, "lr": 7.959152642807411e-05, "epoch": 0.7377049180327869, "percentage": 36.89, "elapsed_time": "0:35:24", "remaining_time": "1:00:35"}
181
+ {"current_steps": 181, "total_steps": 488, "loss": 0.1209, "lr": 7.930235206510821e-05, "epoch": 0.7418032786885246, "percentage": 37.09, "elapsed_time": "0:35:36", "remaining_time": "1:00:23"}
182
+ {"current_steps": 182, "total_steps": 488, "loss": 0.1264, "lr": 7.901167708005812e-05, "epoch": 0.7459016393442623, "percentage": 37.3, "elapsed_time": "0:35:47", "remaining_time": "1:00:11"}
183
+ {"current_steps": 183, "total_steps": 488, "loss": 0.1287, "lr": 7.871951635887228e-05, "epoch": 0.75, "percentage": 37.5, "elapsed_time": "0:35:59", "remaining_time": "0:59:59"}
184
+ {"current_steps": 184, "total_steps": 488, "loss": 0.1268, "lr": 7.842588486358611e-05, "epoch": 0.7540983606557377, "percentage": 37.7, "elapsed_time": "0:36:11", "remaining_time": "0:59:47"}
185
+ {"current_steps": 185, "total_steps": 488, "loss": 0.149, "lr": 7.813079763155587e-05, "epoch": 0.7581967213114754, "percentage": 37.91, "elapsed_time": "0:36:23", "remaining_time": "0:59:35"}
186
+ {"current_steps": 186, "total_steps": 488, "loss": 0.1154, "lr": 7.783426977468847e-05, "epoch": 0.7622950819672131, "percentage": 38.11, "elapsed_time": "0:36:34", "remaining_time": "0:59:23"}
187
+ {"current_steps": 187, "total_steps": 488, "loss": 0.1287, "lr": 7.753631647866764e-05, "epoch": 0.7663934426229508, "percentage": 38.32, "elapsed_time": "0:36:46", "remaining_time": "0:59:12"}
188
+ {"current_steps": 188, "total_steps": 488, "loss": 0.1442, "lr": 7.723695300217619e-05, "epoch": 0.7704918032786885, "percentage": 38.52, "elapsed_time": "0:36:58", "remaining_time": "0:59:00"}
189
+ {"current_steps": 189, "total_steps": 488, "loss": 0.1122, "lr": 7.693619467611464e-05, "epoch": 0.7745901639344263, "percentage": 38.73, "elapsed_time": "0:37:10", "remaining_time": "0:58:48"}
190
+ {"current_steps": 190, "total_steps": 488, "loss": 0.1434, "lr": 7.663405690281602e-05, "epoch": 0.7786885245901639, "percentage": 38.93, "elapsed_time": "0:37:22", "remaining_time": "0:58:36"}
191
+ {"current_steps": 191, "total_steps": 488, "loss": 0.1387, "lr": 7.633055515525721e-05, "epoch": 0.7827868852459017, "percentage": 39.14, "elapsed_time": "0:37:33", "remaining_time": "0:58:24"}
192
+ {"current_steps": 192, "total_steps": 488, "loss": 0.1247, "lr": 7.602570497626641e-05, "epoch": 0.7868852459016393, "percentage": 39.34, "elapsed_time": "0:37:45", "remaining_time": "0:58:12"}
193
+ {"current_steps": 193, "total_steps": 488, "loss": 0.1346, "lr": 7.571952197772733e-05, "epoch": 0.7909836065573771, "percentage": 39.55, "elapsed_time": "0:37:57", "remaining_time": "0:58:00"}
194
+ {"current_steps": 194, "total_steps": 488, "loss": 0.1343, "lr": 7.541202183977944e-05, "epoch": 0.7950819672131147, "percentage": 39.75, "elapsed_time": "0:38:09", "remaining_time": "0:57:49"}
195
+ {"current_steps": 195, "total_steps": 488, "loss": 0.1403, "lr": 7.510322031001523e-05, "epoch": 0.7991803278688525, "percentage": 39.96, "elapsed_time": "0:38:20", "remaining_time": "0:57:37"}
196
+ {"current_steps": 196, "total_steps": 488, "loss": 0.1203, "lr": 7.479313320267356e-05, "epoch": 0.8032786885245902, "percentage": 40.16, "elapsed_time": "0:38:32", "remaining_time": "0:57:25"}
197
+ {"current_steps": 197, "total_steps": 488, "loss": 0.1021, "lr": 7.448177639782988e-05, "epoch": 0.8073770491803278, "percentage": 40.37, "elapsed_time": "0:38:44", "remaining_time": "0:57:13"}
198
+ {"current_steps": 198, "total_steps": 488, "loss": 0.1324, "lr": 7.416916584058291e-05, "epoch": 0.8114754098360656, "percentage": 40.57, "elapsed_time": "0:38:56", "remaining_time": "0:57:01"}
199
+ {"current_steps": 199, "total_steps": 488, "loss": 0.1246, "lr": 7.385531754023818e-05, "epoch": 0.8155737704918032, "percentage": 40.78, "elapsed_time": "0:39:08", "remaining_time": "0:56:50"}
200
+ {"current_steps": 200, "total_steps": 488, "loss": 0.1143, "lr": 7.354024756948805e-05, "epoch": 0.819672131147541, "percentage": 40.98, "elapsed_time": "0:39:19", "remaining_time": "0:56:38"}
201
+ {"current_steps": 200, "total_steps": 488, "eval_loss": 0.13085269927978516, "epoch": 0.819672131147541, "percentage": 40.98, "elapsed_time": "0:39:35", "remaining_time": "0:57:01"}
202
+ {"current_steps": 201, "total_steps": 488, "loss": 0.1242, "lr": 7.322397206358868e-05, "epoch": 0.8237704918032787, "percentage": 41.19, "elapsed_time": "0:39:47", "remaining_time": "0:56:49"}
203
+ {"current_steps": 202, "total_steps": 488, "loss": 0.1102, "lr": 7.290650721953365e-05, "epoch": 0.8278688524590164, "percentage": 41.39, "elapsed_time": "0:39:59", "remaining_time": "0:56:36"}
204
+ {"current_steps": 203, "total_steps": 488, "loss": 0.1402, "lr": 7.258786929522454e-05, "epoch": 0.8319672131147541, "percentage": 41.6, "elapsed_time": "0:40:11", "remaining_time": "0:56:24"}
205
+ {"current_steps": 204, "total_steps": 488, "loss": 0.1188, "lr": 7.226807460863834e-05, "epoch": 0.8360655737704918, "percentage": 41.8, "elapsed_time": "0:40:22", "remaining_time": "0:56:12"}
206
+ {"current_steps": 205, "total_steps": 488, "loss": 0.1271, "lr": 7.194713953699171e-05, "epoch": 0.8401639344262295, "percentage": 42.01, "elapsed_time": "0:40:34", "remaining_time": "0:56:00"}
207
+ {"current_steps": 206, "total_steps": 488, "loss": 0.1391, "lr": 7.162508051590236e-05, "epoch": 0.8442622950819673, "percentage": 42.21, "elapsed_time": "0:40:46", "remaining_time": "0:55:48"}
208
+ {"current_steps": 207, "total_steps": 488, "loss": 0.1153, "lr": 7.130191403854728e-05, "epoch": 0.8483606557377049, "percentage": 42.42, "elapsed_time": "0:40:58", "remaining_time": "0:55:37"}
209
+ {"current_steps": 208, "total_steps": 488, "loss": 0.1227, "lr": 7.097765665481818e-05, "epoch": 0.8524590163934426, "percentage": 42.62, "elapsed_time": "0:41:09", "remaining_time": "0:55:24"}
210
+ {"current_steps": 209, "total_steps": 488, "loss": 0.1144, "lr": 7.065232497047384e-05, "epoch": 0.8565573770491803, "percentage": 42.83, "elapsed_time": "0:41:21", "remaining_time": "0:55:12"}
211
+ {"current_steps": 210, "total_steps": 488, "loss": 0.1199, "lr": 7.032593564628982e-05, "epoch": 0.860655737704918, "percentage": 43.03, "elapsed_time": "0:41:33", "remaining_time": "0:55:00"}
212
+ {"current_steps": 211, "total_steps": 488, "loss": 0.1183, "lr": 6.999850539720514e-05, "epoch": 0.8647540983606558, "percentage": 43.24, "elapsed_time": "0:41:45", "remaining_time": "0:54:48"}
213
+ {"current_steps": 212, "total_steps": 488, "loss": 0.1342, "lr": 6.967005099146629e-05, "epoch": 0.8688524590163934, "percentage": 43.44, "elapsed_time": "0:41:56", "remaining_time": "0:54:36"}
214
+ {"current_steps": 213, "total_steps": 488, "loss": 0.1171, "lr": 6.934058924976855e-05, "epoch": 0.8729508196721312, "percentage": 43.65, "elapsed_time": "0:42:08", "remaining_time": "0:54:24"}
215
+ {"current_steps": 214, "total_steps": 488, "loss": 0.1339, "lr": 6.901013704439456e-05, "epoch": 0.8770491803278688, "percentage": 43.85, "elapsed_time": "0:42:20", "remaining_time": "0:54:12"}
216
+ {"current_steps": 215, "total_steps": 488, "loss": 0.1251, "lr": 6.86787112983502e-05, "epoch": 0.8811475409836066, "percentage": 44.06, "elapsed_time": "0:42:32", "remaining_time": "0:54:00"}
217
+ {"current_steps": 216, "total_steps": 488, "loss": 0.1516, "lr": 6.834632898449804e-05, "epoch": 0.8852459016393442, "percentage": 44.26, "elapsed_time": "0:42:44", "remaining_time": "0:53:48"}
218
+ {"current_steps": 217, "total_steps": 488, "loss": 0.1158, "lr": 6.801300712468802e-05, "epoch": 0.889344262295082, "percentage": 44.47, "elapsed_time": "0:42:55", "remaining_time": "0:53:36"}
219
+ {"current_steps": 218, "total_steps": 488, "loss": 0.134, "lr": 6.767876278888585e-05, "epoch": 0.8934426229508197, "percentage": 44.67, "elapsed_time": "0:43:07", "remaining_time": "0:53:24"}
220
+ {"current_steps": 219, "total_steps": 488, "loss": 0.1277, "lr": 6.734361309429871e-05, "epoch": 0.8975409836065574, "percentage": 44.88, "elapsed_time": "0:43:19", "remaining_time": "0:53:12"}
221
+ {"current_steps": 220, "total_steps": 488, "loss": 0.104, "lr": 6.700757520449873e-05, "epoch": 0.9016393442622951, "percentage": 45.08, "elapsed_time": "0:43:31", "remaining_time": "0:53:00"}
222
+ {"current_steps": 221, "total_steps": 488, "loss": 0.1405, "lr": 6.6670666328544e-05, "epoch": 0.9057377049180327, "percentage": 45.29, "elapsed_time": "0:43:42", "remaining_time": "0:52:48"}
223
+ {"current_steps": 222, "total_steps": 488, "loss": 0.119, "lr": 6.633290372009722e-05, "epoch": 0.9098360655737705, "percentage": 45.49, "elapsed_time": "0:43:54", "remaining_time": "0:52:36"}
224
+ {"current_steps": 223, "total_steps": 488, "loss": 0.1426, "lr": 6.599430467654222e-05, "epoch": 0.9139344262295082, "percentage": 45.7, "elapsed_time": "0:44:06", "remaining_time": "0:52:24"}
225
+ {"current_steps": 224, "total_steps": 488, "loss": 0.1241, "lr": 6.565488653809797e-05, "epoch": 0.9180327868852459, "percentage": 45.9, "elapsed_time": "0:44:18", "remaining_time": "0:52:12"}
226
+ {"current_steps": 225, "total_steps": 488, "loss": 0.1217, "lr": 6.531466668693071e-05, "epoch": 0.9221311475409836, "percentage": 46.11, "elapsed_time": "0:44:29", "remaining_time": "0:52:00"}
227
+ {"current_steps": 226, "total_steps": 488, "loss": 0.1444, "lr": 6.497366254626372e-05, "epoch": 0.9262295081967213, "percentage": 46.31, "elapsed_time": "0:44:41", "remaining_time": "0:51:48"}
228
+ {"current_steps": 227, "total_steps": 488, "loss": 0.1157, "lr": 6.463189157948499e-05, "epoch": 0.930327868852459, "percentage": 46.52, "elapsed_time": "0:44:53", "remaining_time": "0:51:36"}
229
+ {"current_steps": 228, "total_steps": 488, "loss": 0.1137, "lr": 6.428937128925303e-05, "epoch": 0.9344262295081968, "percentage": 46.72, "elapsed_time": "0:45:05", "remaining_time": "0:51:25"}
230
+ {"current_steps": 229, "total_steps": 488, "loss": 0.1142, "lr": 6.394611921660036e-05, "epoch": 0.9385245901639344, "percentage": 46.93, "elapsed_time": "0:45:17", "remaining_time": "0:51:13"}
231
+ {"current_steps": 230, "total_steps": 488, "loss": 0.1147, "lr": 6.360215294003538e-05, "epoch": 0.9426229508196722, "percentage": 47.13, "elapsed_time": "0:45:28", "remaining_time": "0:51:00"}
232
+ {"current_steps": 231, "total_steps": 488, "loss": 0.1285, "lr": 6.325749007464201e-05, "epoch": 0.9467213114754098, "percentage": 47.34, "elapsed_time": "0:45:40", "remaining_time": "0:50:48"}
233
+ {"current_steps": 232, "total_steps": 488, "loss": 0.1502, "lr": 6.291214827117761e-05, "epoch": 0.9508196721311475, "percentage": 47.54, "elapsed_time": "0:45:52", "remaining_time": "0:50:37"}
234
+ {"current_steps": 233, "total_steps": 488, "loss": 0.1349, "lr": 6.256614521516915e-05, "epoch": 0.9549180327868853, "percentage": 47.75, "elapsed_time": "0:46:04", "remaining_time": "0:50:25"}
235
+ {"current_steps": 234, "total_steps": 488, "loss": 0.1453, "lr": 6.221949862600741e-05, "epoch": 0.9590163934426229, "percentage": 47.95, "elapsed_time": "0:46:15", "remaining_time": "0:50:13"}
236
+ {"current_steps": 235, "total_steps": 488, "loss": 0.1193, "lr": 6.187222625603957e-05, "epoch": 0.9631147540983607, "percentage": 48.16, "elapsed_time": "0:46:27", "remaining_time": "0:50:01"}
237
+ {"current_steps": 236, "total_steps": 488, "loss": 0.1391, "lr": 6.15243458896601e-05, "epoch": 0.9672131147540983, "percentage": 48.36, "elapsed_time": "0:46:39", "remaining_time": "0:49:49"}
238
+ {"current_steps": 237, "total_steps": 488, "loss": 0.1117, "lr": 6.117587534239992e-05, "epoch": 0.9713114754098361, "percentage": 48.57, "elapsed_time": "0:46:51", "remaining_time": "0:49:37"}
239
+ {"current_steps": 238, "total_steps": 488, "loss": 0.1252, "lr": 6.082683246001416e-05, "epoch": 0.9754098360655737, "percentage": 48.77, "elapsed_time": "0:47:02", "remaining_time": "0:49:25"}
240
+ {"current_steps": 239, "total_steps": 488, "loss": 0.1282, "lr": 6.047723511756815e-05, "epoch": 0.9795081967213115, "percentage": 48.98, "elapsed_time": "0:47:14", "remaining_time": "0:49:13"}
241
+ {"current_steps": 240, "total_steps": 488, "loss": 0.1341, "lr": 6.012710121852205e-05, "epoch": 0.9836065573770492, "percentage": 49.18, "elapsed_time": "0:47:26", "remaining_time": "0:49:01"}
242
+ {"current_steps": 241, "total_steps": 488, "loss": 0.1249, "lr": 5.977644869381398e-05, "epoch": 0.9877049180327869, "percentage": 49.39, "elapsed_time": "0:47:38", "remaining_time": "0:48:49"}
243
+ {"current_steps": 242, "total_steps": 488, "loss": 0.1093, "lr": 5.9425295500941704e-05, "epoch": 0.9918032786885246, "percentage": 49.59, "elapsed_time": "0:47:50", "remaining_time": "0:48:37"}
244
+ {"current_steps": 243, "total_steps": 488, "loss": 0.1183, "lr": 5.907365962304308e-05, "epoch": 0.9959016393442623, "percentage": 49.8, "elapsed_time": "0:48:01", "remaining_time": "0:48:25"}
245
+ {"current_steps": 244, "total_steps": 488, "loss": 0.109, "lr": 5.872155906797503e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:48:13", "remaining_time": "0:48:13"}
246
+ {"current_steps": 245, "total_steps": 488, "loss": 0.0887, "lr": 5.83690118673914e-05, "epoch": 1.0040983606557377, "percentage": 50.2, "elapsed_time": "0:48:25", "remaining_time": "0:48:01"}
247
+ {"current_steps": 246, "total_steps": 488, "loss": 0.0734, "lr": 5.801603607581947e-05, "epoch": 1.0081967213114753, "percentage": 50.41, "elapsed_time": "0:48:37", "remaining_time": "0:47:49"}
248
+ {"current_steps": 247, "total_steps": 488, "loss": 0.0823, "lr": 5.766264976973538e-05, "epoch": 1.0122950819672132, "percentage": 50.61, "elapsed_time": "0:48:48", "remaining_time": "0:47:37"}
249
+ {"current_steps": 248, "total_steps": 488, "loss": 0.0866, "lr": 5.73088710466384e-05, "epoch": 1.0163934426229508, "percentage": 50.82, "elapsed_time": "0:49:00", "remaining_time": "0:47:25"}
250
+ {"current_steps": 249, "total_steps": 488, "loss": 0.0928, "lr": 5.695471802412413e-05, "epoch": 1.0204918032786885, "percentage": 51.02, "elapsed_time": "0:49:12", "remaining_time": "0:47:13"}
251
+ {"current_steps": 250, "total_steps": 488, "loss": 0.0804, "lr": 5.660020883895668e-05, "epoch": 1.0245901639344261, "percentage": 51.23, "elapsed_time": "0:49:24", "remaining_time": "0:47:01"}
252
+ {"current_steps": 251, "total_steps": 488, "loss": 0.0934, "lr": 5.6245361646139794e-05, "epoch": 1.028688524590164, "percentage": 51.43, "elapsed_time": "0:49:36", "remaining_time": "0:46:50"}
253
+ {"current_steps": 252, "total_steps": 488, "loss": 0.0921, "lr": 5.58901946179872e-05, "epoch": 1.0327868852459017, "percentage": 51.64, "elapsed_time": "0:49:47", "remaining_time": "0:46:38"}
254
+ {"current_steps": 253, "total_steps": 488, "loss": 0.0934, "lr": 5.553472594319189e-05, "epoch": 1.0368852459016393, "percentage": 51.84, "elapsed_time": "0:49:59", "remaining_time": "0:46:26"}
255
+ {"current_steps": 254, "total_steps": 488, "loss": 0.1117, "lr": 5.5178973825894706e-05, "epoch": 1.040983606557377, "percentage": 52.05, "elapsed_time": "0:50:11", "remaining_time": "0:46:14"}
256
+ {"current_steps": 255, "total_steps": 488, "loss": 0.1049, "lr": 5.482295648475203e-05, "epoch": 1.0450819672131149, "percentage": 52.25, "elapsed_time": "0:50:23", "remaining_time": "0:46:02"}
257
+ {"current_steps": 256, "total_steps": 488, "loss": 0.1146, "lr": 5.446669215200281e-05, "epoch": 1.0491803278688525, "percentage": 52.46, "elapsed_time": "0:50:34", "remaining_time": "0:45:50"}
258
+ {"current_steps": 257, "total_steps": 488, "loss": 0.0853, "lr": 5.411019907253482e-05, "epoch": 1.0532786885245902, "percentage": 52.66, "elapsed_time": "0:50:46", "remaining_time": "0:45:38"}
259
+ {"current_steps": 258, "total_steps": 488, "loss": 0.0916, "lr": 5.375349550295038e-05, "epoch": 1.0573770491803278, "percentage": 52.87, "elapsed_time": "0:50:58", "remaining_time": "0:45:26"}
260
+ {"current_steps": 259, "total_steps": 488, "loss": 0.0905, "lr": 5.339659971063132e-05, "epoch": 1.0614754098360655, "percentage": 53.07, "elapsed_time": "0:51:10", "remaining_time": "0:45:14"}
261
+ {"current_steps": 260, "total_steps": 488, "loss": 0.0837, "lr": 5.303952997280355e-05, "epoch": 1.0655737704918034, "percentage": 53.28, "elapsed_time": "0:51:21", "remaining_time": "0:45:02"}
262
+ {"current_steps": 261, "total_steps": 488, "loss": 0.0848, "lr": 5.268230457560095e-05, "epoch": 1.069672131147541, "percentage": 53.48, "elapsed_time": "0:51:33", "remaining_time": "0:44:50"}
263
+ {"current_steps": 262, "total_steps": 488, "loss": 0.0882, "lr": 5.232494181312906e-05, "epoch": 1.0737704918032787, "percentage": 53.69, "elapsed_time": "0:51:45", "remaining_time": "0:44:38"}
264
+ {"current_steps": 263, "total_steps": 488, "loss": 0.0886, "lr": 5.196745998652807e-05, "epoch": 1.0778688524590163, "percentage": 53.89, "elapsed_time": "0:51:57", "remaining_time": "0:44:26"}
265
+ {"current_steps": 264, "total_steps": 488, "loss": 0.1024, "lr": 5.160987740303564e-05, "epoch": 1.0819672131147542, "percentage": 54.1, "elapsed_time": "0:52:08", "remaining_time": "0:44:14"}
266
+ {"current_steps": 265, "total_steps": 488, "loss": 0.0803, "lr": 5.12522123750494e-05, "epoch": 1.0860655737704918, "percentage": 54.3, "elapsed_time": "0:52:20", "remaining_time": "0:44:02"}
267
+ {"current_steps": 266, "total_steps": 488, "loss": 0.0855, "lr": 5.0894483219189046e-05, "epoch": 1.0901639344262295, "percentage": 54.51, "elapsed_time": "0:52:32", "remaining_time": "0:43:50"}
268
+ {"current_steps": 267, "total_steps": 488, "loss": 0.0865, "lr": 5.053670825535842e-05, "epoch": 1.0942622950819672, "percentage": 54.71, "elapsed_time": "0:52:43", "remaining_time": "0:43:38"}
269
+ {"current_steps": 268, "total_steps": 488, "loss": 0.0954, "lr": 5.017890580580723e-05, "epoch": 1.098360655737705, "percentage": 54.92, "elapsed_time": "0:52:55", "remaining_time": "0:43:26"}
270
+ {"current_steps": 269, "total_steps": 488, "loss": 0.0861, "lr": 4.982109419419277e-05, "epoch": 1.1024590163934427, "percentage": 55.12, "elapsed_time": "0:53:07", "remaining_time": "0:43:14"}
271
+ {"current_steps": 270, "total_steps": 488, "loss": 0.0811, "lr": 4.946329174464158e-05, "epoch": 1.1065573770491803, "percentage": 55.33, "elapsed_time": "0:53:19", "remaining_time": "0:43:03"}
272
+ {"current_steps": 271, "total_steps": 488, "loss": 0.0738, "lr": 4.9105516780810946e-05, "epoch": 1.110655737704918, "percentage": 55.53, "elapsed_time": "0:53:30", "remaining_time": "0:42:51"}
273
+ {"current_steps": 272, "total_steps": 488, "loss": 0.1044, "lr": 4.8747787624950604e-05, "epoch": 1.1147540983606556, "percentage": 55.74, "elapsed_time": "0:53:42", "remaining_time": "0:42:39"}
274
+ {"current_steps": 273, "total_steps": 488, "loss": 0.0824, "lr": 4.8390122596964355e-05, "epoch": 1.1188524590163935, "percentage": 55.94, "elapsed_time": "0:53:54", "remaining_time": "0:42:27"}
275
+ {"current_steps": 274, "total_steps": 488, "loss": 0.0862, "lr": 4.803254001347193e-05, "epoch": 1.1229508196721312, "percentage": 56.15, "elapsed_time": "0:54:06", "remaining_time": "0:42:15"}
276
+ {"current_steps": 275, "total_steps": 488, "loss": 0.0907, "lr": 4.7675058186870944e-05, "epoch": 1.1270491803278688, "percentage": 56.35, "elapsed_time": "0:54:18", "remaining_time": "0:42:03"}
277
+ {"current_steps": 276, "total_steps": 488, "loss": 0.0932, "lr": 4.7317695424399044e-05, "epoch": 1.1311475409836065, "percentage": 56.56, "elapsed_time": "0:54:29", "remaining_time": "0:41:51"}
278
+ {"current_steps": 277, "total_steps": 488, "loss": 0.085, "lr": 4.6960470027196456e-05, "epoch": 1.1352459016393444, "percentage": 56.76, "elapsed_time": "0:54:41", "remaining_time": "0:41:39"}
279
+ {"current_steps": 278, "total_steps": 488, "loss": 0.088, "lr": 4.6603400289368676e-05, "epoch": 1.139344262295082, "percentage": 56.97, "elapsed_time": "0:54:53", "remaining_time": "0:41:27"}
280
+ {"current_steps": 279, "total_steps": 488, "loss": 0.0914, "lr": 4.624650449704962e-05, "epoch": 1.1434426229508197, "percentage": 57.17, "elapsed_time": "0:55:05", "remaining_time": "0:41:16"}
281
+ {"current_steps": 280, "total_steps": 488, "loss": 0.1042, "lr": 4.588980092746518e-05, "epoch": 1.1475409836065573, "percentage": 57.38, "elapsed_time": "0:55:17", "remaining_time": "0:41:04"}
282
+ {"current_steps": 281, "total_steps": 488, "loss": 0.0801, "lr": 4.553330784799721e-05, "epoch": 1.151639344262295, "percentage": 57.58, "elapsed_time": "0:55:28", "remaining_time": "0:40:52"}
283
+ {"current_steps": 282, "total_steps": 488, "loss": 0.116, "lr": 4.517704351524798e-05, "epoch": 1.1557377049180328, "percentage": 57.79, "elapsed_time": "0:55:40", "remaining_time": "0:40:40"}
284
+ {"current_steps": 283, "total_steps": 488, "loss": 0.08, "lr": 4.48210261741053e-05, "epoch": 1.1598360655737705, "percentage": 57.99, "elapsed_time": "0:55:52", "remaining_time": "0:40:28"}
285
+ {"current_steps": 284, "total_steps": 488, "loss": 0.0843, "lr": 4.446527405680812e-05, "epoch": 1.1639344262295082, "percentage": 58.2, "elapsed_time": "0:56:04", "remaining_time": "0:40:16"}
286
+ {"current_steps": 285, "total_steps": 488, "loss": 0.0783, "lr": 4.410980538201282e-05, "epoch": 1.1680327868852458, "percentage": 58.4, "elapsed_time": "0:56:15", "remaining_time": "0:40:04"}
287
+ {"current_steps": 286, "total_steps": 488, "loss": 0.0832, "lr": 4.375463835386022e-05, "epoch": 1.1721311475409837, "percentage": 58.61, "elapsed_time": "0:56:27", "remaining_time": "0:39:52"}
288
+ {"current_steps": 287, "total_steps": 488, "loss": 0.1102, "lr": 4.339979116104334e-05, "epoch": 1.1762295081967213, "percentage": 58.81, "elapsed_time": "0:56:39", "remaining_time": "0:39:40"}
289
+ {"current_steps": 288, "total_steps": 488, "loss": 0.0687, "lr": 4.3045281975875875e-05, "epoch": 1.180327868852459, "percentage": 59.02, "elapsed_time": "0:56:51", "remaining_time": "0:39:29"}
290
+ {"current_steps": 289, "total_steps": 488, "loss": 0.0765, "lr": 4.269112895336161e-05, "epoch": 1.1844262295081966, "percentage": 59.22, "elapsed_time": "0:57:03", "remaining_time": "0:39:17"}
291
+ {"current_steps": 290, "total_steps": 488, "loss": 0.0773, "lr": 4.2337350230264635e-05, "epoch": 1.1885245901639343, "percentage": 59.43, "elapsed_time": "0:57:15", "remaining_time": "0:39:05"}
292
+ {"current_steps": 291, "total_steps": 488, "loss": 0.0603, "lr": 4.198396392418054e-05, "epoch": 1.1926229508196722, "percentage": 59.63, "elapsed_time": "0:57:26", "remaining_time": "0:38:53"}
293
+ {"current_steps": 292, "total_steps": 488, "loss": 0.0698, "lr": 4.1630988132608614e-05, "epoch": 1.1967213114754098, "percentage": 59.84, "elapsed_time": "0:57:38", "remaining_time": "0:38:41"}
294
+ {"current_steps": 293, "total_steps": 488, "loss": 0.0721, "lr": 4.127844093202498e-05, "epoch": 1.2008196721311475, "percentage": 60.04, "elapsed_time": "0:57:50", "remaining_time": "0:38:29"}
295
+ {"current_steps": 294, "total_steps": 488, "loss": 0.0793, "lr": 4.092634037695694e-05, "epoch": 1.2049180327868854, "percentage": 60.25, "elapsed_time": "0:58:02", "remaining_time": "0:38:17"}
296
+ {"current_steps": 295, "total_steps": 488, "loss": 0.0901, "lr": 4.057470449905831e-05, "epoch": 1.209016393442623, "percentage": 60.45, "elapsed_time": "0:58:13", "remaining_time": "0:38:05"}
297
+ {"current_steps": 296, "total_steps": 488, "loss": 0.0826, "lr": 4.022355130618604e-05, "epoch": 1.2131147540983607, "percentage": 60.66, "elapsed_time": "0:58:25", "remaining_time": "0:37:53"}
298
+ {"current_steps": 297, "total_steps": 488, "loss": 0.0886, "lr": 3.9872898781477954e-05, "epoch": 1.2172131147540983, "percentage": 60.86, "elapsed_time": "0:58:37", "remaining_time": "0:37:42"}
299
+ {"current_steps": 298, "total_steps": 488, "loss": 0.0685, "lr": 3.952276488243186e-05, "epoch": 1.221311475409836, "percentage": 61.07, "elapsed_time": "0:58:49", "remaining_time": "0:37:30"}
300
+ {"current_steps": 299, "total_steps": 488, "loss": 0.0736, "lr": 3.917316753998585e-05, "epoch": 1.2254098360655739, "percentage": 61.27, "elapsed_time": "0:59:01", "remaining_time": "0:37:18"}
301
+ {"current_steps": 300, "total_steps": 488, "loss": 0.0793, "lr": 3.882412465760009e-05, "epoch": 1.2295081967213115, "percentage": 61.48, "elapsed_time": "0:59:12", "remaining_time": "0:37:06"}
302
+ {"current_steps": 301, "total_steps": 488, "loss": 0.0675, "lr": 3.847565411033992e-05, "epoch": 1.2336065573770492, "percentage": 61.68, "elapsed_time": "0:59:24", "remaining_time": "0:36:54"}
303
+ {"current_steps": 302, "total_steps": 488, "loss": 0.0825, "lr": 3.8127773743960426e-05, "epoch": 1.2377049180327868, "percentage": 61.89, "elapsed_time": "0:59:36", "remaining_time": "0:36:42"}
304
+ {"current_steps": 303, "total_steps": 488, "loss": 0.0909, "lr": 3.7780501373992596e-05, "epoch": 1.2418032786885247, "percentage": 62.09, "elapsed_time": "0:59:48", "remaining_time": "0:36:30"}
305
+ {"current_steps": 304, "total_steps": 488, "loss": 0.0844, "lr": 3.7433854784830854e-05, "epoch": 1.2459016393442623, "percentage": 62.3, "elapsed_time": "0:59:59", "remaining_time": "0:36:18"}
306
+ {"current_steps": 305, "total_steps": 488, "loss": 0.0732, "lr": 3.7087851728822405e-05, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "1:00:11", "remaining_time": "0:36:07"}
307
+ {"current_steps": 306, "total_steps": 488, "loss": 0.1133, "lr": 3.674250992535802e-05, "epoch": 1.2540983606557377, "percentage": 62.7, "elapsed_time": "1:00:23", "remaining_time": "0:35:55"}
308
+ {"current_steps": 307, "total_steps": 488, "loss": 0.1028, "lr": 3.639784705996463e-05, "epoch": 1.2581967213114753, "percentage": 62.91, "elapsed_time": "1:00:35", "remaining_time": "0:35:43"}
309
+ {"current_steps": 308, "total_steps": 488, "loss": 0.0748, "lr": 3.6053880783399654e-05, "epoch": 1.2622950819672132, "percentage": 63.11, "elapsed_time": "1:00:46", "remaining_time": "0:35:31"}
310
+ {"current_steps": 309, "total_steps": 488, "loss": 0.0909, "lr": 3.5710628710747e-05, "epoch": 1.2663934426229508, "percentage": 63.32, "elapsed_time": "1:00:58", "remaining_time": "0:35:19"}
311
+ {"current_steps": 310, "total_steps": 488, "loss": 0.0827, "lr": 3.5368108420515036e-05, "epoch": 1.2704918032786885, "percentage": 63.52, "elapsed_time": "1:01:10", "remaining_time": "0:35:07"}
312
+ {"current_steps": 311, "total_steps": 488, "loss": 0.0843, "lr": 3.5026337453736314e-05, "epoch": 1.2745901639344264, "percentage": 63.73, "elapsed_time": "1:01:22", "remaining_time": "0:34:55"}
313
+ {"current_steps": 312, "total_steps": 488, "loss": 0.0908, "lr": 3.4685333313069315e-05, "epoch": 1.278688524590164, "percentage": 63.93, "elapsed_time": "1:01:34", "remaining_time": "0:34:43"}
314
+ {"current_steps": 313, "total_steps": 488, "loss": 0.0859, "lr": 3.4345113461902055e-05, "epoch": 1.2827868852459017, "percentage": 64.14, "elapsed_time": "1:01:45", "remaining_time": "0:34:31"}
315
+ {"current_steps": 314, "total_steps": 488, "loss": 0.0837, "lr": 3.400569532345781e-05, "epoch": 1.2868852459016393, "percentage": 64.34, "elapsed_time": "1:01:57", "remaining_time": "0:34:20"}
316
+ {"current_steps": 315, "total_steps": 488, "loss": 0.0708, "lr": 3.3667096279902794e-05, "epoch": 1.290983606557377, "percentage": 64.55, "elapsed_time": "1:02:09", "remaining_time": "0:34:08"}
317
+ {"current_steps": 316, "total_steps": 488, "loss": 0.0739, "lr": 3.3329333671456024e-05, "epoch": 1.2950819672131146, "percentage": 64.75, "elapsed_time": "1:02:21", "remaining_time": "0:33:56"}
318
+ {"current_steps": 317, "total_steps": 488, "loss": 0.089, "lr": 3.2992424795501284e-05, "epoch": 1.2991803278688525, "percentage": 64.96, "elapsed_time": "1:02:32", "remaining_time": "0:33:44"}
319
+ {"current_steps": 318, "total_steps": 488, "loss": 0.0804, "lr": 3.26563869057013e-05, "epoch": 1.3032786885245902, "percentage": 65.16, "elapsed_time": "1:02:44", "remaining_time": "0:33:32"}
320
+ {"current_steps": 319, "total_steps": 488, "loss": 0.0816, "lr": 3.232123721111415e-05, "epoch": 1.3073770491803278, "percentage": 65.37, "elapsed_time": "1:02:56", "remaining_time": "0:33:20"}
321
+ {"current_steps": 320, "total_steps": 488, "loss": 0.1007, "lr": 3.198699287531198e-05, "epoch": 1.3114754098360657, "percentage": 65.57, "elapsed_time": "1:03:07", "remaining_time": "0:33:08"}
322
+ {"current_steps": 321, "total_steps": 488, "loss": 0.1016, "lr": 3.165367101550197e-05, "epoch": 1.3155737704918034, "percentage": 65.78, "elapsed_time": "1:03:19", "remaining_time": "0:32:56"}
323
+ {"current_steps": 322, "total_steps": 488, "loss": 0.0698, "lr": 3.13212887016498e-05, "epoch": 1.319672131147541, "percentage": 65.98, "elapsed_time": "1:03:31", "remaining_time": "0:32:44"}
324
+ {"current_steps": 323, "total_steps": 488, "loss": 0.092, "lr": 3.098986295560545e-05, "epoch": 1.3237704918032787, "percentage": 66.19, "elapsed_time": "1:03:43", "remaining_time": "0:32:33"}
325
+ {"current_steps": 324, "total_steps": 488, "loss": 0.0965, "lr": 3.0659410750231454e-05, "epoch": 1.3278688524590163, "percentage": 66.39, "elapsed_time": "1:03:54", "remaining_time": "0:32:21"}
326
+ {"current_steps": 325, "total_steps": 488, "loss": 0.0861, "lr": 3.032994900853372e-05, "epoch": 1.331967213114754, "percentage": 66.6, "elapsed_time": "1:04:06", "remaining_time": "0:32:09"}
327
+ {"current_steps": 326, "total_steps": 488, "loss": 0.1088, "lr": 3.0001494602794867e-05, "epoch": 1.3360655737704918, "percentage": 66.8, "elapsed_time": "1:04:18", "remaining_time": "0:31:57"}
328
+ {"current_steps": 327, "total_steps": 488, "loss": 0.0862, "lr": 2.967406435371018e-05, "epoch": 1.3401639344262295, "percentage": 67.01, "elapsed_time": "1:04:30", "remaining_time": "0:31:45"}
329
+ {"current_steps": 328, "total_steps": 488, "loss": 0.084, "lr": 2.934767502952616e-05, "epoch": 1.3442622950819672, "percentage": 67.21, "elapsed_time": "1:04:42", "remaining_time": "0:31:33"}
330
+ {"current_steps": 329, "total_steps": 488, "loss": 0.0748, "lr": 2.9022343345181846e-05, "epoch": 1.348360655737705, "percentage": 67.42, "elapsed_time": "1:04:53", "remaining_time": "0:31:21"}
331
+ {"current_steps": 330, "total_steps": 488, "loss": 0.087, "lr": 2.8698085961452724e-05, "epoch": 1.3524590163934427, "percentage": 67.62, "elapsed_time": "1:05:05", "remaining_time": "0:31:09"}
332
+ {"current_steps": 331, "total_steps": 488, "loss": 0.0798, "lr": 2.8374919484097663e-05, "epoch": 1.3565573770491803, "percentage": 67.83, "elapsed_time": "1:05:17", "remaining_time": "0:30:58"}
333
+ {"current_steps": 332, "total_steps": 488, "loss": 0.0778, "lr": 2.8052860463008295e-05, "epoch": 1.360655737704918, "percentage": 68.03, "elapsed_time": "1:05:29", "remaining_time": "0:30:46"}
334
+ {"current_steps": 333, "total_steps": 488, "loss": 0.0699, "lr": 2.7731925391361673e-05, "epoch": 1.3647540983606556, "percentage": 68.24, "elapsed_time": "1:05:40", "remaining_time": "0:30:34"}
335
+ {"current_steps": 334, "total_steps": 488, "loss": 0.0688, "lr": 2.741213070477545e-05, "epoch": 1.3688524590163935, "percentage": 68.44, "elapsed_time": "1:05:52", "remaining_time": "0:30:22"}
336
+ {"current_steps": 335, "total_steps": 488, "loss": 0.1021, "lr": 2.7093492780466355e-05, "epoch": 1.3729508196721312, "percentage": 68.65, "elapsed_time": "1:06:04", "remaining_time": "0:30:10"}
337
+ {"current_steps": 336, "total_steps": 488, "loss": 0.0787, "lr": 2.6776027936411318e-05, "epoch": 1.3770491803278688, "percentage": 68.85, "elapsed_time": "1:06:15", "remaining_time": "0:29:58"}
338
+ {"current_steps": 337, "total_steps": 488, "loss": 0.0968, "lr": 2.6459752430511952e-05, "epoch": 1.3811475409836065, "percentage": 69.06, "elapsed_time": "1:06:27", "remaining_time": "0:29:46"}
339
+ {"current_steps": 338, "total_steps": 488, "loss": 0.0689, "lr": 2.6144682459761814e-05, "epoch": 1.3852459016393444, "percentage": 69.26, "elapsed_time": "1:06:39", "remaining_time": "0:29:34"}
340
+ {"current_steps": 339, "total_steps": 488, "loss": 0.076, "lr": 2.58308341594171e-05, "epoch": 1.389344262295082, "percentage": 69.47, "elapsed_time": "1:06:51", "remaining_time": "0:29:22"}
341
+ {"current_steps": 340, "total_steps": 488, "loss": 0.066, "lr": 2.5518223602170134e-05, "epoch": 1.3934426229508197, "percentage": 69.67, "elapsed_time": "1:07:02", "remaining_time": "0:29:11"}
342
+ {"current_steps": 341, "total_steps": 488, "loss": 0.0795, "lr": 2.5206866797326446e-05, "epoch": 1.3975409836065573, "percentage": 69.88, "elapsed_time": "1:07:14", "remaining_time": "0:28:59"}
343
+ {"current_steps": 342, "total_steps": 488, "loss": 0.0979, "lr": 2.4896779689984783e-05, "epoch": 1.401639344262295, "percentage": 70.08, "elapsed_time": "1:07:26", "remaining_time": "0:28:47"}
344
+ {"current_steps": 343, "total_steps": 488, "loss": 0.0849, "lr": 2.4587978160220563e-05, "epoch": 1.4057377049180328, "percentage": 70.29, "elapsed_time": "1:07:38", "remaining_time": "0:28:35"}
345
+ {"current_steps": 344, "total_steps": 488, "loss": 0.0833, "lr": 2.4280478022272696e-05, "epoch": 1.4098360655737705, "percentage": 70.49, "elapsed_time": "1:07:49", "remaining_time": "0:28:23"}
346
+ {"current_steps": 345, "total_steps": 488, "loss": 0.0924, "lr": 2.3974295023733577e-05, "epoch": 1.4139344262295082, "percentage": 70.7, "elapsed_time": "1:08:01", "remaining_time": "0:28:11"}
347
+ {"current_steps": 346, "total_steps": 488, "loss": 0.0876, "lr": 2.3669444844742812e-05, "epoch": 1.418032786885246, "percentage": 70.9, "elapsed_time": "1:08:13", "remaining_time": "0:27:59"}
348
+ {"current_steps": 347, "total_steps": 488, "loss": 0.0911, "lr": 2.336594309718399e-05, "epoch": 1.4221311475409837, "percentage": 71.11, "elapsed_time": "1:08:25", "remaining_time": "0:27:48"}
349
+ {"current_steps": 348, "total_steps": 488, "loss": 0.0791, "lr": 2.3063805323885383e-05, "epoch": 1.4262295081967213, "percentage": 71.31, "elapsed_time": "1:08:36", "remaining_time": "0:27:36"}
350
+ {"current_steps": 349, "total_steps": 488, "loss": 0.071, "lr": 2.276304699782381e-05, "epoch": 1.430327868852459, "percentage": 71.52, "elapsed_time": "1:08:48", "remaining_time": "0:27:24"}
351
+ {"current_steps": 350, "total_steps": 488, "loss": 0.0883, "lr": 2.2463683521332374e-05, "epoch": 1.4344262295081966, "percentage": 71.72, "elapsed_time": "1:09:00", "remaining_time": "0:27:12"}
352
+ {"current_steps": 351, "total_steps": 488, "loss": 0.0949, "lr": 2.2165730225311532e-05, "epoch": 1.4385245901639343, "percentage": 71.93, "elapsed_time": "1:09:12", "remaining_time": "0:27:00"}
353
+ {"current_steps": 352, "total_steps": 488, "loss": 0.0669, "lr": 2.1869202368444146e-05, "epoch": 1.4426229508196722, "percentage": 72.13, "elapsed_time": "1:09:23", "remaining_time": "0:26:48"}
354
+ {"current_steps": 353, "total_steps": 488, "loss": 0.1115, "lr": 2.1574115136413892e-05, "epoch": 1.4467213114754098, "percentage": 72.34, "elapsed_time": "1:09:35", "remaining_time": "0:26:36"}
355
+ {"current_steps": 354, "total_steps": 488, "loss": 0.0824, "lr": 2.128048364112774e-05, "epoch": 1.4508196721311475, "percentage": 72.54, "elapsed_time": "1:09:47", "remaining_time": "0:26:24"}
356
+ {"current_steps": 355, "total_steps": 488, "loss": 0.0805, "lr": 2.098832291994188e-05, "epoch": 1.4549180327868854, "percentage": 72.75, "elapsed_time": "1:09:58", "remaining_time": "0:26:13"}
357
+ {"current_steps": 356, "total_steps": 488, "loss": 0.0809, "lr": 2.0697647934891807e-05, "epoch": 1.459016393442623, "percentage": 72.95, "elapsed_time": "1:10:10", "remaining_time": "0:26:01"}
358
+ {"current_steps": 357, "total_steps": 488, "loss": 0.0795, "lr": 2.0408473571925908e-05, "epoch": 1.4631147540983607, "percentage": 73.16, "elapsed_time": "1:10:22", "remaining_time": "0:25:49"}
359
+ {"current_steps": 358, "total_steps": 488, "loss": 0.0738, "lr": 2.0120814640143314e-05, "epoch": 1.4672131147540983, "percentage": 73.36, "elapsed_time": "1:10:34", "remaining_time": "0:25:37"}
360
+ {"current_steps": 359, "total_steps": 488, "loss": 0.0747, "lr": 1.983468587103533e-05, "epoch": 1.471311475409836, "percentage": 73.57, "elapsed_time": "1:10:46", "remaining_time": "0:25:25"}
361
+ {"current_steps": 360, "total_steps": 488, "loss": 0.0782, "lr": 1.9550101917731166e-05, "epoch": 1.4754098360655736, "percentage": 73.77, "elapsed_time": "1:10:57", "remaining_time": "0:25:13"}
362
+ {"current_steps": 361, "total_steps": 488, "loss": 0.0785, "lr": 1.9267077354247394e-05, "epoch": 1.4795081967213115, "percentage": 73.98, "elapsed_time": "1:11:09", "remaining_time": "0:25:01"}
363
+ {"current_steps": 362, "total_steps": 488, "loss": 0.1122, "lr": 1.8985626674741643e-05, "epoch": 1.4836065573770492, "percentage": 74.18, "elapsed_time": "1:11:21", "remaining_time": "0:24:50"}
364
+ {"current_steps": 363, "total_steps": 488, "loss": 0.0915, "lr": 1.8705764292770383e-05, "epoch": 1.4877049180327868, "percentage": 74.39, "elapsed_time": "1:11:32", "remaining_time": "0:24:38"}
365
+ {"current_steps": 364, "total_steps": 488, "loss": 0.0665, "lr": 1.8427504540550677e-05, "epoch": 1.4918032786885247, "percentage": 74.59, "elapsed_time": "1:11:44", "remaining_time": "0:24:26"}
366
+ {"current_steps": 365, "total_steps": 488, "loss": 0.075, "lr": 1.8150861668226304e-05, "epoch": 1.4959016393442623, "percentage": 74.8, "elapsed_time": "1:11:56", "remaining_time": "0:24:14"}
367
+ {"current_steps": 366, "total_steps": 488, "loss": 0.0811, "lr": 1.7875849843137893e-05, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "1:12:08", "remaining_time": "0:24:02"}
368
+ {"current_steps": 367, "total_steps": 488, "loss": 0.0756, "lr": 1.760248314909747e-05, "epoch": 1.5040983606557377, "percentage": 75.2, "elapsed_time": "1:12:19", "remaining_time": "0:23:50"}
369
+ {"current_steps": 368, "total_steps": 488, "loss": 0.0843, "lr": 1.7330775585667164e-05, "epoch": 1.5081967213114753, "percentage": 75.41, "elapsed_time": "1:12:31", "remaining_time": "0:23:39"}
370
+ {"current_steps": 369, "total_steps": 488, "loss": 0.0762, "lr": 1.7060741067442288e-05, "epoch": 1.512295081967213, "percentage": 75.61, "elapsed_time": "1:12:43", "remaining_time": "0:23:27"}
371
+ {"current_steps": 370, "total_steps": 488, "loss": 0.0741, "lr": 1.679239342333867e-05, "epoch": 1.5163934426229508, "percentage": 75.82, "elapsed_time": "1:12:55", "remaining_time": "0:23:15"}
372
+ {"current_steps": 371, "total_steps": 488, "loss": 0.0922, "lr": 1.6525746395884605e-05, "epoch": 1.5204918032786885, "percentage": 76.02, "elapsed_time": "1:13:07", "remaining_time": "0:23:03"}
373
+ {"current_steps": 372, "total_steps": 488, "loss": 0.0783, "lr": 1.626081364051691e-05, "epoch": 1.5245901639344264, "percentage": 76.23, "elapsed_time": "1:13:18", "remaining_time": "0:22:51"}
374
+ {"current_steps": 373, "total_steps": 488, "loss": 0.0724, "lr": 1.599760872488171e-05, "epoch": 1.528688524590164, "percentage": 76.43, "elapsed_time": "1:13:30", "remaining_time": "0:22:39"}
375
+ {"current_steps": 374, "total_steps": 488, "loss": 0.0787, "lr": 1.573614512813961e-05, "epoch": 1.5327868852459017, "percentage": 76.64, "elapsed_time": "1:13:42", "remaining_time": "0:22:27"}
376
+ {"current_steps": 375, "total_steps": 488, "loss": 0.0713, "lr": 1.5476436240275344e-05, "epoch": 1.5368852459016393, "percentage": 76.84, "elapsed_time": "1:13:53", "remaining_time": "0:22:16"}
377
+ {"current_steps": 376, "total_steps": 488, "loss": 0.0699, "lr": 1.5218495361412145e-05, "epoch": 1.540983606557377, "percentage": 77.05, "elapsed_time": "1:14:05", "remaining_time": "0:22:04"}
378
+ {"current_steps": 377, "total_steps": 488, "loss": 0.0807, "lr": 1.4962335701130509e-05, "epoch": 1.5450819672131146, "percentage": 77.25, "elapsed_time": "1:14:17", "remaining_time": "0:21:52"}
379
+ {"current_steps": 378, "total_steps": 488, "loss": 0.0833, "lr": 1.470797037779183e-05, "epoch": 1.5491803278688525, "percentage": 77.46, "elapsed_time": "1:14:29", "remaining_time": "0:21:40"}
380
+ {"current_steps": 379, "total_steps": 488, "loss": 0.0908, "lr": 1.4455412417866476e-05, "epoch": 1.5532786885245902, "percentage": 77.66, "elapsed_time": "1:14:41", "remaining_time": "0:21:28"}
381
+ {"current_steps": 380, "total_steps": 488, "loss": 0.0884, "lr": 1.4204674755266789e-05, "epoch": 1.5573770491803278, "percentage": 77.87, "elapsed_time": "1:14:52", "remaining_time": "0:21:16"}
382
+ {"current_steps": 381, "total_steps": 488, "loss": 0.0817, "lr": 1.3955770230684611e-05, "epoch": 1.5614754098360657, "percentage": 78.07, "elapsed_time": "1:15:04", "remaining_time": "0:21:05"}
383
+ {"current_steps": 382, "total_steps": 488, "loss": 0.0774, "lr": 1.3708711590933792e-05, "epoch": 1.5655737704918034, "percentage": 78.28, "elapsed_time": "1:15:16", "remaining_time": "0:20:53"}
384
+ {"current_steps": 383, "total_steps": 488, "loss": 0.0961, "lr": 1.3463511488297304e-05, "epoch": 1.569672131147541, "percentage": 78.48, "elapsed_time": "1:15:28", "remaining_time": "0:20:41"}
385
+ {"current_steps": 384, "total_steps": 488, "loss": 0.0939, "lr": 1.3220182479879406e-05, "epoch": 1.5737704918032787, "percentage": 78.69, "elapsed_time": "1:15:40", "remaining_time": "0:20:29"}
386
+ {"current_steps": 385, "total_steps": 488, "loss": 0.0837, "lr": 1.2978737026962456e-05, "epoch": 1.5778688524590163, "percentage": 78.89, "elapsed_time": "1:15:51", "remaining_time": "0:20:17"}
387
+ {"current_steps": 386, "total_steps": 488, "loss": 0.0875, "lr": 1.2739187494368877e-05, "epoch": 1.581967213114754, "percentage": 79.1, "elapsed_time": "1:16:03", "remaining_time": "0:20:05"}
388
+ {"current_steps": 387, "total_steps": 488, "loss": 0.0854, "lr": 1.2501546149827792e-05, "epoch": 1.5860655737704918, "percentage": 79.3, "elapsed_time": "1:16:15", "remaining_time": "0:19:54"}
389
+ {"current_steps": 388, "total_steps": 488, "loss": 0.0893, "lr": 1.2265825163346911e-05, "epoch": 1.5901639344262295, "percentage": 79.51, "elapsed_time": "1:16:27", "remaining_time": "0:19:42"}
390
+ {"current_steps": 389, "total_steps": 488, "loss": 0.0685, "lr": 1.2032036606589175e-05, "epoch": 1.5942622950819674, "percentage": 79.71, "elapsed_time": "1:16:39", "remaining_time": "0:19:30"}
391
+ {"current_steps": 390, "total_steps": 488, "loss": 0.0897, "lr": 1.1800192452254627e-05, "epoch": 1.598360655737705, "percentage": 79.92, "elapsed_time": "1:16:50", "remaining_time": "0:19:18"}
392
+ {"current_steps": 391, "total_steps": 488, "loss": 0.0957, "lr": 1.15703045734672e-05, "epoch": 1.6024590163934427, "percentage": 80.12, "elapsed_time": "1:17:02", "remaining_time": "0:19:06"}
393
+ {"current_steps": 392, "total_steps": 488, "loss": 0.1042, "lr": 1.1342384743166723e-05, "epoch": 1.6065573770491803, "percentage": 80.33, "elapsed_time": "1:17:14", "remaining_time": "0:18:54"}
394
+ {"current_steps": 393, "total_steps": 488, "loss": 0.0716, "lr": 1.1116444633506019e-05, "epoch": 1.610655737704918, "percentage": 80.53, "elapsed_time": "1:17:26", "remaining_time": "0:18:43"}
395
+ {"current_steps": 394, "total_steps": 488, "loss": 0.0768, "lr": 1.0892495815253085e-05, "epoch": 1.6147540983606556, "percentage": 80.74, "elapsed_time": "1:17:37", "remaining_time": "0:18:31"}
396
+ {"current_steps": 395, "total_steps": 488, "loss": 0.0834, "lr": 1.0670549757198633e-05, "epoch": 1.6188524590163933, "percentage": 80.94, "elapsed_time": "1:17:49", "remaining_time": "0:18:19"}
397
+ {"current_steps": 396, "total_steps": 488, "loss": 0.0786, "lr": 1.0450617825568642e-05, "epoch": 1.6229508196721312, "percentage": 81.15, "elapsed_time": "1:18:01", "remaining_time": "0:18:07"}
398
+ {"current_steps": 397, "total_steps": 488, "loss": 0.075, "lr": 1.0232711283442403e-05, "epoch": 1.6270491803278688, "percentage": 81.35, "elapsed_time": "1:18:13", "remaining_time": "0:17:55"}
399
+ {"current_steps": 398, "total_steps": 488, "loss": 0.077, "lr": 1.0016841290175572e-05, "epoch": 1.6311475409836067, "percentage": 81.56, "elapsed_time": "1:18:24", "remaining_time": "0:17:43"}
400
+ {"current_steps": 399, "total_steps": 488, "loss": 0.0879, "lr": 9.803018900828837e-06, "epoch": 1.6352459016393444, "percentage": 81.76, "elapsed_time": "1:18:36", "remaining_time": "0:17:32"}
401
+ {"current_steps": 400, "total_steps": 488, "loss": 0.0814, "lr": 9.591255065601612e-06, "epoch": 1.639344262295082, "percentage": 81.97, "elapsed_time": "1:18:48", "remaining_time": "0:17:20"}
402
+ {"current_steps": 400, "total_steps": 488, "eval_loss": 0.11391327530145645, "epoch": 1.639344262295082, "percentage": 81.97, "elapsed_time": "1:19:04", "remaining_time": "0:17:23"}
403
+ {"current_steps": 401, "total_steps": 488, "loss": 0.0816, "lr": 9.381560629271407e-06, "epoch": 1.6434426229508197, "percentage": 82.17, "elapsed_time": "1:19:15", "remaining_time": "0:17:11"}
404
+ {"current_steps": 402, "total_steps": 488, "loss": 0.0816, "lr": 9.173946330638328e-06, "epoch": 1.6475409836065573, "percentage": 82.38, "elapsed_time": "1:19:27", "remaining_time": "0:16:59"}
405
+ {"current_steps": 403, "total_steps": 488, "loss": 0.0705, "lr": 8.968422801975223e-06, "epoch": 1.651639344262295, "percentage": 82.58, "elapsed_time": "1:19:39", "remaining_time": "0:16:48"}
406
+ {"current_steps": 404, "total_steps": 488, "loss": 0.097, "lr": 8.765000568483084e-06, "epoch": 1.6557377049180326, "percentage": 82.79, "elapsed_time": "1:19:51", "remaining_time": "0:16:36"}
407
+ {"current_steps": 405, "total_steps": 488, "loss": 0.0765, "lr": 8.563690047752148e-06, "epoch": 1.6598360655737705, "percentage": 82.99, "elapsed_time": "1:20:02", "remaining_time": "0:16:24"}
408
+ {"current_steps": 406, "total_steps": 488, "loss": 0.0991, "lr": 8.364501549228288e-06, "epoch": 1.6639344262295082, "percentage": 83.2, "elapsed_time": "1:20:14", "remaining_time": "0:16:12"}
409
+ {"current_steps": 407, "total_steps": 488, "loss": 0.062, "lr": 8.167445273685143e-06, "epoch": 1.668032786885246, "percentage": 83.4, "elapsed_time": "1:20:26", "remaining_time": "0:16:00"}
410
+ {"current_steps": 408, "total_steps": 488, "loss": 0.0873, "lr": 7.97253131270162e-06, "epoch": 1.6721311475409837, "percentage": 83.61, "elapsed_time": "1:20:38", "remaining_time": "0:15:48"}
411
+ {"current_steps": 409, "total_steps": 488, "loss": 0.0712, "lr": 7.779769648145201e-06, "epoch": 1.6762295081967213, "percentage": 83.81, "elapsed_time": "1:20:50", "remaining_time": "0:15:36"}
412
+ {"current_steps": 410, "total_steps": 488, "loss": 0.0847, "lr": 7.589170151660657e-06, "epoch": 1.680327868852459, "percentage": 84.02, "elapsed_time": "1:21:01", "remaining_time": "0:15:24"}
413
+ {"current_steps": 411, "total_steps": 488, "loss": 0.0832, "lr": 7.400742584164533e-06, "epoch": 1.6844262295081966, "percentage": 84.22, "elapsed_time": "1:21:13", "remaining_time": "0:15:13"}
414
+ {"current_steps": 412, "total_steps": 488, "loss": 0.0813, "lr": 7.2144965953453385e-06, "epoch": 1.6885245901639343, "percentage": 84.43, "elapsed_time": "1:21:25", "remaining_time": "0:15:01"}
415
+ {"current_steps": 413, "total_steps": 488, "loss": 0.0816, "lr": 7.030441723169251e-06, "epoch": 1.6926229508196722, "percentage": 84.63, "elapsed_time": "1:21:37", "remaining_time": "0:14:49"}
416
+ {"current_steps": 414, "total_steps": 488, "loss": 0.0853, "lr": 6.848587393391792e-06, "epoch": 1.6967213114754098, "percentage": 84.84, "elapsed_time": "1:21:49", "remaining_time": "0:14:37"}
417
+ {"current_steps": 415, "total_steps": 488, "loss": 0.0717, "lr": 6.668942919074994e-06, "epoch": 1.7008196721311475, "percentage": 85.04, "elapsed_time": "1:22:01", "remaining_time": "0:14:25"}
418
+ {"current_steps": 416, "total_steps": 488, "loss": 0.0945, "lr": 6.491517500110589e-06, "epoch": 1.7049180327868854, "percentage": 85.25, "elapsed_time": "1:22:13", "remaining_time": "0:14:13"}
419
+ {"current_steps": 417, "total_steps": 488, "loss": 0.0979, "lr": 6.31632022274874e-06, "epoch": 1.709016393442623, "percentage": 85.45, "elapsed_time": "1:22:24", "remaining_time": "0:14:01"}
420
+ {"current_steps": 418, "total_steps": 488, "loss": 0.0889, "lr": 6.1433600591328296e-06, "epoch": 1.7131147540983607, "percentage": 85.66, "elapsed_time": "1:22:36", "remaining_time": "0:13:50"}
421
+ {"current_steps": 419, "total_steps": 488, "loss": 0.0643, "lr": 5.972645866839882e-06, "epoch": 1.7172131147540983, "percentage": 85.86, "elapsed_time": "1:22:48", "remaining_time": "0:13:38"}
422
+ {"current_steps": 420, "total_steps": 488, "loss": 0.0909, "lr": 5.804186388427052e-06, "epoch": 1.721311475409836, "percentage": 86.07, "elapsed_time": "1:23:00", "remaining_time": "0:13:26"}
423
+ {"current_steps": 421, "total_steps": 488, "loss": 0.0906, "lr": 5.637990250983821e-06, "epoch": 1.7254098360655736, "percentage": 86.27, "elapsed_time": "1:23:12", "remaining_time": "0:13:14"}
424
+ {"current_steps": 422, "total_steps": 488, "loss": 0.0811, "lr": 5.4740659656902284e-06, "epoch": 1.7295081967213115, "percentage": 86.48, "elapsed_time": "1:23:23", "remaining_time": "0:13:02"}
425
+ {"current_steps": 423, "total_steps": 488, "loss": 0.0827, "lr": 5.312421927381017e-06, "epoch": 1.7336065573770492, "percentage": 86.68, "elapsed_time": "1:23:35", "remaining_time": "0:12:50"}
426
+ {"current_steps": 424, "total_steps": 488, "loss": 0.0669, "lr": 5.153066414115659e-06, "epoch": 1.737704918032787, "percentage": 86.89, "elapsed_time": "1:23:47", "remaining_time": "0:12:38"}
427
+ {"current_steps": 425, "total_steps": 488, "loss": 0.1088, "lr": 4.9960075867544974e-06, "epoch": 1.7418032786885247, "percentage": 87.09, "elapsed_time": "1:23:58", "remaining_time": "0:12:26"}
428
+ {"current_steps": 426, "total_steps": 488, "loss": 0.0945, "lr": 4.841253488540748e-06, "epoch": 1.7459016393442623, "percentage": 87.3, "elapsed_time": "1:24:10", "remaining_time": "0:12:15"}
429
+ {"current_steps": 427, "total_steps": 488, "loss": 0.0719, "lr": 4.688812044688645e-06, "epoch": 1.75, "percentage": 87.5, "elapsed_time": "1:24:22", "remaining_time": "0:12:03"}
430
+ {"current_steps": 428, "total_steps": 488, "loss": 0.068, "lr": 4.53869106197754e-06, "epoch": 1.7540983606557377, "percentage": 87.7, "elapsed_time": "1:24:34", "remaining_time": "0:11:51"}
431
+ {"current_steps": 429, "total_steps": 488, "loss": 0.1061, "lr": 4.390898228352131e-06, "epoch": 1.7581967213114753, "percentage": 87.91, "elapsed_time": "1:24:46", "remaining_time": "0:11:39"}
432
+ {"current_steps": 430, "total_steps": 488, "loss": 0.0908, "lr": 4.245441112528714e-06, "epoch": 1.762295081967213, "percentage": 88.11, "elapsed_time": "1:24:57", "remaining_time": "0:11:27"}
433
+ {"current_steps": 431, "total_steps": 488, "loss": 0.0926, "lr": 4.1023271636076335e-06, "epoch": 1.7663934426229508, "percentage": 88.32, "elapsed_time": "1:25:09", "remaining_time": "0:11:15"}
434
+ {"current_steps": 432, "total_steps": 488, "loss": 0.0779, "lr": 3.961563710691729e-06, "epoch": 1.7704918032786885, "percentage": 88.52, "elapsed_time": "1:25:21", "remaining_time": "0:11:03"}
435
+ {"current_steps": 433, "total_steps": 488, "loss": 0.0728, "lr": 3.823157962511076e-06, "epoch": 1.7745901639344264, "percentage": 88.73, "elapsed_time": "1:25:33", "remaining_time": "0:10:52"}
436
+ {"current_steps": 434, "total_steps": 488, "loss": 0.0867, "lr": 3.687117007053742e-06, "epoch": 1.778688524590164, "percentage": 88.93, "elapsed_time": "1:25:45", "remaining_time": "0:10:40"}
437
+ {"current_steps": 435, "total_steps": 488, "loss": 0.0929, "lr": 3.553447811202876e-06, "epoch": 1.7827868852459017, "percentage": 89.14, "elapsed_time": "1:25:56", "remaining_time": "0:10:28"}
438
+ {"current_steps": 436, "total_steps": 488, "loss": 0.0743, "lr": 3.4221572203798234e-06, "epoch": 1.7868852459016393, "percentage": 89.34, "elapsed_time": "1:26:08", "remaining_time": "0:10:16"}
439
+ {"current_steps": 437, "total_steps": 488, "loss": 0.0706, "lr": 3.293251958193683e-06, "epoch": 1.790983606557377, "percentage": 89.55, "elapsed_time": "1:26:20", "remaining_time": "0:10:04"}
440
+ {"current_steps": 438, "total_steps": 488, "loss": 0.0681, "lr": 3.1667386260968657e-06, "epoch": 1.7950819672131146, "percentage": 89.75, "elapsed_time": "1:26:32", "remaining_time": "0:09:52"}
441
+ {"current_steps": 439, "total_steps": 488, "loss": 0.0895, "lr": 3.0426237030470984e-06, "epoch": 1.7991803278688525, "percentage": 89.96, "elapsed_time": "1:26:44", "remaining_time": "0:09:40"}
442
+ {"current_steps": 440, "total_steps": 488, "loss": 0.0667, "lr": 2.9209135451755854e-06, "epoch": 1.8032786885245902, "percentage": 90.16, "elapsed_time": "1:26:55", "remaining_time": "0:09:29"}
443
+ {"current_steps": 441, "total_steps": 488, "loss": 0.0811, "lr": 2.8016143854615207e-06, "epoch": 1.8073770491803278, "percentage": 90.37, "elapsed_time": "1:27:07", "remaining_time": "0:09:17"}
444
+ {"current_steps": 442, "total_steps": 488, "loss": 0.0676, "lr": 2.6847323334128927e-06, "epoch": 1.8114754098360657, "percentage": 90.57, "elapsed_time": "1:27:19", "remaining_time": "0:09:05"}
445
+ {"current_steps": 443, "total_steps": 488, "loss": 0.0808, "lr": 2.570273374753568e-06, "epoch": 1.8155737704918034, "percentage": 90.78, "elapsed_time": "1:27:31", "remaining_time": "0:08:53"}
446
+ {"current_steps": 444, "total_steps": 488, "loss": 0.0716, "lr": 2.458243371116803e-06, "epoch": 1.819672131147541, "percentage": 90.98, "elapsed_time": "1:27:43", "remaining_time": "0:08:41"}
447
+ {"current_steps": 445, "total_steps": 488, "loss": 0.0666, "lr": 2.3486480597450233e-06, "epoch": 1.8237704918032787, "percentage": 91.19, "elapsed_time": "1:27:54", "remaining_time": "0:08:29"}
448
+ {"current_steps": 446, "total_steps": 488, "loss": 0.0804, "lr": 2.2414930531960366e-06, "epoch": 1.8278688524590163, "percentage": 91.39, "elapsed_time": "1:28:06", "remaining_time": "0:08:17"}
449
+ {"current_steps": 447, "total_steps": 488, "loss": 0.0822, "lr": 2.1367838390555615e-06, "epoch": 1.831967213114754, "percentage": 91.6, "elapsed_time": "1:28:18", "remaining_time": "0:08:05"}
450
+ {"current_steps": 448, "total_steps": 488, "loss": 0.0697, "lr": 2.0345257796562657e-06, "epoch": 1.8360655737704918, "percentage": 91.8, "elapsed_time": "1:28:30", "remaining_time": "0:07:54"}
451
+ {"current_steps": 449, "total_steps": 488, "loss": 0.1039, "lr": 1.9347241118030823e-06, "epoch": 1.8401639344262295, "percentage": 92.01, "elapsed_time": "1:28:41", "remaining_time": "0:07:42"}
452
+ {"current_steps": 450, "total_steps": 488, "loss": 0.0945, "lr": 1.8373839465050779e-06, "epoch": 1.8442622950819674, "percentage": 92.21, "elapsed_time": "1:28:53", "remaining_time": "0:07:30"}
453
+ {"current_steps": 451, "total_steps": 488, "loss": 0.0717, "lr": 1.7425102687136708e-06, "epoch": 1.848360655737705, "percentage": 92.42, "elapsed_time": "1:29:05", "remaining_time": "0:07:18"}
454
+ {"current_steps": 452, "total_steps": 488, "loss": 0.0846, "lr": 1.65010793706738e-06, "epoch": 1.8524590163934427, "percentage": 92.62, "elapsed_time": "1:29:17", "remaining_time": "0:07:06"}
455
+ {"current_steps": 453, "total_steps": 488, "loss": 0.0864, "lr": 1.5601816836429584e-06, "epoch": 1.8565573770491803, "percentage": 92.83, "elapsed_time": "1:29:29", "remaining_time": "0:06:54"}
456
+ {"current_steps": 454, "total_steps": 488, "loss": 0.0769, "lr": 1.4727361137131136e-06, "epoch": 1.860655737704918, "percentage": 93.03, "elapsed_time": "1:29:40", "remaining_time": "0:06:42"}
457
+ {"current_steps": 455, "total_steps": 488, "loss": 0.0752, "lr": 1.3877757055106132e-06, "epoch": 1.8647540983606556, "percentage": 93.24, "elapsed_time": "1:29:52", "remaining_time": "0:06:31"}
458
+ {"current_steps": 456, "total_steps": 488, "loss": 0.0817, "lr": 1.3053048099989807e-06, "epoch": 1.8688524590163933, "percentage": 93.44, "elapsed_time": "1:30:04", "remaining_time": "0:06:19"}
459
+ {"current_steps": 457, "total_steps": 488, "loss": 0.0928, "lr": 1.2253276506496547e-06, "epoch": 1.8729508196721312, "percentage": 93.65, "elapsed_time": "1:30:16", "remaining_time": "0:06:07"}
460
+ {"current_steps": 458, "total_steps": 488, "loss": 0.0685, "lr": 1.1478483232257088e-06, "epoch": 1.8770491803278688, "percentage": 93.85, "elapsed_time": "1:30:27", "remaining_time": "0:05:55"}
461
+ {"current_steps": 459, "total_steps": 488, "loss": 0.0677, "lr": 1.0728707955721006e-06, "epoch": 1.8811475409836067, "percentage": 94.06, "elapsed_time": "1:30:39", "remaining_time": "0:05:43"}
462
+ {"current_steps": 460, "total_steps": 488, "loss": 0.0807, "lr": 1.000398907412453e-06, "epoch": 1.8852459016393444, "percentage": 94.26, "elapsed_time": "1:30:51", "remaining_time": "0:05:31"}
463
+ {"current_steps": 461, "total_steps": 488, "loss": 0.076, "lr": 9.304363701524654e-07, "epoch": 1.889344262295082, "percentage": 94.47, "elapsed_time": "1:31:03", "remaining_time": "0:05:19"}
464
+ {"current_steps": 462, "total_steps": 488, "loss": 0.0735, "lr": 8.629867666897773e-07, "epoch": 1.8934426229508197, "percentage": 94.67, "elapsed_time": "1:31:14", "remaining_time": "0:05:08"}
465
+ {"current_steps": 463, "total_steps": 488, "loss": 0.0749, "lr": 7.980535512305376e-07, "epoch": 1.8975409836065573, "percentage": 94.88, "elapsed_time": "1:31:26", "remaining_time": "0:04:56"}
466
+ {"current_steps": 464, "total_steps": 488, "loss": 0.0739, "lr": 7.356400491124737e-07, "epoch": 1.901639344262295, "percentage": 95.08, "elapsed_time": "1:31:38", "remaining_time": "0:04:44"}
467
+ {"current_steps": 465, "total_steps": 488, "loss": 0.0635, "lr": 6.757494566346445e-07, "epoch": 1.9057377049180326, "percentage": 95.29, "elapsed_time": "1:31:50", "remaining_time": "0:04:32"}
468
+ {"current_steps": 466, "total_steps": 488, "loss": 0.0978, "lr": 6.183848408936709e-07, "epoch": 1.9098360655737705, "percentage": 95.49, "elapsed_time": "1:32:01", "remaining_time": "0:04:20"}
469
+ {"current_steps": 467, "total_steps": 488, "loss": 0.0728, "lr": 5.635491396267456e-07, "epoch": 1.9139344262295082, "percentage": 95.7, "elapsed_time": "1:32:13", "remaining_time": "0:04:08"}
470
+ {"current_steps": 468, "total_steps": 488, "loss": 0.0735, "lr": 5.112451610611469e-07, "epoch": 1.918032786885246, "percentage": 95.9, "elapsed_time": "1:32:25", "remaining_time": "0:03:56"}
471
+ {"current_steps": 469, "total_steps": 488, "loss": 0.0845, "lr": 4.614755837704321e-07, "epoch": 1.9221311475409837, "percentage": 96.11, "elapsed_time": "1:32:37", "remaining_time": "0:03:45"}
472
+ {"current_steps": 470, "total_steps": 488, "loss": 0.079, "lr": 4.14242956537253e-07, "epoch": 1.9262295081967213, "percentage": 96.31, "elapsed_time": "1:32:48", "remaining_time": "0:03:33"}
473
+ {"current_steps": 471, "total_steps": 488, "loss": 0.0787, "lr": 3.69549698222843e-07, "epoch": 1.930327868852459, "percentage": 96.52, "elapsed_time": "1:33:00", "remaining_time": "0:03:21"}
474
+ {"current_steps": 472, "total_steps": 488, "loss": 0.0901, "lr": 3.273980976431501e-07, "epoch": 1.9344262295081966, "percentage": 96.72, "elapsed_time": "1:33:12", "remaining_time": "0:03:09"}
475
+ {"current_steps": 473, "total_steps": 488, "loss": 0.0767, "lr": 2.8779031345159136e-07, "epoch": 1.9385245901639343, "percentage": 96.93, "elapsed_time": "1:33:24", "remaining_time": "0:02:57"}
476
+ {"current_steps": 474, "total_steps": 488, "loss": 0.0928, "lr": 2.5072837402854157e-07, "epoch": 1.9426229508196722, "percentage": 97.13, "elapsed_time": "1:33:36", "remaining_time": "0:02:45"}
477
+ {"current_steps": 475, "total_steps": 488, "loss": 0.0944, "lr": 2.162141773774329e-07, "epoch": 1.9467213114754098, "percentage": 97.34, "elapsed_time": "1:33:47", "remaining_time": "0:02:34"}
478
+ {"current_steps": 476, "total_steps": 488, "loss": 0.0818, "lr": 1.842494910275605e-07, "epoch": 1.9508196721311475, "percentage": 97.54, "elapsed_time": "1:33:59", "remaining_time": "0:02:22"}
479
+ {"current_steps": 477, "total_steps": 488, "loss": 0.0633, "lr": 1.5483595194356048e-07, "epoch": 1.9549180327868854, "percentage": 97.75, "elapsed_time": "1:34:11", "remaining_time": "0:02:10"}
480
+ {"current_steps": 478, "total_steps": 488, "loss": 0.0694, "lr": 1.2797506644159351e-07, "epoch": 1.959016393442623, "percentage": 97.95, "elapsed_time": "1:34:23", "remaining_time": "0:01:58"}
481
+ {"current_steps": 479, "total_steps": 488, "loss": 0.065, "lr": 1.0366821011218997e-07, "epoch": 1.9631147540983607, "percentage": 98.16, "elapsed_time": "1:34:34", "remaining_time": "0:01:46"}
482
+ {"current_steps": 480, "total_steps": 488, "loss": 0.0831, "lr": 8.191662774980625e-08, "epoch": 1.9672131147540983, "percentage": 98.36, "elapsed_time": "1:34:46", "remaining_time": "0:01:34"}
483
+ {"current_steps": 481, "total_steps": 488, "loss": 0.0849, "lr": 6.272143328907575e-08, "epoch": 1.971311475409836, "percentage": 98.57, "elapsed_time": "1:34:58", "remaining_time": "0:01:22"}
484
+ {"current_steps": 482, "total_steps": 488, "loss": 0.0773, "lr": 4.608360974776571e-08, "epoch": 1.9754098360655736, "percentage": 98.77, "elapsed_time": "1:35:10", "remaining_time": "0:01:11"}
485
+ {"current_steps": 483, "total_steps": 488, "loss": 0.1115, "lr": 3.200400917643398e-08, "epoch": 1.9795081967213115, "percentage": 98.98, "elapsed_time": "1:35:22", "remaining_time": "0:00:59"}
486
+ {"current_steps": 484, "total_steps": 488, "loss": 0.0668, "lr": 2.048335261479739e-08, "epoch": 1.9836065573770492, "percentage": 99.18, "elapsed_time": "1:35:34", "remaining_time": "0:00:47"}
487
+ {"current_steps": 485, "total_steps": 488, "loss": 0.0768, "lr": 1.152223005479458e-08, "epoch": 1.987704918032787, "percentage": 99.39, "elapsed_time": "1:35:45", "remaining_time": "0:00:35"}
488
+ {"current_steps": 486, "total_steps": 488, "loss": 0.0691, "lr": 5.121100410393487e-09, "epoch": 1.9918032786885247, "percentage": 99.59, "elapsed_time": "1:35:57", "remaining_time": "0:00:23"}
489
+ {"current_steps": 487, "total_steps": 488, "loss": 0.082, "lr": 1.2802914940601707e-09, "epoch": 1.9959016393442623, "percentage": 99.8, "elapsed_time": "1:36:09", "remaining_time": "0:00:11"}
490
+ {"current_steps": 488, "total_steps": 488, "loss": 0.0848, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "1:36:21", "remaining_time": "0:00:00"}
491
+ {"current_steps": 488, "total_steps": 488, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "1:37:00", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,3474 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 200,
6
+ "global_step": 488,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004098360655737705,
13
+ "grad_norm": 0.10885735931524154,
14
+ "learning_rate": 2.040816326530612e-06,
15
+ "loss": 0.5811,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.00819672131147541,
20
+ "grad_norm": 0.09543984170626801,
21
+ "learning_rate": 4.081632653061224e-06,
22
+ "loss": 0.5563,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.012295081967213115,
27
+ "grad_norm": 0.10737563422882106,
28
+ "learning_rate": 6.122448979591837e-06,
29
+ "loss": 0.6131,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.01639344262295082,
34
+ "grad_norm": 0.10229836665000518,
35
+ "learning_rate": 8.163265306122448e-06,
36
+ "loss": 0.5505,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.020491803278688523,
41
+ "grad_norm": 0.10892687282476174,
42
+ "learning_rate": 1.0204081632653061e-05,
43
+ "loss": 0.6017,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.02459016393442623,
48
+ "grad_norm": 0.10094785009524743,
49
+ "learning_rate": 1.2244897959183674e-05,
50
+ "loss": 0.5789,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.028688524590163935,
55
+ "grad_norm": 0.10851202963964662,
56
+ "learning_rate": 1.4285714285714285e-05,
57
+ "loss": 0.5539,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.03278688524590164,
62
+ "grad_norm": 0.12753413559171203,
63
+ "learning_rate": 1.6326530612244897e-05,
64
+ "loss": 0.5965,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.036885245901639344,
69
+ "grad_norm": 0.0919789082515372,
70
+ "learning_rate": 1.836734693877551e-05,
71
+ "loss": 0.4591,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.040983606557377046,
76
+ "grad_norm": 0.14112664773884412,
77
+ "learning_rate": 2.0408163265306123e-05,
78
+ "loss": 0.5436,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.045081967213114756,
83
+ "grad_norm": 0.1499072991458913,
84
+ "learning_rate": 2.2448979591836737e-05,
85
+ "loss": 0.5932,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.04918032786885246,
90
+ "grad_norm": 0.16694128474867986,
91
+ "learning_rate": 2.448979591836735e-05,
92
+ "loss": 0.6225,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.05327868852459016,
97
+ "grad_norm": 0.1588995885349821,
98
+ "learning_rate": 2.6530612244897963e-05,
99
+ "loss": 0.5069,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.05737704918032787,
104
+ "grad_norm": 0.18129701774719173,
105
+ "learning_rate": 2.857142857142857e-05,
106
+ "loss": 0.5482,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.06147540983606557,
111
+ "grad_norm": 0.2183572552487636,
112
+ "learning_rate": 3.061224489795919e-05,
113
+ "loss": 0.5687,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.06557377049180328,
118
+ "grad_norm": 0.18334307701927258,
119
+ "learning_rate": 3.265306122448979e-05,
120
+ "loss": 0.5238,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.06967213114754098,
125
+ "grad_norm": 0.217210631302923,
126
+ "learning_rate": 3.469387755102041e-05,
127
+ "loss": 0.5037,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.07377049180327869,
132
+ "grad_norm": 0.2215307239284415,
133
+ "learning_rate": 3.673469387755102e-05,
134
+ "loss": 0.5432,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.0778688524590164,
139
+ "grad_norm": 0.17636357532215036,
140
+ "learning_rate": 3.8775510204081634e-05,
141
+ "loss": 0.539,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.08196721311475409,
146
+ "grad_norm": 0.1328655781521927,
147
+ "learning_rate": 4.0816326530612245e-05,
148
+ "loss": 0.424,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.0860655737704918,
153
+ "grad_norm": 0.14615441733689596,
154
+ "learning_rate": 4.2857142857142856e-05,
155
+ "loss": 0.4999,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.09016393442622951,
160
+ "grad_norm": 0.14657086694880161,
161
+ "learning_rate": 4.4897959183673474e-05,
162
+ "loss": 0.4599,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.0942622950819672,
167
+ "grad_norm": 0.18601844475495982,
168
+ "learning_rate": 4.6938775510204086e-05,
169
+ "loss": 0.4769,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.09836065573770492,
174
+ "grad_norm": 0.14918312992832872,
175
+ "learning_rate": 4.89795918367347e-05,
176
+ "loss": 0.524,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.10245901639344263,
181
+ "grad_norm": 0.12351557422248065,
182
+ "learning_rate": 5.102040816326531e-05,
183
+ "loss": 0.4415,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.10655737704918032,
188
+ "grad_norm": 0.1426398947034758,
189
+ "learning_rate": 5.3061224489795926e-05,
190
+ "loss": 0.4785,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.11065573770491803,
195
+ "grad_norm": 0.10410317953089403,
196
+ "learning_rate": 5.510204081632653e-05,
197
+ "loss": 0.4654,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.11475409836065574,
202
+ "grad_norm": 0.10825565630969619,
203
+ "learning_rate": 5.714285714285714e-05,
204
+ "loss": 0.3948,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.11885245901639344,
209
+ "grad_norm": 0.10198414371268509,
210
+ "learning_rate": 5.918367346938776e-05,
211
+ "loss": 0.3919,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.12295081967213115,
216
+ "grad_norm": 0.11312291852027019,
217
+ "learning_rate": 6.122448979591838e-05,
218
+ "loss": 0.3686,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.12704918032786885,
223
+ "grad_norm": 0.09311311604978195,
224
+ "learning_rate": 6.326530612244899e-05,
225
+ "loss": 0.3657,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.13114754098360656,
230
+ "grad_norm": 0.09879942365923487,
231
+ "learning_rate": 6.530612244897959e-05,
232
+ "loss": 0.3603,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.13524590163934427,
237
+ "grad_norm": 0.10475690388929891,
238
+ "learning_rate": 6.73469387755102e-05,
239
+ "loss": 0.3936,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.13934426229508196,
244
+ "grad_norm": 0.10155707550196463,
245
+ "learning_rate": 6.938775510204082e-05,
246
+ "loss": 0.3886,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.14344262295081966,
251
+ "grad_norm": 0.0926126977092899,
252
+ "learning_rate": 7.142857142857143e-05,
253
+ "loss": 0.3437,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.14754098360655737,
258
+ "grad_norm": 0.10340542063874245,
259
+ "learning_rate": 7.346938775510205e-05,
260
+ "loss": 0.3732,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.15163934426229508,
265
+ "grad_norm": 0.08967895723482798,
266
+ "learning_rate": 7.551020408163266e-05,
267
+ "loss": 0.3843,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.1557377049180328,
272
+ "grad_norm": 0.08021185638722013,
273
+ "learning_rate": 7.755102040816327e-05,
274
+ "loss": 0.3499,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.1598360655737705,
279
+ "grad_norm": 0.08290688475528614,
280
+ "learning_rate": 7.959183673469388e-05,
281
+ "loss": 0.3199,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.16393442622950818,
286
+ "grad_norm": 0.1025320920521767,
287
+ "learning_rate": 8.163265306122449e-05,
288
+ "loss": 0.3394,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.1680327868852459,
293
+ "grad_norm": 0.10293043209271259,
294
+ "learning_rate": 8.367346938775511e-05,
295
+ "loss": 0.3431,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.1721311475409836,
300
+ "grad_norm": 0.09025360865879611,
301
+ "learning_rate": 8.571428571428571e-05,
302
+ "loss": 0.3199,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.1762295081967213,
307
+ "grad_norm": 0.0798997188410711,
308
+ "learning_rate": 8.775510204081632e-05,
309
+ "loss": 0.2775,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.18032786885245902,
314
+ "grad_norm": 0.0897092505499119,
315
+ "learning_rate": 8.979591836734695e-05,
316
+ "loss": 0.3086,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.18442622950819673,
321
+ "grad_norm": 0.09029803208911406,
322
+ "learning_rate": 9.183673469387756e-05,
323
+ "loss": 0.2814,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.1885245901639344,
328
+ "grad_norm": 0.11450944516178525,
329
+ "learning_rate": 9.387755102040817e-05,
330
+ "loss": 0.3394,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.19262295081967212,
335
+ "grad_norm": 0.09462426859596793,
336
+ "learning_rate": 9.591836734693878e-05,
337
+ "loss": 0.2795,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.19672131147540983,
342
+ "grad_norm": 0.09550025936843255,
343
+ "learning_rate": 9.79591836734694e-05,
344
+ "loss": 0.2901,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.20081967213114754,
349
+ "grad_norm": 0.10107778614583034,
350
+ "learning_rate": 0.0001,
351
+ "loss": 0.2772,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.20491803278688525,
356
+ "grad_norm": 0.10654444377790294,
357
+ "learning_rate": 9.999871970850594e-05,
358
+ "loss": 0.2801,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.20901639344262296,
363
+ "grad_norm": 0.09722504544564385,
364
+ "learning_rate": 9.99948788995896e-05,
365
+ "loss": 0.2908,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.21311475409836064,
370
+ "grad_norm": 0.09187510891379361,
371
+ "learning_rate": 9.998847776994521e-05,
372
+ "loss": 0.2662,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.21721311475409835,
377
+ "grad_norm": 0.09903882074067999,
378
+ "learning_rate": 9.99795166473852e-05,
379
+ "loss": 0.3133,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.22131147540983606,
384
+ "grad_norm": 0.10275668687634087,
385
+ "learning_rate": 9.996799599082358e-05,
386
+ "loss": 0.2974,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.22540983606557377,
391
+ "grad_norm": 0.08972023342314824,
392
+ "learning_rate": 9.995391639025224e-05,
393
+ "loss": 0.251,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.22950819672131148,
398
+ "grad_norm": 0.09464401309394976,
399
+ "learning_rate": 9.993727856671093e-05,
400
+ "loss": 0.2477,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.2336065573770492,
405
+ "grad_norm": 0.10011396555704247,
406
+ "learning_rate": 9.99180833722502e-05,
407
+ "loss": 0.2493,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.23770491803278687,
412
+ "grad_norm": 0.11226340201350676,
413
+ "learning_rate": 9.989633178988782e-05,
414
+ "loss": 0.263,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.24180327868852458,
419
+ "grad_norm": 0.09792926575267794,
420
+ "learning_rate": 9.98720249335584e-05,
421
+ "loss": 0.2326,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.2459016393442623,
426
+ "grad_norm": 0.11495988550279207,
427
+ "learning_rate": 9.984516404805643e-05,
428
+ "loss": 0.2696,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.25,
433
+ "grad_norm": 0.0832562354006034,
434
+ "learning_rate": 9.981575050897245e-05,
435
+ "loss": 0.2272,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.2540983606557377,
440
+ "grad_norm": 0.09272122094979285,
441
+ "learning_rate": 9.978378582262258e-05,
442
+ "loss": 0.2277,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.2581967213114754,
447
+ "grad_norm": 0.0926643761595329,
448
+ "learning_rate": 9.974927162597147e-05,
449
+ "loss": 0.2222,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.26229508196721313,
454
+ "grad_norm": 0.09529461804236374,
455
+ "learning_rate": 9.971220968654842e-05,
456
+ "loss": 0.2147,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.26639344262295084,
461
+ "grad_norm": 0.10578872457966666,
462
+ "learning_rate": 9.967260190235686e-05,
463
+ "loss": 0.2395,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.27049180327868855,
468
+ "grad_norm": 0.08716137251502158,
469
+ "learning_rate": 9.963045030177716e-05,
470
+ "loss": 0.191,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.27459016393442626,
475
+ "grad_norm": 0.0933351028764273,
476
+ "learning_rate": 9.958575704346275e-05,
477
+ "loss": 0.2106,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.2786885245901639,
482
+ "grad_norm": 0.09293060930004443,
483
+ "learning_rate": 9.953852441622958e-05,
484
+ "loss": 0.2045,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.2827868852459016,
489
+ "grad_norm": 0.11576298641567612,
490
+ "learning_rate": 9.948875483893885e-05,
491
+ "loss": 0.2129,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.28688524590163933,
496
+ "grad_norm": 0.10041163065836892,
497
+ "learning_rate": 9.943645086037325e-05,
498
+ "loss": 0.2115,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.29098360655737704,
503
+ "grad_norm": 0.11798299846536875,
504
+ "learning_rate": 9.938161515910633e-05,
505
+ "loss": 0.2481,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.29508196721311475,
510
+ "grad_norm": 0.10102114528623451,
511
+ "learning_rate": 9.932425054336536e-05,
512
+ "loss": 0.2177,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.29918032786885246,
517
+ "grad_norm": 0.09976403649412756,
518
+ "learning_rate": 9.926435995088751e-05,
519
+ "loss": 0.1893,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.30327868852459017,
524
+ "grad_norm": 0.11235776084128149,
525
+ "learning_rate": 9.920194644876948e-05,
526
+ "loss": 0.2272,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.3073770491803279,
531
+ "grad_norm": 0.11132462529983536,
532
+ "learning_rate": 9.913701323331024e-05,
533
+ "loss": 0.1853,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.3114754098360656,
538
+ "grad_norm": 0.09930579681430861,
539
+ "learning_rate": 9.906956362984754e-05,
540
+ "loss": 0.1728,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.3155737704918033,
545
+ "grad_norm": 0.09952860431385552,
546
+ "learning_rate": 9.899960109258755e-05,
547
+ "loss": 0.1731,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.319672131147541,
552
+ "grad_norm": 0.12343923967205338,
553
+ "learning_rate": 9.89271292044279e-05,
554
+ "loss": 0.2246,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.3237704918032787,
559
+ "grad_norm": 0.12308319513476172,
560
+ "learning_rate": 9.88521516767743e-05,
561
+ "loss": 0.2027,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.32786885245901637,
566
+ "grad_norm": 0.13087972401563355,
567
+ "learning_rate": 9.877467234935035e-05,
568
+ "loss": 0.2154,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.3319672131147541,
573
+ "grad_norm": 0.1045904395470389,
574
+ "learning_rate": 9.869469519000103e-05,
575
+ "loss": 0.178,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.3360655737704918,
580
+ "grad_norm": 0.14375976436812823,
581
+ "learning_rate": 9.861222429448939e-05,
582
+ "loss": 0.1973,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.3401639344262295,
587
+ "grad_norm": 0.11828496216829337,
588
+ "learning_rate": 9.852726388628689e-05,
589
+ "loss": 0.1611,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.3442622950819672,
594
+ "grad_norm": 0.11221666880904256,
595
+ "learning_rate": 9.843981831635704e-05,
596
+ "loss": 0.1885,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.3483606557377049,
601
+ "grad_norm": 0.12144099494087787,
602
+ "learning_rate": 9.834989206293264e-05,
603
+ "loss": 0.1896,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.3524590163934426,
608
+ "grad_norm": 0.11011171362279154,
609
+ "learning_rate": 9.825748973128633e-05,
610
+ "loss": 0.1811,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.35655737704918034,
615
+ "grad_norm": 0.12633893642514252,
616
+ "learning_rate": 9.816261605349493e-05,
617
+ "loss": 0.1992,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.36065573770491804,
622
+ "grad_norm": 0.12484980936203433,
623
+ "learning_rate": 9.806527588819692e-05,
624
+ "loss": 0.1956,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.36475409836065575,
629
+ "grad_norm": 0.12944319616467373,
630
+ "learning_rate": 9.796547422034374e-05,
631
+ "loss": 0.1825,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.36885245901639346,
636
+ "grad_norm": 0.13039578366779397,
637
+ "learning_rate": 9.786321616094444e-05,
638
+ "loss": 0.1749,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.3729508196721312,
643
+ "grad_norm": 0.16458414758299922,
644
+ "learning_rate": 9.775850694680397e-05,
645
+ "loss": 0.1944,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.3770491803278688,
650
+ "grad_norm": 0.13219546608772784,
651
+ "learning_rate": 9.765135194025499e-05,
652
+ "loss": 0.1771,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.38114754098360654,
657
+ "grad_norm": 0.14006629744621393,
658
+ "learning_rate": 9.754175662888321e-05,
659
+ "loss": 0.1661,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.38524590163934425,
664
+ "grad_norm": 0.14470317387177975,
665
+ "learning_rate": 9.742972662524644e-05,
666
+ "loss": 0.1981,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.38934426229508196,
671
+ "grad_norm": 0.13843078519217147,
672
+ "learning_rate": 9.731526766658712e-05,
673
+ "loss": 0.1735,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.39344262295081966,
678
+ "grad_norm": 0.1353061977442374,
679
+ "learning_rate": 9.719838561453848e-05,
680
+ "loss": 0.1582,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.3975409836065574,
685
+ "grad_norm": 0.1357950229192003,
686
+ "learning_rate": 9.707908645482442e-05,
687
+ "loss": 0.18,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.4016393442622951,
692
+ "grad_norm": 0.14178080733722706,
693
+ "learning_rate": 9.695737629695292e-05,
694
+ "loss": 0.158,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.4057377049180328,
699
+ "grad_norm": 0.1515071621238269,
700
+ "learning_rate": 9.683326137390314e-05,
701
+ "loss": 0.1829,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.4098360655737705,
706
+ "grad_norm": 0.12126660667998342,
707
+ "learning_rate": 9.670674804180633e-05,
708
+ "loss": 0.158,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.4139344262295082,
713
+ "grad_norm": 0.15274368057486823,
714
+ "learning_rate": 9.657784277962017e-05,
715
+ "loss": 0.1912,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.4180327868852459,
720
+ "grad_norm": 0.14586661447264065,
721
+ "learning_rate": 9.644655218879713e-05,
722
+ "loss": 0.1585,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.42213114754098363,
727
+ "grad_norm": 0.13918569664369232,
728
+ "learning_rate": 9.631288299294625e-05,
729
+ "loss": 0.1642,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.4262295081967213,
734
+ "grad_norm": 0.13062238504926085,
735
+ "learning_rate": 9.617684203748894e-05,
736
+ "loss": 0.1719,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.430327868852459,
741
+ "grad_norm": 0.13095311012132155,
742
+ "learning_rate": 9.603843628930827e-05,
743
+ "loss": 0.1366,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.4344262295081967,
748
+ "grad_norm": 0.1378443383619325,
749
+ "learning_rate": 9.589767283639238e-05,
750
+ "loss": 0.1484,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.4385245901639344,
755
+ "grad_norm": 0.1588568831317976,
756
+ "learning_rate": 9.575455888747129e-05,
757
+ "loss": 0.1426,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.4426229508196721,
762
+ "grad_norm": 0.14141099713374855,
763
+ "learning_rate": 9.560910177164788e-05,
764
+ "loss": 0.1442,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.44672131147540983,
769
+ "grad_norm": 0.15511211544124912,
770
+ "learning_rate": 9.546130893802246e-05,
771
+ "loss": 0.1495,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.45081967213114754,
776
+ "grad_norm": 0.13807932571830756,
777
+ "learning_rate": 9.531118795531136e-05,
778
+ "loss": 0.1395,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.45491803278688525,
783
+ "grad_norm": 0.15789654305622566,
784
+ "learning_rate": 9.515874651145926e-05,
785
+ "loss": 0.1871,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.45901639344262296,
790
+ "grad_norm": 0.15796719793789657,
791
+ "learning_rate": 9.50039924132455e-05,
792
+ "loss": 0.1634,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.46311475409836067,
797
+ "grad_norm": 0.14938155771658035,
798
+ "learning_rate": 9.484693358588435e-05,
799
+ "loss": 0.1819,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.4672131147540984,
804
+ "grad_norm": 0.18259563364597392,
805
+ "learning_rate": 9.468757807261899e-05,
806
+ "loss": 0.1749,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.4713114754098361,
811
+ "grad_norm": 0.17556492537142315,
812
+ "learning_rate": 9.452593403430978e-05,
813
+ "loss": 0.1856,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.47540983606557374,
818
+ "grad_norm": 0.1602448986838981,
819
+ "learning_rate": 9.436200974901619e-05,
820
+ "loss": 0.1723,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.47950819672131145,
825
+ "grad_norm": 0.1691861443696351,
826
+ "learning_rate": 9.419581361157295e-05,
827
+ "loss": 0.1927,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.48360655737704916,
832
+ "grad_norm": 0.16086945108806114,
833
+ "learning_rate": 9.402735413316012e-05,
834
+ "loss": 0.1593,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.48770491803278687,
839
+ "grad_norm": 0.17451078487412305,
840
+ "learning_rate": 9.385663994086717e-05,
841
+ "loss": 0.1463,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.4918032786885246,
846
+ "grad_norm": 0.1702475093023926,
847
+ "learning_rate": 9.368367977725126e-05,
848
+ "loss": 0.1757,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.4959016393442623,
853
+ "grad_norm": 0.16478933308887905,
854
+ "learning_rate": 9.350848249988942e-05,
855
+ "loss": 0.1488,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.5,
860
+ "grad_norm": 0.16273089994599113,
861
+ "learning_rate": 9.333105708092499e-05,
862
+ "loss": 0.1689,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.5040983606557377,
867
+ "grad_norm": 0.1409960739640557,
868
+ "learning_rate": 9.315141260660823e-05,
869
+ "loss": 0.1389,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.5081967213114754,
874
+ "grad_norm": 0.15124176821591653,
875
+ "learning_rate": 9.296955827683075e-05,
876
+ "loss": 0.1521,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.5122950819672131,
881
+ "grad_norm": 0.1587729268931332,
882
+ "learning_rate": 9.278550340465469e-05,
883
+ "loss": 0.1717,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.5163934426229508,
888
+ "grad_norm": 0.13589035641321393,
889
+ "learning_rate": 9.259925741583549e-05,
890
+ "loss": 0.1347,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.5204918032786885,
895
+ "grad_norm": 0.13759923174432373,
896
+ "learning_rate": 9.241082984833937e-05,
897
+ "loss": 0.1378,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.5245901639344263,
902
+ "grad_norm": 0.15855139799675505,
903
+ "learning_rate": 9.222023035185481e-05,
904
+ "loss": 0.1545,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.5286885245901639,
909
+ "grad_norm": 0.15545461669283303,
910
+ "learning_rate": 9.20274686872984e-05,
911
+ "loss": 0.1502,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.5327868852459017,
916
+ "grad_norm": 0.15510775952098196,
917
+ "learning_rate": 9.183255472631486e-05,
918
+ "loss": 0.1338,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.5368852459016393,
923
+ "grad_norm": 0.2008082231462037,
924
+ "learning_rate": 9.163549845077172e-05,
925
+ "loss": 0.1671,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.5409836065573771,
930
+ "grad_norm": 0.16870678428794317,
931
+ "learning_rate": 9.143630995224785e-05,
932
+ "loss": 0.1512,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.5450819672131147,
937
+ "grad_norm": 0.16476629914112087,
938
+ "learning_rate": 9.123499943151692e-05,
939
+ "loss": 0.1565,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.5491803278688525,
944
+ "grad_norm": 0.17078350636291376,
945
+ "learning_rate": 9.10315771980248e-05,
946
+ "loss": 0.153,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.5532786885245902,
951
+ "grad_norm": 0.15909313462691074,
952
+ "learning_rate": 9.082605366936168e-05,
953
+ "loss": 0.1392,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.5573770491803278,
958
+ "grad_norm": 0.16223350919827026,
959
+ "learning_rate": 9.061843937072861e-05,
960
+ "loss": 0.1677,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.5614754098360656,
965
+ "grad_norm": 0.17376681067395994,
966
+ "learning_rate": 9.040874493439839e-05,
967
+ "loss": 0.1383,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.5655737704918032,
972
+ "grad_norm": 0.1641172902680086,
973
+ "learning_rate": 9.019698109917119e-05,
974
+ "loss": 0.1668,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.569672131147541,
979
+ "grad_norm": 0.15234776968115493,
980
+ "learning_rate": 8.998315870982444e-05,
981
+ "loss": 0.1218,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.5737704918032787,
986
+ "grad_norm": 0.1872820726954906,
987
+ "learning_rate": 8.976728871655762e-05,
988
+ "loss": 0.1676,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.5778688524590164,
993
+ "grad_norm": 0.16023446148249956,
994
+ "learning_rate": 8.954938217443136e-05,
995
+ "loss": 0.1437,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.5819672131147541,
1000
+ "grad_norm": 0.19633500296640014,
1001
+ "learning_rate": 8.932945024280139e-05,
1002
+ "loss": 0.1739,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.5860655737704918,
1007
+ "grad_norm": 0.1704501675079385,
1008
+ "learning_rate": 8.910750418474693e-05,
1009
+ "loss": 0.1537,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.5901639344262295,
1014
+ "grad_norm": 0.1800207222497811,
1015
+ "learning_rate": 8.8883555366494e-05,
1016
+ "loss": 0.1475,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.5942622950819673,
1021
+ "grad_norm": 0.19139439132267907,
1022
+ "learning_rate": 8.865761525683329e-05,
1023
+ "loss": 0.1733,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.5983606557377049,
1028
+ "grad_norm": 0.1812519339640167,
1029
+ "learning_rate": 8.842969542653281e-05,
1030
+ "loss": 0.1416,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.6024590163934426,
1035
+ "grad_norm": 0.168458137590727,
1036
+ "learning_rate": 8.819980754774539e-05,
1037
+ "loss": 0.1408,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.6065573770491803,
1042
+ "grad_norm": 0.17241876574464468,
1043
+ "learning_rate": 8.796796339341083e-05,
1044
+ "loss": 0.1404,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.610655737704918,
1049
+ "grad_norm": 0.19062819140366627,
1050
+ "learning_rate": 8.773417483665309e-05,
1051
+ "loss": 0.1442,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.6147540983606558,
1056
+ "grad_norm": 0.15972796819072785,
1057
+ "learning_rate": 8.749845385017221e-05,
1058
+ "loss": 0.1373,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.6188524590163934,
1063
+ "grad_norm": 0.16127899772885856,
1064
+ "learning_rate": 8.726081250563114e-05,
1065
+ "loss": 0.1386,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.6229508196721312,
1070
+ "grad_norm": 0.18918243767524542,
1071
+ "learning_rate": 8.702126297303754e-05,
1072
+ "loss": 0.1563,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.6270491803278688,
1077
+ "grad_norm": 0.18155811710350117,
1078
+ "learning_rate": 8.677981752012061e-05,
1079
+ "loss": 0.1457,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.6311475409836066,
1084
+ "grad_norm": 0.17684911682878873,
1085
+ "learning_rate": 8.65364885117027e-05,
1086
+ "loss": 0.1451,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.6352459016393442,
1091
+ "grad_norm": 0.17235430323704784,
1092
+ "learning_rate": 8.629128840906622e-05,
1093
+ "loss": 0.1346,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.639344262295082,
1098
+ "grad_norm": 0.18565663737598154,
1099
+ "learning_rate": 8.604422976931538e-05,
1100
+ "loss": 0.1447,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.6434426229508197,
1105
+ "grad_norm": 0.20944409129337707,
1106
+ "learning_rate": 8.579532524473322e-05,
1107
+ "loss": 0.1274,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.6475409836065574,
1112
+ "grad_norm": 0.17754246041424776,
1113
+ "learning_rate": 8.554458758213352e-05,
1114
+ "loss": 0.1329,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.6516393442622951,
1119
+ "grad_norm": 0.17810845667806482,
1120
+ "learning_rate": 8.529202962220818e-05,
1121
+ "loss": 0.1361,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.6557377049180327,
1126
+ "grad_norm": 0.1608582250209417,
1127
+ "learning_rate": 8.50376642988695e-05,
1128
+ "loss": 0.1197,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.6598360655737705,
1133
+ "grad_norm": 0.17739164241648425,
1134
+ "learning_rate": 8.478150463858788e-05,
1135
+ "loss": 0.1593,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.6639344262295082,
1140
+ "grad_norm": 0.1656512173363593,
1141
+ "learning_rate": 8.452356375972466e-05,
1142
+ "loss": 0.1339,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.6680327868852459,
1147
+ "grad_norm": 0.1788275198288848,
1148
+ "learning_rate": 8.42638548718604e-05,
1149
+ "loss": 0.1658,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.6721311475409836,
1154
+ "grad_norm": 0.25206698616186196,
1155
+ "learning_rate": 8.40023912751183e-05,
1156
+ "loss": 0.1391,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.6762295081967213,
1161
+ "grad_norm": 0.17369829387561495,
1162
+ "learning_rate": 8.373918635948311e-05,
1163
+ "loss": 0.1332,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.680327868852459,
1168
+ "grad_norm": 0.16861239567737674,
1169
+ "learning_rate": 8.34742536041154e-05,
1170
+ "loss": 0.1263,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.6844262295081968,
1175
+ "grad_norm": 0.1929344032900212,
1176
+ "learning_rate": 8.320760657666133e-05,
1177
+ "loss": 0.1278,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.6885245901639344,
1182
+ "grad_norm": 0.17898592779538816,
1183
+ "learning_rate": 8.293925893255771e-05,
1184
+ "loss": 0.1336,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.6926229508196722,
1189
+ "grad_norm": 0.19635180613433656,
1190
+ "learning_rate": 8.266922441433284e-05,
1191
+ "loss": 0.1453,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.6967213114754098,
1196
+ "grad_norm": 0.16858384058703138,
1197
+ "learning_rate": 8.239751685090253e-05,
1198
+ "loss": 0.1139,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.7008196721311475,
1203
+ "grad_norm": 0.19395668797648288,
1204
+ "learning_rate": 8.212415015686213e-05,
1205
+ "loss": 0.1251,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.7049180327868853,
1210
+ "grad_norm": 0.19396674290108995,
1211
+ "learning_rate": 8.184913833177372e-05,
1212
+ "loss": 0.1569,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.7090163934426229,
1217
+ "grad_norm": 0.18760069818410455,
1218
+ "learning_rate": 8.157249545944934e-05,
1219
+ "loss": 0.1519,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.7131147540983607,
1224
+ "grad_norm": 0.18143260363629768,
1225
+ "learning_rate": 8.129423570722964e-05,
1226
+ "loss": 0.1338,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.7172131147540983,
1231
+ "grad_norm": 0.1853756885298579,
1232
+ "learning_rate": 8.101437332525837e-05,
1233
+ "loss": 0.1359,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.7213114754098361,
1238
+ "grad_norm": 0.17905848511103561,
1239
+ "learning_rate": 8.073292264575263e-05,
1240
+ "loss": 0.1197,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.7254098360655737,
1245
+ "grad_norm": 0.1693931071052849,
1246
+ "learning_rate": 8.044989808226885e-05,
1247
+ "loss": 0.1183,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.7295081967213115,
1252
+ "grad_norm": 0.19298527281872263,
1253
+ "learning_rate": 8.016531412896468e-05,
1254
+ "loss": 0.1372,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.7336065573770492,
1259
+ "grad_norm": 0.18769205530531333,
1260
+ "learning_rate": 7.98791853598567e-05,
1261
+ "loss": 0.1214,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.7377049180327869,
1266
+ "grad_norm": 0.18199077690644846,
1267
+ "learning_rate": 7.959152642807411e-05,
1268
+ "loss": 0.1364,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.7418032786885246,
1273
+ "grad_norm": 0.18257163156810308,
1274
+ "learning_rate": 7.930235206510821e-05,
1275
+ "loss": 0.1209,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.7459016393442623,
1280
+ "grad_norm": 0.18002525316518497,
1281
+ "learning_rate": 7.901167708005812e-05,
1282
+ "loss": 0.1264,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.75,
1287
+ "grad_norm": 0.18519588230164483,
1288
+ "learning_rate": 7.871951635887228e-05,
1289
+ "loss": 0.1287,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.7540983606557377,
1294
+ "grad_norm": 0.1848979809474253,
1295
+ "learning_rate": 7.842588486358611e-05,
1296
+ "loss": 0.1268,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.7581967213114754,
1301
+ "grad_norm": 0.22212797312114452,
1302
+ "learning_rate": 7.813079763155587e-05,
1303
+ "loss": 0.149,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.7622950819672131,
1308
+ "grad_norm": 0.17739677448000538,
1309
+ "learning_rate": 7.783426977468847e-05,
1310
+ "loss": 0.1154,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.7663934426229508,
1315
+ "grad_norm": 0.18735600614636536,
1316
+ "learning_rate": 7.753631647866764e-05,
1317
+ "loss": 0.1287,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.7704918032786885,
1322
+ "grad_norm": 0.1927980118919512,
1323
+ "learning_rate": 7.723695300217619e-05,
1324
+ "loss": 0.1442,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.7745901639344263,
1329
+ "grad_norm": 0.17103075338378548,
1330
+ "learning_rate": 7.693619467611464e-05,
1331
+ "loss": 0.1122,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.7786885245901639,
1336
+ "grad_norm": 0.19226189850908318,
1337
+ "learning_rate": 7.663405690281602e-05,
1338
+ "loss": 0.1434,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.7827868852459017,
1343
+ "grad_norm": 0.2022866385878345,
1344
+ "learning_rate": 7.633055515525721e-05,
1345
+ "loss": 0.1387,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.7868852459016393,
1350
+ "grad_norm": 0.17280425691572138,
1351
+ "learning_rate": 7.602570497626641e-05,
1352
+ "loss": 0.1247,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.7909836065573771,
1357
+ "grad_norm": 0.1953392846226545,
1358
+ "learning_rate": 7.571952197772733e-05,
1359
+ "loss": 0.1346,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.7950819672131147,
1364
+ "grad_norm": 0.1819827161854772,
1365
+ "learning_rate": 7.541202183977944e-05,
1366
+ "loss": 0.1343,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.7991803278688525,
1371
+ "grad_norm": 0.18956673745527652,
1372
+ "learning_rate": 7.510322031001523e-05,
1373
+ "loss": 0.1403,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.8032786885245902,
1378
+ "grad_norm": 0.17710158780741328,
1379
+ "learning_rate": 7.479313320267356e-05,
1380
+ "loss": 0.1203,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.8073770491803278,
1385
+ "grad_norm": 0.17208339576484202,
1386
+ "learning_rate": 7.448177639782988e-05,
1387
+ "loss": 0.1021,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.8114754098360656,
1392
+ "grad_norm": 0.19679964840557646,
1393
+ "learning_rate": 7.416916584058291e-05,
1394
+ "loss": 0.1324,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.8155737704918032,
1399
+ "grad_norm": 0.18208263603534253,
1400
+ "learning_rate": 7.385531754023818e-05,
1401
+ "loss": 0.1246,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.819672131147541,
1406
+ "grad_norm": 0.17562187461702322,
1407
+ "learning_rate": 7.354024756948805e-05,
1408
+ "loss": 0.1143,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.819672131147541,
1413
+ "eval_loss": 0.13085269927978516,
1414
+ "eval_runtime": 15.8068,
1415
+ "eval_samples_per_second": 1.265,
1416
+ "eval_steps_per_second": 0.316,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.8237704918032787,
1421
+ "grad_norm": 0.17110972100979424,
1422
+ "learning_rate": 7.322397206358868e-05,
1423
+ "loss": 0.1242,
1424
+ "step": 201
1425
+ },
1426
+ {
1427
+ "epoch": 0.8278688524590164,
1428
+ "grad_norm": 0.18437063894283692,
1429
+ "learning_rate": 7.290650721953365e-05,
1430
+ "loss": 0.1102,
1431
+ "step": 202
1432
+ },
1433
+ {
1434
+ "epoch": 0.8319672131147541,
1435
+ "grad_norm": 0.20407404831982653,
1436
+ "learning_rate": 7.258786929522454e-05,
1437
+ "loss": 0.1402,
1438
+ "step": 203
1439
+ },
1440
+ {
1441
+ "epoch": 0.8360655737704918,
1442
+ "grad_norm": 0.18871267379413306,
1443
+ "learning_rate": 7.226807460863834e-05,
1444
+ "loss": 0.1188,
1445
+ "step": 204
1446
+ },
1447
+ {
1448
+ "epoch": 0.8401639344262295,
1449
+ "grad_norm": 0.1818608820461858,
1450
+ "learning_rate": 7.194713953699171e-05,
1451
+ "loss": 0.1271,
1452
+ "step": 205
1453
+ },
1454
+ {
1455
+ "epoch": 0.8442622950819673,
1456
+ "grad_norm": 0.1963272550808891,
1457
+ "learning_rate": 7.162508051590236e-05,
1458
+ "loss": 0.1391,
1459
+ "step": 206
1460
+ },
1461
+ {
1462
+ "epoch": 0.8483606557377049,
1463
+ "grad_norm": 0.17373436467685702,
1464
+ "learning_rate": 7.130191403854728e-05,
1465
+ "loss": 0.1153,
1466
+ "step": 207
1467
+ },
1468
+ {
1469
+ "epoch": 0.8524590163934426,
1470
+ "grad_norm": 0.19266380445159845,
1471
+ "learning_rate": 7.097765665481818e-05,
1472
+ "loss": 0.1227,
1473
+ "step": 208
1474
+ },
1475
+ {
1476
+ "epoch": 0.8565573770491803,
1477
+ "grad_norm": 0.18106479081023585,
1478
+ "learning_rate": 7.065232497047384e-05,
1479
+ "loss": 0.1144,
1480
+ "step": 209
1481
+ },
1482
+ {
1483
+ "epoch": 0.860655737704918,
1484
+ "grad_norm": 0.19507966902057225,
1485
+ "learning_rate": 7.032593564628982e-05,
1486
+ "loss": 0.1199,
1487
+ "step": 210
1488
+ },
1489
+ {
1490
+ "epoch": 0.8647540983606558,
1491
+ "grad_norm": 0.17636125591066742,
1492
+ "learning_rate": 6.999850539720514e-05,
1493
+ "loss": 0.1183,
1494
+ "step": 211
1495
+ },
1496
+ {
1497
+ "epoch": 0.8688524590163934,
1498
+ "grad_norm": 0.19919789500462576,
1499
+ "learning_rate": 6.967005099146629e-05,
1500
+ "loss": 0.1342,
1501
+ "step": 212
1502
+ },
1503
+ {
1504
+ "epoch": 0.8729508196721312,
1505
+ "grad_norm": 0.19745218824351637,
1506
+ "learning_rate": 6.934058924976855e-05,
1507
+ "loss": 0.1171,
1508
+ "step": 213
1509
+ },
1510
+ {
1511
+ "epoch": 0.8770491803278688,
1512
+ "grad_norm": 0.19184610328273202,
1513
+ "learning_rate": 6.901013704439456e-05,
1514
+ "loss": 0.1339,
1515
+ "step": 214
1516
+ },
1517
+ {
1518
+ "epoch": 0.8811475409836066,
1519
+ "grad_norm": 0.1892246102487988,
1520
+ "learning_rate": 6.86787112983502e-05,
1521
+ "loss": 0.1251,
1522
+ "step": 215
1523
+ },
1524
+ {
1525
+ "epoch": 0.8852459016393442,
1526
+ "grad_norm": 0.19330230046016966,
1527
+ "learning_rate": 6.834632898449804e-05,
1528
+ "loss": 0.1516,
1529
+ "step": 216
1530
+ },
1531
+ {
1532
+ "epoch": 0.889344262295082,
1533
+ "grad_norm": 0.17725855021655712,
1534
+ "learning_rate": 6.801300712468802e-05,
1535
+ "loss": 0.1158,
1536
+ "step": 217
1537
+ },
1538
+ {
1539
+ "epoch": 0.8934426229508197,
1540
+ "grad_norm": 0.1897706357212999,
1541
+ "learning_rate": 6.767876278888585e-05,
1542
+ "loss": 0.134,
1543
+ "step": 218
1544
+ },
1545
+ {
1546
+ "epoch": 0.8975409836065574,
1547
+ "grad_norm": 0.20290492492222809,
1548
+ "learning_rate": 6.734361309429871e-05,
1549
+ "loss": 0.1277,
1550
+ "step": 219
1551
+ },
1552
+ {
1553
+ "epoch": 0.9016393442622951,
1554
+ "grad_norm": 0.18241237783566233,
1555
+ "learning_rate": 6.700757520449873e-05,
1556
+ "loss": 0.104,
1557
+ "step": 220
1558
+ },
1559
+ {
1560
+ "epoch": 0.9057377049180327,
1561
+ "grad_norm": 0.19405703008792743,
1562
+ "learning_rate": 6.6670666328544e-05,
1563
+ "loss": 0.1405,
1564
+ "step": 221
1565
+ },
1566
+ {
1567
+ "epoch": 0.9098360655737705,
1568
+ "grad_norm": 0.17961334851449848,
1569
+ "learning_rate": 6.633290372009722e-05,
1570
+ "loss": 0.119,
1571
+ "step": 222
1572
+ },
1573
+ {
1574
+ "epoch": 0.9139344262295082,
1575
+ "grad_norm": 0.20202960404041628,
1576
+ "learning_rate": 6.599430467654222e-05,
1577
+ "loss": 0.1426,
1578
+ "step": 223
1579
+ },
1580
+ {
1581
+ "epoch": 0.9180327868852459,
1582
+ "grad_norm": 0.19111258609207246,
1583
+ "learning_rate": 6.565488653809797e-05,
1584
+ "loss": 0.1241,
1585
+ "step": 224
1586
+ },
1587
+ {
1588
+ "epoch": 0.9221311475409836,
1589
+ "grad_norm": 0.18774100787950773,
1590
+ "learning_rate": 6.531466668693071e-05,
1591
+ "loss": 0.1217,
1592
+ "step": 225
1593
+ },
1594
+ {
1595
+ "epoch": 0.9262295081967213,
1596
+ "grad_norm": 0.20807525080372385,
1597
+ "learning_rate": 6.497366254626372e-05,
1598
+ "loss": 0.1444,
1599
+ "step": 226
1600
+ },
1601
+ {
1602
+ "epoch": 0.930327868852459,
1603
+ "grad_norm": 0.17361340661409613,
1604
+ "learning_rate": 6.463189157948499e-05,
1605
+ "loss": 0.1157,
1606
+ "step": 227
1607
+ },
1608
+ {
1609
+ "epoch": 0.9344262295081968,
1610
+ "grad_norm": 0.17667512844881067,
1611
+ "learning_rate": 6.428937128925303e-05,
1612
+ "loss": 0.1137,
1613
+ "step": 228
1614
+ },
1615
+ {
1616
+ "epoch": 0.9385245901639344,
1617
+ "grad_norm": 0.19522411577627083,
1618
+ "learning_rate": 6.394611921660036e-05,
1619
+ "loss": 0.1142,
1620
+ "step": 229
1621
+ },
1622
+ {
1623
+ "epoch": 0.9426229508196722,
1624
+ "grad_norm": 0.19061253813497658,
1625
+ "learning_rate": 6.360215294003538e-05,
1626
+ "loss": 0.1147,
1627
+ "step": 230
1628
+ },
1629
+ {
1630
+ "epoch": 0.9467213114754098,
1631
+ "grad_norm": 0.1889320875988051,
1632
+ "learning_rate": 6.325749007464201e-05,
1633
+ "loss": 0.1285,
1634
+ "step": 231
1635
+ },
1636
+ {
1637
+ "epoch": 0.9508196721311475,
1638
+ "grad_norm": 0.20098732591185248,
1639
+ "learning_rate": 6.291214827117761e-05,
1640
+ "loss": 0.1502,
1641
+ "step": 232
1642
+ },
1643
+ {
1644
+ "epoch": 0.9549180327868853,
1645
+ "grad_norm": 0.1946804559624313,
1646
+ "learning_rate": 6.256614521516915e-05,
1647
+ "loss": 0.1349,
1648
+ "step": 233
1649
+ },
1650
+ {
1651
+ "epoch": 0.9590163934426229,
1652
+ "grad_norm": 0.2146414059717948,
1653
+ "learning_rate": 6.221949862600741e-05,
1654
+ "loss": 0.1453,
1655
+ "step": 234
1656
+ },
1657
+ {
1658
+ "epoch": 0.9631147540983607,
1659
+ "grad_norm": 0.19717528258719821,
1660
+ "learning_rate": 6.187222625603957e-05,
1661
+ "loss": 0.1193,
1662
+ "step": 235
1663
+ },
1664
+ {
1665
+ "epoch": 0.9672131147540983,
1666
+ "grad_norm": 0.20399136486459374,
1667
+ "learning_rate": 6.15243458896601e-05,
1668
+ "loss": 0.1391,
1669
+ "step": 236
1670
+ },
1671
+ {
1672
+ "epoch": 0.9713114754098361,
1673
+ "grad_norm": 0.1926288686899339,
1674
+ "learning_rate": 6.117587534239992e-05,
1675
+ "loss": 0.1117,
1676
+ "step": 237
1677
+ },
1678
+ {
1679
+ "epoch": 0.9754098360655737,
1680
+ "grad_norm": 0.19247883868686658,
1681
+ "learning_rate": 6.082683246001416e-05,
1682
+ "loss": 0.1252,
1683
+ "step": 238
1684
+ },
1685
+ {
1686
+ "epoch": 0.9795081967213115,
1687
+ "grad_norm": 0.19242584781802,
1688
+ "learning_rate": 6.047723511756815e-05,
1689
+ "loss": 0.1282,
1690
+ "step": 239
1691
+ },
1692
+ {
1693
+ "epoch": 0.9836065573770492,
1694
+ "grad_norm": 0.21275544312497674,
1695
+ "learning_rate": 6.012710121852205e-05,
1696
+ "loss": 0.1341,
1697
+ "step": 240
1698
+ },
1699
+ {
1700
+ "epoch": 0.9877049180327869,
1701
+ "grad_norm": 0.1804664142069766,
1702
+ "learning_rate": 5.977644869381398e-05,
1703
+ "loss": 0.1249,
1704
+ "step": 241
1705
+ },
1706
+ {
1707
+ "epoch": 0.9918032786885246,
1708
+ "grad_norm": 0.18351682596698626,
1709
+ "learning_rate": 5.9425295500941704e-05,
1710
+ "loss": 0.1093,
1711
+ "step": 242
1712
+ },
1713
+ {
1714
+ "epoch": 0.9959016393442623,
1715
+ "grad_norm": 0.19849556475127272,
1716
+ "learning_rate": 5.907365962304308e-05,
1717
+ "loss": 0.1183,
1718
+ "step": 243
1719
+ },
1720
+ {
1721
+ "epoch": 1.0,
1722
+ "grad_norm": 0.2024234506725076,
1723
+ "learning_rate": 5.872155906797503e-05,
1724
+ "loss": 0.109,
1725
+ "step": 244
1726
+ },
1727
+ {
1728
+ "epoch": 1.0040983606557377,
1729
+ "grad_norm": 0.17645238784331063,
1730
+ "learning_rate": 5.83690118673914e-05,
1731
+ "loss": 0.0887,
1732
+ "step": 245
1733
+ },
1734
+ {
1735
+ "epoch": 1.0081967213114753,
1736
+ "grad_norm": 0.17707033906237873,
1737
+ "learning_rate": 5.801603607581947e-05,
1738
+ "loss": 0.0734,
1739
+ "step": 246
1740
+ },
1741
+ {
1742
+ "epoch": 1.0122950819672132,
1743
+ "grad_norm": 0.1879118674622085,
1744
+ "learning_rate": 5.766264976973538e-05,
1745
+ "loss": 0.0823,
1746
+ "step": 247
1747
+ },
1748
+ {
1749
+ "epoch": 1.0163934426229508,
1750
+ "grad_norm": 0.20061285756993943,
1751
+ "learning_rate": 5.73088710466384e-05,
1752
+ "loss": 0.0866,
1753
+ "step": 248
1754
+ },
1755
+ {
1756
+ "epoch": 1.0204918032786885,
1757
+ "grad_norm": 0.19444493978087618,
1758
+ "learning_rate": 5.695471802412413e-05,
1759
+ "loss": 0.0928,
1760
+ "step": 249
1761
+ },
1762
+ {
1763
+ "epoch": 1.0245901639344261,
1764
+ "grad_norm": 0.19996457964971276,
1765
+ "learning_rate": 5.660020883895668e-05,
1766
+ "loss": 0.0804,
1767
+ "step": 250
1768
+ },
1769
+ {
1770
+ "epoch": 1.028688524590164,
1771
+ "grad_norm": 0.21425344554956094,
1772
+ "learning_rate": 5.6245361646139794e-05,
1773
+ "loss": 0.0934,
1774
+ "step": 251
1775
+ },
1776
+ {
1777
+ "epoch": 1.0327868852459017,
1778
+ "grad_norm": 0.22898083674351027,
1779
+ "learning_rate": 5.58901946179872e-05,
1780
+ "loss": 0.0921,
1781
+ "step": 252
1782
+ },
1783
+ {
1784
+ "epoch": 1.0368852459016393,
1785
+ "grad_norm": 0.290540627425331,
1786
+ "learning_rate": 5.553472594319189e-05,
1787
+ "loss": 0.0934,
1788
+ "step": 253
1789
+ },
1790
+ {
1791
+ "epoch": 1.040983606557377,
1792
+ "grad_norm": 0.273931261917051,
1793
+ "learning_rate": 5.5178973825894706e-05,
1794
+ "loss": 0.1117,
1795
+ "step": 254
1796
+ },
1797
+ {
1798
+ "epoch": 1.0450819672131149,
1799
+ "grad_norm": 0.25430931712778365,
1800
+ "learning_rate": 5.482295648475203e-05,
1801
+ "loss": 0.1049,
1802
+ "step": 255
1803
+ },
1804
+ {
1805
+ "epoch": 1.0491803278688525,
1806
+ "grad_norm": 0.24194932502272815,
1807
+ "learning_rate": 5.446669215200281e-05,
1808
+ "loss": 0.1146,
1809
+ "step": 256
1810
+ },
1811
+ {
1812
+ "epoch": 1.0532786885245902,
1813
+ "grad_norm": 0.20579577668490157,
1814
+ "learning_rate": 5.411019907253482e-05,
1815
+ "loss": 0.0853,
1816
+ "step": 257
1817
+ },
1818
+ {
1819
+ "epoch": 1.0573770491803278,
1820
+ "grad_norm": 0.2185751015406012,
1821
+ "learning_rate": 5.375349550295038e-05,
1822
+ "loss": 0.0916,
1823
+ "step": 258
1824
+ },
1825
+ {
1826
+ "epoch": 1.0614754098360655,
1827
+ "grad_norm": 0.21677244042516453,
1828
+ "learning_rate": 5.339659971063132e-05,
1829
+ "loss": 0.0905,
1830
+ "step": 259
1831
+ },
1832
+ {
1833
+ "epoch": 1.0655737704918034,
1834
+ "grad_norm": 0.2109428012580277,
1835
+ "learning_rate": 5.303952997280355e-05,
1836
+ "loss": 0.0837,
1837
+ "step": 260
1838
+ },
1839
+ {
1840
+ "epoch": 1.069672131147541,
1841
+ "grad_norm": 0.1988852883385447,
1842
+ "learning_rate": 5.268230457560095e-05,
1843
+ "loss": 0.0848,
1844
+ "step": 261
1845
+ },
1846
+ {
1847
+ "epoch": 1.0737704918032787,
1848
+ "grad_norm": 0.20185225614786018,
1849
+ "learning_rate": 5.232494181312906e-05,
1850
+ "loss": 0.0882,
1851
+ "step": 262
1852
+ },
1853
+ {
1854
+ "epoch": 1.0778688524590163,
1855
+ "grad_norm": 0.21775228450593942,
1856
+ "learning_rate": 5.196745998652807e-05,
1857
+ "loss": 0.0886,
1858
+ "step": 263
1859
+ },
1860
+ {
1861
+ "epoch": 1.0819672131147542,
1862
+ "grad_norm": 0.23117101550005217,
1863
+ "learning_rate": 5.160987740303564e-05,
1864
+ "loss": 0.1024,
1865
+ "step": 264
1866
+ },
1867
+ {
1868
+ "epoch": 1.0860655737704918,
1869
+ "grad_norm": 0.21437209879423688,
1870
+ "learning_rate": 5.12522123750494e-05,
1871
+ "loss": 0.0803,
1872
+ "step": 265
1873
+ },
1874
+ {
1875
+ "epoch": 1.0901639344262295,
1876
+ "grad_norm": 0.2265139026178152,
1877
+ "learning_rate": 5.0894483219189046e-05,
1878
+ "loss": 0.0855,
1879
+ "step": 266
1880
+ },
1881
+ {
1882
+ "epoch": 1.0942622950819672,
1883
+ "grad_norm": 0.22534362681306327,
1884
+ "learning_rate": 5.053670825535842e-05,
1885
+ "loss": 0.0865,
1886
+ "step": 267
1887
+ },
1888
+ {
1889
+ "epoch": 1.098360655737705,
1890
+ "grad_norm": 0.23493559614373521,
1891
+ "learning_rate": 5.017890580580723e-05,
1892
+ "loss": 0.0954,
1893
+ "step": 268
1894
+ },
1895
+ {
1896
+ "epoch": 1.1024590163934427,
1897
+ "grad_norm": 0.22639122256659971,
1898
+ "learning_rate": 4.982109419419277e-05,
1899
+ "loss": 0.0861,
1900
+ "step": 269
1901
+ },
1902
+ {
1903
+ "epoch": 1.1065573770491803,
1904
+ "grad_norm": 0.20366634594892993,
1905
+ "learning_rate": 4.946329174464158e-05,
1906
+ "loss": 0.0811,
1907
+ "step": 270
1908
+ },
1909
+ {
1910
+ "epoch": 1.110655737704918,
1911
+ "grad_norm": 0.20832107440198078,
1912
+ "learning_rate": 4.9105516780810946e-05,
1913
+ "loss": 0.0738,
1914
+ "step": 271
1915
+ },
1916
+ {
1917
+ "epoch": 1.1147540983606556,
1918
+ "grad_norm": 0.24035085358430688,
1919
+ "learning_rate": 4.8747787624950604e-05,
1920
+ "loss": 0.1044,
1921
+ "step": 272
1922
+ },
1923
+ {
1924
+ "epoch": 1.1188524590163935,
1925
+ "grad_norm": 0.1941737888109515,
1926
+ "learning_rate": 4.8390122596964355e-05,
1927
+ "loss": 0.0824,
1928
+ "step": 273
1929
+ },
1930
+ {
1931
+ "epoch": 1.1229508196721312,
1932
+ "grad_norm": 0.20919358980409994,
1933
+ "learning_rate": 4.803254001347193e-05,
1934
+ "loss": 0.0862,
1935
+ "step": 274
1936
+ },
1937
+ {
1938
+ "epoch": 1.1270491803278688,
1939
+ "grad_norm": 0.231047601436464,
1940
+ "learning_rate": 4.7675058186870944e-05,
1941
+ "loss": 0.0907,
1942
+ "step": 275
1943
+ },
1944
+ {
1945
+ "epoch": 1.1311475409836065,
1946
+ "grad_norm": 0.21531381241133493,
1947
+ "learning_rate": 4.7317695424399044e-05,
1948
+ "loss": 0.0932,
1949
+ "step": 276
1950
+ },
1951
+ {
1952
+ "epoch": 1.1352459016393444,
1953
+ "grad_norm": 0.24193852025077817,
1954
+ "learning_rate": 4.6960470027196456e-05,
1955
+ "loss": 0.085,
1956
+ "step": 277
1957
+ },
1958
+ {
1959
+ "epoch": 1.139344262295082,
1960
+ "grad_norm": 0.20448950800710466,
1961
+ "learning_rate": 4.6603400289368676e-05,
1962
+ "loss": 0.088,
1963
+ "step": 278
1964
+ },
1965
+ {
1966
+ "epoch": 1.1434426229508197,
1967
+ "grad_norm": 0.2257853631598955,
1968
+ "learning_rate": 4.624650449704962e-05,
1969
+ "loss": 0.0914,
1970
+ "step": 279
1971
+ },
1972
+ {
1973
+ "epoch": 1.1475409836065573,
1974
+ "grad_norm": 0.23959875777441447,
1975
+ "learning_rate": 4.588980092746518e-05,
1976
+ "loss": 0.1042,
1977
+ "step": 280
1978
+ },
1979
+ {
1980
+ "epoch": 1.151639344262295,
1981
+ "grad_norm": 0.21621082794043103,
1982
+ "learning_rate": 4.553330784799721e-05,
1983
+ "loss": 0.0801,
1984
+ "step": 281
1985
+ },
1986
+ {
1987
+ "epoch": 1.1557377049180328,
1988
+ "grad_norm": 0.23154362074682183,
1989
+ "learning_rate": 4.517704351524798e-05,
1990
+ "loss": 0.116,
1991
+ "step": 282
1992
+ },
1993
+ {
1994
+ "epoch": 1.1598360655737705,
1995
+ "grad_norm": 0.21749721579038517,
1996
+ "learning_rate": 4.48210261741053e-05,
1997
+ "loss": 0.08,
1998
+ "step": 283
1999
+ },
2000
+ {
2001
+ "epoch": 1.1639344262295082,
2002
+ "grad_norm": 0.22621057695770447,
2003
+ "learning_rate": 4.446527405680812e-05,
2004
+ "loss": 0.0843,
2005
+ "step": 284
2006
+ },
2007
+ {
2008
+ "epoch": 1.1680327868852458,
2009
+ "grad_norm": 0.21629529519346516,
2010
+ "learning_rate": 4.410980538201282e-05,
2011
+ "loss": 0.0783,
2012
+ "step": 285
2013
+ },
2014
+ {
2015
+ "epoch": 1.1721311475409837,
2016
+ "grad_norm": 0.2583962088351615,
2017
+ "learning_rate": 4.375463835386022e-05,
2018
+ "loss": 0.0832,
2019
+ "step": 286
2020
+ },
2021
+ {
2022
+ "epoch": 1.1762295081967213,
2023
+ "grad_norm": 0.2550952219128452,
2024
+ "learning_rate": 4.339979116104334e-05,
2025
+ "loss": 0.1102,
2026
+ "step": 287
2027
+ },
2028
+ {
2029
+ "epoch": 1.180327868852459,
2030
+ "grad_norm": 0.22046670945180735,
2031
+ "learning_rate": 4.3045281975875875e-05,
2032
+ "loss": 0.0687,
2033
+ "step": 288
2034
+ },
2035
+ {
2036
+ "epoch": 1.1844262295081966,
2037
+ "grad_norm": 0.21963199970259858,
2038
+ "learning_rate": 4.269112895336161e-05,
2039
+ "loss": 0.0765,
2040
+ "step": 289
2041
+ },
2042
+ {
2043
+ "epoch": 1.1885245901639343,
2044
+ "grad_norm": 0.20549051860300943,
2045
+ "learning_rate": 4.2337350230264635e-05,
2046
+ "loss": 0.0773,
2047
+ "step": 290
2048
+ },
2049
+ {
2050
+ "epoch": 1.1926229508196722,
2051
+ "grad_norm": 0.20173502922198425,
2052
+ "learning_rate": 4.198396392418054e-05,
2053
+ "loss": 0.0603,
2054
+ "step": 291
2055
+ },
2056
+ {
2057
+ "epoch": 1.1967213114754098,
2058
+ "grad_norm": 0.20756479162187122,
2059
+ "learning_rate": 4.1630988132608614e-05,
2060
+ "loss": 0.0698,
2061
+ "step": 292
2062
+ },
2063
+ {
2064
+ "epoch": 1.2008196721311475,
2065
+ "grad_norm": 0.19579961343255203,
2066
+ "learning_rate": 4.127844093202498e-05,
2067
+ "loss": 0.0721,
2068
+ "step": 293
2069
+ },
2070
+ {
2071
+ "epoch": 1.2049180327868854,
2072
+ "grad_norm": 0.22373098356251547,
2073
+ "learning_rate": 4.092634037695694e-05,
2074
+ "loss": 0.0793,
2075
+ "step": 294
2076
+ },
2077
+ {
2078
+ "epoch": 1.209016393442623,
2079
+ "grad_norm": 0.22555565622897975,
2080
+ "learning_rate": 4.057470449905831e-05,
2081
+ "loss": 0.0901,
2082
+ "step": 295
2083
+ },
2084
+ {
2085
+ "epoch": 1.2131147540983607,
2086
+ "grad_norm": 0.22693118605112406,
2087
+ "learning_rate": 4.022355130618604e-05,
2088
+ "loss": 0.0826,
2089
+ "step": 296
2090
+ },
2091
+ {
2092
+ "epoch": 1.2172131147540983,
2093
+ "grad_norm": 0.23153954853832903,
2094
+ "learning_rate": 3.9872898781477954e-05,
2095
+ "loss": 0.0886,
2096
+ "step": 297
2097
+ },
2098
+ {
2099
+ "epoch": 1.221311475409836,
2100
+ "grad_norm": 0.22314167716303715,
2101
+ "learning_rate": 3.952276488243186e-05,
2102
+ "loss": 0.0685,
2103
+ "step": 298
2104
+ },
2105
+ {
2106
+ "epoch": 1.2254098360655739,
2107
+ "grad_norm": 0.22032532570326238,
2108
+ "learning_rate": 3.917316753998585e-05,
2109
+ "loss": 0.0736,
2110
+ "step": 299
2111
+ },
2112
+ {
2113
+ "epoch": 1.2295081967213115,
2114
+ "grad_norm": 0.23039264717337804,
2115
+ "learning_rate": 3.882412465760009e-05,
2116
+ "loss": 0.0793,
2117
+ "step": 300
2118
+ },
2119
+ {
2120
+ "epoch": 1.2336065573770492,
2121
+ "grad_norm": 0.21565650717021032,
2122
+ "learning_rate": 3.847565411033992e-05,
2123
+ "loss": 0.0675,
2124
+ "step": 301
2125
+ },
2126
+ {
2127
+ "epoch": 1.2377049180327868,
2128
+ "grad_norm": 0.22078315656307607,
2129
+ "learning_rate": 3.8127773743960426e-05,
2130
+ "loss": 0.0825,
2131
+ "step": 302
2132
+ },
2133
+ {
2134
+ "epoch": 1.2418032786885247,
2135
+ "grad_norm": 0.277778960283362,
2136
+ "learning_rate": 3.7780501373992596e-05,
2137
+ "loss": 0.0909,
2138
+ "step": 303
2139
+ },
2140
+ {
2141
+ "epoch": 1.2459016393442623,
2142
+ "grad_norm": 0.25457025493811986,
2143
+ "learning_rate": 3.7433854784830854e-05,
2144
+ "loss": 0.0844,
2145
+ "step": 304
2146
+ },
2147
+ {
2148
+ "epoch": 1.25,
2149
+ "grad_norm": 0.230488602289965,
2150
+ "learning_rate": 3.7087851728822405e-05,
2151
+ "loss": 0.0732,
2152
+ "step": 305
2153
+ },
2154
+ {
2155
+ "epoch": 1.2540983606557377,
2156
+ "grad_norm": 0.2769088300832485,
2157
+ "learning_rate": 3.674250992535802e-05,
2158
+ "loss": 0.1133,
2159
+ "step": 306
2160
+ },
2161
+ {
2162
+ "epoch": 1.2581967213114753,
2163
+ "grad_norm": 0.25238428313016165,
2164
+ "learning_rate": 3.639784705996463e-05,
2165
+ "loss": 0.1028,
2166
+ "step": 307
2167
+ },
2168
+ {
2169
+ "epoch": 1.2622950819672132,
2170
+ "grad_norm": 0.22474085546390393,
2171
+ "learning_rate": 3.6053880783399654e-05,
2172
+ "loss": 0.0748,
2173
+ "step": 308
2174
+ },
2175
+ {
2176
+ "epoch": 1.2663934426229508,
2177
+ "grad_norm": 0.2306185209891483,
2178
+ "learning_rate": 3.5710628710747e-05,
2179
+ "loss": 0.0909,
2180
+ "step": 309
2181
+ },
2182
+ {
2183
+ "epoch": 1.2704918032786885,
2184
+ "grad_norm": 0.21441826461789973,
2185
+ "learning_rate": 3.5368108420515036e-05,
2186
+ "loss": 0.0827,
2187
+ "step": 310
2188
+ },
2189
+ {
2190
+ "epoch": 1.2745901639344264,
2191
+ "grad_norm": 0.21674907407231,
2192
+ "learning_rate": 3.5026337453736314e-05,
2193
+ "loss": 0.0843,
2194
+ "step": 311
2195
+ },
2196
+ {
2197
+ "epoch": 1.278688524590164,
2198
+ "grad_norm": 0.23693824083399773,
2199
+ "learning_rate": 3.4685333313069315e-05,
2200
+ "loss": 0.0908,
2201
+ "step": 312
2202
+ },
2203
+ {
2204
+ "epoch": 1.2827868852459017,
2205
+ "grad_norm": 0.22068000066238444,
2206
+ "learning_rate": 3.4345113461902055e-05,
2207
+ "loss": 0.0859,
2208
+ "step": 313
2209
+ },
2210
+ {
2211
+ "epoch": 1.2868852459016393,
2212
+ "grad_norm": 0.2141000026469413,
2213
+ "learning_rate": 3.400569532345781e-05,
2214
+ "loss": 0.0837,
2215
+ "step": 314
2216
+ },
2217
+ {
2218
+ "epoch": 1.290983606557377,
2219
+ "grad_norm": 0.20219236400730675,
2220
+ "learning_rate": 3.3667096279902794e-05,
2221
+ "loss": 0.0708,
2222
+ "step": 315
2223
+ },
2224
+ {
2225
+ "epoch": 1.2950819672131146,
2226
+ "grad_norm": 0.20804695200056297,
2227
+ "learning_rate": 3.3329333671456024e-05,
2228
+ "loss": 0.0739,
2229
+ "step": 316
2230
+ },
2231
+ {
2232
+ "epoch": 1.2991803278688525,
2233
+ "grad_norm": 0.2343703975098053,
2234
+ "learning_rate": 3.2992424795501284e-05,
2235
+ "loss": 0.089,
2236
+ "step": 317
2237
+ },
2238
+ {
2239
+ "epoch": 1.3032786885245902,
2240
+ "grad_norm": 0.21489328846354372,
2241
+ "learning_rate": 3.26563869057013e-05,
2242
+ "loss": 0.0804,
2243
+ "step": 318
2244
+ },
2245
+ {
2246
+ "epoch": 1.3073770491803278,
2247
+ "grad_norm": 0.2198465103470338,
2248
+ "learning_rate": 3.232123721111415e-05,
2249
+ "loss": 0.0816,
2250
+ "step": 319
2251
+ },
2252
+ {
2253
+ "epoch": 1.3114754098360657,
2254
+ "grad_norm": 0.2484592052479722,
2255
+ "learning_rate": 3.198699287531198e-05,
2256
+ "loss": 0.1007,
2257
+ "step": 320
2258
+ },
2259
+ {
2260
+ "epoch": 1.3155737704918034,
2261
+ "grad_norm": 0.25565736054210597,
2262
+ "learning_rate": 3.165367101550197e-05,
2263
+ "loss": 0.1016,
2264
+ "step": 321
2265
+ },
2266
+ {
2267
+ "epoch": 1.319672131147541,
2268
+ "grad_norm": 0.19989451433971764,
2269
+ "learning_rate": 3.13212887016498e-05,
2270
+ "loss": 0.0698,
2271
+ "step": 322
2272
+ },
2273
+ {
2274
+ "epoch": 1.3237704918032787,
2275
+ "grad_norm": 0.21152406721818276,
2276
+ "learning_rate": 3.098986295560545e-05,
2277
+ "loss": 0.092,
2278
+ "step": 323
2279
+ },
2280
+ {
2281
+ "epoch": 1.3278688524590163,
2282
+ "grad_norm": 0.24438562628885818,
2283
+ "learning_rate": 3.0659410750231454e-05,
2284
+ "loss": 0.0965,
2285
+ "step": 324
2286
+ },
2287
+ {
2288
+ "epoch": 1.331967213114754,
2289
+ "grad_norm": 0.21428460598845647,
2290
+ "learning_rate": 3.032994900853372e-05,
2291
+ "loss": 0.0861,
2292
+ "step": 325
2293
+ },
2294
+ {
2295
+ "epoch": 1.3360655737704918,
2296
+ "grad_norm": 0.2459292100893367,
2297
+ "learning_rate": 3.0001494602794867e-05,
2298
+ "loss": 0.1088,
2299
+ "step": 326
2300
+ },
2301
+ {
2302
+ "epoch": 1.3401639344262295,
2303
+ "grad_norm": 0.22552854130941782,
2304
+ "learning_rate": 2.967406435371018e-05,
2305
+ "loss": 0.0862,
2306
+ "step": 327
2307
+ },
2308
+ {
2309
+ "epoch": 1.3442622950819672,
2310
+ "grad_norm": 0.22398158633984547,
2311
+ "learning_rate": 2.934767502952616e-05,
2312
+ "loss": 0.084,
2313
+ "step": 328
2314
+ },
2315
+ {
2316
+ "epoch": 1.348360655737705,
2317
+ "grad_norm": 0.22664651281034953,
2318
+ "learning_rate": 2.9022343345181846e-05,
2319
+ "loss": 0.0748,
2320
+ "step": 329
2321
+ },
2322
+ {
2323
+ "epoch": 1.3524590163934427,
2324
+ "grad_norm": 0.22062475345873886,
2325
+ "learning_rate": 2.8698085961452724e-05,
2326
+ "loss": 0.087,
2327
+ "step": 330
2328
+ },
2329
+ {
2330
+ "epoch": 1.3565573770491803,
2331
+ "grad_norm": 0.22114071809701424,
2332
+ "learning_rate": 2.8374919484097663e-05,
2333
+ "loss": 0.0798,
2334
+ "step": 331
2335
+ },
2336
+ {
2337
+ "epoch": 1.360655737704918,
2338
+ "grad_norm": 0.2318013572074171,
2339
+ "learning_rate": 2.8052860463008295e-05,
2340
+ "loss": 0.0778,
2341
+ "step": 332
2342
+ },
2343
+ {
2344
+ "epoch": 1.3647540983606556,
2345
+ "grad_norm": 0.21592005617557827,
2346
+ "learning_rate": 2.7731925391361673e-05,
2347
+ "loss": 0.0699,
2348
+ "step": 333
2349
+ },
2350
+ {
2351
+ "epoch": 1.3688524590163935,
2352
+ "grad_norm": 0.22284005643229798,
2353
+ "learning_rate": 2.741213070477545e-05,
2354
+ "loss": 0.0688,
2355
+ "step": 334
2356
+ },
2357
+ {
2358
+ "epoch": 1.3729508196721312,
2359
+ "grad_norm": 0.24331228121733403,
2360
+ "learning_rate": 2.7093492780466355e-05,
2361
+ "loss": 0.1021,
2362
+ "step": 335
2363
+ },
2364
+ {
2365
+ "epoch": 1.3770491803278688,
2366
+ "grad_norm": 0.22916717485660554,
2367
+ "learning_rate": 2.6776027936411318e-05,
2368
+ "loss": 0.0787,
2369
+ "step": 336
2370
+ },
2371
+ {
2372
+ "epoch": 1.3811475409836065,
2373
+ "grad_norm": 0.2486820570939316,
2374
+ "learning_rate": 2.6459752430511952e-05,
2375
+ "loss": 0.0968,
2376
+ "step": 337
2377
+ },
2378
+ {
2379
+ "epoch": 1.3852459016393444,
2380
+ "grad_norm": 0.21399877551380306,
2381
+ "learning_rate": 2.6144682459761814e-05,
2382
+ "loss": 0.0689,
2383
+ "step": 338
2384
+ },
2385
+ {
2386
+ "epoch": 1.389344262295082,
2387
+ "grad_norm": 0.23817514427496975,
2388
+ "learning_rate": 2.58308341594171e-05,
2389
+ "loss": 0.076,
2390
+ "step": 339
2391
+ },
2392
+ {
2393
+ "epoch": 1.3934426229508197,
2394
+ "grad_norm": 0.19580850481427564,
2395
+ "learning_rate": 2.5518223602170134e-05,
2396
+ "loss": 0.066,
2397
+ "step": 340
2398
+ },
2399
+ {
2400
+ "epoch": 1.3975409836065573,
2401
+ "grad_norm": 0.23341882458103203,
2402
+ "learning_rate": 2.5206866797326446e-05,
2403
+ "loss": 0.0795,
2404
+ "step": 341
2405
+ },
2406
+ {
2407
+ "epoch": 1.401639344262295,
2408
+ "grad_norm": 0.24905408203075094,
2409
+ "learning_rate": 2.4896779689984783e-05,
2410
+ "loss": 0.0979,
2411
+ "step": 342
2412
+ },
2413
+ {
2414
+ "epoch": 1.4057377049180328,
2415
+ "grad_norm": 0.2373253447398963,
2416
+ "learning_rate": 2.4587978160220563e-05,
2417
+ "loss": 0.0849,
2418
+ "step": 343
2419
+ },
2420
+ {
2421
+ "epoch": 1.4098360655737705,
2422
+ "grad_norm": 0.23312222655260098,
2423
+ "learning_rate": 2.4280478022272696e-05,
2424
+ "loss": 0.0833,
2425
+ "step": 344
2426
+ },
2427
+ {
2428
+ "epoch": 1.4139344262295082,
2429
+ "grad_norm": 0.24464678291649106,
2430
+ "learning_rate": 2.3974295023733577e-05,
2431
+ "loss": 0.0924,
2432
+ "step": 345
2433
+ },
2434
+ {
2435
+ "epoch": 1.418032786885246,
2436
+ "grad_norm": 0.2423574669974183,
2437
+ "learning_rate": 2.3669444844742812e-05,
2438
+ "loss": 0.0876,
2439
+ "step": 346
2440
+ },
2441
+ {
2442
+ "epoch": 1.4221311475409837,
2443
+ "grad_norm": 0.24768803714943216,
2444
+ "learning_rate": 2.336594309718399e-05,
2445
+ "loss": 0.0911,
2446
+ "step": 347
2447
+ },
2448
+ {
2449
+ "epoch": 1.4262295081967213,
2450
+ "grad_norm": 0.2353256965607498,
2451
+ "learning_rate": 2.3063805323885383e-05,
2452
+ "loss": 0.0791,
2453
+ "step": 348
2454
+ },
2455
+ {
2456
+ "epoch": 1.430327868852459,
2457
+ "grad_norm": 0.2184971836745015,
2458
+ "learning_rate": 2.276304699782381e-05,
2459
+ "loss": 0.071,
2460
+ "step": 349
2461
+ },
2462
+ {
2463
+ "epoch": 1.4344262295081966,
2464
+ "grad_norm": 0.22589388512628691,
2465
+ "learning_rate": 2.2463683521332374e-05,
2466
+ "loss": 0.0883,
2467
+ "step": 350
2468
+ },
2469
+ {
2470
+ "epoch": 1.4385245901639343,
2471
+ "grad_norm": 0.23861282261739694,
2472
+ "learning_rate": 2.2165730225311532e-05,
2473
+ "loss": 0.0949,
2474
+ "step": 351
2475
+ },
2476
+ {
2477
+ "epoch": 1.4426229508196722,
2478
+ "grad_norm": 0.21125222504207164,
2479
+ "learning_rate": 2.1869202368444146e-05,
2480
+ "loss": 0.0669,
2481
+ "step": 352
2482
+ },
2483
+ {
2484
+ "epoch": 1.4467213114754098,
2485
+ "grad_norm": 0.23839842143172482,
2486
+ "learning_rate": 2.1574115136413892e-05,
2487
+ "loss": 0.1115,
2488
+ "step": 353
2489
+ },
2490
+ {
2491
+ "epoch": 1.4508196721311475,
2492
+ "grad_norm": 0.23021878248583671,
2493
+ "learning_rate": 2.128048364112774e-05,
2494
+ "loss": 0.0824,
2495
+ "step": 354
2496
+ },
2497
+ {
2498
+ "epoch": 1.4549180327868854,
2499
+ "grad_norm": 0.21922671215563078,
2500
+ "learning_rate": 2.098832291994188e-05,
2501
+ "loss": 0.0805,
2502
+ "step": 355
2503
+ },
2504
+ {
2505
+ "epoch": 1.459016393442623,
2506
+ "grad_norm": 0.22973971719352562,
2507
+ "learning_rate": 2.0697647934891807e-05,
2508
+ "loss": 0.0809,
2509
+ "step": 356
2510
+ },
2511
+ {
2512
+ "epoch": 1.4631147540983607,
2513
+ "grad_norm": 0.23888720332729385,
2514
+ "learning_rate": 2.0408473571925908e-05,
2515
+ "loss": 0.0795,
2516
+ "step": 357
2517
+ },
2518
+ {
2519
+ "epoch": 1.4672131147540983,
2520
+ "grad_norm": 0.20105531202188945,
2521
+ "learning_rate": 2.0120814640143314e-05,
2522
+ "loss": 0.0738,
2523
+ "step": 358
2524
+ },
2525
+ {
2526
+ "epoch": 1.471311475409836,
2527
+ "grad_norm": 0.20815592735234387,
2528
+ "learning_rate": 1.983468587103533e-05,
2529
+ "loss": 0.0747,
2530
+ "step": 359
2531
+ },
2532
+ {
2533
+ "epoch": 1.4754098360655736,
2534
+ "grad_norm": 0.21875945763540222,
2535
+ "learning_rate": 1.9550101917731166e-05,
2536
+ "loss": 0.0782,
2537
+ "step": 360
2538
+ },
2539
+ {
2540
+ "epoch": 1.4795081967213115,
2541
+ "grad_norm": 0.23652904185716042,
2542
+ "learning_rate": 1.9267077354247394e-05,
2543
+ "loss": 0.0785,
2544
+ "step": 361
2545
+ },
2546
+ {
2547
+ "epoch": 1.4836065573770492,
2548
+ "grad_norm": 0.22747137570450954,
2549
+ "learning_rate": 1.8985626674741643e-05,
2550
+ "loss": 0.1122,
2551
+ "step": 362
2552
+ },
2553
+ {
2554
+ "epoch": 1.4877049180327868,
2555
+ "grad_norm": 0.2331279262069605,
2556
+ "learning_rate": 1.8705764292770383e-05,
2557
+ "loss": 0.0915,
2558
+ "step": 363
2559
+ },
2560
+ {
2561
+ "epoch": 1.4918032786885247,
2562
+ "grad_norm": 0.22030724266502305,
2563
+ "learning_rate": 1.8427504540550677e-05,
2564
+ "loss": 0.0665,
2565
+ "step": 364
2566
+ },
2567
+ {
2568
+ "epoch": 1.4959016393442623,
2569
+ "grad_norm": 0.22505977083225506,
2570
+ "learning_rate": 1.8150861668226304e-05,
2571
+ "loss": 0.075,
2572
+ "step": 365
2573
+ },
2574
+ {
2575
+ "epoch": 1.5,
2576
+ "grad_norm": 0.21199992455583846,
2577
+ "learning_rate": 1.7875849843137893e-05,
2578
+ "loss": 0.0811,
2579
+ "step": 366
2580
+ },
2581
+ {
2582
+ "epoch": 1.5040983606557377,
2583
+ "grad_norm": 0.21810290159002446,
2584
+ "learning_rate": 1.760248314909747e-05,
2585
+ "loss": 0.0756,
2586
+ "step": 367
2587
+ },
2588
+ {
2589
+ "epoch": 1.5081967213114753,
2590
+ "grad_norm": 0.2558311827574221,
2591
+ "learning_rate": 1.7330775585667164e-05,
2592
+ "loss": 0.0843,
2593
+ "step": 368
2594
+ },
2595
+ {
2596
+ "epoch": 1.512295081967213,
2597
+ "grad_norm": 0.2233574367138228,
2598
+ "learning_rate": 1.7060741067442288e-05,
2599
+ "loss": 0.0762,
2600
+ "step": 369
2601
+ },
2602
+ {
2603
+ "epoch": 1.5163934426229508,
2604
+ "grad_norm": 0.21907681063831233,
2605
+ "learning_rate": 1.679239342333867e-05,
2606
+ "loss": 0.0741,
2607
+ "step": 370
2608
+ },
2609
+ {
2610
+ "epoch": 1.5204918032786885,
2611
+ "grad_norm": 0.2386759157009457,
2612
+ "learning_rate": 1.6525746395884605e-05,
2613
+ "loss": 0.0922,
2614
+ "step": 371
2615
+ },
2616
+ {
2617
+ "epoch": 1.5245901639344264,
2618
+ "grad_norm": 0.22163173702404845,
2619
+ "learning_rate": 1.626081364051691e-05,
2620
+ "loss": 0.0783,
2621
+ "step": 372
2622
+ },
2623
+ {
2624
+ "epoch": 1.528688524590164,
2625
+ "grad_norm": 0.2610954803411835,
2626
+ "learning_rate": 1.599760872488171e-05,
2627
+ "loss": 0.0724,
2628
+ "step": 373
2629
+ },
2630
+ {
2631
+ "epoch": 1.5327868852459017,
2632
+ "grad_norm": 0.2439120392285164,
2633
+ "learning_rate": 1.573614512813961e-05,
2634
+ "loss": 0.0787,
2635
+ "step": 374
2636
+ },
2637
+ {
2638
+ "epoch": 1.5368852459016393,
2639
+ "grad_norm": 0.22669981293370467,
2640
+ "learning_rate": 1.5476436240275344e-05,
2641
+ "loss": 0.0713,
2642
+ "step": 375
2643
+ },
2644
+ {
2645
+ "epoch": 1.540983606557377,
2646
+ "grad_norm": 0.22032890300346933,
2647
+ "learning_rate": 1.5218495361412145e-05,
2648
+ "loss": 0.0699,
2649
+ "step": 376
2650
+ },
2651
+ {
2652
+ "epoch": 1.5450819672131146,
2653
+ "grad_norm": 0.23028230012736722,
2654
+ "learning_rate": 1.4962335701130509e-05,
2655
+ "loss": 0.0807,
2656
+ "step": 377
2657
+ },
2658
+ {
2659
+ "epoch": 1.5491803278688525,
2660
+ "grad_norm": 0.2357458200653599,
2661
+ "learning_rate": 1.470797037779183e-05,
2662
+ "loss": 0.0833,
2663
+ "step": 378
2664
+ },
2665
+ {
2666
+ "epoch": 1.5532786885245902,
2667
+ "grad_norm": 0.23495810636275852,
2668
+ "learning_rate": 1.4455412417866476e-05,
2669
+ "loss": 0.0908,
2670
+ "step": 379
2671
+ },
2672
+ {
2673
+ "epoch": 1.5573770491803278,
2674
+ "grad_norm": 0.24624217602429513,
2675
+ "learning_rate": 1.4204674755266789e-05,
2676
+ "loss": 0.0884,
2677
+ "step": 380
2678
+ },
2679
+ {
2680
+ "epoch": 1.5614754098360657,
2681
+ "grad_norm": 0.24094166363923858,
2682
+ "learning_rate": 1.3955770230684611e-05,
2683
+ "loss": 0.0817,
2684
+ "step": 381
2685
+ },
2686
+ {
2687
+ "epoch": 1.5655737704918034,
2688
+ "grad_norm": 0.2304769705042891,
2689
+ "learning_rate": 1.3708711590933792e-05,
2690
+ "loss": 0.0774,
2691
+ "step": 382
2692
+ },
2693
+ {
2694
+ "epoch": 1.569672131147541,
2695
+ "grad_norm": 0.2377015225778547,
2696
+ "learning_rate": 1.3463511488297304e-05,
2697
+ "loss": 0.0961,
2698
+ "step": 383
2699
+ },
2700
+ {
2701
+ "epoch": 1.5737704918032787,
2702
+ "grad_norm": 0.25107490882186423,
2703
+ "learning_rate": 1.3220182479879406e-05,
2704
+ "loss": 0.0939,
2705
+ "step": 384
2706
+ },
2707
+ {
2708
+ "epoch": 1.5778688524590163,
2709
+ "grad_norm": 0.23260968536054955,
2710
+ "learning_rate": 1.2978737026962456e-05,
2711
+ "loss": 0.0837,
2712
+ "step": 385
2713
+ },
2714
+ {
2715
+ "epoch": 1.581967213114754,
2716
+ "grad_norm": 0.23108056293448653,
2717
+ "learning_rate": 1.2739187494368877e-05,
2718
+ "loss": 0.0875,
2719
+ "step": 386
2720
+ },
2721
+ {
2722
+ "epoch": 1.5860655737704918,
2723
+ "grad_norm": 0.23368547866832753,
2724
+ "learning_rate": 1.2501546149827792e-05,
2725
+ "loss": 0.0854,
2726
+ "step": 387
2727
+ },
2728
+ {
2729
+ "epoch": 1.5901639344262295,
2730
+ "grad_norm": 0.24320292213137776,
2731
+ "learning_rate": 1.2265825163346911e-05,
2732
+ "loss": 0.0893,
2733
+ "step": 388
2734
+ },
2735
+ {
2736
+ "epoch": 1.5942622950819674,
2737
+ "grad_norm": 0.21570274646869986,
2738
+ "learning_rate": 1.2032036606589175e-05,
2739
+ "loss": 0.0685,
2740
+ "step": 389
2741
+ },
2742
+ {
2743
+ "epoch": 1.598360655737705,
2744
+ "grad_norm": 0.22099512747621203,
2745
+ "learning_rate": 1.1800192452254627e-05,
2746
+ "loss": 0.0897,
2747
+ "step": 390
2748
+ },
2749
+ {
2750
+ "epoch": 1.6024590163934427,
2751
+ "grad_norm": 0.23793535397292723,
2752
+ "learning_rate": 1.15703045734672e-05,
2753
+ "loss": 0.0957,
2754
+ "step": 391
2755
+ },
2756
+ {
2757
+ "epoch": 1.6065573770491803,
2758
+ "grad_norm": 0.24731877068153732,
2759
+ "learning_rate": 1.1342384743166723e-05,
2760
+ "loss": 0.1042,
2761
+ "step": 392
2762
+ },
2763
+ {
2764
+ "epoch": 1.610655737704918,
2765
+ "grad_norm": 0.22927608698188615,
2766
+ "learning_rate": 1.1116444633506019e-05,
2767
+ "loss": 0.0716,
2768
+ "step": 393
2769
+ },
2770
+ {
2771
+ "epoch": 1.6147540983606556,
2772
+ "grad_norm": 0.23857230000679394,
2773
+ "learning_rate": 1.0892495815253085e-05,
2774
+ "loss": 0.0768,
2775
+ "step": 394
2776
+ },
2777
+ {
2778
+ "epoch": 1.6188524590163933,
2779
+ "grad_norm": 0.24372403659065045,
2780
+ "learning_rate": 1.0670549757198633e-05,
2781
+ "loss": 0.0834,
2782
+ "step": 395
2783
+ },
2784
+ {
2785
+ "epoch": 1.6229508196721312,
2786
+ "grad_norm": 0.22414275748214862,
2787
+ "learning_rate": 1.0450617825568642e-05,
2788
+ "loss": 0.0786,
2789
+ "step": 396
2790
+ },
2791
+ {
2792
+ "epoch": 1.6270491803278688,
2793
+ "grad_norm": 0.21841238944069888,
2794
+ "learning_rate": 1.0232711283442403e-05,
2795
+ "loss": 0.075,
2796
+ "step": 397
2797
+ },
2798
+ {
2799
+ "epoch": 1.6311475409836067,
2800
+ "grad_norm": 0.23509123920348915,
2801
+ "learning_rate": 1.0016841290175572e-05,
2802
+ "loss": 0.077,
2803
+ "step": 398
2804
+ },
2805
+ {
2806
+ "epoch": 1.6352459016393444,
2807
+ "grad_norm": 0.2357206152062922,
2808
+ "learning_rate": 9.803018900828837e-06,
2809
+ "loss": 0.0879,
2810
+ "step": 399
2811
+ },
2812
+ {
2813
+ "epoch": 1.639344262295082,
2814
+ "grad_norm": 0.2192628484070166,
2815
+ "learning_rate": 9.591255065601612e-06,
2816
+ "loss": 0.0814,
2817
+ "step": 400
2818
+ },
2819
+ {
2820
+ "epoch": 1.639344262295082,
2821
+ "eval_loss": 0.11391327530145645,
2822
+ "eval_runtime": 15.815,
2823
+ "eval_samples_per_second": 1.265,
2824
+ "eval_steps_per_second": 0.316,
2825
+ "step": 400
2826
+ },
2827
+ {
2828
+ "epoch": 1.6434426229508197,
2829
+ "grad_norm": 0.22464264802842762,
2830
+ "learning_rate": 9.381560629271407e-06,
2831
+ "loss": 0.0816,
2832
+ "step": 401
2833
+ },
2834
+ {
2835
+ "epoch": 1.6475409836065573,
2836
+ "grad_norm": 0.261870721310818,
2837
+ "learning_rate": 9.173946330638328e-06,
2838
+ "loss": 0.0816,
2839
+ "step": 402
2840
+ },
2841
+ {
2842
+ "epoch": 1.651639344262295,
2843
+ "grad_norm": 0.2149823369960777,
2844
+ "learning_rate": 8.968422801975223e-06,
2845
+ "loss": 0.0705,
2846
+ "step": 403
2847
+ },
2848
+ {
2849
+ "epoch": 1.6557377049180326,
2850
+ "grad_norm": 0.2474828411009011,
2851
+ "learning_rate": 8.765000568483084e-06,
2852
+ "loss": 0.097,
2853
+ "step": 404
2854
+ },
2855
+ {
2856
+ "epoch": 1.6598360655737705,
2857
+ "grad_norm": 0.22154288128693178,
2858
+ "learning_rate": 8.563690047752148e-06,
2859
+ "loss": 0.0765,
2860
+ "step": 405
2861
+ },
2862
+ {
2863
+ "epoch": 1.6639344262295082,
2864
+ "grad_norm": 0.23677782055144925,
2865
+ "learning_rate": 8.364501549228288e-06,
2866
+ "loss": 0.0991,
2867
+ "step": 406
2868
+ },
2869
+ {
2870
+ "epoch": 1.668032786885246,
2871
+ "grad_norm": 0.2197162495146224,
2872
+ "learning_rate": 8.167445273685143e-06,
2873
+ "loss": 0.062,
2874
+ "step": 407
2875
+ },
2876
+ {
2877
+ "epoch": 1.6721311475409837,
2878
+ "grad_norm": 0.23637971545996592,
2879
+ "learning_rate": 7.97253131270162e-06,
2880
+ "loss": 0.0873,
2881
+ "step": 408
2882
+ },
2883
+ {
2884
+ "epoch": 1.6762295081967213,
2885
+ "grad_norm": 0.22398519500886505,
2886
+ "learning_rate": 7.779769648145201e-06,
2887
+ "loss": 0.0712,
2888
+ "step": 409
2889
+ },
2890
+ {
2891
+ "epoch": 1.680327868852459,
2892
+ "grad_norm": 0.23937512798359475,
2893
+ "learning_rate": 7.589170151660657e-06,
2894
+ "loss": 0.0847,
2895
+ "step": 410
2896
+ },
2897
+ {
2898
+ "epoch": 1.6844262295081966,
2899
+ "grad_norm": 0.22939957435275588,
2900
+ "learning_rate": 7.400742584164533e-06,
2901
+ "loss": 0.0832,
2902
+ "step": 411
2903
+ },
2904
+ {
2905
+ "epoch": 1.6885245901639343,
2906
+ "grad_norm": 0.22699971772595506,
2907
+ "learning_rate": 7.2144965953453385e-06,
2908
+ "loss": 0.0813,
2909
+ "step": 412
2910
+ },
2911
+ {
2912
+ "epoch": 1.6926229508196722,
2913
+ "grad_norm": 0.23071893713415165,
2914
+ "learning_rate": 7.030441723169251e-06,
2915
+ "loss": 0.0816,
2916
+ "step": 413
2917
+ },
2918
+ {
2919
+ "epoch": 1.6967213114754098,
2920
+ "grad_norm": 0.23702923002235138,
2921
+ "learning_rate": 6.848587393391792e-06,
2922
+ "loss": 0.0853,
2923
+ "step": 414
2924
+ },
2925
+ {
2926
+ "epoch": 1.7008196721311475,
2927
+ "grad_norm": 0.22339505663904513,
2928
+ "learning_rate": 6.668942919074994e-06,
2929
+ "loss": 0.0717,
2930
+ "step": 415
2931
+ },
2932
+ {
2933
+ "epoch": 1.7049180327868854,
2934
+ "grad_norm": 0.24483844945562266,
2935
+ "learning_rate": 6.491517500110589e-06,
2936
+ "loss": 0.0945,
2937
+ "step": 416
2938
+ },
2939
+ {
2940
+ "epoch": 1.709016393442623,
2941
+ "grad_norm": 0.25539399462778006,
2942
+ "learning_rate": 6.31632022274874e-06,
2943
+ "loss": 0.0979,
2944
+ "step": 417
2945
+ },
2946
+ {
2947
+ "epoch": 1.7131147540983607,
2948
+ "grad_norm": 0.24626473814812097,
2949
+ "learning_rate": 6.1433600591328296e-06,
2950
+ "loss": 0.0889,
2951
+ "step": 418
2952
+ },
2953
+ {
2954
+ "epoch": 1.7172131147540983,
2955
+ "grad_norm": 0.20413994594867838,
2956
+ "learning_rate": 5.972645866839882e-06,
2957
+ "loss": 0.0643,
2958
+ "step": 419
2959
+ },
2960
+ {
2961
+ "epoch": 1.721311475409836,
2962
+ "grad_norm": 0.22121713216766659,
2963
+ "learning_rate": 5.804186388427052e-06,
2964
+ "loss": 0.0909,
2965
+ "step": 420
2966
+ },
2967
+ {
2968
+ "epoch": 1.7254098360655736,
2969
+ "grad_norm": 0.23283310959693312,
2970
+ "learning_rate": 5.637990250983821e-06,
2971
+ "loss": 0.0906,
2972
+ "step": 421
2973
+ },
2974
+ {
2975
+ "epoch": 1.7295081967213115,
2976
+ "grad_norm": 0.2443306803824525,
2977
+ "learning_rate": 5.4740659656902284e-06,
2978
+ "loss": 0.0811,
2979
+ "step": 422
2980
+ },
2981
+ {
2982
+ "epoch": 1.7336065573770492,
2983
+ "grad_norm": 0.22756772215296253,
2984
+ "learning_rate": 5.312421927381017e-06,
2985
+ "loss": 0.0827,
2986
+ "step": 423
2987
+ },
2988
+ {
2989
+ "epoch": 1.737704918032787,
2990
+ "grad_norm": 0.2228814962421585,
2991
+ "learning_rate": 5.153066414115659e-06,
2992
+ "loss": 0.0669,
2993
+ "step": 424
2994
+ },
2995
+ {
2996
+ "epoch": 1.7418032786885247,
2997
+ "grad_norm": 0.2661863386779688,
2998
+ "learning_rate": 4.9960075867544974e-06,
2999
+ "loss": 0.1088,
3000
+ "step": 425
3001
+ },
3002
+ {
3003
+ "epoch": 1.7459016393442623,
3004
+ "grad_norm": 0.2561903847946149,
3005
+ "learning_rate": 4.841253488540748e-06,
3006
+ "loss": 0.0945,
3007
+ "step": 426
3008
+ },
3009
+ {
3010
+ "epoch": 1.75,
3011
+ "grad_norm": 0.2267206036798771,
3012
+ "learning_rate": 4.688812044688645e-06,
3013
+ "loss": 0.0719,
3014
+ "step": 427
3015
+ },
3016
+ {
3017
+ "epoch": 1.7540983606557377,
3018
+ "grad_norm": 0.22796746097335438,
3019
+ "learning_rate": 4.53869106197754e-06,
3020
+ "loss": 0.068,
3021
+ "step": 428
3022
+ },
3023
+ {
3024
+ "epoch": 1.7581967213114753,
3025
+ "grad_norm": 0.26106758617331294,
3026
+ "learning_rate": 4.390898228352131e-06,
3027
+ "loss": 0.1061,
3028
+ "step": 429
3029
+ },
3030
+ {
3031
+ "epoch": 1.762295081967213,
3032
+ "grad_norm": 0.247381900560375,
3033
+ "learning_rate": 4.245441112528714e-06,
3034
+ "loss": 0.0908,
3035
+ "step": 430
3036
+ },
3037
+ {
3038
+ "epoch": 1.7663934426229508,
3039
+ "grad_norm": 0.24294560089179307,
3040
+ "learning_rate": 4.1023271636076335e-06,
3041
+ "loss": 0.0926,
3042
+ "step": 431
3043
+ },
3044
+ {
3045
+ "epoch": 1.7704918032786885,
3046
+ "grad_norm": 0.24215296053576252,
3047
+ "learning_rate": 3.961563710691729e-06,
3048
+ "loss": 0.0779,
3049
+ "step": 432
3050
+ },
3051
+ {
3052
+ "epoch": 1.7745901639344264,
3053
+ "grad_norm": 0.23374549340723078,
3054
+ "learning_rate": 3.823157962511076e-06,
3055
+ "loss": 0.0728,
3056
+ "step": 433
3057
+ },
3058
+ {
3059
+ "epoch": 1.778688524590164,
3060
+ "grad_norm": 0.24289701548347858,
3061
+ "learning_rate": 3.687117007053742e-06,
3062
+ "loss": 0.0867,
3063
+ "step": 434
3064
+ },
3065
+ {
3066
+ "epoch": 1.7827868852459017,
3067
+ "grad_norm": 0.2522452950320934,
3068
+ "learning_rate": 3.553447811202876e-06,
3069
+ "loss": 0.0929,
3070
+ "step": 435
3071
+ },
3072
+ {
3073
+ "epoch": 1.7868852459016393,
3074
+ "grad_norm": 0.22114275777413536,
3075
+ "learning_rate": 3.4221572203798234e-06,
3076
+ "loss": 0.0743,
3077
+ "step": 436
3078
+ },
3079
+ {
3080
+ "epoch": 1.790983606557377,
3081
+ "grad_norm": 0.21366511169828778,
3082
+ "learning_rate": 3.293251958193683e-06,
3083
+ "loss": 0.0706,
3084
+ "step": 437
3085
+ },
3086
+ {
3087
+ "epoch": 1.7950819672131146,
3088
+ "grad_norm": 0.21948702570848402,
3089
+ "learning_rate": 3.1667386260968657e-06,
3090
+ "loss": 0.0681,
3091
+ "step": 438
3092
+ },
3093
+ {
3094
+ "epoch": 1.7991803278688525,
3095
+ "grad_norm": 0.23774843706100457,
3096
+ "learning_rate": 3.0426237030470984e-06,
3097
+ "loss": 0.0895,
3098
+ "step": 439
3099
+ },
3100
+ {
3101
+ "epoch": 1.8032786885245902,
3102
+ "grad_norm": 0.22399865620122292,
3103
+ "learning_rate": 2.9209135451755854e-06,
3104
+ "loss": 0.0667,
3105
+ "step": 440
3106
+ },
3107
+ {
3108
+ "epoch": 1.8073770491803278,
3109
+ "grad_norm": 0.21426419849873798,
3110
+ "learning_rate": 2.8016143854615207e-06,
3111
+ "loss": 0.0811,
3112
+ "step": 441
3113
+ },
3114
+ {
3115
+ "epoch": 1.8114754098360657,
3116
+ "grad_norm": 0.21259033673347263,
3117
+ "learning_rate": 2.6847323334128927e-06,
3118
+ "loss": 0.0676,
3119
+ "step": 442
3120
+ },
3121
+ {
3122
+ "epoch": 1.8155737704918034,
3123
+ "grad_norm": 0.24929681837203466,
3124
+ "learning_rate": 2.570273374753568e-06,
3125
+ "loss": 0.0808,
3126
+ "step": 443
3127
+ },
3128
+ {
3129
+ "epoch": 1.819672131147541,
3130
+ "grad_norm": 0.23655301701967882,
3131
+ "learning_rate": 2.458243371116803e-06,
3132
+ "loss": 0.0716,
3133
+ "step": 444
3134
+ },
3135
+ {
3136
+ "epoch": 1.8237704918032787,
3137
+ "grad_norm": 0.21403845251592035,
3138
+ "learning_rate": 2.3486480597450233e-06,
3139
+ "loss": 0.0666,
3140
+ "step": 445
3141
+ },
3142
+ {
3143
+ "epoch": 1.8278688524590163,
3144
+ "grad_norm": 0.23585733424654748,
3145
+ "learning_rate": 2.2414930531960366e-06,
3146
+ "loss": 0.0804,
3147
+ "step": 446
3148
+ },
3149
+ {
3150
+ "epoch": 1.831967213114754,
3151
+ "grad_norm": 0.23393497320481016,
3152
+ "learning_rate": 2.1367838390555615e-06,
3153
+ "loss": 0.0822,
3154
+ "step": 447
3155
+ },
3156
+ {
3157
+ "epoch": 1.8360655737704918,
3158
+ "grad_norm": 0.22648840130944828,
3159
+ "learning_rate": 2.0345257796562657e-06,
3160
+ "loss": 0.0697,
3161
+ "step": 448
3162
+ },
3163
+ {
3164
+ "epoch": 1.8401639344262295,
3165
+ "grad_norm": 0.26501948838229905,
3166
+ "learning_rate": 1.9347241118030823e-06,
3167
+ "loss": 0.1039,
3168
+ "step": 449
3169
+ },
3170
+ {
3171
+ "epoch": 1.8442622950819674,
3172
+ "grad_norm": 0.24866758119966959,
3173
+ "learning_rate": 1.8373839465050779e-06,
3174
+ "loss": 0.0945,
3175
+ "step": 450
3176
+ },
3177
+ {
3178
+ "epoch": 1.848360655737705,
3179
+ "grad_norm": 0.23782724905733918,
3180
+ "learning_rate": 1.7425102687136708e-06,
3181
+ "loss": 0.0717,
3182
+ "step": 451
3183
+ },
3184
+ {
3185
+ "epoch": 1.8524590163934427,
3186
+ "grad_norm": 0.24694288793510444,
3187
+ "learning_rate": 1.65010793706738e-06,
3188
+ "loss": 0.0846,
3189
+ "step": 452
3190
+ },
3191
+ {
3192
+ "epoch": 1.8565573770491803,
3193
+ "grad_norm": 0.23687783352322112,
3194
+ "learning_rate": 1.5601816836429584e-06,
3195
+ "loss": 0.0864,
3196
+ "step": 453
3197
+ },
3198
+ {
3199
+ "epoch": 1.860655737704918,
3200
+ "grad_norm": 0.22117276028464855,
3201
+ "learning_rate": 1.4727361137131136e-06,
3202
+ "loss": 0.0769,
3203
+ "step": 454
3204
+ },
3205
+ {
3206
+ "epoch": 1.8647540983606556,
3207
+ "grad_norm": 0.22732784122754088,
3208
+ "learning_rate": 1.3877757055106132e-06,
3209
+ "loss": 0.0752,
3210
+ "step": 455
3211
+ },
3212
+ {
3213
+ "epoch": 1.8688524590163933,
3214
+ "grad_norm": 0.23983266256314234,
3215
+ "learning_rate": 1.3053048099989807e-06,
3216
+ "loss": 0.0817,
3217
+ "step": 456
3218
+ },
3219
+ {
3220
+ "epoch": 1.8729508196721312,
3221
+ "grad_norm": 0.29876460611279054,
3222
+ "learning_rate": 1.2253276506496547e-06,
3223
+ "loss": 0.0928,
3224
+ "step": 457
3225
+ },
3226
+ {
3227
+ "epoch": 1.8770491803278688,
3228
+ "grad_norm": 0.25065773079557147,
3229
+ "learning_rate": 1.1478483232257088e-06,
3230
+ "loss": 0.0685,
3231
+ "step": 458
3232
+ },
3233
+ {
3234
+ "epoch": 1.8811475409836067,
3235
+ "grad_norm": 0.22154067972076463,
3236
+ "learning_rate": 1.0728707955721006e-06,
3237
+ "loss": 0.0677,
3238
+ "step": 459
3239
+ },
3240
+ {
3241
+ "epoch": 1.8852459016393444,
3242
+ "grad_norm": 0.24820921053712106,
3243
+ "learning_rate": 1.000398907412453e-06,
3244
+ "loss": 0.0807,
3245
+ "step": 460
3246
+ },
3247
+ {
3248
+ "epoch": 1.889344262295082,
3249
+ "grad_norm": 0.23265461838690038,
3250
+ "learning_rate": 9.304363701524654e-07,
3251
+ "loss": 0.076,
3252
+ "step": 461
3253
+ },
3254
+ {
3255
+ "epoch": 1.8934426229508197,
3256
+ "grad_norm": 0.2212340843550487,
3257
+ "learning_rate": 8.629867666897773e-07,
3258
+ "loss": 0.0735,
3259
+ "step": 462
3260
+ },
3261
+ {
3262
+ "epoch": 1.8975409836065573,
3263
+ "grad_norm": 0.22696045078695706,
3264
+ "learning_rate": 7.980535512305376e-07,
3265
+ "loss": 0.0749,
3266
+ "step": 463
3267
+ },
3268
+ {
3269
+ "epoch": 1.901639344262295,
3270
+ "grad_norm": 0.23353372696636585,
3271
+ "learning_rate": 7.356400491124737e-07,
3272
+ "loss": 0.0739,
3273
+ "step": 464
3274
+ },
3275
+ {
3276
+ "epoch": 1.9057377049180326,
3277
+ "grad_norm": 0.22465718167778462,
3278
+ "learning_rate": 6.757494566346445e-07,
3279
+ "loss": 0.0635,
3280
+ "step": 465
3281
+ },
3282
+ {
3283
+ "epoch": 1.9098360655737705,
3284
+ "grad_norm": 0.2714574406648733,
3285
+ "learning_rate": 6.183848408936709e-07,
3286
+ "loss": 0.0978,
3287
+ "step": 466
3288
+ },
3289
+ {
3290
+ "epoch": 1.9139344262295082,
3291
+ "grad_norm": 0.2241827281383872,
3292
+ "learning_rate": 5.635491396267456e-07,
3293
+ "loss": 0.0728,
3294
+ "step": 467
3295
+ },
3296
+ {
3297
+ "epoch": 1.918032786885246,
3298
+ "grad_norm": 0.22303567853923986,
3299
+ "learning_rate": 5.112451610611469e-07,
3300
+ "loss": 0.0735,
3301
+ "step": 468
3302
+ },
3303
+ {
3304
+ "epoch": 1.9221311475409837,
3305
+ "grad_norm": 0.25184864069673707,
3306
+ "learning_rate": 4.614755837704321e-07,
3307
+ "loss": 0.0845,
3308
+ "step": 469
3309
+ },
3310
+ {
3311
+ "epoch": 1.9262295081967213,
3312
+ "grad_norm": 0.2238797951927238,
3313
+ "learning_rate": 4.14242956537253e-07,
3314
+ "loss": 0.079,
3315
+ "step": 470
3316
+ },
3317
+ {
3318
+ "epoch": 1.930327868852459,
3319
+ "grad_norm": 0.2323006006995677,
3320
+ "learning_rate": 3.69549698222843e-07,
3321
+ "loss": 0.0787,
3322
+ "step": 471
3323
+ },
3324
+ {
3325
+ "epoch": 1.9344262295081966,
3326
+ "grad_norm": 0.23426756288417372,
3327
+ "learning_rate": 3.273980976431501e-07,
3328
+ "loss": 0.0901,
3329
+ "step": 472
3330
+ },
3331
+ {
3332
+ "epoch": 1.9385245901639343,
3333
+ "grad_norm": 0.23048072960491015,
3334
+ "learning_rate": 2.8779031345159136e-07,
3335
+ "loss": 0.0767,
3336
+ "step": 473
3337
+ },
3338
+ {
3339
+ "epoch": 1.9426229508196722,
3340
+ "grad_norm": 0.24308841255499397,
3341
+ "learning_rate": 2.5072837402854157e-07,
3342
+ "loss": 0.0928,
3343
+ "step": 474
3344
+ },
3345
+ {
3346
+ "epoch": 1.9467213114754098,
3347
+ "grad_norm": 0.2889749002741685,
3348
+ "learning_rate": 2.162141773774329e-07,
3349
+ "loss": 0.0944,
3350
+ "step": 475
3351
+ },
3352
+ {
3353
+ "epoch": 1.9508196721311475,
3354
+ "grad_norm": 0.24338145335001735,
3355
+ "learning_rate": 1.842494910275605e-07,
3356
+ "loss": 0.0818,
3357
+ "step": 476
3358
+ },
3359
+ {
3360
+ "epoch": 1.9549180327868854,
3361
+ "grad_norm": 0.20651636363797357,
3362
+ "learning_rate": 1.5483595194356048e-07,
3363
+ "loss": 0.0633,
3364
+ "step": 477
3365
+ },
3366
+ {
3367
+ "epoch": 1.959016393442623,
3368
+ "grad_norm": 0.22304906627189303,
3369
+ "learning_rate": 1.2797506644159351e-07,
3370
+ "loss": 0.0694,
3371
+ "step": 478
3372
+ },
3373
+ {
3374
+ "epoch": 1.9631147540983607,
3375
+ "grad_norm": 0.20982729632198355,
3376
+ "learning_rate": 1.0366821011218997e-07,
3377
+ "loss": 0.065,
3378
+ "step": 479
3379
+ },
3380
+ {
3381
+ "epoch": 1.9672131147540983,
3382
+ "grad_norm": 0.23590436160688563,
3383
+ "learning_rate": 8.191662774980625e-08,
3384
+ "loss": 0.0831,
3385
+ "step": 480
3386
+ },
3387
+ {
3388
+ "epoch": 1.971311475409836,
3389
+ "grad_norm": 0.2550649137151106,
3390
+ "learning_rate": 6.272143328907575e-08,
3391
+ "loss": 0.0849,
3392
+ "step": 481
3393
+ },
3394
+ {
3395
+ "epoch": 1.9754098360655736,
3396
+ "grad_norm": 0.2280158394119794,
3397
+ "learning_rate": 4.608360974776571e-08,
3398
+ "loss": 0.0773,
3399
+ "step": 482
3400
+ },
3401
+ {
3402
+ "epoch": 1.9795081967213115,
3403
+ "grad_norm": 0.24398300931602282,
3404
+ "learning_rate": 3.200400917643398e-08,
3405
+ "loss": 0.1115,
3406
+ "step": 483
3407
+ },
3408
+ {
3409
+ "epoch": 1.9836065573770492,
3410
+ "grad_norm": 0.23215824795287876,
3411
+ "learning_rate": 2.048335261479739e-08,
3412
+ "loss": 0.0668,
3413
+ "step": 484
3414
+ },
3415
+ {
3416
+ "epoch": 1.987704918032787,
3417
+ "grad_norm": 0.23261181672658787,
3418
+ "learning_rate": 1.152223005479458e-08,
3419
+ "loss": 0.0768,
3420
+ "step": 485
3421
+ },
3422
+ {
3423
+ "epoch": 1.9918032786885247,
3424
+ "grad_norm": 0.22434385789931668,
3425
+ "learning_rate": 5.121100410393487e-09,
3426
+ "loss": 0.0691,
3427
+ "step": 486
3428
+ },
3429
+ {
3430
+ "epoch": 1.9959016393442623,
3431
+ "grad_norm": 0.23535013520501705,
3432
+ "learning_rate": 1.2802914940601707e-09,
3433
+ "loss": 0.082,
3434
+ "step": 487
3435
+ },
3436
+ {
3437
+ "epoch": 2.0,
3438
+ "grad_norm": 0.2273460494952869,
3439
+ "learning_rate": 0.0,
3440
+ "loss": 0.0848,
3441
+ "step": 488
3442
+ },
3443
+ {
3444
+ "epoch": 2.0,
3445
+ "step": 488,
3446
+ "total_flos": 2471609260572672.0,
3447
+ "train_loss": 0.1494467844423212,
3448
+ "train_runtime": 5820.7005,
3449
+ "train_samples_per_second": 0.671,
3450
+ "train_steps_per_second": 0.084
3451
+ }
3452
+ ],
3453
+ "logging_steps": 1,
3454
+ "max_steps": 488,
3455
+ "num_input_tokens_seen": 0,
3456
+ "num_train_epochs": 2,
3457
+ "save_steps": 500,
3458
+ "stateful_callbacks": {
3459
+ "TrainerControl": {
3460
+ "args": {
3461
+ "should_epoch_stop": false,
3462
+ "should_evaluate": false,
3463
+ "should_log": false,
3464
+ "should_save": true,
3465
+ "should_training_stop": true
3466
+ },
3467
+ "attributes": {}
3468
+ }
3469
+ },
3470
+ "total_flos": 2471609260572672.0,
3471
+ "train_batch_size": 2,
3472
+ "trial_name": null,
3473
+ "trial_params": null
3474
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e28d5a694dcc87bb87ef3714e10773ffabd3a875a526d06a25f145cda03afe
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