cutelemonlili commited on
Commit
574f8c3
·
verified ·
1 Parent(s): 7a6ebda

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Qwen/Qwen2.5-0.5B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: omni_training_no_less_than_5
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
+ # omni_training_no_less_than_5
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the omni_training_no_less_than_5 dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.1181
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - total_train_batch_size: 8
47
+ - total_eval_batch_size: 4
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - num_epochs: 2
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 1.1461 | 0.8696 | 200 | 1.1071 |
57
+ | 0.6251 | 1.7391 | 400 | 1.1194 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.46.1
63
+ - Pytorch 2.5.1+cu124
64
+ - Datasets 3.1.0
65
+ - Tokenizers 0.20.3
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 1.1181042194366455,
4
+ "eval_runtime": 0.6984,
5
+ "eval_samples_per_second": 27.205,
6
+ "eval_steps_per_second": 7.159,
7
+ "total_flos": 1314917400576.0,
8
+ "train_loss": 0.9610995156609494,
9
+ "train_runtime": 290.1657,
10
+ "train_samples_per_second": 12.682,
11
+ "train_steps_per_second": 1.585
12
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 14,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 151936
29
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 1.1181042194366455,
4
+ "eval_runtime": 0.6984,
5
+ "eval_samples_per_second": 27.205,
6
+ "eval_steps_per_second": 7.159
7
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.1"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ccdc68f7c4aee8e8688c7c55f9d847a075a1c729e1661164299de64dc78ff68
3
+ size 988097824
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 1314917400576.0,
4
+ "train_loss": 0.9610995156609494,
5
+ "train_runtime": 290.1657,
6
+ "train_samples_per_second": 12.682,
7
+ "train_steps_per_second": 1.585
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,463 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 460, "loss": 1.2388, "lr": 9.999883393595949e-06, "epoch": 0.004347826086956522, "percentage": 0.22, "elapsed_time": "0:00:02", "remaining_time": "0:15:49"}
2
+ {"current_steps": 2, "total_steps": 460, "loss": 1.1524, "lr": 9.999533579822611e-06, "epoch": 0.008695652173913044, "percentage": 0.43, "elapsed_time": "0:00:06", "remaining_time": "0:23:37"}
3
+ {"current_steps": 3, "total_steps": 460, "loss": 1.1518, "lr": 9.9989505749962e-06, "epoch": 0.013043478260869565, "percentage": 0.65, "elapsed_time": "0:00:06", "remaining_time": "0:17:16"}
4
+ {"current_steps": 4, "total_steps": 460, "loss": 0.9891, "lr": 9.998134406309555e-06, "epoch": 0.017391304347826087, "percentage": 0.87, "elapsed_time": "0:00:07", "remaining_time": "0:14:04"}
5
+ {"current_steps": 5, "total_steps": 460, "loss": 0.8734, "lr": 9.99708511183087e-06, "epoch": 0.021739130434782608, "percentage": 1.09, "elapsed_time": "0:00:08", "remaining_time": "0:12:10"}
6
+ {"current_steps": 6, "total_steps": 460, "loss": 1.0579, "lr": 9.995802740501933e-06, "epoch": 0.02608695652173913, "percentage": 1.3, "elapsed_time": "0:00:08", "remaining_time": "0:10:53"}
7
+ {"current_steps": 7, "total_steps": 460, "loss": 0.9832, "lr": 9.994287352135826e-06, "epoch": 0.030434782608695653, "percentage": 1.52, "elapsed_time": "0:00:09", "remaining_time": "0:09:58"}
8
+ {"current_steps": 8, "total_steps": 460, "loss": 1.041, "lr": 9.99253901741414e-06, "epoch": 0.034782608695652174, "percentage": 1.74, "elapsed_time": "0:00:09", "remaining_time": "0:09:17"}
9
+ {"current_steps": 9, "total_steps": 460, "loss": 1.126, "lr": 9.99055781788369e-06, "epoch": 0.0391304347826087, "percentage": 1.96, "elapsed_time": "0:00:10", "remaining_time": "0:08:44"}
10
+ {"current_steps": 10, "total_steps": 460, "loss": 1.2885, "lr": 9.988343845952697e-06, "epoch": 0.043478260869565216, "percentage": 2.17, "elapsed_time": "0:00:11", "remaining_time": "0:08:18"}
11
+ {"current_steps": 11, "total_steps": 460, "loss": 0.8854, "lr": 9.985897204886481e-06, "epoch": 0.04782608695652174, "percentage": 2.39, "elapsed_time": "0:00:11", "remaining_time": "0:07:58"}
12
+ {"current_steps": 12, "total_steps": 460, "loss": 1.2227, "lr": 9.983218008802648e-06, "epoch": 0.05217391304347826, "percentage": 2.61, "elapsed_time": "0:00:12", "remaining_time": "0:07:39"}
13
+ {"current_steps": 13, "total_steps": 460, "loss": 1.2126, "lr": 9.98030638266577e-06, "epoch": 0.05652173913043478, "percentage": 2.83, "elapsed_time": "0:00:12", "remaining_time": "0:07:24"}
14
+ {"current_steps": 14, "total_steps": 460, "loss": 1.0473, "lr": 9.977162462281544e-06, "epoch": 0.06086956521739131, "percentage": 3.04, "elapsed_time": "0:00:13", "remaining_time": "0:07:10"}
15
+ {"current_steps": 15, "total_steps": 460, "loss": 1.069, "lr": 9.973786394290475e-06, "epoch": 0.06521739130434782, "percentage": 3.26, "elapsed_time": "0:00:14", "remaining_time": "0:06:59"}
16
+ {"current_steps": 16, "total_steps": 460, "loss": 1.0858, "lr": 9.970178336161018e-06, "epoch": 0.06956521739130435, "percentage": 3.48, "elapsed_time": "0:00:14", "remaining_time": "0:06:48"}
17
+ {"current_steps": 17, "total_steps": 460, "loss": 0.857, "lr": 9.96633845618225e-06, "epoch": 0.07391304347826087, "percentage": 3.7, "elapsed_time": "0:00:15", "remaining_time": "0:06:39"}
18
+ {"current_steps": 18, "total_steps": 460, "loss": 1.5511, "lr": 9.962266933456008e-06, "epoch": 0.0782608695652174, "percentage": 3.91, "elapsed_time": "0:00:15", "remaining_time": "0:06:31"}
19
+ {"current_steps": 19, "total_steps": 460, "loss": 1.1189, "lr": 9.957963957888542e-06, "epoch": 0.08260869565217391, "percentage": 4.13, "elapsed_time": "0:00:16", "remaining_time": "0:06:24"}
20
+ {"current_steps": 20, "total_steps": 460, "loss": 1.1901, "lr": 9.953429730181653e-06, "epoch": 0.08695652173913043, "percentage": 4.35, "elapsed_time": "0:00:17", "remaining_time": "0:06:17"}
21
+ {"current_steps": 21, "total_steps": 460, "loss": 1.1392, "lr": 9.94866446182334e-06, "epoch": 0.09130434782608696, "percentage": 4.57, "elapsed_time": "0:00:17", "remaining_time": "0:06:11"}
22
+ {"current_steps": 22, "total_steps": 460, "loss": 1.2286, "lr": 9.943668375077926e-06, "epoch": 0.09565217391304348, "percentage": 4.78, "elapsed_time": "0:00:18", "remaining_time": "0:06:05"}
23
+ {"current_steps": 23, "total_steps": 460, "loss": 1.1547, "lr": 9.938441702975689e-06, "epoch": 0.1, "percentage": 5.0, "elapsed_time": "0:00:19", "remaining_time": "0:06:01"}
24
+ {"current_steps": 24, "total_steps": 460, "loss": 0.9822, "lr": 9.932984689302012e-06, "epoch": 0.10434782608695652, "percentage": 5.22, "elapsed_time": "0:00:19", "remaining_time": "0:05:56"}
25
+ {"current_steps": 25, "total_steps": 460, "loss": 1.1524, "lr": 9.927297588585984e-06, "epoch": 0.10869565217391304, "percentage": 5.43, "elapsed_time": "0:00:20", "remaining_time": "0:05:52"}
26
+ {"current_steps": 26, "total_steps": 460, "loss": 1.1971, "lr": 9.921380666088558e-06, "epoch": 0.11304347826086956, "percentage": 5.65, "elapsed_time": "0:00:20", "remaining_time": "0:05:48"}
27
+ {"current_steps": 27, "total_steps": 460, "loss": 0.8627, "lr": 9.915234197790153e-06, "epoch": 0.11739130434782609, "percentage": 5.87, "elapsed_time": "0:00:21", "remaining_time": "0:05:44"}
28
+ {"current_steps": 28, "total_steps": 460, "loss": 1.0703, "lr": 9.908858470377793e-06, "epoch": 0.12173913043478261, "percentage": 6.09, "elapsed_time": "0:00:22", "remaining_time": "0:05:40"}
29
+ {"current_steps": 29, "total_steps": 460, "loss": 1.1291, "lr": 9.902253781231741e-06, "epoch": 0.12608695652173912, "percentage": 6.3, "elapsed_time": "0:00:22", "remaining_time": "0:05:37"}
30
+ {"current_steps": 30, "total_steps": 460, "loss": 0.8515, "lr": 9.895420438411616e-06, "epoch": 0.13043478260869565, "percentage": 6.52, "elapsed_time": "0:00:23", "remaining_time": "0:05:34"}
31
+ {"current_steps": 31, "total_steps": 460, "loss": 1.0999, "lr": 9.88835876064203e-06, "epoch": 0.13478260869565217, "percentage": 6.74, "elapsed_time": "0:00:23", "remaining_time": "0:05:31"}
32
+ {"current_steps": 32, "total_steps": 460, "loss": 1.2162, "lr": 9.881069077297724e-06, "epoch": 0.1391304347826087, "percentage": 6.96, "elapsed_time": "0:00:24", "remaining_time": "0:05:28"}
33
+ {"current_steps": 33, "total_steps": 460, "loss": 1.0254, "lr": 9.873551728388203e-06, "epoch": 0.14347826086956522, "percentage": 7.17, "elapsed_time": "0:00:25", "remaining_time": "0:05:25"}
34
+ {"current_steps": 34, "total_steps": 460, "loss": 1.2162, "lr": 9.865807064541878e-06, "epoch": 0.14782608695652175, "percentage": 7.39, "elapsed_time": "0:00:25", "remaining_time": "0:05:23"}
35
+ {"current_steps": 35, "total_steps": 460, "loss": 1.2053, "lr": 9.857835446989708e-06, "epoch": 0.15217391304347827, "percentage": 7.61, "elapsed_time": "0:00:26", "remaining_time": "0:05:20"}
36
+ {"current_steps": 36, "total_steps": 460, "loss": 0.8951, "lr": 9.849637247548356e-06, "epoch": 0.1565217391304348, "percentage": 7.83, "elapsed_time": "0:00:27", "remaining_time": "0:05:18"}
37
+ {"current_steps": 37, "total_steps": 460, "loss": 1.2886, "lr": 9.841212848602848e-06, "epoch": 0.1608695652173913, "percentage": 8.04, "elapsed_time": "0:00:27", "remaining_time": "0:05:15"}
38
+ {"current_steps": 38, "total_steps": 460, "loss": 1.1409, "lr": 9.832562643088724e-06, "epoch": 0.16521739130434782, "percentage": 8.26, "elapsed_time": "0:00:28", "remaining_time": "0:05:13"}
39
+ {"current_steps": 39, "total_steps": 460, "loss": 1.1393, "lr": 9.823687034473734e-06, "epoch": 0.16956521739130434, "percentage": 8.48, "elapsed_time": "0:00:28", "remaining_time": "0:05:11"}
40
+ {"current_steps": 40, "total_steps": 460, "loss": 1.2827, "lr": 9.814586436738998e-06, "epoch": 0.17391304347826086, "percentage": 8.7, "elapsed_time": "0:00:29", "remaining_time": "0:05:09"}
41
+ {"current_steps": 41, "total_steps": 460, "loss": 1.0051, "lr": 9.805261274359705e-06, "epoch": 0.1782608695652174, "percentage": 8.91, "elapsed_time": "0:00:30", "remaining_time": "0:05:06"}
42
+ {"current_steps": 42, "total_steps": 460, "loss": 1.0446, "lr": 9.795711982285317e-06, "epoch": 0.1826086956521739, "percentage": 9.13, "elapsed_time": "0:00:30", "remaining_time": "0:05:04"}
43
+ {"current_steps": 43, "total_steps": 460, "loss": 0.9145, "lr": 9.785939005919279e-06, "epoch": 0.18695652173913044, "percentage": 9.35, "elapsed_time": "0:00:31", "remaining_time": "0:05:02"}
44
+ {"current_steps": 44, "total_steps": 460, "loss": 1.0196, "lr": 9.775942801098241e-06, "epoch": 0.19130434782608696, "percentage": 9.57, "elapsed_time": "0:00:31", "remaining_time": "0:05:01"}
45
+ {"current_steps": 45, "total_steps": 460, "loss": 0.9979, "lr": 9.765723834070805e-06, "epoch": 0.1956521739130435, "percentage": 9.78, "elapsed_time": "0:00:32", "remaining_time": "0:04:59"}
46
+ {"current_steps": 46, "total_steps": 460, "loss": 1.0051, "lr": 9.755282581475769e-06, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:00:33", "remaining_time": "0:04:57"}
47
+ {"current_steps": 47, "total_steps": 460, "loss": 1.1931, "lr": 9.7446195303199e-06, "epoch": 0.20434782608695654, "percentage": 10.22, "elapsed_time": "0:00:33", "remaining_time": "0:04:55"}
48
+ {"current_steps": 48, "total_steps": 460, "loss": 0.9187, "lr": 9.733735177955219e-06, "epoch": 0.20869565217391303, "percentage": 10.43, "elapsed_time": "0:00:34", "remaining_time": "0:04:54"}
49
+ {"current_steps": 49, "total_steps": 460, "loss": 0.9918, "lr": 9.722630032055804e-06, "epoch": 0.21304347826086956, "percentage": 10.65, "elapsed_time": "0:00:34", "remaining_time": "0:04:52"}
50
+ {"current_steps": 50, "total_steps": 460, "loss": 0.7698, "lr": 9.711304610594104e-06, "epoch": 0.21739130434782608, "percentage": 10.87, "elapsed_time": "0:00:35", "remaining_time": "0:04:51"}
51
+ {"current_steps": 51, "total_steps": 460, "loss": 1.0155, "lr": 9.699759441816788e-06, "epoch": 0.2217391304347826, "percentage": 11.09, "elapsed_time": "0:00:36", "remaining_time": "0:04:49"}
52
+ {"current_steps": 52, "total_steps": 460, "loss": 1.0465, "lr": 9.687995064220102e-06, "epoch": 0.22608695652173913, "percentage": 11.3, "elapsed_time": "0:00:36", "remaining_time": "0:04:48"}
53
+ {"current_steps": 53, "total_steps": 460, "loss": 1.1731, "lr": 9.676012026524755e-06, "epoch": 0.23043478260869565, "percentage": 11.52, "elapsed_time": "0:00:37", "remaining_time": "0:04:46"}
54
+ {"current_steps": 54, "total_steps": 460, "loss": 1.0759, "lr": 9.66381088765032e-06, "epoch": 0.23478260869565218, "percentage": 11.74, "elapsed_time": "0:00:37", "remaining_time": "0:04:45"}
55
+ {"current_steps": 55, "total_steps": 460, "loss": 1.2107, "lr": 9.651392216689167e-06, "epoch": 0.2391304347826087, "percentage": 11.96, "elapsed_time": "0:00:38", "remaining_time": "0:04:44"}
56
+ {"current_steps": 56, "total_steps": 460, "loss": 1.0933, "lr": 9.638756592879923e-06, "epoch": 0.24347826086956523, "percentage": 12.17, "elapsed_time": "0:00:39", "remaining_time": "0:04:42"}
57
+ {"current_steps": 57, "total_steps": 460, "loss": 1.0525, "lr": 9.625904605580452e-06, "epoch": 0.24782608695652175, "percentage": 12.39, "elapsed_time": "0:00:39", "remaining_time": "0:04:41"}
58
+ {"current_steps": 58, "total_steps": 460, "loss": 1.0356, "lr": 9.61283685424036e-06, "epoch": 0.25217391304347825, "percentage": 12.61, "elapsed_time": "0:00:40", "remaining_time": "0:04:40"}
59
+ {"current_steps": 59, "total_steps": 460, "loss": 0.9344, "lr": 9.599553948373047e-06, "epoch": 0.2565217391304348, "percentage": 12.83, "elapsed_time": "0:00:41", "remaining_time": "0:04:38"}
60
+ {"current_steps": 60, "total_steps": 460, "loss": 1.3272, "lr": 9.586056507527266e-06, "epoch": 0.2608695652173913, "percentage": 13.04, "elapsed_time": "0:00:41", "remaining_time": "0:04:37"}
61
+ {"current_steps": 61, "total_steps": 460, "loss": 1.473, "lr": 9.572345161258235e-06, "epoch": 0.26521739130434785, "percentage": 13.26, "elapsed_time": "0:00:42", "remaining_time": "0:04:36"}
62
+ {"current_steps": 62, "total_steps": 460, "loss": 0.9302, "lr": 9.558420549098269e-06, "epoch": 0.26956521739130435, "percentage": 13.48, "elapsed_time": "0:00:42", "remaining_time": "0:04:34"}
63
+ {"current_steps": 63, "total_steps": 460, "loss": 0.9316, "lr": 9.544283320526943e-06, "epoch": 0.27391304347826084, "percentage": 13.7, "elapsed_time": "0:00:43", "remaining_time": "0:04:33"}
64
+ {"current_steps": 64, "total_steps": 460, "loss": 1.4276, "lr": 9.529934134940819e-06, "epoch": 0.2782608695652174, "percentage": 13.91, "elapsed_time": "0:00:44", "remaining_time": "0:04:32"}
65
+ {"current_steps": 65, "total_steps": 460, "loss": 1.1629, "lr": 9.515373661622665e-06, "epoch": 0.2826086956521739, "percentage": 14.13, "elapsed_time": "0:00:44", "remaining_time": "0:04:31"}
66
+ {"current_steps": 66, "total_steps": 460, "loss": 1.2463, "lr": 9.500602579710256e-06, "epoch": 0.28695652173913044, "percentage": 14.35, "elapsed_time": "0:00:45", "remaining_time": "0:04:30"}
67
+ {"current_steps": 67, "total_steps": 460, "loss": 1.3279, "lr": 9.48562157816469e-06, "epoch": 0.29130434782608694, "percentage": 14.57, "elapsed_time": "0:00:45", "remaining_time": "0:04:28"}
68
+ {"current_steps": 68, "total_steps": 460, "loss": 1.1167, "lr": 9.470431355738257e-06, "epoch": 0.2956521739130435, "percentage": 14.78, "elapsed_time": "0:00:46", "remaining_time": "0:04:27"}
69
+ {"current_steps": 69, "total_steps": 460, "loss": 1.0509, "lr": 9.45503262094184e-06, "epoch": 0.3, "percentage": 15.0, "elapsed_time": "0:00:47", "remaining_time": "0:04:26"}
70
+ {"current_steps": 70, "total_steps": 460, "loss": 1.03, "lr": 9.439426092011877e-06, "epoch": 0.30434782608695654, "percentage": 15.22, "elapsed_time": "0:00:47", "remaining_time": "0:04:25"}
71
+ {"current_steps": 71, "total_steps": 460, "loss": 1.0454, "lr": 9.423612496876856e-06, "epoch": 0.30869565217391304, "percentage": 15.43, "elapsed_time": "0:00:48", "remaining_time": "0:04:24"}
72
+ {"current_steps": 72, "total_steps": 460, "loss": 1.0803, "lr": 9.407592573123359e-06, "epoch": 0.3130434782608696, "percentage": 15.65, "elapsed_time": "0:00:48", "remaining_time": "0:04:23"}
73
+ {"current_steps": 73, "total_steps": 460, "loss": 1.2031, "lr": 9.39136706796167e-06, "epoch": 0.3173913043478261, "percentage": 15.87, "elapsed_time": "0:00:49", "remaining_time": "0:04:22"}
74
+ {"current_steps": 74, "total_steps": 460, "loss": 0.9793, "lr": 9.374936738190913e-06, "epoch": 0.3217391304347826, "percentage": 16.09, "elapsed_time": "0:00:50", "remaining_time": "0:04:21"}
75
+ {"current_steps": 75, "total_steps": 460, "loss": 1.2657, "lr": 9.358302350163758e-06, "epoch": 0.32608695652173914, "percentage": 16.3, "elapsed_time": "0:00:50", "remaining_time": "0:04:20"}
76
+ {"current_steps": 76, "total_steps": 460, "loss": 1.2294, "lr": 9.341464679750669e-06, "epoch": 0.33043478260869563, "percentage": 16.52, "elapsed_time": "0:00:51", "remaining_time": "0:04:19"}
77
+ {"current_steps": 77, "total_steps": 460, "loss": 0.9039, "lr": 9.32442451230373e-06, "epoch": 0.3347826086956522, "percentage": 16.74, "elapsed_time": "0:00:51", "remaining_time": "0:04:18"}
78
+ {"current_steps": 78, "total_steps": 460, "loss": 1.2323, "lr": 9.307182642620001e-06, "epoch": 0.3391304347826087, "percentage": 16.96, "elapsed_time": "0:00:52", "remaining_time": "0:04:17"}
79
+ {"current_steps": 79, "total_steps": 460, "loss": 0.9413, "lr": 9.289739874904448e-06, "epoch": 0.34347826086956523, "percentage": 17.17, "elapsed_time": "0:00:53", "remaining_time": "0:04:16"}
80
+ {"current_steps": 80, "total_steps": 460, "loss": 1.0413, "lr": 9.272097022732444e-06, "epoch": 0.34782608695652173, "percentage": 17.39, "elapsed_time": "0:00:53", "remaining_time": "0:04:15"}
81
+ {"current_steps": 81, "total_steps": 460, "loss": 1.3961, "lr": 9.254254909011805e-06, "epoch": 0.3521739130434783, "percentage": 17.61, "elapsed_time": "0:00:54", "remaining_time": "0:04:14"}
82
+ {"current_steps": 82, "total_steps": 460, "loss": 0.9989, "lr": 9.236214365944418e-06, "epoch": 0.3565217391304348, "percentage": 17.83, "elapsed_time": "0:00:54", "remaining_time": "0:04:13"}
83
+ {"current_steps": 83, "total_steps": 460, "loss": 0.8743, "lr": 9.217976234987429e-06, "epoch": 0.36086956521739133, "percentage": 18.04, "elapsed_time": "0:00:55", "remaining_time": "0:04:12"}
84
+ {"current_steps": 84, "total_steps": 460, "loss": 0.9145, "lr": 9.199541366813984e-06, "epoch": 0.3652173913043478, "percentage": 18.26, "elapsed_time": "0:00:56", "remaining_time": "0:04:11"}
85
+ {"current_steps": 85, "total_steps": 460, "loss": 1.2925, "lr": 9.180910621273555e-06, "epoch": 0.3695652173913043, "percentage": 18.48, "elapsed_time": "0:00:56", "remaining_time": "0:04:10"}
86
+ {"current_steps": 86, "total_steps": 460, "loss": 1.0503, "lr": 9.16208486735184e-06, "epoch": 0.3739130434782609, "percentage": 18.7, "elapsed_time": "0:00:57", "remaining_time": "0:04:09"}
87
+ {"current_steps": 87, "total_steps": 460, "loss": 0.8255, "lr": 9.14306498313023e-06, "epoch": 0.3782608695652174, "percentage": 18.91, "elapsed_time": "0:00:57", "remaining_time": "0:04:08"}
88
+ {"current_steps": 88, "total_steps": 460, "loss": 1.1568, "lr": 9.123851855744842e-06, "epoch": 0.3826086956521739, "percentage": 19.13, "elapsed_time": "0:00:58", "remaining_time": "0:04:07"}
89
+ {"current_steps": 89, "total_steps": 460, "loss": 0.8883, "lr": 9.10444638134516e-06, "epoch": 0.3869565217391304, "percentage": 19.35, "elapsed_time": "0:00:59", "remaining_time": "0:04:06"}
90
+ {"current_steps": 90, "total_steps": 460, "loss": 0.9659, "lr": 9.08484946505221e-06, "epoch": 0.391304347826087, "percentage": 19.57, "elapsed_time": "0:00:59", "remaining_time": "0:04:05"}
91
+ {"current_steps": 91, "total_steps": 460, "loss": 1.2357, "lr": 9.065062020916376e-06, "epoch": 0.39565217391304347, "percentage": 19.78, "elapsed_time": "0:01:00", "remaining_time": "0:04:05"}
92
+ {"current_steps": 92, "total_steps": 460, "loss": 0.8322, "lr": 9.045084971874738e-06, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "0:01:01", "remaining_time": "0:04:04"}
93
+ {"current_steps": 93, "total_steps": 460, "loss": 1.2271, "lr": 9.024919249708034e-06, "epoch": 0.4043478260869565, "percentage": 20.22, "elapsed_time": "0:01:01", "remaining_time": "0:04:03"}
94
+ {"current_steps": 94, "total_steps": 460, "loss": 1.2211, "lr": 9.004565794997209e-06, "epoch": 0.40869565217391307, "percentage": 20.43, "elapsed_time": "0:01:02", "remaining_time": "0:04:02"}
95
+ {"current_steps": 95, "total_steps": 460, "loss": 1.0053, "lr": 8.984025557079523e-06, "epoch": 0.41304347826086957, "percentage": 20.65, "elapsed_time": "0:01:02", "remaining_time": "0:04:01"}
96
+ {"current_steps": 96, "total_steps": 460, "loss": 0.8724, "lr": 8.963299494004292e-06, "epoch": 0.41739130434782606, "percentage": 20.87, "elapsed_time": "0:01:03", "remaining_time": "0:04:00"}
97
+ {"current_steps": 97, "total_steps": 460, "loss": 0.8214, "lr": 8.942388572488188e-06, "epoch": 0.4217391304347826, "percentage": 21.09, "elapsed_time": "0:01:04", "remaining_time": "0:03:59"}
98
+ {"current_steps": 98, "total_steps": 460, "loss": 0.9179, "lr": 8.921293767870157e-06, "epoch": 0.4260869565217391, "percentage": 21.3, "elapsed_time": "0:01:04", "remaining_time": "0:03:58"}
99
+ {"current_steps": 99, "total_steps": 460, "loss": 0.9423, "lr": 8.900016064065923e-06, "epoch": 0.43043478260869567, "percentage": 21.52, "elapsed_time": "0:01:05", "remaining_time": "0:03:58"}
100
+ {"current_steps": 100, "total_steps": 460, "loss": 0.7706, "lr": 8.8785564535221e-06, "epoch": 0.43478260869565216, "percentage": 21.74, "elapsed_time": "0:01:05", "remaining_time": "0:03:57"}
101
+ {"current_steps": 101, "total_steps": 460, "loss": 1.0521, "lr": 8.85691593716989e-06, "epoch": 0.4391304347826087, "percentage": 21.96, "elapsed_time": "0:01:06", "remaining_time": "0:03:56"}
102
+ {"current_steps": 102, "total_steps": 460, "loss": 1.113, "lr": 8.835095524378413e-06, "epoch": 0.4434782608695652, "percentage": 22.17, "elapsed_time": "0:01:07", "remaining_time": "0:03:55"}
103
+ {"current_steps": 103, "total_steps": 460, "loss": 1.016, "lr": 8.81309623290762e-06, "epoch": 0.44782608695652176, "percentage": 22.39, "elapsed_time": "0:01:07", "remaining_time": "0:03:54"}
104
+ {"current_steps": 104, "total_steps": 460, "loss": 0.938, "lr": 8.790919088860815e-06, "epoch": 0.45217391304347826, "percentage": 22.61, "elapsed_time": "0:01:08", "remaining_time": "0:03:53"}
105
+ {"current_steps": 105, "total_steps": 460, "loss": 1.0994, "lr": 8.768565126636806e-06, "epoch": 0.45652173913043476, "percentage": 22.83, "elapsed_time": "0:01:08", "remaining_time": "0:03:53"}
106
+ {"current_steps": 106, "total_steps": 460, "loss": 0.9525, "lr": 8.746035388881655e-06, "epoch": 0.4608695652173913, "percentage": 23.04, "elapsed_time": "0:01:09", "remaining_time": "0:03:52"}
107
+ {"current_steps": 107, "total_steps": 460, "loss": 1.3073, "lr": 8.723330926440045e-06, "epoch": 0.4652173913043478, "percentage": 23.26, "elapsed_time": "0:01:10", "remaining_time": "0:03:51"}
108
+ {"current_steps": 108, "total_steps": 460, "loss": 1.0389, "lr": 8.70045279830626e-06, "epoch": 0.46956521739130436, "percentage": 23.48, "elapsed_time": "0:01:10", "remaining_time": "0:03:50"}
109
+ {"current_steps": 109, "total_steps": 460, "loss": 1.0662, "lr": 8.677402071574806e-06, "epoch": 0.47391304347826085, "percentage": 23.7, "elapsed_time": "0:01:11", "remaining_time": "0:03:49"}
110
+ {"current_steps": 110, "total_steps": 460, "loss": 0.8443, "lr": 8.65417982139062e-06, "epoch": 0.4782608695652174, "percentage": 23.91, "elapsed_time": "0:01:12", "remaining_time": "0:03:49"}
111
+ {"current_steps": 111, "total_steps": 460, "loss": 0.9891, "lr": 8.630787130898943e-06, "epoch": 0.4826086956521739, "percentage": 24.13, "elapsed_time": "0:01:12", "remaining_time": "0:03:48"}
112
+ {"current_steps": 112, "total_steps": 460, "loss": 1.0268, "lr": 8.60722509119478e-06, "epoch": 0.48695652173913045, "percentage": 24.35, "elapsed_time": "0:01:13", "remaining_time": "0:03:47"}
113
+ {"current_steps": 113, "total_steps": 460, "loss": 1.0829, "lr": 8.583494801272018e-06, "epoch": 0.49130434782608695, "percentage": 24.57, "elapsed_time": "0:01:13", "remaining_time": "0:03:46"}
114
+ {"current_steps": 114, "total_steps": 460, "loss": 1.1713, "lr": 8.559597367972168e-06, "epoch": 0.4956521739130435, "percentage": 24.78, "elapsed_time": "0:01:14", "remaining_time": "0:03:45"}
115
+ {"current_steps": 115, "total_steps": 460, "loss": 1.2119, "lr": 8.535533905932739e-06, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:01:15", "remaining_time": "0:03:45"}
116
+ {"current_steps": 116, "total_steps": 460, "loss": 0.903, "lr": 8.511305537535238e-06, "epoch": 0.5043478260869565, "percentage": 25.22, "elapsed_time": "0:01:15", "remaining_time": "0:03:44"}
117
+ {"current_steps": 117, "total_steps": 460, "loss": 0.7318, "lr": 8.48691339285283e-06, "epoch": 0.508695652173913, "percentage": 25.43, "elapsed_time": "0:01:16", "remaining_time": "0:03:43"}
118
+ {"current_steps": 118, "total_steps": 460, "loss": 0.8296, "lr": 8.462358609597629e-06, "epoch": 0.5130434782608696, "percentage": 25.65, "elapsed_time": "0:01:16", "remaining_time": "0:03:42"}
119
+ {"current_steps": 119, "total_steps": 460, "loss": 0.889, "lr": 8.437642333067626e-06, "epoch": 0.5173913043478261, "percentage": 25.87, "elapsed_time": "0:01:17", "remaining_time": "0:03:42"}
120
+ {"current_steps": 120, "total_steps": 460, "loss": 1.2065, "lr": 8.412765716093273e-06, "epoch": 0.5217391304347826, "percentage": 26.09, "elapsed_time": "0:01:18", "remaining_time": "0:03:41"}
121
+ {"current_steps": 121, "total_steps": 460, "loss": 1.1523, "lr": 8.387729918983706e-06, "epoch": 0.5260869565217391, "percentage": 26.3, "elapsed_time": "0:01:18", "remaining_time": "0:03:40"}
122
+ {"current_steps": 122, "total_steps": 460, "loss": 0.8868, "lr": 8.362536109472637e-06, "epoch": 0.5304347826086957, "percentage": 26.52, "elapsed_time": "0:01:19", "remaining_time": "0:03:39"}
123
+ {"current_steps": 123, "total_steps": 460, "loss": 1.0169, "lr": 8.33718546266388e-06, "epoch": 0.5347826086956522, "percentage": 26.74, "elapsed_time": "0:01:19", "remaining_time": "0:03:38"}
124
+ {"current_steps": 124, "total_steps": 460, "loss": 1.2231, "lr": 8.31167916097654e-06, "epoch": 0.5391304347826087, "percentage": 26.96, "elapsed_time": "0:01:20", "remaining_time": "0:03:38"}
125
+ {"current_steps": 125, "total_steps": 460, "loss": 0.7684, "lr": 8.286018394089864e-06, "epoch": 0.5434782608695652, "percentage": 27.17, "elapsed_time": "0:01:21", "remaining_time": "0:03:37"}
126
+ {"current_steps": 126, "total_steps": 460, "loss": 1.0544, "lr": 8.260204358887753e-06, "epoch": 0.5478260869565217, "percentage": 27.39, "elapsed_time": "0:01:21", "remaining_time": "0:03:36"}
127
+ {"current_steps": 127, "total_steps": 460, "loss": 0.8784, "lr": 8.234238259402936e-06, "epoch": 0.5521739130434783, "percentage": 27.61, "elapsed_time": "0:01:22", "remaining_time": "0:03:35"}
128
+ {"current_steps": 128, "total_steps": 460, "loss": 1.2738, "lr": 8.208121306760806e-06, "epoch": 0.5565217391304348, "percentage": 27.83, "elapsed_time": "0:01:22", "remaining_time": "0:03:35"}
129
+ {"current_steps": 129, "total_steps": 460, "loss": 1.1752, "lr": 8.181854719122938e-06, "epoch": 0.5608695652173913, "percentage": 28.04, "elapsed_time": "0:01:23", "remaining_time": "0:03:34"}
130
+ {"current_steps": 130, "total_steps": 460, "loss": 1.0924, "lr": 8.155439721630265e-06, "epoch": 0.5652173913043478, "percentage": 28.26, "elapsed_time": "0:01:24", "remaining_time": "0:03:33"}
131
+ {"current_steps": 131, "total_steps": 460, "loss": 1.1432, "lr": 8.128877546345932e-06, "epoch": 0.5695652173913044, "percentage": 28.48, "elapsed_time": "0:01:24", "remaining_time": "0:03:32"}
132
+ {"current_steps": 132, "total_steps": 460, "loss": 0.872, "lr": 8.102169432197842e-06, "epoch": 0.5739130434782609, "percentage": 28.7, "elapsed_time": "0:01:25", "remaining_time": "0:03:32"}
133
+ {"current_steps": 133, "total_steps": 460, "loss": 1.1222, "lr": 8.075316624920848e-06, "epoch": 0.5782608695652174, "percentage": 28.91, "elapsed_time": "0:01:25", "remaining_time": "0:03:31"}
134
+ {"current_steps": 134, "total_steps": 460, "loss": 0.9484, "lr": 8.048320376998675e-06, "epoch": 0.5826086956521739, "percentage": 29.13, "elapsed_time": "0:01:26", "remaining_time": "0:03:30"}
135
+ {"current_steps": 135, "total_steps": 460, "loss": 1.0617, "lr": 8.021181947605474e-06, "epoch": 0.5869565217391305, "percentage": 29.35, "elapsed_time": "0:01:27", "remaining_time": "0:03:29"}
136
+ {"current_steps": 136, "total_steps": 460, "loss": 1.1889, "lr": 7.993902602547113e-06, "epoch": 0.591304347826087, "percentage": 29.57, "elapsed_time": "0:01:27", "remaining_time": "0:03:29"}
137
+ {"current_steps": 137, "total_steps": 460, "loss": 1.1285, "lr": 7.966483614202127e-06, "epoch": 0.5956521739130435, "percentage": 29.78, "elapsed_time": "0:01:28", "remaining_time": "0:03:28"}
138
+ {"current_steps": 138, "total_steps": 460, "loss": 1.1612, "lr": 7.938926261462366e-06, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "0:01:29", "remaining_time": "0:03:27"}
139
+ {"current_steps": 139, "total_steps": 460, "loss": 0.8389, "lr": 7.911231829673356e-06, "epoch": 0.6043478260869565, "percentage": 30.22, "elapsed_time": "0:01:29", "remaining_time": "0:03:27"}
140
+ {"current_steps": 140, "total_steps": 460, "loss": 0.8591, "lr": 7.883401610574338e-06, "epoch": 0.6086956521739131, "percentage": 30.43, "elapsed_time": "0:01:30", "remaining_time": "0:03:26"}
141
+ {"current_steps": 141, "total_steps": 460, "loss": 0.9255, "lr": 7.855436902238018e-06, "epoch": 0.6130434782608696, "percentage": 30.65, "elapsed_time": "0:01:30", "remaining_time": "0:03:25"}
142
+ {"current_steps": 142, "total_steps": 460, "loss": 0.7571, "lr": 7.82733900901003e-06, "epoch": 0.6173913043478261, "percentage": 30.87, "elapsed_time": "0:01:31", "remaining_time": "0:03:24"}
143
+ {"current_steps": 143, "total_steps": 460, "loss": 0.9604, "lr": 7.799109241448091e-06, "epoch": 0.6217391304347826, "percentage": 31.09, "elapsed_time": "0:01:32", "remaining_time": "0:03:24"}
144
+ {"current_steps": 144, "total_steps": 460, "loss": 1.1188, "lr": 7.770748916260875e-06, "epoch": 0.6260869565217392, "percentage": 31.3, "elapsed_time": "0:01:32", "remaining_time": "0:03:23"}
145
+ {"current_steps": 145, "total_steps": 460, "loss": 1.0338, "lr": 7.742259356246594e-06, "epoch": 0.6304347826086957, "percentage": 31.52, "elapsed_time": "0:01:33", "remaining_time": "0:03:22"}
146
+ {"current_steps": 146, "total_steps": 460, "loss": 1.2981, "lr": 7.71364189023131e-06, "epoch": 0.6347826086956522, "percentage": 31.74, "elapsed_time": "0:01:33", "remaining_time": "0:03:21"}
147
+ {"current_steps": 147, "total_steps": 460, "loss": 1.0437, "lr": 7.68489785300694e-06, "epoch": 0.6391304347826087, "percentage": 31.96, "elapsed_time": "0:01:34", "remaining_time": "0:03:21"}
148
+ {"current_steps": 148, "total_steps": 460, "loss": 0.8826, "lr": 7.656028585269017e-06, "epoch": 0.6434782608695652, "percentage": 32.17, "elapsed_time": "0:01:35", "remaining_time": "0:03:20"}
149
+ {"current_steps": 149, "total_steps": 460, "loss": 1.3544, "lr": 7.627035433554138e-06, "epoch": 0.6478260869565218, "percentage": 32.39, "elapsed_time": "0:01:35", "remaining_time": "0:03:19"}
150
+ {"current_steps": 150, "total_steps": 460, "loss": 0.957, "lr": 7.597919750177168e-06, "epoch": 0.6521739130434783, "percentage": 32.61, "elapsed_time": "0:01:36", "remaining_time": "0:03:19"}
151
+ {"current_steps": 151, "total_steps": 460, "loss": 1.1804, "lr": 7.5686828931681646e-06, "epoch": 0.6565217391304348, "percentage": 32.83, "elapsed_time": "0:01:36", "remaining_time": "0:03:18"}
152
+ {"current_steps": 152, "total_steps": 460, "loss": 1.0273, "lr": 7.539326226209032e-06, "epoch": 0.6608695652173913, "percentage": 33.04, "elapsed_time": "0:01:37", "remaining_time": "0:03:17"}
153
+ {"current_steps": 153, "total_steps": 460, "loss": 1.1271, "lr": 7.509851118569915e-06, "epoch": 0.6652173913043479, "percentage": 33.26, "elapsed_time": "0:01:38", "remaining_time": "0:03:16"}
154
+ {"current_steps": 154, "total_steps": 460, "loss": 1.059, "lr": 7.4802589450453415e-06, "epoch": 0.6695652173913044, "percentage": 33.48, "elapsed_time": "0:01:38", "remaining_time": "0:03:16"}
155
+ {"current_steps": 155, "total_steps": 460, "loss": 1.2174, "lr": 7.450551085890087e-06, "epoch": 0.6739130434782609, "percentage": 33.7, "elapsed_time": "0:01:39", "remaining_time": "0:03:15"}
156
+ {"current_steps": 156, "total_steps": 460, "loss": 0.9316, "lr": 7.420728926754803e-06, "epoch": 0.6782608695652174, "percentage": 33.91, "elapsed_time": "0:01:39", "remaining_time": "0:03:14"}
157
+ {"current_steps": 157, "total_steps": 460, "loss": 1.0431, "lr": 7.390793858621386e-06, "epoch": 0.6826086956521739, "percentage": 34.13, "elapsed_time": "0:01:40", "remaining_time": "0:03:13"}
158
+ {"current_steps": 158, "total_steps": 460, "loss": 1.1624, "lr": 7.360747277738094e-06, "epoch": 0.6869565217391305, "percentage": 34.35, "elapsed_time": "0:01:41", "remaining_time": "0:03:13"}
159
+ {"current_steps": 159, "total_steps": 460, "loss": 0.9388, "lr": 7.330590585554428e-06, "epoch": 0.691304347826087, "percentage": 34.57, "elapsed_time": "0:01:41", "remaining_time": "0:03:12"}
160
+ {"current_steps": 160, "total_steps": 460, "loss": 1.0772, "lr": 7.300325188655762e-06, "epoch": 0.6956521739130435, "percentage": 34.78, "elapsed_time": "0:01:42", "remaining_time": "0:03:11"}
161
+ {"current_steps": 161, "total_steps": 460, "loss": 1.0588, "lr": 7.269952498697734e-06, "epoch": 0.7, "percentage": 35.0, "elapsed_time": "0:01:42", "remaining_time": "0:03:11"}
162
+ {"current_steps": 162, "total_steps": 460, "loss": 1.2744, "lr": 7.2394739323404105e-06, "epoch": 0.7043478260869566, "percentage": 35.22, "elapsed_time": "0:01:43", "remaining_time": "0:03:10"}
163
+ {"current_steps": 163, "total_steps": 460, "loss": 1.2523, "lr": 7.208890911182198e-06, "epoch": 0.7086956521739131, "percentage": 35.43, "elapsed_time": "0:01:44", "remaining_time": "0:03:09"}
164
+ {"current_steps": 164, "total_steps": 460, "loss": 1.0201, "lr": 7.178204861693546e-06, "epoch": 0.7130434782608696, "percentage": 35.65, "elapsed_time": "0:01:44", "remaining_time": "0:03:09"}
165
+ {"current_steps": 165, "total_steps": 460, "loss": 0.8982, "lr": 7.147417215150411e-06, "epoch": 0.717391304347826, "percentage": 35.87, "elapsed_time": "0:01:45", "remaining_time": "0:03:08"}
166
+ {"current_steps": 166, "total_steps": 460, "loss": 1.006, "lr": 7.116529407567489e-06, "epoch": 0.7217391304347827, "percentage": 36.09, "elapsed_time": "0:01:45", "remaining_time": "0:03:07"}
167
+ {"current_steps": 167, "total_steps": 460, "loss": 0.8732, "lr": 7.085542879631253e-06, "epoch": 0.7260869565217392, "percentage": 36.3, "elapsed_time": "0:01:46", "remaining_time": "0:03:07"}
168
+ {"current_steps": 168, "total_steps": 460, "loss": 0.9237, "lr": 7.054459076632742e-06, "epoch": 0.7304347826086957, "percentage": 36.52, "elapsed_time": "0:01:47", "remaining_time": "0:03:06"}
169
+ {"current_steps": 169, "total_steps": 460, "loss": 1.1508, "lr": 7.0232794484001495e-06, "epoch": 0.7347826086956522, "percentage": 36.74, "elapsed_time": "0:01:47", "remaining_time": "0:03:05"}
170
+ {"current_steps": 170, "total_steps": 460, "loss": 1.2019, "lr": 6.9920054492312086e-06, "epoch": 0.7391304347826086, "percentage": 36.96, "elapsed_time": "0:01:48", "remaining_time": "0:03:04"}
171
+ {"current_steps": 171, "total_steps": 460, "loss": 0.8571, "lr": 6.960638537825352e-06, "epoch": 0.7434782608695653, "percentage": 37.17, "elapsed_time": "0:01:49", "remaining_time": "0:03:04"}
172
+ {"current_steps": 172, "total_steps": 460, "loss": 1.2769, "lr": 6.9291801772156775e-06, "epoch": 0.7478260869565218, "percentage": 37.39, "elapsed_time": "0:01:49", "remaining_time": "0:03:03"}
173
+ {"current_steps": 173, "total_steps": 460, "loss": 1.2594, "lr": 6.89763183470071e-06, "epoch": 0.7521739130434782, "percentage": 37.61, "elapsed_time": "0:01:50", "remaining_time": "0:03:02"}
174
+ {"current_steps": 174, "total_steps": 460, "loss": 1.2394, "lr": 6.865994981775958e-06, "epoch": 0.7565217391304347, "percentage": 37.83, "elapsed_time": "0:01:50", "remaining_time": "0:03:02"}
175
+ {"current_steps": 175, "total_steps": 460, "loss": 1.0616, "lr": 6.834271094065284e-06, "epoch": 0.7608695652173914, "percentage": 38.04, "elapsed_time": "0:01:51", "remaining_time": "0:03:01"}
176
+ {"current_steps": 176, "total_steps": 460, "loss": 1.0179, "lr": 6.802461651252073e-06, "epoch": 0.7652173913043478, "percentage": 38.26, "elapsed_time": "0:01:52", "remaining_time": "0:03:00"}
177
+ {"current_steps": 177, "total_steps": 460, "loss": 1.1243, "lr": 6.770568137010226e-06, "epoch": 0.7695652173913043, "percentage": 38.48, "elapsed_time": "0:01:52", "remaining_time": "0:03:00"}
178
+ {"current_steps": 178, "total_steps": 460, "loss": 1.0372, "lr": 6.738592038934946e-06, "epoch": 0.7739130434782608, "percentage": 38.7, "elapsed_time": "0:01:53", "remaining_time": "0:02:59"}
179
+ {"current_steps": 179, "total_steps": 460, "loss": 1.1002, "lr": 6.706534848473353e-06, "epoch": 0.7782608695652173, "percentage": 38.91, "elapsed_time": "0:01:53", "remaining_time": "0:02:58"}
180
+ {"current_steps": 180, "total_steps": 460, "loss": 0.8485, "lr": 6.674398060854931e-06, "epoch": 0.782608695652174, "percentage": 39.13, "elapsed_time": "0:01:54", "remaining_time": "0:02:58"}
181
+ {"current_steps": 181, "total_steps": 460, "loss": 1.0909, "lr": 6.642183175021779e-06, "epoch": 0.7869565217391304, "percentage": 39.35, "elapsed_time": "0:01:55", "remaining_time": "0:02:57"}
182
+ {"current_steps": 182, "total_steps": 460, "loss": 1.126, "lr": 6.609891693558692e-06, "epoch": 0.7913043478260869, "percentage": 39.57, "elapsed_time": "0:01:55", "remaining_time": "0:02:56"}
183
+ {"current_steps": 183, "total_steps": 460, "loss": 1.0741, "lr": 6.5775251226230855e-06, "epoch": 0.7956521739130434, "percentage": 39.78, "elapsed_time": "0:01:56", "remaining_time": "0:02:56"}
184
+ {"current_steps": 184, "total_steps": 460, "loss": 1.3962, "lr": 6.545084971874738e-06, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "0:01:56", "remaining_time": "0:02:55"}
185
+ {"current_steps": 185, "total_steps": 460, "loss": 1.3245, "lr": 6.51257275440538e-06, "epoch": 0.8043478260869565, "percentage": 40.22, "elapsed_time": "0:01:57", "remaining_time": "0:02:54"}
186
+ {"current_steps": 186, "total_steps": 460, "loss": 1.0462, "lr": 6.479989986668118e-06, "epoch": 0.808695652173913, "percentage": 40.43, "elapsed_time": "0:01:58", "remaining_time": "0:02:54"}
187
+ {"current_steps": 187, "total_steps": 460, "loss": 1.2675, "lr": 6.447338188406705e-06, "epoch": 0.8130434782608695, "percentage": 40.65, "elapsed_time": "0:01:58", "remaining_time": "0:02:53"}
188
+ {"current_steps": 188, "total_steps": 460, "loss": 1.1843, "lr": 6.41461888258465e-06, "epoch": 0.8173913043478261, "percentage": 40.87, "elapsed_time": "0:01:59", "remaining_time": "0:02:52"}
189
+ {"current_steps": 189, "total_steps": 460, "loss": 1.1212, "lr": 6.3818335953141955e-06, "epoch": 0.8217391304347826, "percentage": 41.09, "elapsed_time": "0:01:59", "remaining_time": "0:02:51"}
190
+ {"current_steps": 190, "total_steps": 460, "loss": 1.4108, "lr": 6.348983855785122e-06, "epoch": 0.8260869565217391, "percentage": 41.3, "elapsed_time": "0:02:00", "remaining_time": "0:02:51"}
191
+ {"current_steps": 191, "total_steps": 460, "loss": 0.9868, "lr": 6.31607119619343e-06, "epoch": 0.8304347826086956, "percentage": 41.52, "elapsed_time": "0:02:01", "remaining_time": "0:02:50"}
192
+ {"current_steps": 192, "total_steps": 460, "loss": 1.0539, "lr": 6.283097151669869e-06, "epoch": 0.8347826086956521, "percentage": 41.74, "elapsed_time": "0:02:01", "remaining_time": "0:02:49"}
193
+ {"current_steps": 193, "total_steps": 460, "loss": 0.9145, "lr": 6.250063260208345e-06, "epoch": 0.8391304347826087, "percentage": 41.96, "elapsed_time": "0:02:02", "remaining_time": "0:02:49"}
194
+ {"current_steps": 194, "total_steps": 460, "loss": 0.8883, "lr": 6.216971062594179e-06, "epoch": 0.8434782608695652, "percentage": 42.17, "elapsed_time": "0:02:02", "remaining_time": "0:02:48"}
195
+ {"current_steps": 195, "total_steps": 460, "loss": 0.8907, "lr": 6.183822102332234e-06, "epoch": 0.8478260869565217, "percentage": 42.39, "elapsed_time": "0:02:03", "remaining_time": "0:02:47"}
196
+ {"current_steps": 196, "total_steps": 460, "loss": 1.329, "lr": 6.1506179255749335e-06, "epoch": 0.8521739130434782, "percentage": 42.61, "elapsed_time": "0:02:04", "remaining_time": "0:02:47"}
197
+ {"current_steps": 197, "total_steps": 460, "loss": 1.0296, "lr": 6.1173600810501355e-06, "epoch": 0.8565217391304348, "percentage": 42.83, "elapsed_time": "0:02:04", "remaining_time": "0:02:46"}
198
+ {"current_steps": 198, "total_steps": 460, "loss": 1.3987, "lr": 6.084050119988905e-06, "epoch": 0.8608695652173913, "percentage": 43.04, "elapsed_time": "0:02:05", "remaining_time": "0:02:45"}
199
+ {"current_steps": 199, "total_steps": 460, "loss": 1.1243, "lr": 6.050689596053151e-06, "epoch": 0.8652173913043478, "percentage": 43.26, "elapsed_time": "0:02:06", "remaining_time": "0:02:45"}
200
+ {"current_steps": 200, "total_steps": 460, "loss": 1.1461, "lr": 6.0172800652631706e-06, "epoch": 0.8695652173913043, "percentage": 43.48, "elapsed_time": "0:02:06", "remaining_time": "0:02:44"}
201
+ {"current_steps": 200, "total_steps": 460, "eval_loss": 1.1071234941482544, "epoch": 0.8695652173913043, "percentage": 43.48, "elapsed_time": "0:02:07", "remaining_time": "0:02:45"}
202
+ {"current_steps": 201, "total_steps": 460, "loss": 1.1235, "lr": 5.983823085925059e-06, "epoch": 0.8739130434782608, "percentage": 43.7, "elapsed_time": "0:02:07", "remaining_time": "0:02:44"}
203
+ {"current_steps": 202, "total_steps": 460, "loss": 0.9737, "lr": 5.950320218558037e-06, "epoch": 0.8782608695652174, "percentage": 43.91, "elapsed_time": "0:02:08", "remaining_time": "0:02:44"}
204
+ {"current_steps": 203, "total_steps": 460, "loss": 1.1481, "lr": 5.916773025821662e-06, "epoch": 0.8826086956521739, "percentage": 44.13, "elapsed_time": "0:02:09", "remaining_time": "0:02:43"}
205
+ {"current_steps": 204, "total_steps": 460, "loss": 1.2084, "lr": 5.883183072442938e-06, "epoch": 0.8869565217391304, "percentage": 44.35, "elapsed_time": "0:02:09", "remaining_time": "0:02:42"}
206
+ {"current_steps": 205, "total_steps": 460, "loss": 1.0912, "lr": 5.849551925143334e-06, "epoch": 0.8913043478260869, "percentage": 44.57, "elapsed_time": "0:02:10", "remaining_time": "0:02:42"}
207
+ {"current_steps": 206, "total_steps": 460, "loss": 1.2877, "lr": 5.815881152565712e-06, "epoch": 0.8956521739130435, "percentage": 44.78, "elapsed_time": "0:02:10", "remaining_time": "0:02:41"}
208
+ {"current_steps": 207, "total_steps": 460, "loss": 1.1675, "lr": 5.782172325201155e-06, "epoch": 0.9, "percentage": 45.0, "elapsed_time": "0:02:11", "remaining_time": "0:02:40"}
209
+ {"current_steps": 208, "total_steps": 460, "loss": 0.9163, "lr": 5.7484270153157215e-06, "epoch": 0.9043478260869565, "percentage": 45.22, "elapsed_time": "0:02:12", "remaining_time": "0:02:40"}
210
+ {"current_steps": 209, "total_steps": 460, "loss": 0.9048, "lr": 5.714646796877108e-06, "epoch": 0.908695652173913, "percentage": 45.43, "elapsed_time": "0:02:12", "remaining_time": "0:02:39"}
211
+ {"current_steps": 210, "total_steps": 460, "loss": 1.2898, "lr": 5.680833245481234e-06, "epoch": 0.9130434782608695, "percentage": 45.65, "elapsed_time": "0:02:13", "remaining_time": "0:02:38"}
212
+ {"current_steps": 211, "total_steps": 460, "loss": 1.2326, "lr": 5.646987938278753e-06, "epoch": 0.9173913043478261, "percentage": 45.87, "elapsed_time": "0:02:13", "remaining_time": "0:02:38"}
213
+ {"current_steps": 212, "total_steps": 460, "loss": 1.2061, "lr": 5.613112453901493e-06, "epoch": 0.9217391304347826, "percentage": 46.09, "elapsed_time": "0:02:14", "remaining_time": "0:02:37"}
214
+ {"current_steps": 213, "total_steps": 460, "loss": 1.1821, "lr": 5.579208372388822e-06, "epoch": 0.9260869565217391, "percentage": 46.3, "elapsed_time": "0:02:15", "remaining_time": "0:02:36"}
215
+ {"current_steps": 214, "total_steps": 460, "loss": 1.005, "lr": 5.5452772751139496e-06, "epoch": 0.9304347826086956, "percentage": 46.52, "elapsed_time": "0:02:15", "remaining_time": "0:02:36"}
216
+ {"current_steps": 215, "total_steps": 460, "loss": 1.1842, "lr": 5.511320744710171e-06, "epoch": 0.9347826086956522, "percentage": 46.74, "elapsed_time": "0:02:16", "remaining_time": "0:02:35"}
217
+ {"current_steps": 216, "total_steps": 460, "loss": 1.3129, "lr": 5.477340364997051e-06, "epoch": 0.9391304347826087, "percentage": 46.96, "elapsed_time": "0:02:17", "remaining_time": "0:02:34"}
218
+ {"current_steps": 217, "total_steps": 460, "loss": 0.8211, "lr": 5.443337720906542e-06, "epoch": 0.9434782608695652, "percentage": 47.17, "elapsed_time": "0:02:17", "remaining_time": "0:02:34"}
219
+ {"current_steps": 218, "total_steps": 460, "loss": 1.0426, "lr": 5.409314398409067e-06, "epoch": 0.9478260869565217, "percentage": 47.39, "elapsed_time": "0:02:18", "remaining_time": "0:02:33"}
220
+ {"current_steps": 219, "total_steps": 460, "loss": 0.8146, "lr": 5.375271984439541e-06, "epoch": 0.9521739130434783, "percentage": 47.61, "elapsed_time": "0:02:18", "remaining_time": "0:02:32"}
221
+ {"current_steps": 220, "total_steps": 460, "loss": 1.1587, "lr": 5.341212066823356e-06, "epoch": 0.9565217391304348, "percentage": 47.83, "elapsed_time": "0:02:19", "remaining_time": "0:02:32"}
222
+ {"current_steps": 221, "total_steps": 460, "loss": 0.8552, "lr": 5.307136234202318e-06, "epoch": 0.9608695652173913, "percentage": 48.04, "elapsed_time": "0:02:20", "remaining_time": "0:02:31"}
223
+ {"current_steps": 222, "total_steps": 460, "loss": 0.8439, "lr": 5.27304607596055e-06, "epoch": 0.9652173913043478, "percentage": 48.26, "elapsed_time": "0:02:20", "remaining_time": "0:02:30"}
224
+ {"current_steps": 223, "total_steps": 460, "loss": 1.0496, "lr": 5.238943182150361e-06, "epoch": 0.9695652173913043, "percentage": 48.48, "elapsed_time": "0:02:21", "remaining_time": "0:02:30"}
225
+ {"current_steps": 224, "total_steps": 460, "loss": 1.1575, "lr": 5.204829143418072e-06, "epoch": 0.9739130434782609, "percentage": 48.7, "elapsed_time": "0:02:21", "remaining_time": "0:02:29"}
226
+ {"current_steps": 225, "total_steps": 460, "loss": 0.8573, "lr": 5.17070555092984e-06, "epoch": 0.9782608695652174, "percentage": 48.91, "elapsed_time": "0:02:22", "remaining_time": "0:02:28"}
227
+ {"current_steps": 226, "total_steps": 460, "loss": 1.2469, "lr": 5.136573996297431e-06, "epoch": 0.9826086956521739, "percentage": 49.13, "elapsed_time": "0:02:23", "remaining_time": "0:02:28"}
228
+ {"current_steps": 227, "total_steps": 460, "loss": 0.9794, "lr": 5.102436071503983e-06, "epoch": 0.9869565217391304, "percentage": 49.35, "elapsed_time": "0:02:23", "remaining_time": "0:02:27"}
229
+ {"current_steps": 228, "total_steps": 460, "loss": 0.8575, "lr": 5.068293368829755e-06, "epoch": 0.991304347826087, "percentage": 49.57, "elapsed_time": "0:02:24", "remaining_time": "0:02:26"}
230
+ {"current_steps": 229, "total_steps": 460, "loss": 1.0591, "lr": 5.034147480777867e-06, "epoch": 0.9956521739130435, "percentage": 49.78, "elapsed_time": "0:02:24", "remaining_time": "0:02:26"}
231
+ {"current_steps": 230, "total_steps": 460, "loss": 1.242, "lr": 5e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:02:25", "remaining_time": "0:02:25"}
232
+ {"current_steps": 231, "total_steps": 460, "loss": 0.8372, "lr": 4.965852519222135e-06, "epoch": 1.0043478260869565, "percentage": 50.22, "elapsed_time": "0:02:26", "remaining_time": "0:02:24"}
233
+ {"current_steps": 232, "total_steps": 460, "loss": 0.8391, "lr": 4.931706631170246e-06, "epoch": 1.008695652173913, "percentage": 50.43, "elapsed_time": "0:02:26", "remaining_time": "0:02:24"}
234
+ {"current_steps": 233, "total_steps": 460, "loss": 0.7721, "lr": 4.89756392849602e-06, "epoch": 1.0130434782608695, "percentage": 50.65, "elapsed_time": "0:02:27", "remaining_time": "0:02:23"}
235
+ {"current_steps": 234, "total_steps": 460, "loss": 0.7296, "lr": 4.863426003702572e-06, "epoch": 1.017391304347826, "percentage": 50.87, "elapsed_time": "0:02:27", "remaining_time": "0:02:22"}
236
+ {"current_steps": 235, "total_steps": 460, "loss": 1.0094, "lr": 4.829294449070161e-06, "epoch": 1.0217391304347827, "percentage": 51.09, "elapsed_time": "0:02:28", "remaining_time": "0:02:22"}
237
+ {"current_steps": 236, "total_steps": 460, "loss": 0.7659, "lr": 4.795170856581929e-06, "epoch": 1.0260869565217392, "percentage": 51.3, "elapsed_time": "0:02:29", "remaining_time": "0:02:21"}
238
+ {"current_steps": 237, "total_steps": 460, "loss": 0.9442, "lr": 4.7610568178496405e-06, "epoch": 1.0304347826086957, "percentage": 51.52, "elapsed_time": "0:02:29", "remaining_time": "0:02:20"}
239
+ {"current_steps": 238, "total_steps": 460, "loss": 0.8058, "lr": 4.7269539240394505e-06, "epoch": 1.0347826086956522, "percentage": 51.74, "elapsed_time": "0:02:30", "remaining_time": "0:02:20"}
240
+ {"current_steps": 239, "total_steps": 460, "loss": 0.5696, "lr": 4.692863765797683e-06, "epoch": 1.0391304347826087, "percentage": 51.96, "elapsed_time": "0:02:31", "remaining_time": "0:02:19"}
241
+ {"current_steps": 240, "total_steps": 460, "loss": 0.7507, "lr": 4.6587879331766465e-06, "epoch": 1.0434782608695652, "percentage": 52.17, "elapsed_time": "0:02:31", "remaining_time": "0:02:18"}
242
+ {"current_steps": 241, "total_steps": 460, "loss": 0.9429, "lr": 4.624728015560461e-06, "epoch": 1.0478260869565217, "percentage": 52.39, "elapsed_time": "0:02:32", "remaining_time": "0:02:18"}
243
+ {"current_steps": 242, "total_steps": 460, "loss": 0.7721, "lr": 4.5906856015909365e-06, "epoch": 1.0521739130434782, "percentage": 52.61, "elapsed_time": "0:02:32", "remaining_time": "0:02:17"}
244
+ {"current_steps": 243, "total_steps": 460, "loss": 0.8443, "lr": 4.556662279093461e-06, "epoch": 1.0565217391304347, "percentage": 52.83, "elapsed_time": "0:02:33", "remaining_time": "0:02:17"}
245
+ {"current_steps": 244, "total_steps": 460, "loss": 0.902, "lr": 4.52265963500295e-06, "epoch": 1.0608695652173914, "percentage": 53.04, "elapsed_time": "0:02:34", "remaining_time": "0:02:16"}
246
+ {"current_steps": 245, "total_steps": 460, "loss": 0.9596, "lr": 4.488679255289829e-06, "epoch": 1.065217391304348, "percentage": 53.26, "elapsed_time": "0:02:34", "remaining_time": "0:02:15"}
247
+ {"current_steps": 246, "total_steps": 460, "loss": 0.6492, "lr": 4.454722724886051e-06, "epoch": 1.0695652173913044, "percentage": 53.48, "elapsed_time": "0:02:35", "remaining_time": "0:02:15"}
248
+ {"current_steps": 247, "total_steps": 460, "loss": 0.8424, "lr": 4.4207916276111795e-06, "epoch": 1.0739130434782609, "percentage": 53.7, "elapsed_time": "0:02:35", "remaining_time": "0:02:14"}
249
+ {"current_steps": 248, "total_steps": 460, "loss": 0.9892, "lr": 4.386887546098509e-06, "epoch": 1.0782608695652174, "percentage": 53.91, "elapsed_time": "0:02:36", "remaining_time": "0:02:13"}
250
+ {"current_steps": 249, "total_steps": 460, "loss": 0.9134, "lr": 4.353012061721249e-06, "epoch": 1.0826086956521739, "percentage": 54.13, "elapsed_time": "0:02:37", "remaining_time": "0:02:13"}
251
+ {"current_steps": 250, "total_steps": 460, "loss": 0.8252, "lr": 4.319166754518768e-06, "epoch": 1.0869565217391304, "percentage": 54.35, "elapsed_time": "0:02:37", "remaining_time": "0:02:12"}
252
+ {"current_steps": 251, "total_steps": 460, "loss": 0.7877, "lr": 4.285353203122894e-06, "epoch": 1.0913043478260869, "percentage": 54.57, "elapsed_time": "0:02:38", "remaining_time": "0:02:11"}
253
+ {"current_steps": 252, "total_steps": 460, "loss": 1.0032, "lr": 4.251572984684281e-06, "epoch": 1.0956521739130434, "percentage": 54.78, "elapsed_time": "0:02:38", "remaining_time": "0:02:11"}
254
+ {"current_steps": 253, "total_steps": 460, "loss": 1.0623, "lr": 4.217827674798845e-06, "epoch": 1.1, "percentage": 55.0, "elapsed_time": "0:02:39", "remaining_time": "0:02:10"}
255
+ {"current_steps": 254, "total_steps": 460, "loss": 0.9584, "lr": 4.18411884743429e-06, "epoch": 1.1043478260869566, "percentage": 55.22, "elapsed_time": "0:02:40", "remaining_time": "0:02:09"}
256
+ {"current_steps": 255, "total_steps": 460, "loss": 0.7825, "lr": 4.150448074856667e-06, "epoch": 1.108695652173913, "percentage": 55.43, "elapsed_time": "0:02:40", "remaining_time": "0:02:09"}
257
+ {"current_steps": 256, "total_steps": 460, "loss": 0.7528, "lr": 4.116816927557063e-06, "epoch": 1.1130434782608696, "percentage": 55.65, "elapsed_time": "0:02:41", "remaining_time": "0:02:08"}
258
+ {"current_steps": 257, "total_steps": 460, "loss": 0.7756, "lr": 4.083226974178339e-06, "epoch": 1.117391304347826, "percentage": 55.87, "elapsed_time": "0:02:41", "remaining_time": "0:02:07"}
259
+ {"current_steps": 258, "total_steps": 460, "loss": 1.0968, "lr": 4.0496797814419655e-06, "epoch": 1.1217391304347826, "percentage": 56.09, "elapsed_time": "0:02:42", "remaining_time": "0:02:07"}
260
+ {"current_steps": 259, "total_steps": 460, "loss": 1.0054, "lr": 4.016176914074944e-06, "epoch": 1.126086956521739, "percentage": 56.3, "elapsed_time": "0:02:43", "remaining_time": "0:02:06"}
261
+ {"current_steps": 260, "total_steps": 460, "loss": 0.9057, "lr": 3.982719934736832e-06, "epoch": 1.1304347826086956, "percentage": 56.52, "elapsed_time": "0:02:43", "remaining_time": "0:02:05"}
262
+ {"current_steps": 261, "total_steps": 460, "loss": 0.7052, "lr": 3.949310403946849e-06, "epoch": 1.134782608695652, "percentage": 56.74, "elapsed_time": "0:02:44", "remaining_time": "0:02:05"}
263
+ {"current_steps": 262, "total_steps": 460, "loss": 0.8225, "lr": 3.915949880011096e-06, "epoch": 1.1391304347826088, "percentage": 56.96, "elapsed_time": "0:02:45", "remaining_time": "0:02:04"}
264
+ {"current_steps": 263, "total_steps": 460, "loss": 0.9477, "lr": 3.882639918949865e-06, "epoch": 1.1434782608695653, "percentage": 57.17, "elapsed_time": "0:02:45", "remaining_time": "0:02:04"}
265
+ {"current_steps": 264, "total_steps": 460, "loss": 0.9194, "lr": 3.849382074425069e-06, "epoch": 1.1478260869565218, "percentage": 57.39, "elapsed_time": "0:02:46", "remaining_time": "0:02:03"}
266
+ {"current_steps": 265, "total_steps": 460, "loss": 0.9798, "lr": 3.816177897667767e-06, "epoch": 1.1521739130434783, "percentage": 57.61, "elapsed_time": "0:02:46", "remaining_time": "0:02:02"}
267
+ {"current_steps": 266, "total_steps": 460, "loss": 0.7764, "lr": 3.7830289374058214e-06, "epoch": 1.1565217391304348, "percentage": 57.83, "elapsed_time": "0:02:47", "remaining_time": "0:02:02"}
268
+ {"current_steps": 267, "total_steps": 460, "loss": 0.9234, "lr": 3.749936739791656e-06, "epoch": 1.1608695652173913, "percentage": 58.04, "elapsed_time": "0:02:48", "remaining_time": "0:02:01"}
269
+ {"current_steps": 268, "total_steps": 460, "loss": 0.7672, "lr": 3.7169028483301333e-06, "epoch": 1.1652173913043478, "percentage": 58.26, "elapsed_time": "0:02:48", "remaining_time": "0:02:00"}
270
+ {"current_steps": 269, "total_steps": 460, "loss": 0.8168, "lr": 3.6839288038065736e-06, "epoch": 1.1695652173913043, "percentage": 58.48, "elapsed_time": "0:02:49", "remaining_time": "0:02:00"}
271
+ {"current_steps": 270, "total_steps": 460, "loss": 0.9159, "lr": 3.6510161442148783e-06, "epoch": 1.1739130434782608, "percentage": 58.7, "elapsed_time": "0:02:49", "remaining_time": "0:01:59"}
272
+ {"current_steps": 271, "total_steps": 460, "loss": 0.8255, "lr": 3.6181664046858045e-06, "epoch": 1.1782608695652175, "percentage": 58.91, "elapsed_time": "0:02:50", "remaining_time": "0:01:58"}
273
+ {"current_steps": 272, "total_steps": 460, "loss": 0.7073, "lr": 3.58538111741535e-06, "epoch": 1.182608695652174, "percentage": 59.13, "elapsed_time": "0:02:51", "remaining_time": "0:01:58"}
274
+ {"current_steps": 273, "total_steps": 460, "loss": 0.9158, "lr": 3.5526618115932974e-06, "epoch": 1.1869565217391305, "percentage": 59.35, "elapsed_time": "0:02:51", "remaining_time": "0:01:57"}
275
+ {"current_steps": 274, "total_steps": 460, "loss": 0.9469, "lr": 3.5200100133318836e-06, "epoch": 1.191304347826087, "percentage": 59.57, "elapsed_time": "0:02:52", "remaining_time": "0:01:56"}
276
+ {"current_steps": 275, "total_steps": 460, "loss": 0.627, "lr": 3.4874272455946217e-06, "epoch": 1.1956521739130435, "percentage": 59.78, "elapsed_time": "0:02:52", "remaining_time": "0:01:56"}
277
+ {"current_steps": 276, "total_steps": 460, "loss": 0.7849, "lr": 3.4549150281252635e-06, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "0:02:53", "remaining_time": "0:01:55"}
278
+ {"current_steps": 277, "total_steps": 460, "loss": 0.9044, "lr": 3.4224748773769166e-06, "epoch": 1.2043478260869565, "percentage": 60.22, "elapsed_time": "0:02:54", "remaining_time": "0:01:55"}
279
+ {"current_steps": 278, "total_steps": 460, "loss": 0.8066, "lr": 3.39010830644131e-06, "epoch": 1.208695652173913, "percentage": 60.43, "elapsed_time": "0:02:54", "remaining_time": "0:01:54"}
280
+ {"current_steps": 279, "total_steps": 460, "loss": 0.7914, "lr": 3.357816824978222e-06, "epoch": 1.2130434782608694, "percentage": 60.65, "elapsed_time": "0:02:55", "remaining_time": "0:01:53"}
281
+ {"current_steps": 280, "total_steps": 460, "loss": 0.9335, "lr": 3.3256019391450696e-06, "epoch": 1.2173913043478262, "percentage": 60.87, "elapsed_time": "0:02:56", "remaining_time": "0:01:53"}
282
+ {"current_steps": 281, "total_steps": 460, "loss": 0.9117, "lr": 3.2934651515266485e-06, "epoch": 1.2217391304347827, "percentage": 61.09, "elapsed_time": "0:02:56", "remaining_time": "0:01:52"}
283
+ {"current_steps": 282, "total_steps": 460, "loss": 0.7945, "lr": 3.261407961065056e-06, "epoch": 1.2260869565217392, "percentage": 61.3, "elapsed_time": "0:02:57", "remaining_time": "0:01:51"}
284
+ {"current_steps": 283, "total_steps": 460, "loss": 0.6501, "lr": 3.2294318629897746e-06, "epoch": 1.2304347826086957, "percentage": 61.52, "elapsed_time": "0:02:57", "remaining_time": "0:01:51"}
285
+ {"current_steps": 284, "total_steps": 460, "loss": 0.6971, "lr": 3.197538348747927e-06, "epoch": 1.2347826086956522, "percentage": 61.74, "elapsed_time": "0:02:58", "remaining_time": "0:01:50"}
286
+ {"current_steps": 285, "total_steps": 460, "loss": 0.8393, "lr": 3.1657289059347184e-06, "epoch": 1.2391304347826086, "percentage": 61.96, "elapsed_time": "0:02:59", "remaining_time": "0:01:49"}
287
+ {"current_steps": 286, "total_steps": 460, "loss": 0.879, "lr": 3.1340050182240438e-06, "epoch": 1.2434782608695651, "percentage": 62.17, "elapsed_time": "0:02:59", "remaining_time": "0:01:49"}
288
+ {"current_steps": 287, "total_steps": 460, "loss": 0.9016, "lr": 3.1023681652992925e-06, "epoch": 1.2478260869565219, "percentage": 62.39, "elapsed_time": "0:03:00", "remaining_time": "0:01:48"}
289
+ {"current_steps": 288, "total_steps": 460, "loss": 0.8995, "lr": 3.070819822784323e-06, "epoch": 1.2521739130434781, "percentage": 62.61, "elapsed_time": "0:03:00", "remaining_time": "0:01:48"}
290
+ {"current_steps": 289, "total_steps": 460, "loss": 0.6588, "lr": 3.03936146217465e-06, "epoch": 1.2565217391304349, "percentage": 62.83, "elapsed_time": "0:03:01", "remaining_time": "0:01:47"}
291
+ {"current_steps": 290, "total_steps": 460, "loss": 1.1011, "lr": 3.007994550768793e-06, "epoch": 1.2608695652173914, "percentage": 63.04, "elapsed_time": "0:03:02", "remaining_time": "0:01:46"}
292
+ {"current_steps": 291, "total_steps": 460, "loss": 1.0702, "lr": 2.976720551599852e-06, "epoch": 1.2652173913043478, "percentage": 63.26, "elapsed_time": "0:03:02", "remaining_time": "0:01:46"}
293
+ {"current_steps": 292, "total_steps": 460, "loss": 0.8589, "lr": 2.9455409233672594e-06, "epoch": 1.2695652173913043, "percentage": 63.48, "elapsed_time": "0:03:03", "remaining_time": "0:01:45"}
294
+ {"current_steps": 293, "total_steps": 460, "loss": 0.8448, "lr": 2.914457120368748e-06, "epoch": 1.2739130434782608, "percentage": 63.7, "elapsed_time": "0:03:03", "remaining_time": "0:01:44"}
295
+ {"current_steps": 294, "total_steps": 460, "loss": 1.1018, "lr": 2.883470592432512e-06, "epoch": 1.2782608695652173, "percentage": 63.91, "elapsed_time": "0:03:04", "remaining_time": "0:01:44"}
296
+ {"current_steps": 295, "total_steps": 460, "loss": 0.725, "lr": 2.8525827848495912e-06, "epoch": 1.2826086956521738, "percentage": 64.13, "elapsed_time": "0:03:05", "remaining_time": "0:01:43"}
297
+ {"current_steps": 296, "total_steps": 460, "loss": 0.9542, "lr": 2.8217951383064546e-06, "epoch": 1.2869565217391306, "percentage": 64.35, "elapsed_time": "0:03:05", "remaining_time": "0:01:42"}
298
+ {"current_steps": 297, "total_steps": 460, "loss": 0.7781, "lr": 2.7911090888178033e-06, "epoch": 1.2913043478260868, "percentage": 64.57, "elapsed_time": "0:03:06", "remaining_time": "0:01:42"}
299
+ {"current_steps": 298, "total_steps": 460, "loss": 0.6704, "lr": 2.760526067659591e-06, "epoch": 1.2956521739130435, "percentage": 64.78, "elapsed_time": "0:03:06", "remaining_time": "0:01:41"}
300
+ {"current_steps": 299, "total_steps": 460, "loss": 0.7291, "lr": 2.7300475013022666e-06, "epoch": 1.3, "percentage": 65.0, "elapsed_time": "0:03:07", "remaining_time": "0:01:40"}
301
+ {"current_steps": 300, "total_steps": 460, "loss": 1.0302, "lr": 2.6996748113442397e-06, "epoch": 1.3043478260869565, "percentage": 65.22, "elapsed_time": "0:03:08", "remaining_time": "0:01:40"}
302
+ {"current_steps": 301, "total_steps": 460, "loss": 0.8353, "lr": 2.669409414445574e-06, "epoch": 1.308695652173913, "percentage": 65.43, "elapsed_time": "0:03:08", "remaining_time": "0:01:39"}
303
+ {"current_steps": 302, "total_steps": 460, "loss": 0.6688, "lr": 2.6392527222619078e-06, "epoch": 1.3130434782608695, "percentage": 65.65, "elapsed_time": "0:03:09", "remaining_time": "0:01:39"}
304
+ {"current_steps": 303, "total_steps": 460, "loss": 0.9068, "lr": 2.6092061413786158e-06, "epoch": 1.317391304347826, "percentage": 65.87, "elapsed_time": "0:03:09", "remaining_time": "0:01:38"}
305
+ {"current_steps": 304, "total_steps": 460, "loss": 0.8414, "lr": 2.5792710732452e-06, "epoch": 1.3217391304347825, "percentage": 66.09, "elapsed_time": "0:03:10", "remaining_time": "0:01:37"}
306
+ {"current_steps": 305, "total_steps": 460, "loss": 0.8915, "lr": 2.5494489141099155e-06, "epoch": 1.3260869565217392, "percentage": 66.3, "elapsed_time": "0:03:11", "remaining_time": "0:01:37"}
307
+ {"current_steps": 306, "total_steps": 460, "loss": 0.8047, "lr": 2.5197410549546598e-06, "epoch": 1.3304347826086955, "percentage": 66.52, "elapsed_time": "0:03:11", "remaining_time": "0:01:36"}
308
+ {"current_steps": 307, "total_steps": 460, "loss": 0.9956, "lr": 2.4901488814300855e-06, "epoch": 1.3347826086956522, "percentage": 66.74, "elapsed_time": "0:03:12", "remaining_time": "0:01:35"}
309
+ {"current_steps": 308, "total_steps": 460, "loss": 0.9945, "lr": 2.4606737737909696e-06, "epoch": 1.3391304347826087, "percentage": 66.96, "elapsed_time": "0:03:13", "remaining_time": "0:01:35"}
310
+ {"current_steps": 309, "total_steps": 460, "loss": 1.0954, "lr": 2.431317106831836e-06, "epoch": 1.3434782608695652, "percentage": 67.17, "elapsed_time": "0:03:13", "remaining_time": "0:01:34"}
311
+ {"current_steps": 310, "total_steps": 460, "loss": 0.9187, "lr": 2.4020802498228333e-06, "epoch": 1.3478260869565217, "percentage": 67.39, "elapsed_time": "0:03:14", "remaining_time": "0:01:34"}
312
+ {"current_steps": 311, "total_steps": 460, "loss": 0.9233, "lr": 2.3729645664458637e-06, "epoch": 1.3521739130434782, "percentage": 67.61, "elapsed_time": "0:03:14", "remaining_time": "0:01:33"}
313
+ {"current_steps": 312, "total_steps": 460, "loss": 0.834, "lr": 2.3439714147309845e-06, "epoch": 1.3565217391304347, "percentage": 67.83, "elapsed_time": "0:03:15", "remaining_time": "0:01:32"}
314
+ {"current_steps": 313, "total_steps": 460, "loss": 0.8543, "lr": 2.315102146993061e-06, "epoch": 1.3608695652173912, "percentage": 68.04, "elapsed_time": "0:03:16", "remaining_time": "0:01:32"}
315
+ {"current_steps": 314, "total_steps": 460, "loss": 0.8543, "lr": 2.286358109768693e-06, "epoch": 1.365217391304348, "percentage": 68.26, "elapsed_time": "0:03:16", "remaining_time": "0:01:31"}
316
+ {"current_steps": 315, "total_steps": 460, "loss": 0.9254, "lr": 2.2577406437534055e-06, "epoch": 1.3695652173913042, "percentage": 68.48, "elapsed_time": "0:03:17", "remaining_time": "0:01:30"}
317
+ {"current_steps": 316, "total_steps": 460, "loss": 0.6516, "lr": 2.229251083739127e-06, "epoch": 1.373913043478261, "percentage": 68.7, "elapsed_time": "0:03:17", "remaining_time": "0:01:30"}
318
+ {"current_steps": 317, "total_steps": 460, "loss": 0.7393, "lr": 2.2008907585519094e-06, "epoch": 1.3782608695652174, "percentage": 68.91, "elapsed_time": "0:03:18", "remaining_time": "0:01:29"}
319
+ {"current_steps": 318, "total_steps": 460, "loss": 0.8385, "lr": 2.172660990989971e-06, "epoch": 1.382608695652174, "percentage": 69.13, "elapsed_time": "0:03:19", "remaining_time": "0:01:28"}
320
+ {"current_steps": 319, "total_steps": 460, "loss": 1.049, "lr": 2.144563097761984e-06, "epoch": 1.3869565217391304, "percentage": 69.35, "elapsed_time": "0:03:19", "remaining_time": "0:01:28"}
321
+ {"current_steps": 320, "total_steps": 460, "loss": 0.7784, "lr": 2.1165983894256647e-06, "epoch": 1.391304347826087, "percentage": 69.57, "elapsed_time": "0:03:20", "remaining_time": "0:01:27"}
322
+ {"current_steps": 321, "total_steps": 460, "loss": 0.7853, "lr": 2.0887681703266453e-06, "epoch": 1.3956521739130434, "percentage": 69.78, "elapsed_time": "0:03:20", "remaining_time": "0:01:26"}
323
+ {"current_steps": 322, "total_steps": 460, "loss": 0.9568, "lr": 2.061073738537635e-06, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "0:03:21", "remaining_time": "0:01:26"}
324
+ {"current_steps": 323, "total_steps": 460, "loss": 1.0086, "lr": 2.0335163857978747e-06, "epoch": 1.4043478260869566, "percentage": 70.22, "elapsed_time": "0:03:22", "remaining_time": "0:01:25"}
325
+ {"current_steps": 324, "total_steps": 460, "loss": 0.9203, "lr": 2.0060973974528873e-06, "epoch": 1.4086956521739131, "percentage": 70.43, "elapsed_time": "0:03:22", "remaining_time": "0:01:25"}
326
+ {"current_steps": 325, "total_steps": 460, "loss": 0.8118, "lr": 1.978818052394528e-06, "epoch": 1.4130434782608696, "percentage": 70.65, "elapsed_time": "0:03:23", "remaining_time": "0:01:24"}
327
+ {"current_steps": 326, "total_steps": 460, "loss": 0.6701, "lr": 1.9516796230013275e-06, "epoch": 1.4173913043478261, "percentage": 70.87, "elapsed_time": "0:03:23", "remaining_time": "0:01:23"}
328
+ {"current_steps": 327, "total_steps": 460, "loss": 0.9489, "lr": 1.9246833750791526e-06, "epoch": 1.4217391304347826, "percentage": 71.09, "elapsed_time": "0:03:24", "remaining_time": "0:01:23"}
329
+ {"current_steps": 328, "total_steps": 460, "loss": 1.1619, "lr": 1.8978305678021598e-06, "epoch": 1.4260869565217391, "percentage": 71.3, "elapsed_time": "0:03:25", "remaining_time": "0:01:22"}
330
+ {"current_steps": 329, "total_steps": 460, "loss": 1.0378, "lr": 1.8711224536540678e-06, "epoch": 1.4304347826086956, "percentage": 71.52, "elapsed_time": "0:03:25", "remaining_time": "0:01:21"}
331
+ {"current_steps": 330, "total_steps": 460, "loss": 0.7789, "lr": 1.8445602783697375e-06, "epoch": 1.434782608695652, "percentage": 71.74, "elapsed_time": "0:03:26", "remaining_time": "0:01:21"}
332
+ {"current_steps": 331, "total_steps": 460, "loss": 0.8897, "lr": 1.8181452808770638e-06, "epoch": 1.4391304347826086, "percentage": 71.96, "elapsed_time": "0:03:26", "remaining_time": "0:01:20"}
333
+ {"current_steps": 332, "total_steps": 460, "loss": 0.7022, "lr": 1.7918786932391945e-06, "epoch": 1.4434782608695653, "percentage": 72.17, "elapsed_time": "0:03:27", "remaining_time": "0:01:19"}
334
+ {"current_steps": 333, "total_steps": 460, "loss": 0.9281, "lr": 1.765761740597065e-06, "epoch": 1.4478260869565218, "percentage": 72.39, "elapsed_time": "0:03:28", "remaining_time": "0:01:19"}
335
+ {"current_steps": 334, "total_steps": 460, "loss": 0.9605, "lr": 1.739795641112248e-06, "epoch": 1.4521739130434783, "percentage": 72.61, "elapsed_time": "0:03:28", "remaining_time": "0:01:18"}
336
+ {"current_steps": 335, "total_steps": 460, "loss": 0.7956, "lr": 1.7139816059101372e-06, "epoch": 1.4565217391304348, "percentage": 72.83, "elapsed_time": "0:03:29", "remaining_time": "0:01:18"}
337
+ {"current_steps": 336, "total_steps": 460, "loss": 0.8153, "lr": 1.688320839023463e-06, "epoch": 1.4608695652173913, "percentage": 73.04, "elapsed_time": "0:03:29", "remaining_time": "0:01:17"}
338
+ {"current_steps": 337, "total_steps": 460, "loss": 0.7702, "lr": 1.662814537336122e-06, "epoch": 1.4652173913043478, "percentage": 73.26, "elapsed_time": "0:03:30", "remaining_time": "0:01:16"}
339
+ {"current_steps": 338, "total_steps": 460, "loss": 0.6835, "lr": 1.6374638905273643e-06, "epoch": 1.4695652173913043, "percentage": 73.48, "elapsed_time": "0:03:31", "remaining_time": "0:01:16"}
340
+ {"current_steps": 339, "total_steps": 460, "loss": 1.1026, "lr": 1.6122700810162967e-06, "epoch": 1.4739130434782608, "percentage": 73.7, "elapsed_time": "0:03:31", "remaining_time": "0:01:15"}
341
+ {"current_steps": 340, "total_steps": 460, "loss": 0.6443, "lr": 1.5872342839067305e-06, "epoch": 1.4782608695652173, "percentage": 73.91, "elapsed_time": "0:03:32", "remaining_time": "0:01:14"}
342
+ {"current_steps": 341, "total_steps": 460, "loss": 0.671, "lr": 1.5623576669323743e-06, "epoch": 1.482608695652174, "percentage": 74.13, "elapsed_time": "0:03:32", "remaining_time": "0:01:14"}
343
+ {"current_steps": 342, "total_steps": 460, "loss": 0.8094, "lr": 1.5376413904023723e-06, "epoch": 1.4869565217391305, "percentage": 74.35, "elapsed_time": "0:03:33", "remaining_time": "0:01:13"}
344
+ {"current_steps": 343, "total_steps": 460, "loss": 0.8523, "lr": 1.5130866071471717e-06, "epoch": 1.491304347826087, "percentage": 74.57, "elapsed_time": "0:03:34", "remaining_time": "0:01:13"}
345
+ {"current_steps": 344, "total_steps": 460, "loss": 0.9123, "lr": 1.4886944624647647e-06, "epoch": 1.4956521739130435, "percentage": 74.78, "elapsed_time": "0:03:34", "remaining_time": "0:01:12"}
346
+ {"current_steps": 345, "total_steps": 460, "loss": 0.8279, "lr": 1.4644660940672628e-06, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "0:03:35", "remaining_time": "0:01:11"}
347
+ {"current_steps": 346, "total_steps": 460, "loss": 0.8804, "lr": 1.4404026320278318e-06, "epoch": 1.5043478260869565, "percentage": 75.22, "elapsed_time": "0:03:36", "remaining_time": "0:01:11"}
348
+ {"current_steps": 347, "total_steps": 460, "loss": 0.9302, "lr": 1.4165051987279832e-06, "epoch": 1.508695652173913, "percentage": 75.43, "elapsed_time": "0:03:36", "remaining_time": "0:01:10"}
349
+ {"current_steps": 348, "total_steps": 460, "loss": 0.6735, "lr": 1.3927749088052218e-06, "epoch": 1.5130434782608697, "percentage": 75.65, "elapsed_time": "0:03:37", "remaining_time": "0:01:09"}
350
+ {"current_steps": 349, "total_steps": 460, "loss": 0.9032, "lr": 1.3692128691010592e-06, "epoch": 1.517391304347826, "percentage": 75.87, "elapsed_time": "0:03:37", "remaining_time": "0:01:09"}
351
+ {"current_steps": 350, "total_steps": 460, "loss": 0.9474, "lr": 1.3458201786093795e-06, "epoch": 1.5217391304347827, "percentage": 76.09, "elapsed_time": "0:03:38", "remaining_time": "0:01:08"}
352
+ {"current_steps": 351, "total_steps": 460, "loss": 0.9148, "lr": 1.3225979284251955e-06, "epoch": 1.526086956521739, "percentage": 76.3, "elapsed_time": "0:03:39", "remaining_time": "0:01:08"}
353
+ {"current_steps": 352, "total_steps": 460, "loss": 0.5777, "lr": 1.2995472016937405e-06, "epoch": 1.5304347826086957, "percentage": 76.52, "elapsed_time": "0:03:39", "remaining_time": "0:01:07"}
354
+ {"current_steps": 353, "total_steps": 460, "loss": 0.8865, "lr": 1.2766690735599569e-06, "epoch": 1.5347826086956522, "percentage": 76.74, "elapsed_time": "0:03:40", "remaining_time": "0:01:06"}
355
+ {"current_steps": 354, "total_steps": 460, "loss": 0.5584, "lr": 1.2539646111183452e-06, "epoch": 1.5391304347826087, "percentage": 76.96, "elapsed_time": "0:03:40", "remaining_time": "0:01:06"}
356
+ {"current_steps": 355, "total_steps": 460, "loss": 0.7646, "lr": 1.2314348733631958e-06, "epoch": 1.5434782608695652, "percentage": 77.17, "elapsed_time": "0:03:41", "remaining_time": "0:01:05"}
357
+ {"current_steps": 356, "total_steps": 460, "loss": 0.9251, "lr": 1.209080911139187e-06, "epoch": 1.5478260869565217, "percentage": 77.39, "elapsed_time": "0:03:42", "remaining_time": "0:01:04"}
358
+ {"current_steps": 357, "total_steps": 460, "loss": 0.9067, "lr": 1.1869037670923817e-06, "epoch": 1.5521739130434784, "percentage": 77.61, "elapsed_time": "0:03:42", "remaining_time": "0:01:04"}
359
+ {"current_steps": 358, "total_steps": 460, "loss": 0.8872, "lr": 1.1649044756215872e-06, "epoch": 1.5565217391304347, "percentage": 77.83, "elapsed_time": "0:03:43", "remaining_time": "0:01:03"}
360
+ {"current_steps": 359, "total_steps": 460, "loss": 0.856, "lr": 1.1430840628301093e-06, "epoch": 1.5608695652173914, "percentage": 78.04, "elapsed_time": "0:03:43", "remaining_time": "0:01:02"}
361
+ {"current_steps": 360, "total_steps": 460, "loss": 0.9335, "lr": 1.1214435464779006e-06, "epoch": 1.5652173913043477, "percentage": 78.26, "elapsed_time": "0:03:44", "remaining_time": "0:01:02"}
362
+ {"current_steps": 361, "total_steps": 460, "loss": 0.7533, "lr": 1.099983935934077e-06, "epoch": 1.5695652173913044, "percentage": 78.48, "elapsed_time": "0:03:45", "remaining_time": "0:01:01"}
363
+ {"current_steps": 362, "total_steps": 460, "loss": 0.6399, "lr": 1.0787062321298441e-06, "epoch": 1.5739130434782609, "percentage": 78.7, "elapsed_time": "0:03:45", "remaining_time": "0:01:01"}
364
+ {"current_steps": 363, "total_steps": 460, "loss": 0.9435, "lr": 1.0576114275118132e-06, "epoch": 1.5782608695652174, "percentage": 78.91, "elapsed_time": "0:03:46", "remaining_time": "0:01:00"}
365
+ {"current_steps": 364, "total_steps": 460, "loss": 0.8294, "lr": 1.0367005059957097e-06, "epoch": 1.5826086956521739, "percentage": 79.13, "elapsed_time": "0:03:46", "remaining_time": "0:00:59"}
366
+ {"current_steps": 365, "total_steps": 460, "loss": 0.8276, "lr": 1.0159744429204776e-06, "epoch": 1.5869565217391304, "percentage": 79.35, "elapsed_time": "0:03:47", "remaining_time": "0:00:59"}
367
+ {"current_steps": 366, "total_steps": 460, "loss": 1.0012, "lr": 9.954342050027922e-07, "epoch": 1.591304347826087, "percentage": 79.57, "elapsed_time": "0:03:48", "remaining_time": "0:00:58"}
368
+ {"current_steps": 367, "total_steps": 460, "loss": 0.8968, "lr": 9.75080750291965e-07, "epoch": 1.5956521739130434, "percentage": 79.78, "elapsed_time": "0:03:48", "remaining_time": "0:00:57"}
369
+ {"current_steps": 368, "total_steps": 460, "loss": 0.8566, "lr": 9.549150281252633e-07, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "0:03:49", "remaining_time": "0:00:57"}
370
+ {"current_steps": 369, "total_steps": 460, "loss": 0.9576, "lr": 9.349379790836243e-07, "epoch": 1.6043478260869564, "percentage": 80.22, "elapsed_time": "0:03:49", "remaining_time": "0:00:56"}
371
+ {"current_steps": 370, "total_steps": 460, "loss": 0.8896, "lr": 9.151505349477901e-07, "epoch": 1.608695652173913, "percentage": 80.43, "elapsed_time": "0:03:50", "remaining_time": "0:00:56"}
372
+ {"current_steps": 371, "total_steps": 460, "loss": 0.8589, "lr": 8.955536186548425e-07, "epoch": 1.6130434782608696, "percentage": 80.65, "elapsed_time": "0:03:51", "remaining_time": "0:00:55"}
373
+ {"current_steps": 372, "total_steps": 460, "loss": 0.7389, "lr": 8.761481442551573e-07, "epoch": 1.617391304347826, "percentage": 80.87, "elapsed_time": "0:03:51", "remaining_time": "0:00:54"}
374
+ {"current_steps": 373, "total_steps": 460, "loss": 0.9191, "lr": 8.569350168697705e-07, "epoch": 1.6217391304347826, "percentage": 81.09, "elapsed_time": "0:03:52", "remaining_time": "0:00:54"}
375
+ {"current_steps": 374, "total_steps": 460, "loss": 0.9844, "lr": 8.379151326481588e-07, "epoch": 1.626086956521739, "percentage": 81.3, "elapsed_time": "0:03:53", "remaining_time": "0:00:53"}
376
+ {"current_steps": 375, "total_steps": 460, "loss": 0.9641, "lr": 8.19089378726447e-07, "epoch": 1.6304347826086958, "percentage": 81.52, "elapsed_time": "0:03:53", "remaining_time": "0:00:52"}
377
+ {"current_steps": 376, "total_steps": 460, "loss": 0.693, "lr": 8.004586331860176e-07, "epoch": 1.634782608695652, "percentage": 81.74, "elapsed_time": "0:03:54", "remaining_time": "0:00:52"}
378
+ {"current_steps": 377, "total_steps": 460, "loss": 0.8997, "lr": 7.820237650125711e-07, "epoch": 1.6391304347826088, "percentage": 81.96, "elapsed_time": "0:03:54", "remaining_time": "0:00:51"}
379
+ {"current_steps": 378, "total_steps": 460, "loss": 0.9602, "lr": 7.637856340555822e-07, "epoch": 1.643478260869565, "percentage": 82.17, "elapsed_time": "0:03:55", "remaining_time": "0:00:51"}
380
+ {"current_steps": 379, "total_steps": 460, "loss": 0.9661, "lr": 7.457450909881969e-07, "epoch": 1.6478260869565218, "percentage": 82.39, "elapsed_time": "0:03:56", "remaining_time": "0:00:50"}
381
+ {"current_steps": 380, "total_steps": 460, "loss": 0.7581, "lr": 7.279029772675572e-07, "epoch": 1.6521739130434783, "percentage": 82.61, "elapsed_time": "0:03:56", "remaining_time": "0:00:49"}
382
+ {"current_steps": 381, "total_steps": 460, "loss": 1.0387, "lr": 7.102601250955526e-07, "epoch": 1.6565217391304348, "percentage": 82.83, "elapsed_time": "0:03:57", "remaining_time": "0:00:49"}
383
+ {"current_steps": 382, "total_steps": 460, "loss": 0.8253, "lr": 6.928173573800007e-07, "epoch": 1.6608695652173913, "percentage": 83.04, "elapsed_time": "0:03:57", "remaining_time": "0:00:48"}
384
+ {"current_steps": 383, "total_steps": 460, "loss": 0.7812, "lr": 6.755754876962711e-07, "epoch": 1.6652173913043478, "percentage": 83.26, "elapsed_time": "0:03:58", "remaining_time": "0:00:47"}
385
+ {"current_steps": 384, "total_steps": 460, "loss": 0.8385, "lr": 6.585353202493322e-07, "epoch": 1.6695652173913045, "percentage": 83.48, "elapsed_time": "0:03:59", "remaining_time": "0:00:47"}
386
+ {"current_steps": 385, "total_steps": 460, "loss": 0.8158, "lr": 6.416976498362432e-07, "epoch": 1.6739130434782608, "percentage": 83.7, "elapsed_time": "0:03:59", "remaining_time": "0:00:46"}
387
+ {"current_steps": 386, "total_steps": 460, "loss": 0.743, "lr": 6.250632618090868e-07, "epoch": 1.6782608695652175, "percentage": 83.91, "elapsed_time": "0:04:00", "remaining_time": "0:00:46"}
388
+ {"current_steps": 387, "total_steps": 460, "loss": 0.8247, "lr": 6.086329320383311e-07, "epoch": 1.6826086956521737, "percentage": 84.13, "elapsed_time": "0:04:00", "remaining_time": "0:00:45"}
389
+ {"current_steps": 388, "total_steps": 460, "loss": 0.9462, "lr": 5.924074268766422e-07, "epoch": 1.6869565217391305, "percentage": 84.35, "elapsed_time": "0:04:01", "remaining_time": "0:00:44"}
390
+ {"current_steps": 389, "total_steps": 460, "loss": 0.7075, "lr": 5.763875031231464e-07, "epoch": 1.691304347826087, "percentage": 84.57, "elapsed_time": "0:04:02", "remaining_time": "0:00:44"}
391
+ {"current_steps": 390, "total_steps": 460, "loss": 0.9472, "lr": 5.60573907988124e-07, "epoch": 1.6956521739130435, "percentage": 84.78, "elapsed_time": "0:04:02", "remaining_time": "0:00:43"}
392
+ {"current_steps": 391, "total_steps": 460, "loss": 0.8564, "lr": 5.449673790581611e-07, "epoch": 1.7, "percentage": 85.0, "elapsed_time": "0:04:03", "remaining_time": "0:00:42"}
393
+ {"current_steps": 392, "total_steps": 460, "loss": 0.5747, "lr": 5.295686442617442e-07, "epoch": 1.7043478260869565, "percentage": 85.22, "elapsed_time": "0:04:03", "remaining_time": "0:00:42"}
394
+ {"current_steps": 393, "total_steps": 460, "loss": 0.8275, "lr": 5.143784218353104e-07, "epoch": 1.7086956521739132, "percentage": 85.43, "elapsed_time": "0:04:04", "remaining_time": "0:00:41"}
395
+ {"current_steps": 394, "total_steps": 460, "loss": 0.9133, "lr": 4.993974202897456e-07, "epoch": 1.7130434782608694, "percentage": 85.65, "elapsed_time": "0:04:05", "remaining_time": "0:00:41"}
396
+ {"current_steps": 395, "total_steps": 460, "loss": 0.8795, "lr": 4.846263383773364e-07, "epoch": 1.7173913043478262, "percentage": 85.87, "elapsed_time": "0:04:05", "remaining_time": "0:00:40"}
397
+ {"current_steps": 396, "total_steps": 460, "loss": 0.7673, "lr": 4.7006586505918273e-07, "epoch": 1.7217391304347827, "percentage": 86.09, "elapsed_time": "0:04:06", "remaining_time": "0:00:39"}
398
+ {"current_steps": 397, "total_steps": 460, "loss": 0.8222, "lr": 4.557166794730572e-07, "epoch": 1.7260869565217392, "percentage": 86.3, "elapsed_time": "0:04:06", "remaining_time": "0:00:39"}
399
+ {"current_steps": 398, "total_steps": 460, "loss": 0.8417, "lr": 4.4157945090173294e-07, "epoch": 1.7304347826086957, "percentage": 86.52, "elapsed_time": "0:04:07", "remaining_time": "0:00:38"}
400
+ {"current_steps": 399, "total_steps": 460, "loss": 1.2644, "lr": 4.276548387417656e-07, "epoch": 1.7347826086956522, "percentage": 86.74, "elapsed_time": "0:04:08", "remaining_time": "0:00:37"}
401
+ {"current_steps": 400, "total_steps": 460, "loss": 0.6251, "lr": 4.139434924727359e-07, "epoch": 1.7391304347826086, "percentage": 86.96, "elapsed_time": "0:04:08", "remaining_time": "0:00:37"}
402
+ {"current_steps": 400, "total_steps": 460, "eval_loss": 1.1194324493408203, "epoch": 1.7391304347826086, "percentage": 86.96, "elapsed_time": "0:04:09", "remaining_time": "0:00:37"}
403
+ {"current_steps": 401, "total_steps": 460, "loss": 0.9746, "lr": 4.004460516269554e-07, "epoch": 1.7434782608695651, "percentage": 87.17, "elapsed_time": "0:04:10", "remaining_time": "0:00:36"}
404
+ {"current_steps": 402, "total_steps": 460, "loss": 0.8921, "lr": 3.8716314575964197e-07, "epoch": 1.7478260869565219, "percentage": 87.39, "elapsed_time": "0:04:10", "remaining_time": "0:00:36"}
405
+ {"current_steps": 403, "total_steps": 460, "loss": 0.9338, "lr": 3.740953944195497e-07, "epoch": 1.7521739130434781, "percentage": 87.61, "elapsed_time": "0:04:11", "remaining_time": "0:00:35"}
406
+ {"current_steps": 404, "total_steps": 460, "loss": 0.5685, "lr": 3.612434071200771e-07, "epoch": 1.7565217391304349, "percentage": 87.83, "elapsed_time": "0:04:11", "remaining_time": "0:00:34"}
407
+ {"current_steps": 405, "total_steps": 460, "loss": 0.8099, "lr": 3.486077833108342e-07, "epoch": 1.7608695652173914, "percentage": 88.04, "elapsed_time": "0:04:12", "remaining_time": "0:00:34"}
408
+ {"current_steps": 406, "total_steps": 460, "loss": 0.7885, "lr": 3.361891123496824e-07, "epoch": 1.7652173913043478, "percentage": 88.26, "elapsed_time": "0:04:13", "remaining_time": "0:00:33"}
409
+ {"current_steps": 407, "total_steps": 460, "loss": 0.7777, "lr": 3.2398797347524656e-07, "epoch": 1.7695652173913043, "percentage": 88.48, "elapsed_time": "0:04:13", "remaining_time": "0:00:33"}
410
+ {"current_steps": 408, "total_steps": 460, "loss": 0.6199, "lr": 3.1200493577989875e-07, "epoch": 1.7739130434782608, "percentage": 88.7, "elapsed_time": "0:04:14", "remaining_time": "0:00:32"}
411
+ {"current_steps": 409, "total_steps": 460, "loss": 0.5828, "lr": 3.002405581832135e-07, "epoch": 1.7782608695652173, "percentage": 88.91, "elapsed_time": "0:04:14", "remaining_time": "0:00:31"}
412
+ {"current_steps": 410, "total_steps": 460, "loss": 0.7514, "lr": 2.88695389405898e-07, "epoch": 1.7826086956521738, "percentage": 89.13, "elapsed_time": "0:04:15", "remaining_time": "0:00:31"}
413
+ {"current_steps": 411, "total_steps": 460, "loss": 0.8881, "lr": 2.7736996794419767e-07, "epoch": 1.7869565217391306, "percentage": 89.35, "elapsed_time": "0:04:16", "remaining_time": "0:00:30"}
414
+ {"current_steps": 412, "total_steps": 460, "loss": 0.8771, "lr": 2.662648220447811e-07, "epoch": 1.7913043478260868, "percentage": 89.57, "elapsed_time": "0:04:16", "remaining_time": "0:00:29"}
415
+ {"current_steps": 413, "total_steps": 460, "loss": 0.8271, "lr": 2.5538046968010097e-07, "epoch": 1.7956521739130435, "percentage": 89.78, "elapsed_time": "0:04:17", "remaining_time": "0:00:29"}
416
+ {"current_steps": 414, "total_steps": 460, "loss": 1.0165, "lr": 2.447174185242324e-07, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "0:04:17", "remaining_time": "0:00:28"}
417
+ {"current_steps": 415, "total_steps": 460, "loss": 0.8413, "lr": 2.3427616592919587e-07, "epoch": 1.8043478260869565, "percentage": 90.22, "elapsed_time": "0:04:18", "remaining_time": "0:00:28"}
418
+ {"current_steps": 416, "total_steps": 460, "loss": 0.8756, "lr": 2.240571989017598e-07, "epoch": 1.808695652173913, "percentage": 90.43, "elapsed_time": "0:04:19", "remaining_time": "0:00:27"}
419
+ {"current_steps": 417, "total_steps": 460, "loss": 0.6692, "lr": 2.1406099408072256e-07, "epoch": 1.8130434782608695, "percentage": 90.65, "elapsed_time": "0:04:19", "remaining_time": "0:00:26"}
420
+ {"current_steps": 418, "total_steps": 460, "loss": 0.6309, "lr": 2.0428801771468388e-07, "epoch": 1.8173913043478263, "percentage": 90.87, "elapsed_time": "0:04:20", "remaining_time": "0:00:26"}
421
+ {"current_steps": 419, "total_steps": 460, "loss": 0.8685, "lr": 1.947387256402966e-07, "epoch": 1.8217391304347825, "percentage": 91.09, "elapsed_time": "0:04:21", "remaining_time": "0:00:25"}
422
+ {"current_steps": 420, "total_steps": 460, "loss": 0.8765, "lr": 1.8541356326100436e-07, "epoch": 1.8260869565217392, "percentage": 91.3, "elapsed_time": "0:04:21", "remaining_time": "0:00:24"}
423
+ {"current_steps": 421, "total_steps": 460, "loss": 0.8582, "lr": 1.7631296552626687e-07, "epoch": 1.8304347826086955, "percentage": 91.52, "elapsed_time": "0:04:22", "remaining_time": "0:00:24"}
424
+ {"current_steps": 422, "total_steps": 460, "loss": 0.7613, "lr": 1.6743735691127639e-07, "epoch": 1.8347826086956522, "percentage": 91.74, "elapsed_time": "0:04:22", "remaining_time": "0:00:23"}
425
+ {"current_steps": 423, "total_steps": 460, "loss": 0.8236, "lr": 1.5878715139715395e-07, "epoch": 1.8391304347826087, "percentage": 91.96, "elapsed_time": "0:04:23", "remaining_time": "0:00:23"}
426
+ {"current_steps": 424, "total_steps": 460, "loss": 1.0084, "lr": 1.5036275245164377e-07, "epoch": 1.8434782608695652, "percentage": 92.17, "elapsed_time": "0:04:24", "remaining_time": "0:00:22"}
427
+ {"current_steps": 425, "total_steps": 460, "loss": 0.9447, "lr": 1.4216455301029274e-07, "epoch": 1.8478260869565217, "percentage": 92.39, "elapsed_time": "0:04:24", "remaining_time": "0:00:21"}
428
+ {"current_steps": 426, "total_steps": 460, "loss": 0.7521, "lr": 1.341929354581234e-07, "epoch": 1.8521739130434782, "percentage": 92.61, "elapsed_time": "0:04:25", "remaining_time": "0:00:21"}
429
+ {"current_steps": 427, "total_steps": 460, "loss": 0.9034, "lr": 1.2644827161179763e-07, "epoch": 1.856521739130435, "percentage": 92.83, "elapsed_time": "0:04:25", "remaining_time": "0:00:20"}
430
+ {"current_steps": 428, "total_steps": 460, "loss": 0.7957, "lr": 1.1893092270227724e-07, "epoch": 1.8608695652173912, "percentage": 93.04, "elapsed_time": "0:04:26", "remaining_time": "0:00:19"}
431
+ {"current_steps": 429, "total_steps": 460, "loss": 0.7332, "lr": 1.1164123935797189e-07, "epoch": 1.865217391304348, "percentage": 93.26, "elapsed_time": "0:04:27", "remaining_time": "0:00:19"}
432
+ {"current_steps": 430, "total_steps": 460, "loss": 0.756, "lr": 1.0457956158838545e-07, "epoch": 1.8695652173913042, "percentage": 93.48, "elapsed_time": "0:04:27", "remaining_time": "0:00:18"}
433
+ {"current_steps": 431, "total_steps": 460, "loss": 0.7145, "lr": 9.774621876825985e-08, "epoch": 1.873913043478261, "percentage": 93.7, "elapsed_time": "0:04:28", "remaining_time": "0:00:18"}
434
+ {"current_steps": 432, "total_steps": 460, "loss": 0.7814, "lr": 9.114152962220734e-08, "epoch": 1.8782608695652174, "percentage": 93.91, "elapsed_time": "0:04:28", "remaining_time": "0:00:17"}
435
+ {"current_steps": 433, "total_steps": 460, "loss": 0.8234, "lr": 8.476580220984854e-08, "epoch": 1.882608695652174, "percentage": 94.13, "elapsed_time": "0:04:29", "remaining_time": "0:00:16"}
436
+ {"current_steps": 434, "total_steps": 460, "loss": 0.9901, "lr": 7.861933391144272e-08, "epoch": 1.8869565217391304, "percentage": 94.35, "elapsed_time": "0:04:30", "remaining_time": "0:00:16"}
437
+ {"current_steps": 435, "total_steps": 460, "loss": 0.8422, "lr": 7.270241141401568e-08, "epoch": 1.891304347826087, "percentage": 94.57, "elapsed_time": "0:04:30", "remaining_time": "0:00:15"}
438
+ {"current_steps": 436, "total_steps": 460, "loss": 1.0083, "lr": 6.701531069799039e-08, "epoch": 1.8956521739130436, "percentage": 94.78, "elapsed_time": "0:04:31", "remaining_time": "0:00:14"}
439
+ {"current_steps": 437, "total_steps": 460, "loss": 0.7593, "lr": 6.15582970243117e-08, "epoch": 1.9, "percentage": 95.0, "elapsed_time": "0:04:31", "remaining_time": "0:00:14"}
440
+ {"current_steps": 438, "total_steps": 460, "loss": 1.1215, "lr": 5.633162492207633e-08, "epoch": 1.9043478260869566, "percentage": 95.22, "elapsed_time": "0:04:32", "remaining_time": "0:00:13"}
441
+ {"current_steps": 439, "total_steps": 460, "loss": 0.8688, "lr": 5.133553817665948e-08, "epoch": 1.908695652173913, "percentage": 95.43, "elapsed_time": "0:04:33", "remaining_time": "0:00:13"}
442
+ {"current_steps": 440, "total_steps": 460, "loss": 0.8473, "lr": 4.657026981834623e-08, "epoch": 1.9130434782608696, "percentage": 95.65, "elapsed_time": "0:04:33", "remaining_time": "0:00:12"}
443
+ {"current_steps": 441, "total_steps": 460, "loss": 0.8863, "lr": 4.203604211145851e-08, "epoch": 1.9173913043478261, "percentage": 95.87, "elapsed_time": "0:04:34", "remaining_time": "0:00:11"}
444
+ {"current_steps": 442, "total_steps": 460, "loss": 0.7124, "lr": 3.773306654399234e-08, "epoch": 1.9217391304347826, "percentage": 96.09, "elapsed_time": "0:04:34", "remaining_time": "0:00:11"}
445
+ {"current_steps": 443, "total_steps": 460, "loss": 0.9662, "lr": 3.366154381775011e-08, "epoch": 1.9260869565217391, "percentage": 96.3, "elapsed_time": "0:04:35", "remaining_time": "0:00:10"}
446
+ {"current_steps": 444, "total_steps": 460, "loss": 0.9213, "lr": 2.9821663838981994e-08, "epoch": 1.9304347826086956, "percentage": 96.52, "elapsed_time": "0:04:36", "remaining_time": "0:00:09"}
447
+ {"current_steps": 445, "total_steps": 460, "loss": 0.7552, "lr": 2.6213605709525803e-08, "epoch": 1.9347826086956523, "percentage": 96.74, "elapsed_time": "0:04:36", "remaining_time": "0:00:09"}
448
+ {"current_steps": 446, "total_steps": 460, "loss": 0.7865, "lr": 2.283753771845587e-08, "epoch": 1.9391304347826086, "percentage": 96.96, "elapsed_time": "0:04:37", "remaining_time": "0:00:08"}
449
+ {"current_steps": 447, "total_steps": 460, "loss": 0.9703, "lr": 1.969361733423103e-08, "epoch": 1.9434782608695653, "percentage": 97.17, "elapsed_time": "0:04:37", "remaining_time": "0:00:08"}
450
+ {"current_steps": 448, "total_steps": 460, "loss": 0.8206, "lr": 1.6781991197352133e-08, "epoch": 1.9478260869565216, "percentage": 97.39, "elapsed_time": "0:04:38", "remaining_time": "0:00:07"}
451
+ {"current_steps": 449, "total_steps": 460, "loss": 0.7311, "lr": 1.4102795113520307e-08, "epoch": 1.9521739130434783, "percentage": 97.61, "elapsed_time": "0:04:39", "remaining_time": "0:00:06"}
452
+ {"current_steps": 450, "total_steps": 460, "loss": 0.8387, "lr": 1.1656154047303691e-08, "epoch": 1.9565217391304348, "percentage": 97.83, "elapsed_time": "0:04:39", "remaining_time": "0:00:06"}
453
+ {"current_steps": 451, "total_steps": 460, "loss": 0.8165, "lr": 9.442182116309872e-09, "epoch": 1.9608695652173913, "percentage": 98.04, "elapsed_time": "0:04:40", "remaining_time": "0:00:05"}
454
+ {"current_steps": 452, "total_steps": 460, "loss": 0.7981, "lr": 7.460982585860144e-09, "epoch": 1.9652173913043478, "percentage": 98.26, "elapsed_time": "0:04:41", "remaining_time": "0:00:04"}
455
+ {"current_steps": 453, "total_steps": 460, "loss": 0.7996, "lr": 5.712647864176135e-09, "epoch": 1.9695652173913043, "percentage": 98.48, "elapsed_time": "0:04:41", "remaining_time": "0:00:04"}
456
+ {"current_steps": 454, "total_steps": 460, "loss": 1.0172, "lr": 4.197259498067707e-09, "epoch": 1.973913043478261, "percentage": 98.7, "elapsed_time": "0:04:42", "remaining_time": "0:00:03"}
457
+ {"current_steps": 455, "total_steps": 460, "loss": 0.8608, "lr": 2.9148881691298812e-09, "epoch": 1.9782608695652173, "percentage": 98.91, "elapsed_time": "0:04:42", "remaining_time": "0:00:03"}
458
+ {"current_steps": 456, "total_steps": 460, "loss": 0.7651, "lr": 1.865593690446588e-09, "epoch": 1.982608695652174, "percentage": 99.13, "elapsed_time": "0:04:43", "remaining_time": "0:00:02"}
459
+ {"current_steps": 457, "total_steps": 460, "loss": 0.8231, "lr": 1.0494250038006747e-09, "epoch": 1.9869565217391303, "percentage": 99.35, "elapsed_time": "0:04:44", "remaining_time": "0:00:01"}
460
+ {"current_steps": 458, "total_steps": 460, "loss": 0.5551, "lr": 4.664201773896259e-10, "epoch": 1.991304347826087, "percentage": 99.57, "elapsed_time": "0:04:44", "remaining_time": "0:00:01"}
461
+ {"current_steps": 459, "total_steps": 460, "loss": 0.7338, "lr": 1.1660640405308787e-10, "epoch": 1.9956521739130435, "percentage": 99.78, "elapsed_time": "0:04:45", "remaining_time": "0:00:00"}
462
+ {"current_steps": 460, "total_steps": 460, "loss": 1.1184, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:04:45", "remaining_time": "0:00:00"}
463
+ {"current_steps": 460, "total_steps": 460, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:04:50", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,3278 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 200,
6
+ "global_step": 460,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004347826086956522,
13
+ "grad_norm": 6.9957649631828405,
14
+ "learning_rate": 9.999883393595949e-06,
15
+ "loss": 1.2388,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.008695652173913044,
20
+ "grad_norm": 9.95054310922503,
21
+ "learning_rate": 9.999533579822611e-06,
22
+ "loss": 1.1524,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.013043478260869565,
27
+ "grad_norm": 5.695651384837083,
28
+ "learning_rate": 9.9989505749962e-06,
29
+ "loss": 1.1518,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.017391304347826087,
34
+ "grad_norm": 6.241920295548784,
35
+ "learning_rate": 9.998134406309555e-06,
36
+ "loss": 0.9891,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.021739130434782608,
41
+ "grad_norm": 6.332511203026904,
42
+ "learning_rate": 9.99708511183087e-06,
43
+ "loss": 0.8734,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.02608695652173913,
48
+ "grad_norm": 7.058504523129276,
49
+ "learning_rate": 9.995802740501933e-06,
50
+ "loss": 1.0579,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.030434782608695653,
55
+ "grad_norm": 5.380832042539577,
56
+ "learning_rate": 9.994287352135826e-06,
57
+ "loss": 0.9832,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.034782608695652174,
62
+ "grad_norm": 5.293272427338606,
63
+ "learning_rate": 9.99253901741414e-06,
64
+ "loss": 1.041,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.0391304347826087,
69
+ "grad_norm": 5.573448213307741,
70
+ "learning_rate": 9.99055781788369e-06,
71
+ "loss": 1.126,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.043478260869565216,
76
+ "grad_norm": 7.810498210301582,
77
+ "learning_rate": 9.988343845952697e-06,
78
+ "loss": 1.2885,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.04782608695652174,
83
+ "grad_norm": 4.901543816057656,
84
+ "learning_rate": 9.985897204886481e-06,
85
+ "loss": 0.8854,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.05217391304347826,
90
+ "grad_norm": 5.832114052367384,
91
+ "learning_rate": 9.983218008802648e-06,
92
+ "loss": 1.2227,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.05652173913043478,
97
+ "grad_norm": 6.282340655884838,
98
+ "learning_rate": 9.98030638266577e-06,
99
+ "loss": 1.2126,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.06086956521739131,
104
+ "grad_norm": 7.3459227169456085,
105
+ "learning_rate": 9.977162462281544e-06,
106
+ "loss": 1.0473,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.06521739130434782,
111
+ "grad_norm": 6.209463739051767,
112
+ "learning_rate": 9.973786394290475e-06,
113
+ "loss": 1.069,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.06956521739130435,
118
+ "grad_norm": 7.410164980032177,
119
+ "learning_rate": 9.970178336161018e-06,
120
+ "loss": 1.0858,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.07391304347826087,
125
+ "grad_norm": 4.998866693214577,
126
+ "learning_rate": 9.96633845618225e-06,
127
+ "loss": 0.857,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.0782608695652174,
132
+ "grad_norm": 5.678972680076527,
133
+ "learning_rate": 9.962266933456008e-06,
134
+ "loss": 1.5511,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.08260869565217391,
139
+ "grad_norm": 5.487019930270194,
140
+ "learning_rate": 9.957963957888542e-06,
141
+ "loss": 1.1189,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.08695652173913043,
146
+ "grad_norm": 5.3652261003152,
147
+ "learning_rate": 9.953429730181653e-06,
148
+ "loss": 1.1901,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.09130434782608696,
153
+ "grad_norm": 7.654682198994736,
154
+ "learning_rate": 9.94866446182334e-06,
155
+ "loss": 1.1392,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.09565217391304348,
160
+ "grad_norm": 5.629067114296054,
161
+ "learning_rate": 9.943668375077926e-06,
162
+ "loss": 1.2286,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.1,
167
+ "grad_norm": 5.028919124522457,
168
+ "learning_rate": 9.938441702975689e-06,
169
+ "loss": 1.1547,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.10434782608695652,
174
+ "grad_norm": 6.075245701118606,
175
+ "learning_rate": 9.932984689302012e-06,
176
+ "loss": 0.9822,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.10869565217391304,
181
+ "grad_norm": 5.389031104413729,
182
+ "learning_rate": 9.927297588585984e-06,
183
+ "loss": 1.1524,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.11304347826086956,
188
+ "grad_norm": 6.560079389250751,
189
+ "learning_rate": 9.921380666088558e-06,
190
+ "loss": 1.1971,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.11739130434782609,
195
+ "grad_norm": 4.295239594212597,
196
+ "learning_rate": 9.915234197790153e-06,
197
+ "loss": 0.8627,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.12173913043478261,
202
+ "grad_norm": 5.410624093398277,
203
+ "learning_rate": 9.908858470377793e-06,
204
+ "loss": 1.0703,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.12608695652173912,
209
+ "grad_norm": 5.549654300627365,
210
+ "learning_rate": 9.902253781231741e-06,
211
+ "loss": 1.1291,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.13043478260869565,
216
+ "grad_norm": 4.652940335106497,
217
+ "learning_rate": 9.895420438411616e-06,
218
+ "loss": 0.8515,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.13478260869565217,
223
+ "grad_norm": 4.666458890124793,
224
+ "learning_rate": 9.88835876064203e-06,
225
+ "loss": 1.0999,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.1391304347826087,
230
+ "grad_norm": 7.903256457184446,
231
+ "learning_rate": 9.881069077297724e-06,
232
+ "loss": 1.2162,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.14347826086956522,
237
+ "grad_norm": 5.362324539137533,
238
+ "learning_rate": 9.873551728388203e-06,
239
+ "loss": 1.0254,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.14782608695652175,
244
+ "grad_norm": 7.666771955239573,
245
+ "learning_rate": 9.865807064541878e-06,
246
+ "loss": 1.2162,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.15217391304347827,
251
+ "grad_norm": 6.2830908144605,
252
+ "learning_rate": 9.857835446989708e-06,
253
+ "loss": 1.2053,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.1565217391304348,
258
+ "grad_norm": 4.489664287383312,
259
+ "learning_rate": 9.849637247548356e-06,
260
+ "loss": 0.8951,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.1608695652173913,
265
+ "grad_norm": 4.963912499904992,
266
+ "learning_rate": 9.841212848602848e-06,
267
+ "loss": 1.2886,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.16521739130434782,
272
+ "grad_norm": 4.324113388116558,
273
+ "learning_rate": 9.832562643088724e-06,
274
+ "loss": 1.1409,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.16956521739130434,
279
+ "grad_norm": 5.838457248913322,
280
+ "learning_rate": 9.823687034473734e-06,
281
+ "loss": 1.1393,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.17391304347826086,
286
+ "grad_norm": 6.903605825348034,
287
+ "learning_rate": 9.814586436738998e-06,
288
+ "loss": 1.2827,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.1782608695652174,
293
+ "grad_norm": 4.929566383938446,
294
+ "learning_rate": 9.805261274359705e-06,
295
+ "loss": 1.0051,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.1826086956521739,
300
+ "grad_norm": 4.972540823594019,
301
+ "learning_rate": 9.795711982285317e-06,
302
+ "loss": 1.0446,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.18695652173913044,
307
+ "grad_norm": 7.132830202832695,
308
+ "learning_rate": 9.785939005919279e-06,
309
+ "loss": 0.9145,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.19130434782608696,
314
+ "grad_norm": 4.624026176859361,
315
+ "learning_rate": 9.775942801098241e-06,
316
+ "loss": 1.0196,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.1956521739130435,
321
+ "grad_norm": 4.6090243132558095,
322
+ "learning_rate": 9.765723834070805e-06,
323
+ "loss": 0.9979,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.2,
328
+ "grad_norm": 4.365133873054547,
329
+ "learning_rate": 9.755282581475769e-06,
330
+ "loss": 1.0051,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.20434782608695654,
335
+ "grad_norm": 5.983012403113971,
336
+ "learning_rate": 9.7446195303199e-06,
337
+ "loss": 1.1931,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.20869565217391303,
342
+ "grad_norm": 4.762635673381608,
343
+ "learning_rate": 9.733735177955219e-06,
344
+ "loss": 0.9187,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.21304347826086956,
349
+ "grad_norm": 6.442928154111425,
350
+ "learning_rate": 9.722630032055804e-06,
351
+ "loss": 0.9918,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.21739130434782608,
356
+ "grad_norm": 4.192963782436731,
357
+ "learning_rate": 9.711304610594104e-06,
358
+ "loss": 0.7698,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.2217391304347826,
363
+ "grad_norm": 5.762521453000841,
364
+ "learning_rate": 9.699759441816788e-06,
365
+ "loss": 1.0155,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.22608695652173913,
370
+ "grad_norm": 4.79881156610975,
371
+ "learning_rate": 9.687995064220102e-06,
372
+ "loss": 1.0465,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.23043478260869565,
377
+ "grad_norm": 6.640310691679004,
378
+ "learning_rate": 9.676012026524755e-06,
379
+ "loss": 1.1731,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.23478260869565218,
384
+ "grad_norm": 5.203722038887662,
385
+ "learning_rate": 9.66381088765032e-06,
386
+ "loss": 1.0759,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.2391304347826087,
391
+ "grad_norm": 4.087205894448472,
392
+ "learning_rate": 9.651392216689167e-06,
393
+ "loss": 1.2107,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.24347826086956523,
398
+ "grad_norm": 6.136530429465954,
399
+ "learning_rate": 9.638756592879923e-06,
400
+ "loss": 1.0933,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.24782608695652175,
405
+ "grad_norm": 4.472508648575729,
406
+ "learning_rate": 9.625904605580452e-06,
407
+ "loss": 1.0525,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.25217391304347825,
412
+ "grad_norm": 4.284711266876134,
413
+ "learning_rate": 9.61283685424036e-06,
414
+ "loss": 1.0356,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.2565217391304348,
419
+ "grad_norm": 5.356393077035378,
420
+ "learning_rate": 9.599553948373047e-06,
421
+ "loss": 0.9344,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.2608695652173913,
426
+ "grad_norm": 5.405541048147801,
427
+ "learning_rate": 9.586056507527266e-06,
428
+ "loss": 1.3272,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.26521739130434785,
433
+ "grad_norm": 7.367620711282692,
434
+ "learning_rate": 9.572345161258235e-06,
435
+ "loss": 1.473,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.26956521739130435,
440
+ "grad_norm": 4.995685833591698,
441
+ "learning_rate": 9.558420549098269e-06,
442
+ "loss": 0.9302,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.27391304347826084,
447
+ "grad_norm": 5.705244590557277,
448
+ "learning_rate": 9.544283320526943e-06,
449
+ "loss": 0.9316,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.2782608695652174,
454
+ "grad_norm": 7.284212253457506,
455
+ "learning_rate": 9.529934134940819e-06,
456
+ "loss": 1.4276,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.2826086956521739,
461
+ "grad_norm": 4.995261077070801,
462
+ "learning_rate": 9.515373661622665e-06,
463
+ "loss": 1.1629,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.28695652173913044,
468
+ "grad_norm": 4.619733298626065,
469
+ "learning_rate": 9.500602579710256e-06,
470
+ "loss": 1.2463,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.29130434782608694,
475
+ "grad_norm": 5.522140599108674,
476
+ "learning_rate": 9.48562157816469e-06,
477
+ "loss": 1.3279,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.2956521739130435,
482
+ "grad_norm": 4.703367738372854,
483
+ "learning_rate": 9.470431355738257e-06,
484
+ "loss": 1.1167,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.3,
489
+ "grad_norm": 3.8974458856176413,
490
+ "learning_rate": 9.45503262094184e-06,
491
+ "loss": 1.0509,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.30434782608695654,
496
+ "grad_norm": 5.516509277837715,
497
+ "learning_rate": 9.439426092011877e-06,
498
+ "loss": 1.03,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.30869565217391304,
503
+ "grad_norm": 3.8445888917549897,
504
+ "learning_rate": 9.423612496876856e-06,
505
+ "loss": 1.0454,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.3130434782608696,
510
+ "grad_norm": 4.388706537125176,
511
+ "learning_rate": 9.407592573123359e-06,
512
+ "loss": 1.0803,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.3173913043478261,
517
+ "grad_norm": 6.004781435495349,
518
+ "learning_rate": 9.39136706796167e-06,
519
+ "loss": 1.2031,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.3217391304347826,
524
+ "grad_norm": 4.309098965430049,
525
+ "learning_rate": 9.374936738190913e-06,
526
+ "loss": 0.9793,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.32608695652173914,
531
+ "grad_norm": 6.218626274813902,
532
+ "learning_rate": 9.358302350163758e-06,
533
+ "loss": 1.2657,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.33043478260869563,
538
+ "grad_norm": 6.235659008642887,
539
+ "learning_rate": 9.341464679750669e-06,
540
+ "loss": 1.2294,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.3347826086956522,
545
+ "grad_norm": 4.844840477934557,
546
+ "learning_rate": 9.32442451230373e-06,
547
+ "loss": 0.9039,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.3391304347826087,
552
+ "grad_norm": 5.3232475988197905,
553
+ "learning_rate": 9.307182642620001e-06,
554
+ "loss": 1.2323,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.34347826086956523,
559
+ "grad_norm": 5.3417423502367125,
560
+ "learning_rate": 9.289739874904448e-06,
561
+ "loss": 0.9413,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.34782608695652173,
566
+ "grad_norm": 5.400520396201158,
567
+ "learning_rate": 9.272097022732444e-06,
568
+ "loss": 1.0413,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.3521739130434783,
573
+ "grad_norm": 5.6219560229699335,
574
+ "learning_rate": 9.254254909011805e-06,
575
+ "loss": 1.3961,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.3565217391304348,
580
+ "grad_norm": 4.511409517484716,
581
+ "learning_rate": 9.236214365944418e-06,
582
+ "loss": 0.9989,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.36086956521739133,
587
+ "grad_norm": 4.4749542087590335,
588
+ "learning_rate": 9.217976234987429e-06,
589
+ "loss": 0.8743,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.3652173913043478,
594
+ "grad_norm": 3.72816284187776,
595
+ "learning_rate": 9.199541366813984e-06,
596
+ "loss": 0.9145,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.3695652173913043,
601
+ "grad_norm": 5.097998502542571,
602
+ "learning_rate": 9.180910621273555e-06,
603
+ "loss": 1.2925,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.3739130434782609,
608
+ "grad_norm": 4.564428356895465,
609
+ "learning_rate": 9.16208486735184e-06,
610
+ "loss": 1.0503,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.3782608695652174,
615
+ "grad_norm": 5.251781061231467,
616
+ "learning_rate": 9.14306498313023e-06,
617
+ "loss": 0.8255,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.3826086956521739,
622
+ "grad_norm": 5.486824430895445,
623
+ "learning_rate": 9.123851855744842e-06,
624
+ "loss": 1.1568,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.3869565217391304,
629
+ "grad_norm": 3.898032172322348,
630
+ "learning_rate": 9.10444638134516e-06,
631
+ "loss": 0.8883,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.391304347826087,
636
+ "grad_norm": 4.325108825451344,
637
+ "learning_rate": 9.08484946505221e-06,
638
+ "loss": 0.9659,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.39565217391304347,
643
+ "grad_norm": 5.399283928395589,
644
+ "learning_rate": 9.065062020916376e-06,
645
+ "loss": 1.2357,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.4,
650
+ "grad_norm": 4.053208344591258,
651
+ "learning_rate": 9.045084971874738e-06,
652
+ "loss": 0.8322,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.4043478260869565,
657
+ "grad_norm": 4.5221036386952065,
658
+ "learning_rate": 9.024919249708034e-06,
659
+ "loss": 1.2271,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.40869565217391307,
664
+ "grad_norm": 4.396405322035556,
665
+ "learning_rate": 9.004565794997209e-06,
666
+ "loss": 1.2211,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.41304347826086957,
671
+ "grad_norm": 5.766305829233443,
672
+ "learning_rate": 8.984025557079523e-06,
673
+ "loss": 1.0053,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.41739130434782606,
678
+ "grad_norm": 7.294349363428868,
679
+ "learning_rate": 8.963299494004292e-06,
680
+ "loss": 0.8724,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.4217391304347826,
685
+ "grad_norm": 4.194409361612639,
686
+ "learning_rate": 8.942388572488188e-06,
687
+ "loss": 0.8214,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.4260869565217391,
692
+ "grad_norm": 4.400114893491279,
693
+ "learning_rate": 8.921293767870157e-06,
694
+ "loss": 0.9179,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.43043478260869567,
699
+ "grad_norm": 4.327749965190782,
700
+ "learning_rate": 8.900016064065923e-06,
701
+ "loss": 0.9423,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.43478260869565216,
706
+ "grad_norm": 3.7672733674318923,
707
+ "learning_rate": 8.8785564535221e-06,
708
+ "loss": 0.7706,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.4391304347826087,
713
+ "grad_norm": 4.587229265026844,
714
+ "learning_rate": 8.85691593716989e-06,
715
+ "loss": 1.0521,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.4434782608695652,
720
+ "grad_norm": 4.7399456788152605,
721
+ "learning_rate": 8.835095524378413e-06,
722
+ "loss": 1.113,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.44782608695652176,
727
+ "grad_norm": 4.748572596474643,
728
+ "learning_rate": 8.81309623290762e-06,
729
+ "loss": 1.016,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.45217391304347826,
734
+ "grad_norm": 4.35044493462535,
735
+ "learning_rate": 8.790919088860815e-06,
736
+ "loss": 0.938,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.45652173913043476,
741
+ "grad_norm": 6.135478732686154,
742
+ "learning_rate": 8.768565126636806e-06,
743
+ "loss": 1.0994,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.4608695652173913,
748
+ "grad_norm": 5.0140695274375044,
749
+ "learning_rate": 8.746035388881655e-06,
750
+ "loss": 0.9525,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.4652173913043478,
755
+ "grad_norm": 6.877052897641167,
756
+ "learning_rate": 8.723330926440045e-06,
757
+ "loss": 1.3073,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.46956521739130436,
762
+ "grad_norm": 4.874346220646042,
763
+ "learning_rate": 8.70045279830626e-06,
764
+ "loss": 1.0389,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.47391304347826085,
769
+ "grad_norm": 5.491112012407043,
770
+ "learning_rate": 8.677402071574806e-06,
771
+ "loss": 1.0662,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.4782608695652174,
776
+ "grad_norm": 3.9941253187232255,
777
+ "learning_rate": 8.65417982139062e-06,
778
+ "loss": 0.8443,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.4826086956521739,
783
+ "grad_norm": 4.116069944435131,
784
+ "learning_rate": 8.630787130898943e-06,
785
+ "loss": 0.9891,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.48695652173913045,
790
+ "grad_norm": 7.375780950448022,
791
+ "learning_rate": 8.60722509119478e-06,
792
+ "loss": 1.0268,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.49130434782608695,
797
+ "grad_norm": 5.407611522252324,
798
+ "learning_rate": 8.583494801272018e-06,
799
+ "loss": 1.0829,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.4956521739130435,
804
+ "grad_norm": 7.682665869926958,
805
+ "learning_rate": 8.559597367972168e-06,
806
+ "loss": 1.1713,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.5,
811
+ "grad_norm": 4.546929461992449,
812
+ "learning_rate": 8.535533905932739e-06,
813
+ "loss": 1.2119,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.5043478260869565,
818
+ "grad_norm": 4.334900800756706,
819
+ "learning_rate": 8.511305537535238e-06,
820
+ "loss": 0.903,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.508695652173913,
825
+ "grad_norm": 4.247693351381092,
826
+ "learning_rate": 8.48691339285283e-06,
827
+ "loss": 0.7318,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.5130434782608696,
832
+ "grad_norm": 3.4954569362041688,
833
+ "learning_rate": 8.462358609597629e-06,
834
+ "loss": 0.8296,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.5173913043478261,
839
+ "grad_norm": 4.185648552138604,
840
+ "learning_rate": 8.437642333067626e-06,
841
+ "loss": 0.889,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.5217391304347826,
846
+ "grad_norm": 5.4104534875176205,
847
+ "learning_rate": 8.412765716093273e-06,
848
+ "loss": 1.2065,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.5260869565217391,
853
+ "grad_norm": 7.759317519250015,
854
+ "learning_rate": 8.387729918983706e-06,
855
+ "loss": 1.1523,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.5304347826086957,
860
+ "grad_norm": 4.913924794503322,
861
+ "learning_rate": 8.362536109472637e-06,
862
+ "loss": 0.8868,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.5347826086956522,
867
+ "grad_norm": 5.482552045601355,
868
+ "learning_rate": 8.33718546266388e-06,
869
+ "loss": 1.0169,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.5391304347826087,
874
+ "grad_norm": 5.13902992995023,
875
+ "learning_rate": 8.31167916097654e-06,
876
+ "loss": 1.2231,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.5434782608695652,
881
+ "grad_norm": 4.0633888769676245,
882
+ "learning_rate": 8.286018394089864e-06,
883
+ "loss": 0.7684,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.5478260869565217,
888
+ "grad_norm": 5.6523271968130455,
889
+ "learning_rate": 8.260204358887753e-06,
890
+ "loss": 1.0544,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.5521739130434783,
895
+ "grad_norm": 4.011682274021041,
896
+ "learning_rate": 8.234238259402936e-06,
897
+ "loss": 0.8784,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.5565217391304348,
902
+ "grad_norm": 4.690578918682304,
903
+ "learning_rate": 8.208121306760806e-06,
904
+ "loss": 1.2738,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.5608695652173913,
909
+ "grad_norm": 4.752877661083212,
910
+ "learning_rate": 8.181854719122938e-06,
911
+ "loss": 1.1752,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.5652173913043478,
916
+ "grad_norm": 5.772429945817786,
917
+ "learning_rate": 8.155439721630265e-06,
918
+ "loss": 1.0924,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.5695652173913044,
923
+ "grad_norm": 5.032445858752744,
924
+ "learning_rate": 8.128877546345932e-06,
925
+ "loss": 1.1432,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.5739130434782609,
930
+ "grad_norm": 4.337117623719157,
931
+ "learning_rate": 8.102169432197842e-06,
932
+ "loss": 0.872,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.5782608695652174,
937
+ "grad_norm": 4.592879134340706,
938
+ "learning_rate": 8.075316624920848e-06,
939
+ "loss": 1.1222,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.5826086956521739,
944
+ "grad_norm": 5.509831764805041,
945
+ "learning_rate": 8.048320376998675e-06,
946
+ "loss": 0.9484,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.5869565217391305,
951
+ "grad_norm": 5.387485381803971,
952
+ "learning_rate": 8.021181947605474e-06,
953
+ "loss": 1.0617,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.591304347826087,
958
+ "grad_norm": 5.091216954156963,
959
+ "learning_rate": 7.993902602547113e-06,
960
+ "loss": 1.1889,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.5956521739130435,
965
+ "grad_norm": 8.137531497942417,
966
+ "learning_rate": 7.966483614202127e-06,
967
+ "loss": 1.1285,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.6,
972
+ "grad_norm": 4.411736456223794,
973
+ "learning_rate": 7.938926261462366e-06,
974
+ "loss": 1.1612,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.6043478260869565,
979
+ "grad_norm": 4.433004188870439,
980
+ "learning_rate": 7.911231829673356e-06,
981
+ "loss": 0.8389,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.6086956521739131,
986
+ "grad_norm": 3.7424324012403654,
987
+ "learning_rate": 7.883401610574338e-06,
988
+ "loss": 0.8591,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.6130434782608696,
993
+ "grad_norm": 4.058208375923643,
994
+ "learning_rate": 7.855436902238018e-06,
995
+ "loss": 0.9255,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.6173913043478261,
1000
+ "grad_norm": 3.905219305942562,
1001
+ "learning_rate": 7.82733900901003e-06,
1002
+ "loss": 0.7571,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.6217391304347826,
1007
+ "grad_norm": 6.4190210494816755,
1008
+ "learning_rate": 7.799109241448091e-06,
1009
+ "loss": 0.9604,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.6260869565217392,
1014
+ "grad_norm": 5.893815264943873,
1015
+ "learning_rate": 7.770748916260875e-06,
1016
+ "loss": 1.1188,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.6304347826086957,
1021
+ "grad_norm": 4.328478295857134,
1022
+ "learning_rate": 7.742259356246594e-06,
1023
+ "loss": 1.0338,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.6347826086956522,
1028
+ "grad_norm": 6.278078595346676,
1029
+ "learning_rate": 7.71364189023131e-06,
1030
+ "loss": 1.2981,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.6391304347826087,
1035
+ "grad_norm": 4.616265041098769,
1036
+ "learning_rate": 7.68489785300694e-06,
1037
+ "loss": 1.0437,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.6434782608695652,
1042
+ "grad_norm": 4.300470639158237,
1043
+ "learning_rate": 7.656028585269017e-06,
1044
+ "loss": 0.8826,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.6478260869565218,
1049
+ "grad_norm": 5.9297699637337375,
1050
+ "learning_rate": 7.627035433554138e-06,
1051
+ "loss": 1.3544,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.6521739130434783,
1056
+ "grad_norm": 4.17949423179861,
1057
+ "learning_rate": 7.597919750177168e-06,
1058
+ "loss": 0.957,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.6565217391304348,
1063
+ "grad_norm": 6.613182767372379,
1064
+ "learning_rate": 7.5686828931681646e-06,
1065
+ "loss": 1.1804,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.6608695652173913,
1070
+ "grad_norm": 4.50795146030944,
1071
+ "learning_rate": 7.539326226209032e-06,
1072
+ "loss": 1.0273,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.6652173913043479,
1077
+ "grad_norm": 4.237568377523633,
1078
+ "learning_rate": 7.509851118569915e-06,
1079
+ "loss": 1.1271,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.6695652173913044,
1084
+ "grad_norm": 4.94502311809031,
1085
+ "learning_rate": 7.4802589450453415e-06,
1086
+ "loss": 1.059,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.6739130434782609,
1091
+ "grad_norm": 5.060394538135345,
1092
+ "learning_rate": 7.450551085890087e-06,
1093
+ "loss": 1.2174,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.6782608695652174,
1098
+ "grad_norm": 4.5942800803994945,
1099
+ "learning_rate": 7.420728926754803e-06,
1100
+ "loss": 0.9316,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.6826086956521739,
1105
+ "grad_norm": 5.51548409214014,
1106
+ "learning_rate": 7.390793858621386e-06,
1107
+ "loss": 1.0431,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.6869565217391305,
1112
+ "grad_norm": 3.9414004785606926,
1113
+ "learning_rate": 7.360747277738094e-06,
1114
+ "loss": 1.1624,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.691304347826087,
1119
+ "grad_norm": 3.925569980176714,
1120
+ "learning_rate": 7.330590585554428e-06,
1121
+ "loss": 0.9388,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.6956521739130435,
1126
+ "grad_norm": 6.115985769431068,
1127
+ "learning_rate": 7.300325188655762e-06,
1128
+ "loss": 1.0772,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.7,
1133
+ "grad_norm": 5.287208418848769,
1134
+ "learning_rate": 7.269952498697734e-06,
1135
+ "loss": 1.0588,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.7043478260869566,
1140
+ "grad_norm": 5.887954996775137,
1141
+ "learning_rate": 7.2394739323404105e-06,
1142
+ "loss": 1.2744,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.7086956521739131,
1147
+ "grad_norm": 6.220849387620703,
1148
+ "learning_rate": 7.208890911182198e-06,
1149
+ "loss": 1.2523,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.7130434782608696,
1154
+ "grad_norm": 4.763452389600567,
1155
+ "learning_rate": 7.178204861693546e-06,
1156
+ "loss": 1.0201,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.717391304347826,
1161
+ "grad_norm": 4.674538905758628,
1162
+ "learning_rate": 7.147417215150411e-06,
1163
+ "loss": 0.8982,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.7217391304347827,
1168
+ "grad_norm": 4.548799737161913,
1169
+ "learning_rate": 7.116529407567489e-06,
1170
+ "loss": 1.006,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.7260869565217392,
1175
+ "grad_norm": 4.058628527590492,
1176
+ "learning_rate": 7.085542879631253e-06,
1177
+ "loss": 0.8732,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.7304347826086957,
1182
+ "grad_norm": 5.09133766919963,
1183
+ "learning_rate": 7.054459076632742e-06,
1184
+ "loss": 0.9237,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.7347826086956522,
1189
+ "grad_norm": 6.021664548730539,
1190
+ "learning_rate": 7.0232794484001495e-06,
1191
+ "loss": 1.1508,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.7391304347826086,
1196
+ "grad_norm": 4.279359010963845,
1197
+ "learning_rate": 6.9920054492312086e-06,
1198
+ "loss": 1.2019,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.7434782608695653,
1203
+ "grad_norm": 4.037863747030915,
1204
+ "learning_rate": 6.960638537825352e-06,
1205
+ "loss": 0.8571,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.7478260869565218,
1210
+ "grad_norm": 5.617290575713176,
1211
+ "learning_rate": 6.9291801772156775e-06,
1212
+ "loss": 1.2769,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.7521739130434782,
1217
+ "grad_norm": 4.982747015022736,
1218
+ "learning_rate": 6.89763183470071e-06,
1219
+ "loss": 1.2594,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.7565217391304347,
1224
+ "grad_norm": 7.3296314150433295,
1225
+ "learning_rate": 6.865994981775958e-06,
1226
+ "loss": 1.2394,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.7608695652173914,
1231
+ "grad_norm": 4.483250761122653,
1232
+ "learning_rate": 6.834271094065284e-06,
1233
+ "loss": 1.0616,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.7652173913043478,
1238
+ "grad_norm": 4.490047299810284,
1239
+ "learning_rate": 6.802461651252073e-06,
1240
+ "loss": 1.0179,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.7695652173913043,
1245
+ "grad_norm": 5.104232165677523,
1246
+ "learning_rate": 6.770568137010226e-06,
1247
+ "loss": 1.1243,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.7739130434782608,
1252
+ "grad_norm": 5.695239573682591,
1253
+ "learning_rate": 6.738592038934946e-06,
1254
+ "loss": 1.0372,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.7782608695652173,
1259
+ "grad_norm": 6.009746162117195,
1260
+ "learning_rate": 6.706534848473353e-06,
1261
+ "loss": 1.1002,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.782608695652174,
1266
+ "grad_norm": 5.227843443809238,
1267
+ "learning_rate": 6.674398060854931e-06,
1268
+ "loss": 0.8485,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.7869565217391304,
1273
+ "grad_norm": 4.558192944344445,
1274
+ "learning_rate": 6.642183175021779e-06,
1275
+ "loss": 1.0909,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.7913043478260869,
1280
+ "grad_norm": 5.802313330340321,
1281
+ "learning_rate": 6.609891693558692e-06,
1282
+ "loss": 1.126,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.7956521739130434,
1287
+ "grad_norm": 4.506337049991959,
1288
+ "learning_rate": 6.5775251226230855e-06,
1289
+ "loss": 1.0741,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.8,
1294
+ "grad_norm": 5.074054254570715,
1295
+ "learning_rate": 6.545084971874738e-06,
1296
+ "loss": 1.3962,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.8043478260869565,
1301
+ "grad_norm": 5.103640761958443,
1302
+ "learning_rate": 6.51257275440538e-06,
1303
+ "loss": 1.3245,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.808695652173913,
1308
+ "grad_norm": 4.524106599908443,
1309
+ "learning_rate": 6.479989986668118e-06,
1310
+ "loss": 1.0462,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.8130434782608695,
1315
+ "grad_norm": 4.857171345213971,
1316
+ "learning_rate": 6.447338188406705e-06,
1317
+ "loss": 1.2675,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.8173913043478261,
1322
+ "grad_norm": 5.776473540322822,
1323
+ "learning_rate": 6.41461888258465e-06,
1324
+ "loss": 1.1843,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.8217391304347826,
1329
+ "grad_norm": 4.649197471600448,
1330
+ "learning_rate": 6.3818335953141955e-06,
1331
+ "loss": 1.1212,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.8260869565217391,
1336
+ "grad_norm": 7.588561621006084,
1337
+ "learning_rate": 6.348983855785122e-06,
1338
+ "loss": 1.4108,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.8304347826086956,
1343
+ "grad_norm": 4.686345965265658,
1344
+ "learning_rate": 6.31607119619343e-06,
1345
+ "loss": 0.9868,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.8347826086956521,
1350
+ "grad_norm": 5.022876918735578,
1351
+ "learning_rate": 6.283097151669869e-06,
1352
+ "loss": 1.0539,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.8391304347826087,
1357
+ "grad_norm": 3.849895970120205,
1358
+ "learning_rate": 6.250063260208345e-06,
1359
+ "loss": 0.9145,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.8434782608695652,
1364
+ "grad_norm": 4.3534627971660935,
1365
+ "learning_rate": 6.216971062594179e-06,
1366
+ "loss": 0.8883,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.8478260869565217,
1371
+ "grad_norm": 4.439460175336718,
1372
+ "learning_rate": 6.183822102332234e-06,
1373
+ "loss": 0.8907,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.8521739130434782,
1378
+ "grad_norm": 4.478234644239929,
1379
+ "learning_rate": 6.1506179255749335e-06,
1380
+ "loss": 1.329,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.8565217391304348,
1385
+ "grad_norm": 5.118887260326934,
1386
+ "learning_rate": 6.1173600810501355e-06,
1387
+ "loss": 1.0296,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.8608695652173913,
1392
+ "grad_norm": 4.310125134858147,
1393
+ "learning_rate": 6.084050119988905e-06,
1394
+ "loss": 1.3987,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.8652173913043478,
1399
+ "grad_norm": 4.679816132675286,
1400
+ "learning_rate": 6.050689596053151e-06,
1401
+ "loss": 1.1243,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.8695652173913043,
1406
+ "grad_norm": 5.247209880257937,
1407
+ "learning_rate": 6.0172800652631706e-06,
1408
+ "loss": 1.1461,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.8695652173913043,
1413
+ "eval_loss": 1.1071234941482544,
1414
+ "eval_runtime": 0.692,
1415
+ "eval_samples_per_second": 27.456,
1416
+ "eval_steps_per_second": 7.225,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 0.8739130434782608,
1421
+ "grad_norm": 5.25029183876397,
1422
+ "learning_rate": 5.983823085925059e-06,
1423
+ "loss": 1.1235,
1424
+ "step": 201
1425
+ },
1426
+ {
1427
+ "epoch": 0.8782608695652174,
1428
+ "grad_norm": 5.150388824412168,
1429
+ "learning_rate": 5.950320218558037e-06,
1430
+ "loss": 0.9737,
1431
+ "step": 202
1432
+ },
1433
+ {
1434
+ "epoch": 0.8826086956521739,
1435
+ "grad_norm": 5.669731078013517,
1436
+ "learning_rate": 5.916773025821662e-06,
1437
+ "loss": 1.1481,
1438
+ "step": 203
1439
+ },
1440
+ {
1441
+ "epoch": 0.8869565217391304,
1442
+ "grad_norm": 5.171543723682151,
1443
+ "learning_rate": 5.883183072442938e-06,
1444
+ "loss": 1.2084,
1445
+ "step": 204
1446
+ },
1447
+ {
1448
+ "epoch": 0.8913043478260869,
1449
+ "grad_norm": 4.226063122495129,
1450
+ "learning_rate": 5.849551925143334e-06,
1451
+ "loss": 1.0912,
1452
+ "step": 205
1453
+ },
1454
+ {
1455
+ "epoch": 0.8956521739130435,
1456
+ "grad_norm": 6.142036570826352,
1457
+ "learning_rate": 5.815881152565712e-06,
1458
+ "loss": 1.2877,
1459
+ "step": 206
1460
+ },
1461
+ {
1462
+ "epoch": 0.9,
1463
+ "grad_norm": 4.856994445363066,
1464
+ "learning_rate": 5.782172325201155e-06,
1465
+ "loss": 1.1675,
1466
+ "step": 207
1467
+ },
1468
+ {
1469
+ "epoch": 0.9043478260869565,
1470
+ "grad_norm": 5.711278071947675,
1471
+ "learning_rate": 5.7484270153157215e-06,
1472
+ "loss": 0.9163,
1473
+ "step": 208
1474
+ },
1475
+ {
1476
+ "epoch": 0.908695652173913,
1477
+ "grad_norm": 5.125121400031884,
1478
+ "learning_rate": 5.714646796877108e-06,
1479
+ "loss": 0.9048,
1480
+ "step": 209
1481
+ },
1482
+ {
1483
+ "epoch": 0.9130434782608695,
1484
+ "grad_norm": 6.4438121454828465,
1485
+ "learning_rate": 5.680833245481234e-06,
1486
+ "loss": 1.2898,
1487
+ "step": 210
1488
+ },
1489
+ {
1490
+ "epoch": 0.9173913043478261,
1491
+ "grad_norm": 5.386315060144543,
1492
+ "learning_rate": 5.646987938278753e-06,
1493
+ "loss": 1.2326,
1494
+ "step": 211
1495
+ },
1496
+ {
1497
+ "epoch": 0.9217391304347826,
1498
+ "grad_norm": 5.449628341504898,
1499
+ "learning_rate": 5.613112453901493e-06,
1500
+ "loss": 1.2061,
1501
+ "step": 212
1502
+ },
1503
+ {
1504
+ "epoch": 0.9260869565217391,
1505
+ "grad_norm": 5.075037148159339,
1506
+ "learning_rate": 5.579208372388822e-06,
1507
+ "loss": 1.1821,
1508
+ "step": 213
1509
+ },
1510
+ {
1511
+ "epoch": 0.9304347826086956,
1512
+ "grad_norm": 4.224808221337326,
1513
+ "learning_rate": 5.5452772751139496e-06,
1514
+ "loss": 1.005,
1515
+ "step": 214
1516
+ },
1517
+ {
1518
+ "epoch": 0.9347826086956522,
1519
+ "grad_norm": 4.743403110057113,
1520
+ "learning_rate": 5.511320744710171e-06,
1521
+ "loss": 1.1842,
1522
+ "step": 215
1523
+ },
1524
+ {
1525
+ "epoch": 0.9391304347826087,
1526
+ "grad_norm": 5.120152400673721,
1527
+ "learning_rate": 5.477340364997051e-06,
1528
+ "loss": 1.3129,
1529
+ "step": 216
1530
+ },
1531
+ {
1532
+ "epoch": 0.9434782608695652,
1533
+ "grad_norm": 4.210353730622817,
1534
+ "learning_rate": 5.443337720906542e-06,
1535
+ "loss": 0.8211,
1536
+ "step": 217
1537
+ },
1538
+ {
1539
+ "epoch": 0.9478260869565217,
1540
+ "grad_norm": 4.076106994907175,
1541
+ "learning_rate": 5.409314398409067e-06,
1542
+ "loss": 1.0426,
1543
+ "step": 218
1544
+ },
1545
+ {
1546
+ "epoch": 0.9521739130434783,
1547
+ "grad_norm": 3.932044910838726,
1548
+ "learning_rate": 5.375271984439541e-06,
1549
+ "loss": 0.8146,
1550
+ "step": 219
1551
+ },
1552
+ {
1553
+ "epoch": 0.9565217391304348,
1554
+ "grad_norm": 5.842198051525605,
1555
+ "learning_rate": 5.341212066823356e-06,
1556
+ "loss": 1.1587,
1557
+ "step": 220
1558
+ },
1559
+ {
1560
+ "epoch": 0.9608695652173913,
1561
+ "grad_norm": 3.432078748433599,
1562
+ "learning_rate": 5.307136234202318e-06,
1563
+ "loss": 0.8552,
1564
+ "step": 221
1565
+ },
1566
+ {
1567
+ "epoch": 0.9652173913043478,
1568
+ "grad_norm": 4.115597883450135,
1569
+ "learning_rate": 5.27304607596055e-06,
1570
+ "loss": 0.8439,
1571
+ "step": 222
1572
+ },
1573
+ {
1574
+ "epoch": 0.9695652173913043,
1575
+ "grad_norm": 5.819140393215443,
1576
+ "learning_rate": 5.238943182150361e-06,
1577
+ "loss": 1.0496,
1578
+ "step": 223
1579
+ },
1580
+ {
1581
+ "epoch": 0.9739130434782609,
1582
+ "grad_norm": 4.107409339405474,
1583
+ "learning_rate": 5.204829143418072e-06,
1584
+ "loss": 1.1575,
1585
+ "step": 224
1586
+ },
1587
+ {
1588
+ "epoch": 0.9782608695652174,
1589
+ "grad_norm": 4.22924669739053,
1590
+ "learning_rate": 5.17070555092984e-06,
1591
+ "loss": 0.8573,
1592
+ "step": 225
1593
+ },
1594
+ {
1595
+ "epoch": 0.9826086956521739,
1596
+ "grad_norm": 4.626246857070108,
1597
+ "learning_rate": 5.136573996297431e-06,
1598
+ "loss": 1.2469,
1599
+ "step": 226
1600
+ },
1601
+ {
1602
+ "epoch": 0.9869565217391304,
1603
+ "grad_norm": 4.300073044102186,
1604
+ "learning_rate": 5.102436071503983e-06,
1605
+ "loss": 0.9794,
1606
+ "step": 227
1607
+ },
1608
+ {
1609
+ "epoch": 0.991304347826087,
1610
+ "grad_norm": 5.092993167161381,
1611
+ "learning_rate": 5.068293368829755e-06,
1612
+ "loss": 0.8575,
1613
+ "step": 228
1614
+ },
1615
+ {
1616
+ "epoch": 0.9956521739130435,
1617
+ "grad_norm": 4.025989471723338,
1618
+ "learning_rate": 5.034147480777867e-06,
1619
+ "loss": 1.0591,
1620
+ "step": 229
1621
+ },
1622
+ {
1623
+ "epoch": 1.0,
1624
+ "grad_norm": 4.83648838704195,
1625
+ "learning_rate": 5e-06,
1626
+ "loss": 1.242,
1627
+ "step": 230
1628
+ },
1629
+ {
1630
+ "epoch": 1.0043478260869565,
1631
+ "grad_norm": 4.216210504756369,
1632
+ "learning_rate": 4.965852519222135e-06,
1633
+ "loss": 0.8372,
1634
+ "step": 231
1635
+ },
1636
+ {
1637
+ "epoch": 1.008695652173913,
1638
+ "grad_norm": 3.8938923888512322,
1639
+ "learning_rate": 4.931706631170246e-06,
1640
+ "loss": 0.8391,
1641
+ "step": 232
1642
+ },
1643
+ {
1644
+ "epoch": 1.0130434782608695,
1645
+ "grad_norm": 3.6618520109617654,
1646
+ "learning_rate": 4.89756392849602e-06,
1647
+ "loss": 0.7721,
1648
+ "step": 233
1649
+ },
1650
+ {
1651
+ "epoch": 1.017391304347826,
1652
+ "grad_norm": 4.597697482817842,
1653
+ "learning_rate": 4.863426003702572e-06,
1654
+ "loss": 0.7296,
1655
+ "step": 234
1656
+ },
1657
+ {
1658
+ "epoch": 1.0217391304347827,
1659
+ "grad_norm": 4.756005103416013,
1660
+ "learning_rate": 4.829294449070161e-06,
1661
+ "loss": 1.0094,
1662
+ "step": 235
1663
+ },
1664
+ {
1665
+ "epoch": 1.0260869565217392,
1666
+ "grad_norm": 3.6512711243515983,
1667
+ "learning_rate": 4.795170856581929e-06,
1668
+ "loss": 0.7659,
1669
+ "step": 236
1670
+ },
1671
+ {
1672
+ "epoch": 1.0304347826086957,
1673
+ "grad_norm": 5.138875912118083,
1674
+ "learning_rate": 4.7610568178496405e-06,
1675
+ "loss": 0.9442,
1676
+ "step": 237
1677
+ },
1678
+ {
1679
+ "epoch": 1.0347826086956522,
1680
+ "grad_norm": 3.9938128484625137,
1681
+ "learning_rate": 4.7269539240394505e-06,
1682
+ "loss": 0.8058,
1683
+ "step": 238
1684
+ },
1685
+ {
1686
+ "epoch": 1.0391304347826087,
1687
+ "grad_norm": 3.292568196808699,
1688
+ "learning_rate": 4.692863765797683e-06,
1689
+ "loss": 0.5696,
1690
+ "step": 239
1691
+ },
1692
+ {
1693
+ "epoch": 1.0434782608695652,
1694
+ "grad_norm": 5.0471572354824215,
1695
+ "learning_rate": 4.6587879331766465e-06,
1696
+ "loss": 0.7507,
1697
+ "step": 240
1698
+ },
1699
+ {
1700
+ "epoch": 1.0478260869565217,
1701
+ "grad_norm": 5.395603800188177,
1702
+ "learning_rate": 4.624728015560461e-06,
1703
+ "loss": 0.9429,
1704
+ "step": 241
1705
+ },
1706
+ {
1707
+ "epoch": 1.0521739130434782,
1708
+ "grad_norm": 5.202294544570946,
1709
+ "learning_rate": 4.5906856015909365e-06,
1710
+ "loss": 0.7721,
1711
+ "step": 242
1712
+ },
1713
+ {
1714
+ "epoch": 1.0565217391304347,
1715
+ "grad_norm": 4.440021260130221,
1716
+ "learning_rate": 4.556662279093461e-06,
1717
+ "loss": 0.8443,
1718
+ "step": 243
1719
+ },
1720
+ {
1721
+ "epoch": 1.0608695652173914,
1722
+ "grad_norm": 4.670107169987278,
1723
+ "learning_rate": 4.52265963500295e-06,
1724
+ "loss": 0.902,
1725
+ "step": 244
1726
+ },
1727
+ {
1728
+ "epoch": 1.065217391304348,
1729
+ "grad_norm": 4.68683299302712,
1730
+ "learning_rate": 4.488679255289829e-06,
1731
+ "loss": 0.9596,
1732
+ "step": 245
1733
+ },
1734
+ {
1735
+ "epoch": 1.0695652173913044,
1736
+ "grad_norm": 4.3428851224343115,
1737
+ "learning_rate": 4.454722724886051e-06,
1738
+ "loss": 0.6492,
1739
+ "step": 246
1740
+ },
1741
+ {
1742
+ "epoch": 1.0739130434782609,
1743
+ "grad_norm": 4.738745025361103,
1744
+ "learning_rate": 4.4207916276111795e-06,
1745
+ "loss": 0.8424,
1746
+ "step": 247
1747
+ },
1748
+ {
1749
+ "epoch": 1.0782608695652174,
1750
+ "grad_norm": 4.94215225366946,
1751
+ "learning_rate": 4.386887546098509e-06,
1752
+ "loss": 0.9892,
1753
+ "step": 248
1754
+ },
1755
+ {
1756
+ "epoch": 1.0826086956521739,
1757
+ "grad_norm": 4.752976214295435,
1758
+ "learning_rate": 4.353012061721249e-06,
1759
+ "loss": 0.9134,
1760
+ "step": 249
1761
+ },
1762
+ {
1763
+ "epoch": 1.0869565217391304,
1764
+ "grad_norm": 5.577514195514474,
1765
+ "learning_rate": 4.319166754518768e-06,
1766
+ "loss": 0.8252,
1767
+ "step": 250
1768
+ },
1769
+ {
1770
+ "epoch": 1.0913043478260869,
1771
+ "grad_norm": 5.239053071033857,
1772
+ "learning_rate": 4.285353203122894e-06,
1773
+ "loss": 0.7877,
1774
+ "step": 251
1775
+ },
1776
+ {
1777
+ "epoch": 1.0956521739130434,
1778
+ "grad_norm": 5.492155487456385,
1779
+ "learning_rate": 4.251572984684281e-06,
1780
+ "loss": 1.0032,
1781
+ "step": 252
1782
+ },
1783
+ {
1784
+ "epoch": 1.1,
1785
+ "grad_norm": 6.5009914716923625,
1786
+ "learning_rate": 4.217827674798845e-06,
1787
+ "loss": 1.0623,
1788
+ "step": 253
1789
+ },
1790
+ {
1791
+ "epoch": 1.1043478260869566,
1792
+ "grad_norm": 5.538994055419974,
1793
+ "learning_rate": 4.18411884743429e-06,
1794
+ "loss": 0.9584,
1795
+ "step": 254
1796
+ },
1797
+ {
1798
+ "epoch": 1.108695652173913,
1799
+ "grad_norm": 5.431155333366098,
1800
+ "learning_rate": 4.150448074856667e-06,
1801
+ "loss": 0.7825,
1802
+ "step": 255
1803
+ },
1804
+ {
1805
+ "epoch": 1.1130434782608696,
1806
+ "grad_norm": 5.2486558356133575,
1807
+ "learning_rate": 4.116816927557063e-06,
1808
+ "loss": 0.7528,
1809
+ "step": 256
1810
+ },
1811
+ {
1812
+ "epoch": 1.117391304347826,
1813
+ "grad_norm": 4.49063507819853,
1814
+ "learning_rate": 4.083226974178339e-06,
1815
+ "loss": 0.7756,
1816
+ "step": 257
1817
+ },
1818
+ {
1819
+ "epoch": 1.1217391304347826,
1820
+ "grad_norm": 5.3430479273171825,
1821
+ "learning_rate": 4.0496797814419655e-06,
1822
+ "loss": 1.0968,
1823
+ "step": 258
1824
+ },
1825
+ {
1826
+ "epoch": 1.126086956521739,
1827
+ "grad_norm": 5.6027468332575765,
1828
+ "learning_rate": 4.016176914074944e-06,
1829
+ "loss": 1.0054,
1830
+ "step": 259
1831
+ },
1832
+ {
1833
+ "epoch": 1.1304347826086956,
1834
+ "grad_norm": 4.690259306098318,
1835
+ "learning_rate": 3.982719934736832e-06,
1836
+ "loss": 0.9057,
1837
+ "step": 260
1838
+ },
1839
+ {
1840
+ "epoch": 1.134782608695652,
1841
+ "grad_norm": 5.628356552808444,
1842
+ "learning_rate": 3.949310403946849e-06,
1843
+ "loss": 0.7052,
1844
+ "step": 261
1845
+ },
1846
+ {
1847
+ "epoch": 1.1391304347826088,
1848
+ "grad_norm": 4.977719636100995,
1849
+ "learning_rate": 3.915949880011096e-06,
1850
+ "loss": 0.8225,
1851
+ "step": 262
1852
+ },
1853
+ {
1854
+ "epoch": 1.1434782608695653,
1855
+ "grad_norm": 5.49327275866134,
1856
+ "learning_rate": 3.882639918949865e-06,
1857
+ "loss": 0.9477,
1858
+ "step": 263
1859
+ },
1860
+ {
1861
+ "epoch": 1.1478260869565218,
1862
+ "grad_norm": 5.527542213642167,
1863
+ "learning_rate": 3.849382074425069e-06,
1864
+ "loss": 0.9194,
1865
+ "step": 264
1866
+ },
1867
+ {
1868
+ "epoch": 1.1521739130434783,
1869
+ "grad_norm": 4.992227724164841,
1870
+ "learning_rate": 3.816177897667767e-06,
1871
+ "loss": 0.9798,
1872
+ "step": 265
1873
+ },
1874
+ {
1875
+ "epoch": 1.1565217391304348,
1876
+ "grad_norm": 5.11306656746837,
1877
+ "learning_rate": 3.7830289374058214e-06,
1878
+ "loss": 0.7764,
1879
+ "step": 266
1880
+ },
1881
+ {
1882
+ "epoch": 1.1608695652173913,
1883
+ "grad_norm": 5.0928024270898975,
1884
+ "learning_rate": 3.749936739791656e-06,
1885
+ "loss": 0.9234,
1886
+ "step": 267
1887
+ },
1888
+ {
1889
+ "epoch": 1.1652173913043478,
1890
+ "grad_norm": 3.789308286544844,
1891
+ "learning_rate": 3.7169028483301333e-06,
1892
+ "loss": 0.7672,
1893
+ "step": 268
1894
+ },
1895
+ {
1896
+ "epoch": 1.1695652173913043,
1897
+ "grad_norm": 4.228818650876389,
1898
+ "learning_rate": 3.6839288038065736e-06,
1899
+ "loss": 0.8168,
1900
+ "step": 269
1901
+ },
1902
+ {
1903
+ "epoch": 1.1739130434782608,
1904
+ "grad_norm": 4.500357798004027,
1905
+ "learning_rate": 3.6510161442148783e-06,
1906
+ "loss": 0.9159,
1907
+ "step": 270
1908
+ },
1909
+ {
1910
+ "epoch": 1.1782608695652175,
1911
+ "grad_norm": 5.121324220749025,
1912
+ "learning_rate": 3.6181664046858045e-06,
1913
+ "loss": 0.8255,
1914
+ "step": 271
1915
+ },
1916
+ {
1917
+ "epoch": 1.182608695652174,
1918
+ "grad_norm": 3.7443446663022657,
1919
+ "learning_rate": 3.58538111741535e-06,
1920
+ "loss": 0.7073,
1921
+ "step": 272
1922
+ },
1923
+ {
1924
+ "epoch": 1.1869565217391305,
1925
+ "grad_norm": 6.278543476625317,
1926
+ "learning_rate": 3.5526618115932974e-06,
1927
+ "loss": 0.9158,
1928
+ "step": 273
1929
+ },
1930
+ {
1931
+ "epoch": 1.191304347826087,
1932
+ "grad_norm": 5.392943828219421,
1933
+ "learning_rate": 3.5200100133318836e-06,
1934
+ "loss": 0.9469,
1935
+ "step": 274
1936
+ },
1937
+ {
1938
+ "epoch": 1.1956521739130435,
1939
+ "grad_norm": 4.228287903017584,
1940
+ "learning_rate": 3.4874272455946217e-06,
1941
+ "loss": 0.627,
1942
+ "step": 275
1943
+ },
1944
+ {
1945
+ "epoch": 1.2,
1946
+ "grad_norm": 4.450970684229164,
1947
+ "learning_rate": 3.4549150281252635e-06,
1948
+ "loss": 0.7849,
1949
+ "step": 276
1950
+ },
1951
+ {
1952
+ "epoch": 1.2043478260869565,
1953
+ "grad_norm": 4.3314479272284,
1954
+ "learning_rate": 3.4224748773769166e-06,
1955
+ "loss": 0.9044,
1956
+ "step": 277
1957
+ },
1958
+ {
1959
+ "epoch": 1.208695652173913,
1960
+ "grad_norm": 3.923166515279368,
1961
+ "learning_rate": 3.39010830644131e-06,
1962
+ "loss": 0.8066,
1963
+ "step": 278
1964
+ },
1965
+ {
1966
+ "epoch": 1.2130434782608694,
1967
+ "grad_norm": 4.8315681974084805,
1968
+ "learning_rate": 3.357816824978222e-06,
1969
+ "loss": 0.7914,
1970
+ "step": 279
1971
+ },
1972
+ {
1973
+ "epoch": 1.2173913043478262,
1974
+ "grad_norm": 4.231656059812943,
1975
+ "learning_rate": 3.3256019391450696e-06,
1976
+ "loss": 0.9335,
1977
+ "step": 280
1978
+ },
1979
+ {
1980
+ "epoch": 1.2217391304347827,
1981
+ "grad_norm": 4.905463512539296,
1982
+ "learning_rate": 3.2934651515266485e-06,
1983
+ "loss": 0.9117,
1984
+ "step": 281
1985
+ },
1986
+ {
1987
+ "epoch": 1.2260869565217392,
1988
+ "grad_norm": 4.486859834816784,
1989
+ "learning_rate": 3.261407961065056e-06,
1990
+ "loss": 0.7945,
1991
+ "step": 282
1992
+ },
1993
+ {
1994
+ "epoch": 1.2304347826086957,
1995
+ "grad_norm": 4.130382202262793,
1996
+ "learning_rate": 3.2294318629897746e-06,
1997
+ "loss": 0.6501,
1998
+ "step": 283
1999
+ },
2000
+ {
2001
+ "epoch": 1.2347826086956522,
2002
+ "grad_norm": 7.414516920798354,
2003
+ "learning_rate": 3.197538348747927e-06,
2004
+ "loss": 0.6971,
2005
+ "step": 284
2006
+ },
2007
+ {
2008
+ "epoch": 1.2391304347826086,
2009
+ "grad_norm": 4.919387219394089,
2010
+ "learning_rate": 3.1657289059347184e-06,
2011
+ "loss": 0.8393,
2012
+ "step": 285
2013
+ },
2014
+ {
2015
+ "epoch": 1.2434782608695651,
2016
+ "grad_norm": 5.085078471018995,
2017
+ "learning_rate": 3.1340050182240438e-06,
2018
+ "loss": 0.879,
2019
+ "step": 286
2020
+ },
2021
+ {
2022
+ "epoch": 1.2478260869565219,
2023
+ "grad_norm": 4.865404342366212,
2024
+ "learning_rate": 3.1023681652992925e-06,
2025
+ "loss": 0.9016,
2026
+ "step": 287
2027
+ },
2028
+ {
2029
+ "epoch": 1.2521739130434781,
2030
+ "grad_norm": 5.203561181266795,
2031
+ "learning_rate": 3.070819822784323e-06,
2032
+ "loss": 0.8995,
2033
+ "step": 288
2034
+ },
2035
+ {
2036
+ "epoch": 1.2565217391304349,
2037
+ "grad_norm": 3.9445086236645532,
2038
+ "learning_rate": 3.03936146217465e-06,
2039
+ "loss": 0.6588,
2040
+ "step": 289
2041
+ },
2042
+ {
2043
+ "epoch": 1.2608695652173914,
2044
+ "grad_norm": 4.734831792245303,
2045
+ "learning_rate": 3.007994550768793e-06,
2046
+ "loss": 1.1011,
2047
+ "step": 290
2048
+ },
2049
+ {
2050
+ "epoch": 1.2652173913043478,
2051
+ "grad_norm": 6.468642207478743,
2052
+ "learning_rate": 2.976720551599852e-06,
2053
+ "loss": 1.0702,
2054
+ "step": 291
2055
+ },
2056
+ {
2057
+ "epoch": 1.2695652173913043,
2058
+ "grad_norm": 4.132341882715854,
2059
+ "learning_rate": 2.9455409233672594e-06,
2060
+ "loss": 0.8589,
2061
+ "step": 292
2062
+ },
2063
+ {
2064
+ "epoch": 1.2739130434782608,
2065
+ "grad_norm": 5.7265718722537375,
2066
+ "learning_rate": 2.914457120368748e-06,
2067
+ "loss": 0.8448,
2068
+ "step": 293
2069
+ },
2070
+ {
2071
+ "epoch": 1.2782608695652173,
2072
+ "grad_norm": 6.666921791666777,
2073
+ "learning_rate": 2.883470592432512e-06,
2074
+ "loss": 1.1018,
2075
+ "step": 294
2076
+ },
2077
+ {
2078
+ "epoch": 1.2826086956521738,
2079
+ "grad_norm": 4.411500585735134,
2080
+ "learning_rate": 2.8525827848495912e-06,
2081
+ "loss": 0.725,
2082
+ "step": 295
2083
+ },
2084
+ {
2085
+ "epoch": 1.2869565217391306,
2086
+ "grad_norm": 5.5574110326897594,
2087
+ "learning_rate": 2.8217951383064546e-06,
2088
+ "loss": 0.9542,
2089
+ "step": 296
2090
+ },
2091
+ {
2092
+ "epoch": 1.2913043478260868,
2093
+ "grad_norm": 5.224987719869292,
2094
+ "learning_rate": 2.7911090888178033e-06,
2095
+ "loss": 0.7781,
2096
+ "step": 297
2097
+ },
2098
+ {
2099
+ "epoch": 1.2956521739130435,
2100
+ "grad_norm": 5.3518345737222335,
2101
+ "learning_rate": 2.760526067659591e-06,
2102
+ "loss": 0.6704,
2103
+ "step": 298
2104
+ },
2105
+ {
2106
+ "epoch": 1.3,
2107
+ "grad_norm": 4.947204192180433,
2108
+ "learning_rate": 2.7300475013022666e-06,
2109
+ "loss": 0.7291,
2110
+ "step": 299
2111
+ },
2112
+ {
2113
+ "epoch": 1.3043478260869565,
2114
+ "grad_norm": 7.0524152170418395,
2115
+ "learning_rate": 2.6996748113442397e-06,
2116
+ "loss": 1.0302,
2117
+ "step": 300
2118
+ },
2119
+ {
2120
+ "epoch": 1.308695652173913,
2121
+ "grad_norm": 4.779238275000916,
2122
+ "learning_rate": 2.669409414445574e-06,
2123
+ "loss": 0.8353,
2124
+ "step": 301
2125
+ },
2126
+ {
2127
+ "epoch": 1.3130434782608695,
2128
+ "grad_norm": 4.458153779721889,
2129
+ "learning_rate": 2.6392527222619078e-06,
2130
+ "loss": 0.6688,
2131
+ "step": 302
2132
+ },
2133
+ {
2134
+ "epoch": 1.317391304347826,
2135
+ "grad_norm": 5.414383787323427,
2136
+ "learning_rate": 2.6092061413786158e-06,
2137
+ "loss": 0.9068,
2138
+ "step": 303
2139
+ },
2140
+ {
2141
+ "epoch": 1.3217391304347825,
2142
+ "grad_norm": 4.271753055956581,
2143
+ "learning_rate": 2.5792710732452e-06,
2144
+ "loss": 0.8414,
2145
+ "step": 304
2146
+ },
2147
+ {
2148
+ "epoch": 1.3260869565217392,
2149
+ "grad_norm": 4.9268311031946705,
2150
+ "learning_rate": 2.5494489141099155e-06,
2151
+ "loss": 0.8915,
2152
+ "step": 305
2153
+ },
2154
+ {
2155
+ "epoch": 1.3304347826086955,
2156
+ "grad_norm": 4.498489407106764,
2157
+ "learning_rate": 2.5197410549546598e-06,
2158
+ "loss": 0.8047,
2159
+ "step": 306
2160
+ },
2161
+ {
2162
+ "epoch": 1.3347826086956522,
2163
+ "grad_norm": 4.608705631074555,
2164
+ "learning_rate": 2.4901488814300855e-06,
2165
+ "loss": 0.9956,
2166
+ "step": 307
2167
+ },
2168
+ {
2169
+ "epoch": 1.3391304347826087,
2170
+ "grad_norm": 6.241343352808012,
2171
+ "learning_rate": 2.4606737737909696e-06,
2172
+ "loss": 0.9945,
2173
+ "step": 308
2174
+ },
2175
+ {
2176
+ "epoch": 1.3434782608695652,
2177
+ "grad_norm": 5.8146337347376145,
2178
+ "learning_rate": 2.431317106831836e-06,
2179
+ "loss": 1.0954,
2180
+ "step": 309
2181
+ },
2182
+ {
2183
+ "epoch": 1.3478260869565217,
2184
+ "grad_norm": 6.269349866838113,
2185
+ "learning_rate": 2.4020802498228333e-06,
2186
+ "loss": 0.9187,
2187
+ "step": 310
2188
+ },
2189
+ {
2190
+ "epoch": 1.3521739130434782,
2191
+ "grad_norm": 5.344138118127626,
2192
+ "learning_rate": 2.3729645664458637e-06,
2193
+ "loss": 0.9233,
2194
+ "step": 311
2195
+ },
2196
+ {
2197
+ "epoch": 1.3565217391304347,
2198
+ "grad_norm": 6.793872442814292,
2199
+ "learning_rate": 2.3439714147309845e-06,
2200
+ "loss": 0.834,
2201
+ "step": 312
2202
+ },
2203
+ {
2204
+ "epoch": 1.3608695652173912,
2205
+ "grad_norm": 5.476535249442108,
2206
+ "learning_rate": 2.315102146993061e-06,
2207
+ "loss": 0.8543,
2208
+ "step": 313
2209
+ },
2210
+ {
2211
+ "epoch": 1.365217391304348,
2212
+ "grad_norm": 4.791754739912514,
2213
+ "learning_rate": 2.286358109768693e-06,
2214
+ "loss": 0.8543,
2215
+ "step": 314
2216
+ },
2217
+ {
2218
+ "epoch": 1.3695652173913042,
2219
+ "grad_norm": 6.880512091585953,
2220
+ "learning_rate": 2.2577406437534055e-06,
2221
+ "loss": 0.9254,
2222
+ "step": 315
2223
+ },
2224
+ {
2225
+ "epoch": 1.373913043478261,
2226
+ "grad_norm": 4.259830242366245,
2227
+ "learning_rate": 2.229251083739127e-06,
2228
+ "loss": 0.6516,
2229
+ "step": 316
2230
+ },
2231
+ {
2232
+ "epoch": 1.3782608695652174,
2233
+ "grad_norm": 4.579389155072664,
2234
+ "learning_rate": 2.2008907585519094e-06,
2235
+ "loss": 0.7393,
2236
+ "step": 317
2237
+ },
2238
+ {
2239
+ "epoch": 1.382608695652174,
2240
+ "grad_norm": 4.458499383411305,
2241
+ "learning_rate": 2.172660990989971e-06,
2242
+ "loss": 0.8385,
2243
+ "step": 318
2244
+ },
2245
+ {
2246
+ "epoch": 1.3869565217391304,
2247
+ "grad_norm": 4.734115933791357,
2248
+ "learning_rate": 2.144563097761984e-06,
2249
+ "loss": 1.049,
2250
+ "step": 319
2251
+ },
2252
+ {
2253
+ "epoch": 1.391304347826087,
2254
+ "grad_norm": 4.9282751308580925,
2255
+ "learning_rate": 2.1165983894256647e-06,
2256
+ "loss": 0.7784,
2257
+ "step": 320
2258
+ },
2259
+ {
2260
+ "epoch": 1.3956521739130434,
2261
+ "grad_norm": 7.24308564577786,
2262
+ "learning_rate": 2.0887681703266453e-06,
2263
+ "loss": 0.7853,
2264
+ "step": 321
2265
+ },
2266
+ {
2267
+ "epoch": 1.4,
2268
+ "grad_norm": 4.7230685887420805,
2269
+ "learning_rate": 2.061073738537635e-06,
2270
+ "loss": 0.9568,
2271
+ "step": 322
2272
+ },
2273
+ {
2274
+ "epoch": 1.4043478260869566,
2275
+ "grad_norm": 5.653162369253488,
2276
+ "learning_rate": 2.0335163857978747e-06,
2277
+ "loss": 1.0086,
2278
+ "step": 323
2279
+ },
2280
+ {
2281
+ "epoch": 1.4086956521739131,
2282
+ "grad_norm": 6.308738745365633,
2283
+ "learning_rate": 2.0060973974528873e-06,
2284
+ "loss": 0.9203,
2285
+ "step": 324
2286
+ },
2287
+ {
2288
+ "epoch": 1.4130434782608696,
2289
+ "grad_norm": 4.946972886256346,
2290
+ "learning_rate": 1.978818052394528e-06,
2291
+ "loss": 0.8118,
2292
+ "step": 325
2293
+ },
2294
+ {
2295
+ "epoch": 1.4173913043478261,
2296
+ "grad_norm": 4.270030185333731,
2297
+ "learning_rate": 1.9516796230013275e-06,
2298
+ "loss": 0.6701,
2299
+ "step": 326
2300
+ },
2301
+ {
2302
+ "epoch": 1.4217391304347826,
2303
+ "grad_norm": 5.316519961902904,
2304
+ "learning_rate": 1.9246833750791526e-06,
2305
+ "loss": 0.9489,
2306
+ "step": 327
2307
+ },
2308
+ {
2309
+ "epoch": 1.4260869565217391,
2310
+ "grad_norm": 7.240701131498668,
2311
+ "learning_rate": 1.8978305678021598e-06,
2312
+ "loss": 1.1619,
2313
+ "step": 328
2314
+ },
2315
+ {
2316
+ "epoch": 1.4304347826086956,
2317
+ "grad_norm": 6.788547150323218,
2318
+ "learning_rate": 1.8711224536540678e-06,
2319
+ "loss": 1.0378,
2320
+ "step": 329
2321
+ },
2322
+ {
2323
+ "epoch": 1.434782608695652,
2324
+ "grad_norm": 4.8863708959694945,
2325
+ "learning_rate": 1.8445602783697375e-06,
2326
+ "loss": 0.7789,
2327
+ "step": 330
2328
+ },
2329
+ {
2330
+ "epoch": 1.4391304347826086,
2331
+ "grad_norm": 8.121282185270923,
2332
+ "learning_rate": 1.8181452808770638e-06,
2333
+ "loss": 0.8897,
2334
+ "step": 331
2335
+ },
2336
+ {
2337
+ "epoch": 1.4434782608695653,
2338
+ "grad_norm": 6.419797030405441,
2339
+ "learning_rate": 1.7918786932391945e-06,
2340
+ "loss": 0.7022,
2341
+ "step": 332
2342
+ },
2343
+ {
2344
+ "epoch": 1.4478260869565218,
2345
+ "grad_norm": 4.581500204447942,
2346
+ "learning_rate": 1.765761740597065e-06,
2347
+ "loss": 0.9281,
2348
+ "step": 333
2349
+ },
2350
+ {
2351
+ "epoch": 1.4521739130434783,
2352
+ "grad_norm": 6.280801935427629,
2353
+ "learning_rate": 1.739795641112248e-06,
2354
+ "loss": 0.9605,
2355
+ "step": 334
2356
+ },
2357
+ {
2358
+ "epoch": 1.4565217391304348,
2359
+ "grad_norm": 5.554923487150788,
2360
+ "learning_rate": 1.7139816059101372e-06,
2361
+ "loss": 0.7956,
2362
+ "step": 335
2363
+ },
2364
+ {
2365
+ "epoch": 1.4608695652173913,
2366
+ "grad_norm": 4.472877052002014,
2367
+ "learning_rate": 1.688320839023463e-06,
2368
+ "loss": 0.8153,
2369
+ "step": 336
2370
+ },
2371
+ {
2372
+ "epoch": 1.4652173913043478,
2373
+ "grad_norm": 4.027501863161365,
2374
+ "learning_rate": 1.662814537336122e-06,
2375
+ "loss": 0.7702,
2376
+ "step": 337
2377
+ },
2378
+ {
2379
+ "epoch": 1.4695652173913043,
2380
+ "grad_norm": 4.149319143782173,
2381
+ "learning_rate": 1.6374638905273643e-06,
2382
+ "loss": 0.6835,
2383
+ "step": 338
2384
+ },
2385
+ {
2386
+ "epoch": 1.4739130434782608,
2387
+ "grad_norm": 5.6151088300707945,
2388
+ "learning_rate": 1.6122700810162967e-06,
2389
+ "loss": 1.1026,
2390
+ "step": 339
2391
+ },
2392
+ {
2393
+ "epoch": 1.4782608695652173,
2394
+ "grad_norm": 3.9725818292391817,
2395
+ "learning_rate": 1.5872342839067305e-06,
2396
+ "loss": 0.6443,
2397
+ "step": 340
2398
+ },
2399
+ {
2400
+ "epoch": 1.482608695652174,
2401
+ "grad_norm": 4.581799363876247,
2402
+ "learning_rate": 1.5623576669323743e-06,
2403
+ "loss": 0.671,
2404
+ "step": 341
2405
+ },
2406
+ {
2407
+ "epoch": 1.4869565217391305,
2408
+ "grad_norm": 4.433468432917673,
2409
+ "learning_rate": 1.5376413904023723e-06,
2410
+ "loss": 0.8094,
2411
+ "step": 342
2412
+ },
2413
+ {
2414
+ "epoch": 1.491304347826087,
2415
+ "grad_norm": 4.724580475536117,
2416
+ "learning_rate": 1.5130866071471717e-06,
2417
+ "loss": 0.8523,
2418
+ "step": 343
2419
+ },
2420
+ {
2421
+ "epoch": 1.4956521739130435,
2422
+ "grad_norm": 4.955314264232924,
2423
+ "learning_rate": 1.4886944624647647e-06,
2424
+ "loss": 0.9123,
2425
+ "step": 344
2426
+ },
2427
+ {
2428
+ "epoch": 1.5,
2429
+ "grad_norm": 4.341935173646719,
2430
+ "learning_rate": 1.4644660940672628e-06,
2431
+ "loss": 0.8279,
2432
+ "step": 345
2433
+ },
2434
+ {
2435
+ "epoch": 1.5043478260869565,
2436
+ "grad_norm": 4.705263230712507,
2437
+ "learning_rate": 1.4404026320278318e-06,
2438
+ "loss": 0.8804,
2439
+ "step": 346
2440
+ },
2441
+ {
2442
+ "epoch": 1.508695652173913,
2443
+ "grad_norm": 4.7878663656051845,
2444
+ "learning_rate": 1.4165051987279832e-06,
2445
+ "loss": 0.9302,
2446
+ "step": 347
2447
+ },
2448
+ {
2449
+ "epoch": 1.5130434782608697,
2450
+ "grad_norm": 4.208457272887407,
2451
+ "learning_rate": 1.3927749088052218e-06,
2452
+ "loss": 0.6735,
2453
+ "step": 348
2454
+ },
2455
+ {
2456
+ "epoch": 1.517391304347826,
2457
+ "grad_norm": 4.081172566252578,
2458
+ "learning_rate": 1.3692128691010592e-06,
2459
+ "loss": 0.9032,
2460
+ "step": 349
2461
+ },
2462
+ {
2463
+ "epoch": 1.5217391304347827,
2464
+ "grad_norm": 8.29612327079371,
2465
+ "learning_rate": 1.3458201786093795e-06,
2466
+ "loss": 0.9474,
2467
+ "step": 350
2468
+ },
2469
+ {
2470
+ "epoch": 1.526086956521739,
2471
+ "grad_norm": 5.327771647949608,
2472
+ "learning_rate": 1.3225979284251955e-06,
2473
+ "loss": 0.9148,
2474
+ "step": 351
2475
+ },
2476
+ {
2477
+ "epoch": 1.5304347826086957,
2478
+ "grad_norm": 4.234324713957669,
2479
+ "learning_rate": 1.2995472016937405e-06,
2480
+ "loss": 0.5777,
2481
+ "step": 352
2482
+ },
2483
+ {
2484
+ "epoch": 1.5347826086956522,
2485
+ "grad_norm": 5.261111010281297,
2486
+ "learning_rate": 1.2766690735599569e-06,
2487
+ "loss": 0.8865,
2488
+ "step": 353
2489
+ },
2490
+ {
2491
+ "epoch": 1.5391304347826087,
2492
+ "grad_norm": 4.350004321771643,
2493
+ "learning_rate": 1.2539646111183452e-06,
2494
+ "loss": 0.5584,
2495
+ "step": 354
2496
+ },
2497
+ {
2498
+ "epoch": 1.5434782608695652,
2499
+ "grad_norm": 4.596885790867423,
2500
+ "learning_rate": 1.2314348733631958e-06,
2501
+ "loss": 0.7646,
2502
+ "step": 355
2503
+ },
2504
+ {
2505
+ "epoch": 1.5478260869565217,
2506
+ "grad_norm": 5.313822084071878,
2507
+ "learning_rate": 1.209080911139187e-06,
2508
+ "loss": 0.9251,
2509
+ "step": 356
2510
+ },
2511
+ {
2512
+ "epoch": 1.5521739130434784,
2513
+ "grad_norm": 5.737321516358368,
2514
+ "learning_rate": 1.1869037670923817e-06,
2515
+ "loss": 0.9067,
2516
+ "step": 357
2517
+ },
2518
+ {
2519
+ "epoch": 1.5565217391304347,
2520
+ "grad_norm": 4.203207552458825,
2521
+ "learning_rate": 1.1649044756215872e-06,
2522
+ "loss": 0.8872,
2523
+ "step": 358
2524
+ },
2525
+ {
2526
+ "epoch": 1.5608695652173914,
2527
+ "grad_norm": 7.6690233673067825,
2528
+ "learning_rate": 1.1430840628301093e-06,
2529
+ "loss": 0.856,
2530
+ "step": 359
2531
+ },
2532
+ {
2533
+ "epoch": 1.5652173913043477,
2534
+ "grad_norm": 5.291066270321033,
2535
+ "learning_rate": 1.1214435464779006e-06,
2536
+ "loss": 0.9335,
2537
+ "step": 360
2538
+ },
2539
+ {
2540
+ "epoch": 1.5695652173913044,
2541
+ "grad_norm": 3.8491033747854044,
2542
+ "learning_rate": 1.099983935934077e-06,
2543
+ "loss": 0.7533,
2544
+ "step": 361
2545
+ },
2546
+ {
2547
+ "epoch": 1.5739130434782609,
2548
+ "grad_norm": 4.333118783184382,
2549
+ "learning_rate": 1.0787062321298441e-06,
2550
+ "loss": 0.6399,
2551
+ "step": 362
2552
+ },
2553
+ {
2554
+ "epoch": 1.5782608695652174,
2555
+ "grad_norm": 4.795712560428133,
2556
+ "learning_rate": 1.0576114275118132e-06,
2557
+ "loss": 0.9435,
2558
+ "step": 363
2559
+ },
2560
+ {
2561
+ "epoch": 1.5826086956521739,
2562
+ "grad_norm": 4.245101137061006,
2563
+ "learning_rate": 1.0367005059957097e-06,
2564
+ "loss": 0.8294,
2565
+ "step": 364
2566
+ },
2567
+ {
2568
+ "epoch": 1.5869565217391304,
2569
+ "grad_norm": 6.787501808362482,
2570
+ "learning_rate": 1.0159744429204776e-06,
2571
+ "loss": 0.8276,
2572
+ "step": 365
2573
+ },
2574
+ {
2575
+ "epoch": 1.591304347826087,
2576
+ "grad_norm": 4.770641940975471,
2577
+ "learning_rate": 9.954342050027922e-07,
2578
+ "loss": 1.0012,
2579
+ "step": 366
2580
+ },
2581
+ {
2582
+ "epoch": 1.5956521739130434,
2583
+ "grad_norm": 4.295690689860451,
2584
+ "learning_rate": 9.75080750291965e-07,
2585
+ "loss": 0.8968,
2586
+ "step": 367
2587
+ },
2588
+ {
2589
+ "epoch": 1.6,
2590
+ "grad_norm": 4.710700632869586,
2591
+ "learning_rate": 9.549150281252633e-07,
2592
+ "loss": 0.8566,
2593
+ "step": 368
2594
+ },
2595
+ {
2596
+ "epoch": 1.6043478260869564,
2597
+ "grad_norm": 5.041610185769471,
2598
+ "learning_rate": 9.349379790836243e-07,
2599
+ "loss": 0.9576,
2600
+ "step": 369
2601
+ },
2602
+ {
2603
+ "epoch": 1.608695652173913,
2604
+ "grad_norm": 4.886914714718028,
2605
+ "learning_rate": 9.151505349477901e-07,
2606
+ "loss": 0.8896,
2607
+ "step": 370
2608
+ },
2609
+ {
2610
+ "epoch": 1.6130434782608696,
2611
+ "grad_norm": 4.341261416957616,
2612
+ "learning_rate": 8.955536186548425e-07,
2613
+ "loss": 0.8589,
2614
+ "step": 371
2615
+ },
2616
+ {
2617
+ "epoch": 1.617391304347826,
2618
+ "grad_norm": 4.731466474377154,
2619
+ "learning_rate": 8.761481442551573e-07,
2620
+ "loss": 0.7389,
2621
+ "step": 372
2622
+ },
2623
+ {
2624
+ "epoch": 1.6217391304347826,
2625
+ "grad_norm": 4.590158266819044,
2626
+ "learning_rate": 8.569350168697705e-07,
2627
+ "loss": 0.9191,
2628
+ "step": 373
2629
+ },
2630
+ {
2631
+ "epoch": 1.626086956521739,
2632
+ "grad_norm": 7.243806400252168,
2633
+ "learning_rate": 8.379151326481588e-07,
2634
+ "loss": 0.9844,
2635
+ "step": 374
2636
+ },
2637
+ {
2638
+ "epoch": 1.6304347826086958,
2639
+ "grad_norm": 5.861674329746273,
2640
+ "learning_rate": 8.19089378726447e-07,
2641
+ "loss": 0.9641,
2642
+ "step": 375
2643
+ },
2644
+ {
2645
+ "epoch": 1.634782608695652,
2646
+ "grad_norm": 4.95365217608248,
2647
+ "learning_rate": 8.004586331860176e-07,
2648
+ "loss": 0.693,
2649
+ "step": 376
2650
+ },
2651
+ {
2652
+ "epoch": 1.6391304347826088,
2653
+ "grad_norm": 4.526749278592604,
2654
+ "learning_rate": 7.820237650125711e-07,
2655
+ "loss": 0.8997,
2656
+ "step": 377
2657
+ },
2658
+ {
2659
+ "epoch": 1.643478260869565,
2660
+ "grad_norm": 5.506162213688076,
2661
+ "learning_rate": 7.637856340555822e-07,
2662
+ "loss": 0.9602,
2663
+ "step": 378
2664
+ },
2665
+ {
2666
+ "epoch": 1.6478260869565218,
2667
+ "grad_norm": 6.621539745977003,
2668
+ "learning_rate": 7.457450909881969e-07,
2669
+ "loss": 0.9661,
2670
+ "step": 379
2671
+ },
2672
+ {
2673
+ "epoch": 1.6521739130434783,
2674
+ "grad_norm": 5.311134098362201,
2675
+ "learning_rate": 7.279029772675572e-07,
2676
+ "loss": 0.7581,
2677
+ "step": 380
2678
+ },
2679
+ {
2680
+ "epoch": 1.6565217391304348,
2681
+ "grad_norm": 5.404987205899709,
2682
+ "learning_rate": 7.102601250955526e-07,
2683
+ "loss": 1.0387,
2684
+ "step": 381
2685
+ },
2686
+ {
2687
+ "epoch": 1.6608695652173913,
2688
+ "grad_norm": 5.607132013334533,
2689
+ "learning_rate": 6.928173573800007e-07,
2690
+ "loss": 0.8253,
2691
+ "step": 382
2692
+ },
2693
+ {
2694
+ "epoch": 1.6652173913043478,
2695
+ "grad_norm": 3.8887411796045765,
2696
+ "learning_rate": 6.755754876962711e-07,
2697
+ "loss": 0.7812,
2698
+ "step": 383
2699
+ },
2700
+ {
2701
+ "epoch": 1.6695652173913045,
2702
+ "grad_norm": 4.38500972573999,
2703
+ "learning_rate": 6.585353202493322e-07,
2704
+ "loss": 0.8385,
2705
+ "step": 384
2706
+ },
2707
+ {
2708
+ "epoch": 1.6739130434782608,
2709
+ "grad_norm": 4.22326334047886,
2710
+ "learning_rate": 6.416976498362432e-07,
2711
+ "loss": 0.8158,
2712
+ "step": 385
2713
+ },
2714
+ {
2715
+ "epoch": 1.6782608695652175,
2716
+ "grad_norm": 4.669387960806148,
2717
+ "learning_rate": 6.250632618090868e-07,
2718
+ "loss": 0.743,
2719
+ "step": 386
2720
+ },
2721
+ {
2722
+ "epoch": 1.6826086956521737,
2723
+ "grad_norm": 4.244784446307822,
2724
+ "learning_rate": 6.086329320383311e-07,
2725
+ "loss": 0.8247,
2726
+ "step": 387
2727
+ },
2728
+ {
2729
+ "epoch": 1.6869565217391305,
2730
+ "grad_norm": 5.931045953196883,
2731
+ "learning_rate": 5.924074268766422e-07,
2732
+ "loss": 0.9462,
2733
+ "step": 388
2734
+ },
2735
+ {
2736
+ "epoch": 1.691304347826087,
2737
+ "grad_norm": 4.351961395805549,
2738
+ "learning_rate": 5.763875031231464e-07,
2739
+ "loss": 0.7075,
2740
+ "step": 389
2741
+ },
2742
+ {
2743
+ "epoch": 1.6956521739130435,
2744
+ "grad_norm": 5.872835040621407,
2745
+ "learning_rate": 5.60573907988124e-07,
2746
+ "loss": 0.9472,
2747
+ "step": 390
2748
+ },
2749
+ {
2750
+ "epoch": 1.7,
2751
+ "grad_norm": 4.32286737102296,
2752
+ "learning_rate": 5.449673790581611e-07,
2753
+ "loss": 0.8564,
2754
+ "step": 391
2755
+ },
2756
+ {
2757
+ "epoch": 1.7043478260869565,
2758
+ "grad_norm": 4.428233510720095,
2759
+ "learning_rate": 5.295686442617442e-07,
2760
+ "loss": 0.5747,
2761
+ "step": 392
2762
+ },
2763
+ {
2764
+ "epoch": 1.7086956521739132,
2765
+ "grad_norm": 4.78621214443424,
2766
+ "learning_rate": 5.143784218353104e-07,
2767
+ "loss": 0.8275,
2768
+ "step": 393
2769
+ },
2770
+ {
2771
+ "epoch": 1.7130434782608694,
2772
+ "grad_norm": 4.8940583496231325,
2773
+ "learning_rate": 4.993974202897456e-07,
2774
+ "loss": 0.9133,
2775
+ "step": 394
2776
+ },
2777
+ {
2778
+ "epoch": 1.7173913043478262,
2779
+ "grad_norm": 5.069941366896355,
2780
+ "learning_rate": 4.846263383773364e-07,
2781
+ "loss": 0.8795,
2782
+ "step": 395
2783
+ },
2784
+ {
2785
+ "epoch": 1.7217391304347827,
2786
+ "grad_norm": 5.630921299492473,
2787
+ "learning_rate": 4.7006586505918273e-07,
2788
+ "loss": 0.7673,
2789
+ "step": 396
2790
+ },
2791
+ {
2792
+ "epoch": 1.7260869565217392,
2793
+ "grad_norm": 5.967852102423533,
2794
+ "learning_rate": 4.557166794730572e-07,
2795
+ "loss": 0.8222,
2796
+ "step": 397
2797
+ },
2798
+ {
2799
+ "epoch": 1.7304347826086957,
2800
+ "grad_norm": 4.348230859812264,
2801
+ "learning_rate": 4.4157945090173294e-07,
2802
+ "loss": 0.8417,
2803
+ "step": 398
2804
+ },
2805
+ {
2806
+ "epoch": 1.7347826086956522,
2807
+ "grad_norm": 5.28192214413304,
2808
+ "learning_rate": 4.276548387417656e-07,
2809
+ "loss": 1.2644,
2810
+ "step": 399
2811
+ },
2812
+ {
2813
+ "epoch": 1.7391304347826086,
2814
+ "grad_norm": 4.116713556434484,
2815
+ "learning_rate": 4.139434924727359e-07,
2816
+ "loss": 0.6251,
2817
+ "step": 400
2818
+ },
2819
+ {
2820
+ "epoch": 1.7391304347826086,
2821
+ "eval_loss": 1.1194324493408203,
2822
+ "eval_runtime": 0.6846,
2823
+ "eval_samples_per_second": 27.752,
2824
+ "eval_steps_per_second": 7.303,
2825
+ "step": 400
2826
+ },
2827
+ {
2828
+ "epoch": 1.7434782608695651,
2829
+ "grad_norm": 4.750712704430743,
2830
+ "learning_rate": 4.004460516269554e-07,
2831
+ "loss": 0.9746,
2832
+ "step": 401
2833
+ },
2834
+ {
2835
+ "epoch": 1.7478260869565219,
2836
+ "grad_norm": 4.533512150086533,
2837
+ "learning_rate": 3.8716314575964197e-07,
2838
+ "loss": 0.8921,
2839
+ "step": 402
2840
+ },
2841
+ {
2842
+ "epoch": 1.7521739130434781,
2843
+ "grad_norm": 4.980283008123122,
2844
+ "learning_rate": 3.740953944195497e-07,
2845
+ "loss": 0.9338,
2846
+ "step": 403
2847
+ },
2848
+ {
2849
+ "epoch": 1.7565217391304349,
2850
+ "grad_norm": 3.807887143061497,
2851
+ "learning_rate": 3.612434071200771e-07,
2852
+ "loss": 0.5685,
2853
+ "step": 404
2854
+ },
2855
+ {
2856
+ "epoch": 1.7608695652173914,
2857
+ "grad_norm": 4.56766041784252,
2858
+ "learning_rate": 3.486077833108342e-07,
2859
+ "loss": 0.8099,
2860
+ "step": 405
2861
+ },
2862
+ {
2863
+ "epoch": 1.7652173913043478,
2864
+ "grad_norm": 4.771266830328097,
2865
+ "learning_rate": 3.361891123496824e-07,
2866
+ "loss": 0.7885,
2867
+ "step": 406
2868
+ },
2869
+ {
2870
+ "epoch": 1.7695652173913043,
2871
+ "grad_norm": 4.397479299839718,
2872
+ "learning_rate": 3.2398797347524656e-07,
2873
+ "loss": 0.7777,
2874
+ "step": 407
2875
+ },
2876
+ {
2877
+ "epoch": 1.7739130434782608,
2878
+ "grad_norm": 4.243466795854175,
2879
+ "learning_rate": 3.1200493577989875e-07,
2880
+ "loss": 0.6199,
2881
+ "step": 408
2882
+ },
2883
+ {
2884
+ "epoch": 1.7782608695652173,
2885
+ "grad_norm": 4.564791133954276,
2886
+ "learning_rate": 3.002405581832135e-07,
2887
+ "loss": 0.5828,
2888
+ "step": 409
2889
+ },
2890
+ {
2891
+ "epoch": 1.7826086956521738,
2892
+ "grad_norm": 3.7334263643291576,
2893
+ "learning_rate": 2.88695389405898e-07,
2894
+ "loss": 0.7514,
2895
+ "step": 410
2896
+ },
2897
+ {
2898
+ "epoch": 1.7869565217391306,
2899
+ "grad_norm": 4.119087519286901,
2900
+ "learning_rate": 2.7736996794419767e-07,
2901
+ "loss": 0.8881,
2902
+ "step": 411
2903
+ },
2904
+ {
2905
+ "epoch": 1.7913043478260868,
2906
+ "grad_norm": 6.097981908549218,
2907
+ "learning_rate": 2.662648220447811e-07,
2908
+ "loss": 0.8771,
2909
+ "step": 412
2910
+ },
2911
+ {
2912
+ "epoch": 1.7956521739130435,
2913
+ "grad_norm": 4.479272318801292,
2914
+ "learning_rate": 2.5538046968010097e-07,
2915
+ "loss": 0.8271,
2916
+ "step": 413
2917
+ },
2918
+ {
2919
+ "epoch": 1.8,
2920
+ "grad_norm": 4.116069595970663,
2921
+ "learning_rate": 2.447174185242324e-07,
2922
+ "loss": 1.0165,
2923
+ "step": 414
2924
+ },
2925
+ {
2926
+ "epoch": 1.8043478260869565,
2927
+ "grad_norm": 5.271817339029972,
2928
+ "learning_rate": 2.3427616592919587e-07,
2929
+ "loss": 0.8413,
2930
+ "step": 415
2931
+ },
2932
+ {
2933
+ "epoch": 1.808695652173913,
2934
+ "grad_norm": 4.683763047016193,
2935
+ "learning_rate": 2.240571989017598e-07,
2936
+ "loss": 0.8756,
2937
+ "step": 416
2938
+ },
2939
+ {
2940
+ "epoch": 1.8130434782608695,
2941
+ "grad_norm": 3.809333375940968,
2942
+ "learning_rate": 2.1406099408072256e-07,
2943
+ "loss": 0.6692,
2944
+ "step": 417
2945
+ },
2946
+ {
2947
+ "epoch": 1.8173913043478263,
2948
+ "grad_norm": 4.04512373447352,
2949
+ "learning_rate": 2.0428801771468388e-07,
2950
+ "loss": 0.6309,
2951
+ "step": 418
2952
+ },
2953
+ {
2954
+ "epoch": 1.8217391304347825,
2955
+ "grad_norm": 5.625745627847707,
2956
+ "learning_rate": 1.947387256402966e-07,
2957
+ "loss": 0.8685,
2958
+ "step": 419
2959
+ },
2960
+ {
2961
+ "epoch": 1.8260869565217392,
2962
+ "grad_norm": 4.630347980297652,
2963
+ "learning_rate": 1.8541356326100436e-07,
2964
+ "loss": 0.8765,
2965
+ "step": 420
2966
+ },
2967
+ {
2968
+ "epoch": 1.8304347826086955,
2969
+ "grad_norm": 5.89380885603424,
2970
+ "learning_rate": 1.7631296552626687e-07,
2971
+ "loss": 0.8582,
2972
+ "step": 421
2973
+ },
2974
+ {
2975
+ "epoch": 1.8347826086956522,
2976
+ "grad_norm": 4.110239210371528,
2977
+ "learning_rate": 1.6743735691127639e-07,
2978
+ "loss": 0.7613,
2979
+ "step": 422
2980
+ },
2981
+ {
2982
+ "epoch": 1.8391304347826087,
2983
+ "grad_norm": 6.988812214917044,
2984
+ "learning_rate": 1.5878715139715395e-07,
2985
+ "loss": 0.8236,
2986
+ "step": 423
2987
+ },
2988
+ {
2989
+ "epoch": 1.8434782608695652,
2990
+ "grad_norm": 5.013917155215263,
2991
+ "learning_rate": 1.5036275245164377e-07,
2992
+ "loss": 1.0084,
2993
+ "step": 424
2994
+ },
2995
+ {
2996
+ "epoch": 1.8478260869565217,
2997
+ "grad_norm": 4.950419634836273,
2998
+ "learning_rate": 1.4216455301029274e-07,
2999
+ "loss": 0.9447,
3000
+ "step": 425
3001
+ },
3002
+ {
3003
+ "epoch": 1.8521739130434782,
3004
+ "grad_norm": 6.449563364690532,
3005
+ "learning_rate": 1.341929354581234e-07,
3006
+ "loss": 0.7521,
3007
+ "step": 426
3008
+ },
3009
+ {
3010
+ "epoch": 1.856521739130435,
3011
+ "grad_norm": 4.407548333194476,
3012
+ "learning_rate": 1.2644827161179763e-07,
3013
+ "loss": 0.9034,
3014
+ "step": 427
3015
+ },
3016
+ {
3017
+ "epoch": 1.8608695652173912,
3018
+ "grad_norm": 5.596107015498274,
3019
+ "learning_rate": 1.1893092270227724e-07,
3020
+ "loss": 0.7957,
3021
+ "step": 428
3022
+ },
3023
+ {
3024
+ "epoch": 1.865217391304348,
3025
+ "grad_norm": 4.526553633202143,
3026
+ "learning_rate": 1.1164123935797189e-07,
3027
+ "loss": 0.7332,
3028
+ "step": 429
3029
+ },
3030
+ {
3031
+ "epoch": 1.8695652173913042,
3032
+ "grad_norm": 3.685995073958794,
3033
+ "learning_rate": 1.0457956158838545e-07,
3034
+ "loss": 0.756,
3035
+ "step": 430
3036
+ },
3037
+ {
3038
+ "epoch": 1.873913043478261,
3039
+ "grad_norm": 4.933759469487385,
3040
+ "learning_rate": 9.774621876825985e-08,
3041
+ "loss": 0.7145,
3042
+ "step": 431
3043
+ },
3044
+ {
3045
+ "epoch": 1.8782608695652174,
3046
+ "grad_norm": 4.949634016558405,
3047
+ "learning_rate": 9.114152962220734e-08,
3048
+ "loss": 0.7814,
3049
+ "step": 432
3050
+ },
3051
+ {
3052
+ "epoch": 1.882608695652174,
3053
+ "grad_norm": 6.341878107588485,
3054
+ "learning_rate": 8.476580220984854e-08,
3055
+ "loss": 0.8234,
3056
+ "step": 433
3057
+ },
3058
+ {
3059
+ "epoch": 1.8869565217391304,
3060
+ "grad_norm": 5.2125201778440164,
3061
+ "learning_rate": 7.861933391144272e-08,
3062
+ "loss": 0.9901,
3063
+ "step": 434
3064
+ },
3065
+ {
3066
+ "epoch": 1.891304347826087,
3067
+ "grad_norm": 4.781060315790717,
3068
+ "learning_rate": 7.270241141401568e-08,
3069
+ "loss": 0.8422,
3070
+ "step": 435
3071
+ },
3072
+ {
3073
+ "epoch": 1.8956521739130436,
3074
+ "grad_norm": 5.515367131841009,
3075
+ "learning_rate": 6.701531069799039e-08,
3076
+ "loss": 1.0083,
3077
+ "step": 436
3078
+ },
3079
+ {
3080
+ "epoch": 1.9,
3081
+ "grad_norm": 4.261572736835991,
3082
+ "learning_rate": 6.15582970243117e-08,
3083
+ "loss": 0.7593,
3084
+ "step": 437
3085
+ },
3086
+ {
3087
+ "epoch": 1.9043478260869566,
3088
+ "grad_norm": 5.365964044287966,
3089
+ "learning_rate": 5.633162492207633e-08,
3090
+ "loss": 1.1215,
3091
+ "step": 438
3092
+ },
3093
+ {
3094
+ "epoch": 1.908695652173913,
3095
+ "grad_norm": 5.43150589545604,
3096
+ "learning_rate": 5.133553817665948e-08,
3097
+ "loss": 0.8688,
3098
+ "step": 439
3099
+ },
3100
+ {
3101
+ "epoch": 1.9130434782608696,
3102
+ "grad_norm": 5.122983980225534,
3103
+ "learning_rate": 4.657026981834623e-08,
3104
+ "loss": 0.8473,
3105
+ "step": 440
3106
+ },
3107
+ {
3108
+ "epoch": 1.9173913043478261,
3109
+ "grad_norm": 4.192373569277155,
3110
+ "learning_rate": 4.203604211145851e-08,
3111
+ "loss": 0.8863,
3112
+ "step": 441
3113
+ },
3114
+ {
3115
+ "epoch": 1.9217391304347826,
3116
+ "grad_norm": 4.1082110004364125,
3117
+ "learning_rate": 3.773306654399234e-08,
3118
+ "loss": 0.7124,
3119
+ "step": 442
3120
+ },
3121
+ {
3122
+ "epoch": 1.9260869565217391,
3123
+ "grad_norm": 6.187076737130443,
3124
+ "learning_rate": 3.366154381775011e-08,
3125
+ "loss": 0.9662,
3126
+ "step": 443
3127
+ },
3128
+ {
3129
+ "epoch": 1.9304347826086956,
3130
+ "grad_norm": 5.326278477646107,
3131
+ "learning_rate": 2.9821663838981994e-08,
3132
+ "loss": 0.9213,
3133
+ "step": 444
3134
+ },
3135
+ {
3136
+ "epoch": 1.9347826086956523,
3137
+ "grad_norm": 4.7780556662892435,
3138
+ "learning_rate": 2.6213605709525803e-08,
3139
+ "loss": 0.7552,
3140
+ "step": 445
3141
+ },
3142
+ {
3143
+ "epoch": 1.9391304347826086,
3144
+ "grad_norm": 7.047291711279684,
3145
+ "learning_rate": 2.283753771845587e-08,
3146
+ "loss": 0.7865,
3147
+ "step": 446
3148
+ },
3149
+ {
3150
+ "epoch": 1.9434782608695653,
3151
+ "grad_norm": 4.6767051572965235,
3152
+ "learning_rate": 1.969361733423103e-08,
3153
+ "loss": 0.9703,
3154
+ "step": 447
3155
+ },
3156
+ {
3157
+ "epoch": 1.9478260869565216,
3158
+ "grad_norm": 5.0168213443167815,
3159
+ "learning_rate": 1.6781991197352133e-08,
3160
+ "loss": 0.8206,
3161
+ "step": 448
3162
+ },
3163
+ {
3164
+ "epoch": 1.9521739130434783,
3165
+ "grad_norm": 4.471280458207543,
3166
+ "learning_rate": 1.4102795113520307e-08,
3167
+ "loss": 0.7311,
3168
+ "step": 449
3169
+ },
3170
+ {
3171
+ "epoch": 1.9565217391304348,
3172
+ "grad_norm": 4.125815678664824,
3173
+ "learning_rate": 1.1656154047303691e-08,
3174
+ "loss": 0.8387,
3175
+ "step": 450
3176
+ },
3177
+ {
3178
+ "epoch": 1.9608695652173913,
3179
+ "grad_norm": 4.248347988625125,
3180
+ "learning_rate": 9.442182116309872e-09,
3181
+ "loss": 0.8165,
3182
+ "step": 451
3183
+ },
3184
+ {
3185
+ "epoch": 1.9652173913043478,
3186
+ "grad_norm": 5.177105608031232,
3187
+ "learning_rate": 7.460982585860144e-09,
3188
+ "loss": 0.7981,
3189
+ "step": 452
3190
+ },
3191
+ {
3192
+ "epoch": 1.9695652173913043,
3193
+ "grad_norm": 4.2661734304447805,
3194
+ "learning_rate": 5.712647864176135e-09,
3195
+ "loss": 0.7996,
3196
+ "step": 453
3197
+ },
3198
+ {
3199
+ "epoch": 1.973913043478261,
3200
+ "grad_norm": 4.705862652575779,
3201
+ "learning_rate": 4.197259498067707e-09,
3202
+ "loss": 1.0172,
3203
+ "step": 454
3204
+ },
3205
+ {
3206
+ "epoch": 1.9782608695652173,
3207
+ "grad_norm": 4.622038934587038,
3208
+ "learning_rate": 2.9148881691298812e-09,
3209
+ "loss": 0.8608,
3210
+ "step": 455
3211
+ },
3212
+ {
3213
+ "epoch": 1.982608695652174,
3214
+ "grad_norm": 7.3773081065570425,
3215
+ "learning_rate": 1.865593690446588e-09,
3216
+ "loss": 0.7651,
3217
+ "step": 456
3218
+ },
3219
+ {
3220
+ "epoch": 1.9869565217391303,
3221
+ "grad_norm": 4.675468255772506,
3222
+ "learning_rate": 1.0494250038006747e-09,
3223
+ "loss": 0.8231,
3224
+ "step": 457
3225
+ },
3226
+ {
3227
+ "epoch": 1.991304347826087,
3228
+ "grad_norm": 4.526343700427679,
3229
+ "learning_rate": 4.664201773896259e-10,
3230
+ "loss": 0.5551,
3231
+ "step": 458
3232
+ },
3233
+ {
3234
+ "epoch": 1.9956521739130435,
3235
+ "grad_norm": 6.050272891322758,
3236
+ "learning_rate": 1.1660640405308787e-10,
3237
+ "loss": 0.7338,
3238
+ "step": 459
3239
+ },
3240
+ {
3241
+ "epoch": 2.0,
3242
+ "grad_norm": 7.04327412597719,
3243
+ "learning_rate": 0.0,
3244
+ "loss": 1.1184,
3245
+ "step": 460
3246
+ },
3247
+ {
3248
+ "epoch": 2.0,
3249
+ "step": 460,
3250
+ "total_flos": 1314917400576.0,
3251
+ "train_loss": 0.9610995156609494,
3252
+ "train_runtime": 290.1657,
3253
+ "train_samples_per_second": 12.682,
3254
+ "train_steps_per_second": 1.585
3255
+ }
3256
+ ],
3257
+ "logging_steps": 1,
3258
+ "max_steps": 460,
3259
+ "num_input_tokens_seen": 0,
3260
+ "num_train_epochs": 2,
3261
+ "save_steps": 5000,
3262
+ "stateful_callbacks": {
3263
+ "TrainerControl": {
3264
+ "args": {
3265
+ "should_epoch_stop": false,
3266
+ "should_evaluate": false,
3267
+ "should_log": false,
3268
+ "should_save": true,
3269
+ "should_training_stop": true
3270
+ },
3271
+ "attributes": {}
3272
+ }
3273
+ },
3274
+ "total_flos": 1314917400576.0,
3275
+ "train_batch_size": 2,
3276
+ "trial_name": null,
3277
+ "trial_params": null
3278
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8ec1434cf4276131aff0aeee3f2fcd9e64d83de39465fb7e7d1ba7bbf533c2
3
+ size 7160
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