cutelemonlili commited on
Commit
89dedc6
·
verified ·
1 Parent(s): cb11205

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
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.151201993227005,
4
+ "eval_runtime": 0.694,
5
+ "eval_samples_per_second": 24.496,
6
+ "eval_steps_per_second": 7.205,
7
+ "total_flos": 957358891008.0,
8
+ "train_loss": 0.20337393274982868,
9
+ "train_runtime": 258.6726,
10
+ "train_samples_per_second": 12.688,
11
+ "train_steps_per_second": 1.593
12
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 14,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 151936
29
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.151201993227005,
4
+ "eval_runtime": 0.694,
5
+ "eval_samples_per_second": 24.496,
6
+ "eval_steps_per_second": 7.205
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:c7685eeeb698cda3e7d9bde502de0033420ce18f93dd78d93a3605f870289d70
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": 957358891008.0,
4
+ "train_loss": 0.20337393274982868,
5
+ "train_runtime": 258.6726,
6
+ "train_samples_per_second": 12.688,
7
+ "train_steps_per_second": 1.593
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,413 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 412, "loss": 0.1339, "lr": 9.999854640567861e-06, "epoch": 0.0048543689320388345, "percentage": 0.24, "elapsed_time": "0:00:01", "remaining_time": "0:12:58"}
2
+ {"current_steps": 2, "total_steps": 412, "loss": 0.1354, "lr": 9.999418570723189e-06, "epoch": 0.009708737864077669, "percentage": 0.49, "elapsed_time": "0:00:05", "remaining_time": "0:20:27"}
3
+ {"current_steps": 3, "total_steps": 412, "loss": 0.2009, "lr": 9.998691815820732e-06, "epoch": 0.014563106796116505, "percentage": 0.73, "elapsed_time": "0:00:06", "remaining_time": "0:14:58"}
4
+ {"current_steps": 4, "total_steps": 412, "loss": 0.1982, "lr": 9.997674418116759e-06, "epoch": 0.019417475728155338, "percentage": 0.97, "elapsed_time": "0:00:07", "remaining_time": "0:12:14"}
5
+ {"current_steps": 5, "total_steps": 412, "loss": 0.1883, "lr": 9.996366436766612e-06, "epoch": 0.024271844660194174, "percentage": 1.21, "elapsed_time": "0:00:07", "remaining_time": "0:10:36"}
6
+ {"current_steps": 6, "total_steps": 412, "loss": 0.188, "lr": 9.994767947821261e-06, "epoch": 0.02912621359223301, "percentage": 1.46, "elapsed_time": "0:00:08", "remaining_time": "0:09:30"}
7
+ {"current_steps": 7, "total_steps": 412, "loss": 0.1602, "lr": 9.992879044222887e-06, "epoch": 0.03398058252427184, "percentage": 1.7, "elapsed_time": "0:00:09", "remaining_time": "0:08:42"}
8
+ {"current_steps": 8, "total_steps": 412, "loss": 0.1716, "lr": 9.99069983579947e-06, "epoch": 0.038834951456310676, "percentage": 1.94, "elapsed_time": "0:00:09", "remaining_time": "0:08:06"}
9
+ {"current_steps": 9, "total_steps": 412, "loss": 0.1584, "lr": 9.988230449258409e-06, "epoch": 0.043689320388349516, "percentage": 2.18, "elapsed_time": "0:00:10", "remaining_time": "0:07:38"}
10
+ {"current_steps": 10, "total_steps": 412, "loss": 0.1338, "lr": 9.985471028179155e-06, "epoch": 0.04854368932038835, "percentage": 2.43, "elapsed_time": "0:00:10", "remaining_time": "0:07:15"}
11
+ {"current_steps": 11, "total_steps": 412, "loss": 0.1413, "lr": 9.982421733004857e-06, "epoch": 0.05339805825242718, "percentage": 2.67, "elapsed_time": "0:00:11", "remaining_time": "0:06:57"}
12
+ {"current_steps": 12, "total_steps": 412, "loss": 0.1571, "lr": 9.979082741033047e-06, "epoch": 0.05825242718446602, "percentage": 2.91, "elapsed_time": "0:00:12", "remaining_time": "0:06:41"}
13
+ {"current_steps": 13, "total_steps": 412, "loss": 0.1373, "lr": 9.975454246405312e-06, "epoch": 0.06310679611650485, "percentage": 3.16, "elapsed_time": "0:00:12", "remaining_time": "0:06:28"}
14
+ {"current_steps": 14, "total_steps": 412, "loss": 0.2064, "lr": 9.971536460096021e-06, "epoch": 0.06796116504854369, "percentage": 3.4, "elapsed_time": "0:00:13", "remaining_time": "0:06:17"}
15
+ {"current_steps": 15, "total_steps": 412, "loss": 0.213, "lr": 9.96732960990005e-06, "epoch": 0.07281553398058252, "percentage": 3.64, "elapsed_time": "0:00:13", "remaining_time": "0:06:07"}
16
+ {"current_steps": 16, "total_steps": 412, "loss": 0.1806, "lr": 9.96283394041954e-06, "epoch": 0.07766990291262135, "percentage": 3.88, "elapsed_time": "0:00:14", "remaining_time": "0:05:58"}
17
+ {"current_steps": 17, "total_steps": 412, "loss": 0.1594, "lr": 9.95804971304968e-06, "epoch": 0.0825242718446602, "percentage": 4.13, "elapsed_time": "0:00:15", "remaining_time": "0:05:50"}
18
+ {"current_steps": 18, "total_steps": 412, "loss": 0.143, "lr": 9.952977205963496e-06, "epoch": 0.08737864077669903, "percentage": 4.37, "elapsed_time": "0:00:15", "remaining_time": "0:05:43"}
19
+ {"current_steps": 19, "total_steps": 412, "loss": 0.1604, "lr": 9.94761671409569e-06, "epoch": 0.09223300970873786, "percentage": 4.61, "elapsed_time": "0:00:16", "remaining_time": "0:05:36"}
20
+ {"current_steps": 20, "total_steps": 412, "loss": 0.1618, "lr": 9.941968549125481e-06, "epoch": 0.0970873786407767, "percentage": 4.85, "elapsed_time": "0:00:16", "remaining_time": "0:05:30"}
21
+ {"current_steps": 21, "total_steps": 412, "loss": 0.1778, "lr": 9.936033039458494e-06, "epoch": 0.10194174757281553, "percentage": 5.1, "elapsed_time": "0:00:17", "remaining_time": "0:05:25"}
22
+ {"current_steps": 22, "total_steps": 412, "loss": 0.1591, "lr": 9.929810530207651e-06, "epoch": 0.10679611650485436, "percentage": 5.34, "elapsed_time": "0:00:18", "remaining_time": "0:05:20"}
23
+ {"current_steps": 23, "total_steps": 412, "loss": 0.2006, "lr": 9.923301383173119e-06, "epoch": 0.11165048543689321, "percentage": 5.58, "elapsed_time": "0:00:18", "remaining_time": "0:05:16"}
24
+ {"current_steps": 24, "total_steps": 412, "loss": 0.1657, "lr": 9.916505976821262e-06, "epoch": 0.11650485436893204, "percentage": 5.83, "elapsed_time": "0:00:19", "remaining_time": "0:05:12"}
25
+ {"current_steps": 25, "total_steps": 412, "loss": 0.1569, "lr": 9.909424706262647e-06, "epoch": 0.12135922330097088, "percentage": 6.07, "elapsed_time": "0:00:19", "remaining_time": "0:05:08"}
26
+ {"current_steps": 26, "total_steps": 412, "loss": 0.1909, "lr": 9.902057983229059e-06, "epoch": 0.1262135922330097, "percentage": 6.31, "elapsed_time": "0:00:20", "remaining_time": "0:05:04"}
27
+ {"current_steps": 27, "total_steps": 412, "loss": 0.163, "lr": 9.894406236049569e-06, "epoch": 0.13106796116504854, "percentage": 6.55, "elapsed_time": "0:00:21", "remaining_time": "0:05:01"}
28
+ {"current_steps": 28, "total_steps": 412, "loss": 0.196, "lr": 9.886469909625624e-06, "epoch": 0.13592233009708737, "percentage": 6.8, "elapsed_time": "0:00:21", "remaining_time": "0:04:57"}
29
+ {"current_steps": 29, "total_steps": 412, "loss": 0.208, "lr": 9.87824946540519e-06, "epoch": 0.1407766990291262, "percentage": 7.04, "elapsed_time": "0:00:22", "remaining_time": "0:04:54"}
30
+ {"current_steps": 30, "total_steps": 412, "loss": 0.1664, "lr": 9.869745381355906e-06, "epoch": 0.14563106796116504, "percentage": 7.28, "elapsed_time": "0:00:22", "remaining_time": "0:04:51"}
31
+ {"current_steps": 31, "total_steps": 412, "loss": 0.1877, "lr": 9.860958151937303e-06, "epoch": 0.15048543689320387, "percentage": 7.52, "elapsed_time": "0:00:23", "remaining_time": "0:04:49"}
32
+ {"current_steps": 32, "total_steps": 412, "loss": 0.1735, "lr": 9.851888288072053e-06, "epoch": 0.1553398058252427, "percentage": 7.77, "elapsed_time": "0:00:24", "remaining_time": "0:04:46"}
33
+ {"current_steps": 33, "total_steps": 412, "loss": 0.2067, "lr": 9.842536317116262e-06, "epoch": 0.16019417475728157, "percentage": 8.01, "elapsed_time": "0:00:24", "remaining_time": "0:04:43"}
34
+ {"current_steps": 34, "total_steps": 412, "loss": 0.1915, "lr": 9.832902782828801e-06, "epoch": 0.1650485436893204, "percentage": 8.25, "elapsed_time": "0:00:25", "remaining_time": "0:04:41"}
35
+ {"current_steps": 35, "total_steps": 412, "loss": 0.1979, "lr": 9.822988245339701e-06, "epoch": 0.16990291262135923, "percentage": 8.5, "elapsed_time": "0:00:25", "remaining_time": "0:04:39"}
36
+ {"current_steps": 36, "total_steps": 412, "loss": 0.1596, "lr": 9.81279328111758e-06, "epoch": 0.17475728155339806, "percentage": 8.74, "elapsed_time": "0:00:26", "remaining_time": "0:04:37"}
37
+ {"current_steps": 37, "total_steps": 412, "loss": 2.2571, "lr": 9.802318482936121e-06, "epoch": 0.1796116504854369, "percentage": 8.98, "elapsed_time": "0:00:27", "remaining_time": "0:04:35"}
38
+ {"current_steps": 38, "total_steps": 412, "loss": 1.938, "lr": 9.791564459839609e-06, "epoch": 0.18446601941747573, "percentage": 9.22, "elapsed_time": "0:00:27", "remaining_time": "0:04:34"}
39
+ {"current_steps": 39, "total_steps": 412, "loss": 0.2153, "lr": 9.780531837107519e-06, "epoch": 0.18932038834951456, "percentage": 9.47, "elapsed_time": "0:00:28", "remaining_time": "0:04:32"}
40
+ {"current_steps": 40, "total_steps": 412, "loss": 0.2017, "lr": 9.769221256218165e-06, "epoch": 0.1941747572815534, "percentage": 9.71, "elapsed_time": "0:00:29", "remaining_time": "0:04:30"}
41
+ {"current_steps": 41, "total_steps": 412, "loss": 0.2182, "lr": 9.75763337481139e-06, "epoch": 0.19902912621359223, "percentage": 9.95, "elapsed_time": "0:00:29", "remaining_time": "0:04:28"}
42
+ {"current_steps": 42, "total_steps": 412, "loss": 0.2244, "lr": 9.745768866650339e-06, "epoch": 0.20388349514563106, "percentage": 10.19, "elapsed_time": "0:00:30", "remaining_time": "0:04:26"}
43
+ {"current_steps": 43, "total_steps": 412, "loss": 0.1467, "lr": 9.73362842158228e-06, "epoch": 0.2087378640776699, "percentage": 10.44, "elapsed_time": "0:00:30", "remaining_time": "0:04:24"}
44
+ {"current_steps": 44, "total_steps": 412, "loss": 0.1843, "lr": 9.721212745498493e-06, "epoch": 0.21359223300970873, "percentage": 10.68, "elapsed_time": "0:00:31", "remaining_time": "0:04:23"}
45
+ {"current_steps": 45, "total_steps": 412, "loss": 0.1765, "lr": 9.70852256029323e-06, "epoch": 0.21844660194174756, "percentage": 10.92, "elapsed_time": "0:00:32", "remaining_time": "0:04:21"}
46
+ {"current_steps": 46, "total_steps": 412, "loss": 0.2249, "lr": 9.695558603821735e-06, "epoch": 0.22330097087378642, "percentage": 11.17, "elapsed_time": "0:00:32", "remaining_time": "0:04:19"}
47
+ {"current_steps": 47, "total_steps": 412, "loss": 0.1945, "lr": 9.682321629857348e-06, "epoch": 0.22815533980582525, "percentage": 11.41, "elapsed_time": "0:00:33", "remaining_time": "0:04:18"}
48
+ {"current_steps": 48, "total_steps": 412, "loss": 0.1923, "lr": 9.66881240804768e-06, "epoch": 0.23300970873786409, "percentage": 11.65, "elapsed_time": "0:00:33", "remaining_time": "0:04:16"}
49
+ {"current_steps": 49, "total_steps": 412, "loss": 0.2106, "lr": 9.655031723869848e-06, "epoch": 0.23786407766990292, "percentage": 11.89, "elapsed_time": "0:00:34", "remaining_time": "0:04:15"}
50
+ {"current_steps": 50, "total_steps": 412, "loss": 0.1948, "lr": 9.64098037858483e-06, "epoch": 0.24271844660194175, "percentage": 12.14, "elapsed_time": "0:00:35", "remaining_time": "0:04:13"}
51
+ {"current_steps": 51, "total_steps": 412, "loss": 1.3556, "lr": 9.626659189190852e-06, "epoch": 0.24757281553398058, "percentage": 12.38, "elapsed_time": "0:00:35", "remaining_time": "0:04:12"}
52
+ {"current_steps": 52, "total_steps": 412, "loss": 0.1675, "lr": 9.612068988375898e-06, "epoch": 0.2524271844660194, "percentage": 12.62, "elapsed_time": "0:00:36", "remaining_time": "0:04:11"}
53
+ {"current_steps": 53, "total_steps": 412, "loss": 0.1971, "lr": 9.597210624469288e-06, "epoch": 0.25728155339805825, "percentage": 12.86, "elapsed_time": "0:00:36", "remaining_time": "0:04:10"}
54
+ {"current_steps": 54, "total_steps": 412, "loss": 0.1439, "lr": 9.582084961392358e-06, "epoch": 0.2621359223300971, "percentage": 13.11, "elapsed_time": "0:00:37", "remaining_time": "0:04:08"}
55
+ {"current_steps": 55, "total_steps": 412, "loss": 0.1618, "lr": 9.566692878608229e-06, "epoch": 0.2669902912621359, "percentage": 13.35, "elapsed_time": "0:00:38", "remaining_time": "0:04:07"}
56
+ {"current_steps": 56, "total_steps": 412, "loss": 0.2095, "lr": 9.551035271070665e-06, "epoch": 0.27184466019417475, "percentage": 13.59, "elapsed_time": "0:00:38", "remaining_time": "0:04:06"}
57
+ {"current_steps": 57, "total_steps": 412, "loss": 0.1899, "lr": 9.53511304917204e-06, "epoch": 0.2766990291262136, "percentage": 13.83, "elapsed_time": "0:00:39", "remaining_time": "0:04:05"}
58
+ {"current_steps": 58, "total_steps": 412, "loss": 0.1361, "lr": 9.51892713869041e-06, "epoch": 0.2815533980582524, "percentage": 14.08, "elapsed_time": "0:00:39", "remaining_time": "0:04:03"}
59
+ {"current_steps": 59, "total_steps": 412, "loss": 0.1873, "lr": 9.502478480735678e-06, "epoch": 0.28640776699029125, "percentage": 14.32, "elapsed_time": "0:00:40", "remaining_time": "0:04:02"}
60
+ {"current_steps": 60, "total_steps": 412, "loss": 0.1867, "lr": 9.485768031694872e-06, "epoch": 0.2912621359223301, "percentage": 14.56, "elapsed_time": "0:00:41", "remaining_time": "0:04:01"}
61
+ {"current_steps": 61, "total_steps": 412, "loss": 0.2054, "lr": 9.468796763176549e-06, "epoch": 0.2961165048543689, "percentage": 14.81, "elapsed_time": "0:00:41", "remaining_time": "0:04:00"}
62
+ {"current_steps": 62, "total_steps": 412, "loss": 0.1571, "lr": 9.45156566195429e-06, "epoch": 0.30097087378640774, "percentage": 15.05, "elapsed_time": "0:00:42", "remaining_time": "0:03:59"}
63
+ {"current_steps": 63, "total_steps": 412, "loss": 0.1837, "lr": 9.43407572990933e-06, "epoch": 0.3058252427184466, "percentage": 15.29, "elapsed_time": "0:00:42", "remaining_time": "0:03:58"}
64
+ {"current_steps": 64, "total_steps": 412, "loss": 0.1938, "lr": 9.416327983972304e-06, "epoch": 0.3106796116504854, "percentage": 15.53, "elapsed_time": "0:00:43", "remaining_time": "0:03:56"}
65
+ {"current_steps": 65, "total_steps": 412, "loss": 0.2241, "lr": 9.398323456064124e-06, "epoch": 0.3155339805825243, "percentage": 15.78, "elapsed_time": "0:00:44", "remaining_time": "0:03:55"}
66
+ {"current_steps": 66, "total_steps": 412, "loss": 0.177, "lr": 9.380063193035968e-06, "epoch": 0.32038834951456313, "percentage": 16.02, "elapsed_time": "0:00:44", "remaining_time": "0:03:54"}
67
+ {"current_steps": 67, "total_steps": 412, "loss": 0.1797, "lr": 9.361548256608421e-06, "epoch": 0.32524271844660196, "percentage": 16.26, "elapsed_time": "0:00:45", "remaining_time": "0:03:53"}
68
+ {"current_steps": 68, "total_steps": 412, "loss": 0.2554, "lr": 9.342779723309746e-06, "epoch": 0.3300970873786408, "percentage": 16.5, "elapsed_time": "0:00:46", "remaining_time": "0:03:52"}
69
+ {"current_steps": 69, "total_steps": 412, "loss": 0.1478, "lr": 9.323758684413272e-06, "epoch": 0.33495145631067963, "percentage": 16.75, "elapsed_time": "0:00:46", "remaining_time": "0:03:51"}
70
+ {"current_steps": 70, "total_steps": 412, "loss": 0.1751, "lr": 9.304486245873973e-06, "epoch": 0.33980582524271846, "percentage": 16.99, "elapsed_time": "0:00:47", "remaining_time": "0:03:50"}
71
+ {"current_steps": 71, "total_steps": 412, "loss": 0.1823, "lr": 9.284963528264133e-06, "epoch": 0.3446601941747573, "percentage": 17.23, "elapsed_time": "0:00:47", "remaining_time": "0:03:49"}
72
+ {"current_steps": 72, "total_steps": 412, "loss": 0.1685, "lr": 9.26519166670821e-06, "epoch": 0.34951456310679613, "percentage": 17.48, "elapsed_time": "0:00:48", "remaining_time": "0:03:48"}
73
+ {"current_steps": 73, "total_steps": 412, "loss": 2.1169, "lr": 9.24517181081683e-06, "epoch": 0.35436893203883496, "percentage": 17.72, "elapsed_time": "0:00:49", "remaining_time": "0:03:47"}
74
+ {"current_steps": 74, "total_steps": 412, "loss": 0.1636, "lr": 9.22490512461995e-06, "epoch": 0.3592233009708738, "percentage": 17.96, "elapsed_time": "0:00:49", "remaining_time": "0:03:46"}
75
+ {"current_steps": 75, "total_steps": 412, "loss": 0.2401, "lr": 9.204392786499168e-06, "epoch": 0.3640776699029126, "percentage": 18.2, "elapsed_time": "0:00:50", "remaining_time": "0:03:45"}
76
+ {"current_steps": 76, "total_steps": 412, "loss": 0.1641, "lr": 9.183635989119211e-06, "epoch": 0.36893203883495146, "percentage": 18.45, "elapsed_time": "0:00:50", "remaining_time": "0:03:45"}
77
+ {"current_steps": 77, "total_steps": 412, "loss": 0.1614, "lr": 9.162635939358593e-06, "epoch": 0.3737864077669903, "percentage": 18.69, "elapsed_time": "0:00:51", "remaining_time": "0:03:44"}
78
+ {"current_steps": 78, "total_steps": 412, "loss": 0.1459, "lr": 9.141393858239435e-06, "epoch": 0.3786407766990291, "percentage": 18.93, "elapsed_time": "0:00:52", "remaining_time": "0:03:43"}
79
+ {"current_steps": 79, "total_steps": 412, "loss": 0.1804, "lr": 9.119910980856477e-06, "epoch": 0.38349514563106796, "percentage": 19.17, "elapsed_time": "0:00:52", "remaining_time": "0:03:42"}
80
+ {"current_steps": 80, "total_steps": 412, "loss": 0.19, "lr": 9.098188556305262e-06, "epoch": 0.3883495145631068, "percentage": 19.42, "elapsed_time": "0:00:53", "remaining_time": "0:03:41"}
81
+ {"current_steps": 81, "total_steps": 412, "loss": 0.144, "lr": 9.076227847609513e-06, "epoch": 0.3932038834951456, "percentage": 19.66, "elapsed_time": "0:00:53", "remaining_time": "0:03:40"}
82
+ {"current_steps": 82, "total_steps": 412, "loss": 0.1541, "lr": 9.054030131647682e-06, "epoch": 0.39805825242718446, "percentage": 19.9, "elapsed_time": "0:00:54", "remaining_time": "0:03:39"}
83
+ {"current_steps": 83, "total_steps": 412, "loss": 0.231, "lr": 9.031596699078727e-06, "epoch": 0.4029126213592233, "percentage": 20.15, "elapsed_time": "0:00:55", "remaining_time": "0:03:38"}
84
+ {"current_steps": 84, "total_steps": 412, "loss": 0.1729, "lr": 9.008928854267054e-06, "epoch": 0.4077669902912621, "percentage": 20.39, "elapsed_time": "0:00:55", "remaining_time": "0:03:37"}
85
+ {"current_steps": 85, "total_steps": 412, "loss": 0.1286, "lr": 8.986027915206686e-06, "epoch": 0.41262135922330095, "percentage": 20.63, "elapsed_time": "0:00:56", "remaining_time": "0:03:36"}
86
+ {"current_steps": 86, "total_steps": 412, "loss": 0.1922, "lr": 8.962895213444618e-06, "epoch": 0.4174757281553398, "percentage": 20.87, "elapsed_time": "0:00:56", "remaining_time": "0:03:35"}
87
+ {"current_steps": 87, "total_steps": 412, "loss": 1.6075, "lr": 8.939532094003409e-06, "epoch": 0.4223300970873786, "percentage": 21.12, "elapsed_time": "0:00:57", "remaining_time": "0:03:35"}
88
+ {"current_steps": 88, "total_steps": 412, "loss": 0.1903, "lr": 8.91593991530297e-06, "epoch": 0.42718446601941745, "percentage": 21.36, "elapsed_time": "0:00:58", "remaining_time": "0:03:34"}
89
+ {"current_steps": 89, "total_steps": 412, "loss": 0.2364, "lr": 8.892120049081577e-06, "epoch": 0.4320388349514563, "percentage": 21.6, "elapsed_time": "0:00:58", "remaining_time": "0:03:33"}
90
+ {"current_steps": 90, "total_steps": 412, "loss": 0.2073, "lr": 8.868073880316125e-06, "epoch": 0.4368932038834951, "percentage": 21.84, "elapsed_time": "0:00:59", "remaining_time": "0:03:32"}
91
+ {"current_steps": 91, "total_steps": 412, "loss": 0.1641, "lr": 8.843802807141584e-06, "epoch": 0.441747572815534, "percentage": 22.09, "elapsed_time": "0:01:00", "remaining_time": "0:03:31"}
92
+ {"current_steps": 92, "total_steps": 412, "loss": 0.2238, "lr": 8.819308240769726e-06, "epoch": 0.44660194174757284, "percentage": 22.33, "elapsed_time": "0:01:00", "remaining_time": "0:03:30"}
93
+ {"current_steps": 93, "total_steps": 412, "loss": 0.1974, "lr": 8.794591605407047e-06, "epoch": 0.45145631067961167, "percentage": 22.57, "elapsed_time": "0:01:01", "remaining_time": "0:03:30"}
94
+ {"current_steps": 94, "total_steps": 412, "loss": 0.2162, "lr": 8.769654338171986e-06, "epoch": 0.4563106796116505, "percentage": 22.82, "elapsed_time": "0:01:01", "remaining_time": "0:03:29"}
95
+ {"current_steps": 95, "total_steps": 412, "loss": 0.1779, "lr": 8.744497889011344e-06, "epoch": 0.46116504854368934, "percentage": 23.06, "elapsed_time": "0:01:02", "remaining_time": "0:03:28"}
96
+ {"current_steps": 96, "total_steps": 412, "loss": 0.1827, "lr": 8.71912372061598e-06, "epoch": 0.46601941747572817, "percentage": 23.3, "elapsed_time": "0:01:03", "remaining_time": "0:03:27"}
97
+ {"current_steps": 97, "total_steps": 412, "loss": 0.148, "lr": 8.693533308335786e-06, "epoch": 0.470873786407767, "percentage": 23.54, "elapsed_time": "0:01:03", "remaining_time": "0:03:26"}
98
+ {"current_steps": 98, "total_steps": 412, "loss": 0.2068, "lr": 8.667728140093876e-06, "epoch": 0.47572815533980584, "percentage": 23.79, "elapsed_time": "0:01:04", "remaining_time": "0:03:26"}
99
+ {"current_steps": 99, "total_steps": 412, "loss": 0.2029, "lr": 8.641709716300092e-06, "epoch": 0.48058252427184467, "percentage": 24.03, "elapsed_time": "0:01:04", "remaining_time": "0:03:25"}
100
+ {"current_steps": 100, "total_steps": 412, "loss": 1.8884, "lr": 8.615479549763756e-06, "epoch": 0.4854368932038835, "percentage": 24.27, "elapsed_time": "0:01:05", "remaining_time": "0:03:24"}
101
+ {"current_steps": 101, "total_steps": 412, "loss": 0.1537, "lr": 8.589039165605716e-06, "epoch": 0.49029126213592233, "percentage": 24.51, "elapsed_time": "0:01:06", "remaining_time": "0:03:23"}
102
+ {"current_steps": 102, "total_steps": 412, "loss": 0.1824, "lr": 8.56239010116966e-06, "epoch": 0.49514563106796117, "percentage": 24.76, "elapsed_time": "0:01:06", "remaining_time": "0:03:22"}
103
+ {"current_steps": 103, "total_steps": 412, "loss": 0.1804, "lr": 8.535533905932739e-06, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:01:07", "remaining_time": "0:03:22"}
104
+ {"current_steps": 104, "total_steps": 412, "loss": 0.1617, "lr": 8.508472141415468e-06, "epoch": 0.5048543689320388, "percentage": 25.24, "elapsed_time": "0:01:07", "remaining_time": "0:03:21"}
105
+ {"current_steps": 105, "total_steps": 412, "loss": 0.1887, "lr": 8.481206381090934e-06, "epoch": 0.5097087378640777, "percentage": 25.49, "elapsed_time": "0:01:08", "remaining_time": "0:03:20"}
106
+ {"current_steps": 106, "total_steps": 412, "loss": 0.1721, "lr": 8.453738210293316e-06, "epoch": 0.5145631067961165, "percentage": 25.73, "elapsed_time": "0:01:09", "remaining_time": "0:03:19"}
107
+ {"current_steps": 107, "total_steps": 412, "loss": 0.1838, "lr": 8.426069226125695e-06, "epoch": 0.5194174757281553, "percentage": 25.97, "elapsed_time": "0:01:09", "remaining_time": "0:03:18"}
108
+ {"current_steps": 108, "total_steps": 412, "loss": 0.1961, "lr": 8.398201037367202e-06, "epoch": 0.5242718446601942, "percentage": 26.21, "elapsed_time": "0:01:10", "remaining_time": "0:03:18"}
109
+ {"current_steps": 109, "total_steps": 412, "loss": 0.1474, "lr": 8.370135264379475e-06, "epoch": 0.529126213592233, "percentage": 26.46, "elapsed_time": "0:01:11", "remaining_time": "0:03:17"}
110
+ {"current_steps": 110, "total_steps": 412, "loss": 0.1704, "lr": 8.341873539012443e-06, "epoch": 0.5339805825242718, "percentage": 26.7, "elapsed_time": "0:01:11", "remaining_time": "0:03:16"}
111
+ {"current_steps": 111, "total_steps": 412, "loss": 0.151, "lr": 8.313417504509446e-06, "epoch": 0.5388349514563107, "percentage": 26.94, "elapsed_time": "0:01:12", "remaining_time": "0:03:15"}
112
+ {"current_steps": 112, "total_steps": 412, "loss": 0.164, "lr": 8.284768815411693e-06, "epoch": 0.5436893203883495, "percentage": 27.18, "elapsed_time": "0:01:12", "remaining_time": "0:03:15"}
113
+ {"current_steps": 113, "total_steps": 412, "loss": 0.1844, "lr": 8.255929137462049e-06, "epoch": 0.5485436893203883, "percentage": 27.43, "elapsed_time": "0:01:13", "remaining_time": "0:03:14"}
114
+ {"current_steps": 114, "total_steps": 412, "loss": 0.1726, "lr": 8.226900147508205e-06, "epoch": 0.5533980582524272, "percentage": 27.67, "elapsed_time": "0:01:14", "remaining_time": "0:03:13"}
115
+ {"current_steps": 115, "total_steps": 412, "loss": 0.1651, "lr": 8.197683533405156e-06, "epoch": 0.558252427184466, "percentage": 27.91, "elapsed_time": "0:01:14", "remaining_time": "0:03:12"}
116
+ {"current_steps": 116, "total_steps": 412, "loss": 0.2018, "lr": 8.168280993917078e-06, "epoch": 0.5631067961165048, "percentage": 28.16, "elapsed_time": "0:01:15", "remaining_time": "0:03:12"}
117
+ {"current_steps": 117, "total_steps": 412, "loss": 0.186, "lr": 8.138694238618543e-06, "epoch": 0.5679611650485437, "percentage": 28.4, "elapsed_time": "0:01:15", "remaining_time": "0:03:11"}
118
+ {"current_steps": 118, "total_steps": 412, "loss": 0.1807, "lr": 8.108924987795137e-06, "epoch": 0.5728155339805825, "percentage": 28.64, "elapsed_time": "0:01:16", "remaining_time": "0:03:10"}
119
+ {"current_steps": 119, "total_steps": 412, "loss": 0.1385, "lr": 8.078974972343414e-06, "epoch": 0.5776699029126213, "percentage": 28.88, "elapsed_time": "0:01:17", "remaining_time": "0:03:09"}
120
+ {"current_steps": 120, "total_steps": 412, "loss": 0.1876, "lr": 8.048845933670274e-06, "epoch": 0.5825242718446602, "percentage": 29.13, "elapsed_time": "0:01:17", "remaining_time": "0:03:08"}
121
+ {"current_steps": 121, "total_steps": 412, "loss": 0.1542, "lr": 8.01853962359169e-06, "epoch": 0.587378640776699, "percentage": 29.37, "elapsed_time": "0:01:18", "remaining_time": "0:03:08"}
122
+ {"current_steps": 122, "total_steps": 412, "loss": 0.1855, "lr": 7.988057804230878e-06, "epoch": 0.5922330097087378, "percentage": 29.61, "elapsed_time": "0:01:18", "remaining_time": "0:03:07"}
123
+ {"current_steps": 123, "total_steps": 412, "loss": 0.1398, "lr": 7.957402247915817e-06, "epoch": 0.5970873786407767, "percentage": 29.85, "elapsed_time": "0:01:19", "remaining_time": "0:03:06"}
124
+ {"current_steps": 124, "total_steps": 412, "loss": 0.1571, "lr": 7.92657473707621e-06, "epoch": 0.6019417475728155, "percentage": 30.1, "elapsed_time": "0:01:20", "remaining_time": "0:03:06"}
125
+ {"current_steps": 125, "total_steps": 412, "loss": 0.2838, "lr": 7.895577064139847e-06, "epoch": 0.6067961165048543, "percentage": 30.34, "elapsed_time": "0:01:20", "remaining_time": "0:03:05"}
126
+ {"current_steps": 126, "total_steps": 412, "loss": 0.1605, "lr": 7.864411031428379e-06, "epoch": 0.6116504854368932, "percentage": 30.58, "elapsed_time": "0:01:21", "remaining_time": "0:03:04"}
127
+ {"current_steps": 127, "total_steps": 412, "loss": 0.1552, "lr": 7.833078451052537e-06, "epoch": 0.616504854368932, "percentage": 30.83, "elapsed_time": "0:01:21", "remaining_time": "0:03:03"}
128
+ {"current_steps": 128, "total_steps": 412, "loss": 0.1409, "lr": 7.801581144806752e-06, "epoch": 0.6213592233009708, "percentage": 31.07, "elapsed_time": "0:01:22", "remaining_time": "0:03:03"}
129
+ {"current_steps": 129, "total_steps": 412, "loss": 0.1388, "lr": 7.769920944063244e-06, "epoch": 0.6262135922330098, "percentage": 31.31, "elapsed_time": "0:01:23", "remaining_time": "0:03:02"}
130
+ {"current_steps": 130, "total_steps": 412, "loss": 0.1691, "lr": 7.73809968966554e-06, "epoch": 0.6310679611650486, "percentage": 31.55, "elapsed_time": "0:01:23", "remaining_time": "0:03:01"}
131
+ {"current_steps": 131, "total_steps": 412, "loss": 2.0662, "lr": 7.706119231821423e-06, "epoch": 0.6359223300970874, "percentage": 31.8, "elapsed_time": "0:01:24", "remaining_time": "0:03:01"}
132
+ {"current_steps": 132, "total_steps": 412, "loss": 0.1217, "lr": 7.673981429995372e-06, "epoch": 0.6407766990291263, "percentage": 32.04, "elapsed_time": "0:01:25", "remaining_time": "0:03:00"}
133
+ {"current_steps": 133, "total_steps": 412, "loss": 0.1641, "lr": 7.641688152800433e-06, "epoch": 0.6456310679611651, "percentage": 32.28, "elapsed_time": "0:01:25", "remaining_time": "0:02:59"}
134
+ {"current_steps": 134, "total_steps": 412, "loss": 0.1581, "lr": 7.609241277889583e-06, "epoch": 0.6504854368932039, "percentage": 32.52, "elapsed_time": "0:01:26", "remaining_time": "0:02:58"}
135
+ {"current_steps": 135, "total_steps": 412, "loss": 0.1655, "lr": 7.5766426918465455e-06, "epoch": 0.6553398058252428, "percentage": 32.77, "elapsed_time": "0:01:26", "remaining_time": "0:02:58"}
136
+ {"current_steps": 136, "total_steps": 412, "loss": 0.179, "lr": 7.5438942900761035e-06, "epoch": 0.6601941747572816, "percentage": 33.01, "elapsed_time": "0:01:27", "remaining_time": "0:02:57"}
137
+ {"current_steps": 137, "total_steps": 412, "loss": 0.1838, "lr": 7.51099797669389e-06, "epoch": 0.6650485436893204, "percentage": 33.25, "elapsed_time": "0:01:28", "remaining_time": "0:02:56"}
138
+ {"current_steps": 138, "total_steps": 412, "loss": 0.2121, "lr": 7.477955664415678e-06, "epoch": 0.6699029126213593, "percentage": 33.5, "elapsed_time": "0:01:28", "remaining_time": "0:02:55"}
139
+ {"current_steps": 139, "total_steps": 412, "loss": 0.1522, "lr": 7.444769274446168e-06, "epoch": 0.6747572815533981, "percentage": 33.74, "elapsed_time": "0:01:29", "remaining_time": "0:02:55"}
140
+ {"current_steps": 140, "total_steps": 412, "loss": 0.158, "lr": 7.411440736367281e-06, "epoch": 0.6796116504854369, "percentage": 33.98, "elapsed_time": "0:01:29", "remaining_time": "0:02:54"}
141
+ {"current_steps": 141, "total_steps": 412, "loss": 0.1431, "lr": 7.377971988025964e-06, "epoch": 0.6844660194174758, "percentage": 34.22, "elapsed_time": "0:01:30", "remaining_time": "0:02:53"}
142
+ {"current_steps": 142, "total_steps": 412, "loss": 0.1609, "lr": 7.3443649754215175e-06, "epoch": 0.6893203883495146, "percentage": 34.47, "elapsed_time": "0:01:31", "remaining_time": "0:02:53"}
143
+ {"current_steps": 143, "total_steps": 412, "loss": 0.1537, "lr": 7.310621652592449e-06, "epoch": 0.6941747572815534, "percentage": 34.71, "elapsed_time": "0:01:31", "remaining_time": "0:02:52"}
144
+ {"current_steps": 144, "total_steps": 412, "loss": 0.161, "lr": 7.276743981502856e-06, "epoch": 0.6990291262135923, "percentage": 34.95, "elapsed_time": "0:01:32", "remaining_time": "0:02:51"}
145
+ {"current_steps": 145, "total_steps": 412, "loss": 1.968, "lr": 7.242733931928352e-06, "epoch": 0.7038834951456311, "percentage": 35.19, "elapsed_time": "0:01:32", "remaining_time": "0:02:51"}
146
+ {"current_steps": 146, "total_steps": 412, "loss": 0.164, "lr": 7.208593481341536e-06, "epoch": 0.7087378640776699, "percentage": 35.44, "elapsed_time": "0:01:33", "remaining_time": "0:02:50"}
147
+ {"current_steps": 147, "total_steps": 412, "loss": 0.156, "lr": 7.1743246147970095e-06, "epoch": 0.7135922330097088, "percentage": 35.68, "elapsed_time": "0:01:34", "remaining_time": "0:02:49"}
148
+ {"current_steps": 148, "total_steps": 412, "loss": 0.1884, "lr": 7.139929324815965e-06, "epoch": 0.7184466019417476, "percentage": 35.92, "elapsed_time": "0:01:34", "remaining_time": "0:02:48"}
149
+ {"current_steps": 149, "total_steps": 412, "loss": 0.1219, "lr": 7.105409611270332e-06, "epoch": 0.7233009708737864, "percentage": 36.17, "elapsed_time": "0:01:35", "remaining_time": "0:02:48"}
150
+ {"current_steps": 150, "total_steps": 412, "loss": 0.1732, "lr": 7.070767481266493e-06, "epoch": 0.7281553398058253, "percentage": 36.41, "elapsed_time": "0:01:35", "remaining_time": "0:02:47"}
151
+ {"current_steps": 151, "total_steps": 412, "loss": 0.1481, "lr": 7.036004949028587e-06, "epoch": 0.7330097087378641, "percentage": 36.65, "elapsed_time": "0:01:36", "remaining_time": "0:02:46"}
152
+ {"current_steps": 152, "total_steps": 412, "loss": 0.1673, "lr": 7.00112403578139e-06, "epoch": 0.7378640776699029, "percentage": 36.89, "elapsed_time": "0:01:37", "remaining_time": "0:02:46"}
153
+ {"current_steps": 153, "total_steps": 412, "loss": 0.1883, "lr": 6.9661267696328015e-06, "epoch": 0.7427184466019418, "percentage": 37.14, "elapsed_time": "0:01:37", "remaining_time": "0:02:45"}
154
+ {"current_steps": 154, "total_steps": 412, "loss": 0.2046, "lr": 6.931015185455915e-06, "epoch": 0.7475728155339806, "percentage": 37.38, "elapsed_time": "0:01:38", "remaining_time": "0:02:44"}
155
+ {"current_steps": 155, "total_steps": 412, "loss": 0.2068, "lr": 6.895791324770702e-06, "epoch": 0.7524271844660194, "percentage": 37.62, "elapsed_time": "0:01:38", "remaining_time": "0:02:44"}
156
+ {"current_steps": 156, "total_steps": 412, "loss": 0.169, "lr": 6.860457235625322e-06, "epoch": 0.7572815533980582, "percentage": 37.86, "elapsed_time": "0:01:39", "remaining_time": "0:02:43"}
157
+ {"current_steps": 157, "total_steps": 412, "loss": 0.1662, "lr": 6.825014972477024e-06, "epoch": 0.7621359223300971, "percentage": 38.11, "elapsed_time": "0:01:40", "remaining_time": "0:02:42"}
158
+ {"current_steps": 158, "total_steps": 412, "loss": 0.2034, "lr": 6.7894665960727105e-06, "epoch": 0.7669902912621359, "percentage": 38.35, "elapsed_time": "0:01:40", "remaining_time": "0:02:41"}
159
+ {"current_steps": 159, "total_steps": 412, "loss": 0.2038, "lr": 6.7538141733291e-06, "epoch": 0.7718446601941747, "percentage": 38.59, "elapsed_time": "0:01:41", "remaining_time": "0:02:41"}
160
+ {"current_steps": 160, "total_steps": 412, "loss": 0.1852, "lr": 6.7180597772125665e-06, "epoch": 0.7766990291262136, "percentage": 38.83, "elapsed_time": "0:01:41", "remaining_time": "0:02:40"}
161
+ {"current_steps": 161, "total_steps": 412, "loss": 0.1597, "lr": 6.682205486618592e-06, "epoch": 0.7815533980582524, "percentage": 39.08, "elapsed_time": "0:01:42", "remaining_time": "0:02:39"}
162
+ {"current_steps": 162, "total_steps": 412, "loss": 0.2022, "lr": 6.646253386250909e-06, "epoch": 0.7864077669902912, "percentage": 39.32, "elapsed_time": "0:01:43", "remaining_time": "0:02:39"}
163
+ {"current_steps": 163, "total_steps": 412, "loss": 0.2029, "lr": 6.610205566500272e-06, "epoch": 0.7912621359223301, "percentage": 39.56, "elapsed_time": "0:01:43", "remaining_time": "0:02:38"}
164
+ {"current_steps": 164, "total_steps": 412, "loss": 0.1883, "lr": 6.574064123322925e-06, "epoch": 0.7961165048543689, "percentage": 39.81, "elapsed_time": "0:01:44", "remaining_time": "0:02:37"}
165
+ {"current_steps": 165, "total_steps": 412, "loss": 0.1323, "lr": 6.537831158118733e-06, "epoch": 0.8009708737864077, "percentage": 40.05, "elapsed_time": "0:01:44", "remaining_time": "0:02:37"}
166
+ {"current_steps": 166, "total_steps": 412, "loss": 0.1786, "lr": 6.50150877760899e-06, "epoch": 0.8058252427184466, "percentage": 40.29, "elapsed_time": "0:01:45", "remaining_time": "0:02:36"}
167
+ {"current_steps": 167, "total_steps": 412, "loss": 0.1753, "lr": 6.465099093713944e-06, "epoch": 0.8106796116504854, "percentage": 40.53, "elapsed_time": "0:01:46", "remaining_time": "0:02:35"}
168
+ {"current_steps": 168, "total_steps": 412, "loss": 0.1516, "lr": 6.42860422342998e-06, "epoch": 0.8155339805825242, "percentage": 40.78, "elapsed_time": "0:01:46", "remaining_time": "0:02:35"}
169
+ {"current_steps": 169, "total_steps": 412, "loss": 0.1481, "lr": 6.392026288706549e-06, "epoch": 0.8203883495145631, "percentage": 41.02, "elapsed_time": "0:01:47", "remaining_time": "0:02:34"}
170
+ {"current_steps": 170, "total_steps": 412, "loss": 0.1731, "lr": 6.3553674163227786e-06, "epoch": 0.8252427184466019, "percentage": 41.26, "elapsed_time": "0:01:47", "remaining_time": "0:02:33"}
171
+ {"current_steps": 171, "total_steps": 412, "loss": 0.1609, "lr": 6.318629737763818e-06, "epoch": 0.8300970873786407, "percentage": 41.5, "elapsed_time": "0:01:48", "remaining_time": "0:02:32"}
172
+ {"current_steps": 172, "total_steps": 412, "loss": 0.1881, "lr": 6.281815389096903e-06, "epoch": 0.8349514563106796, "percentage": 41.75, "elapsed_time": "0:01:49", "remaining_time": "0:02:32"}
173
+ {"current_steps": 173, "total_steps": 412, "loss": 0.1479, "lr": 6.244926510847162e-06, "epoch": 0.8398058252427184, "percentage": 41.99, "elapsed_time": "0:01:49", "remaining_time": "0:02:31"}
174
+ {"current_steps": 174, "total_steps": 412, "loss": 0.1903, "lr": 6.207965247873151e-06, "epoch": 0.8446601941747572, "percentage": 42.23, "elapsed_time": "0:01:50", "remaining_time": "0:02:30"}
175
+ {"current_steps": 175, "total_steps": 412, "loss": 0.1295, "lr": 6.1709337492421515e-06, "epoch": 0.8495145631067961, "percentage": 42.48, "elapsed_time": "0:01:50", "remaining_time": "0:02:30"}
176
+ {"current_steps": 176, "total_steps": 412, "loss": 0.1568, "lr": 6.133834168105206e-06, "epoch": 0.8543689320388349, "percentage": 42.72, "elapsed_time": "0:01:51", "remaining_time": "0:02:29"}
177
+ {"current_steps": 177, "total_steps": 412, "loss": 0.1702, "lr": 6.096668661571934e-06, "epoch": 0.8592233009708737, "percentage": 42.96, "elapsed_time": "0:01:52", "remaining_time": "0:02:28"}
178
+ {"current_steps": 178, "total_steps": 412, "loss": 0.2129, "lr": 6.0594393905851065e-06, "epoch": 0.8640776699029126, "percentage": 43.2, "elapsed_time": "0:01:52", "remaining_time": "0:02:28"}
179
+ {"current_steps": 179, "total_steps": 412, "loss": 0.1777, "lr": 6.0221485197949995e-06, "epoch": 0.8689320388349514, "percentage": 43.45, "elapsed_time": "0:01:53", "remaining_time": "0:02:27"}
180
+ {"current_steps": 180, "total_steps": 412, "loss": 0.218, "lr": 5.9847982174335314e-06, "epoch": 0.8737864077669902, "percentage": 43.69, "elapsed_time": "0:01:53", "remaining_time": "0:02:26"}
181
+ {"current_steps": 181, "total_steps": 412, "loss": 0.1915, "lr": 5.9473906551881985e-06, "epoch": 0.8786407766990292, "percentage": 43.93, "elapsed_time": "0:01:54", "remaining_time": "0:02:26"}
182
+ {"current_steps": 182, "total_steps": 412, "loss": 0.2143, "lr": 5.9099280080758085e-06, "epoch": 0.883495145631068, "percentage": 44.17, "elapsed_time": "0:01:55", "remaining_time": "0:02:25"}
183
+ {"current_steps": 183, "total_steps": 412, "loss": 0.1848, "lr": 5.872412454315999e-06, "epoch": 0.8883495145631068, "percentage": 44.42, "elapsed_time": "0:01:55", "remaining_time": "0:02:24"}
184
+ {"current_steps": 184, "total_steps": 412, "loss": 0.1914, "lr": 5.834846175204612e-06, "epoch": 0.8932038834951457, "percentage": 44.66, "elapsed_time": "0:01:56", "remaining_time": "0:02:24"}
185
+ {"current_steps": 185, "total_steps": 412, "loss": 0.1733, "lr": 5.797231354986842e-06, "epoch": 0.8980582524271845, "percentage": 44.9, "elapsed_time": "0:01:56", "remaining_time": "0:02:23"}
186
+ {"current_steps": 186, "total_steps": 412, "loss": 0.1786, "lr": 5.759570180730255e-06, "epoch": 0.9029126213592233, "percentage": 45.15, "elapsed_time": "0:01:57", "remaining_time": "0:02:22"}
187
+ {"current_steps": 187, "total_steps": 412, "loss": 0.1569, "lr": 5.721864842197612e-06, "epoch": 0.9077669902912622, "percentage": 45.39, "elapsed_time": "0:01:58", "remaining_time": "0:02:22"}
188
+ {"current_steps": 188, "total_steps": 412, "loss": 0.2194, "lr": 5.684117531719552e-06, "epoch": 0.912621359223301, "percentage": 45.63, "elapsed_time": "0:01:58", "remaining_time": "0:02:21"}
189
+ {"current_steps": 189, "total_steps": 412, "loss": 0.1515, "lr": 5.646330444067121e-06, "epoch": 0.9174757281553398, "percentage": 45.87, "elapsed_time": "0:01:59", "remaining_time": "0:02:20"}
190
+ {"current_steps": 190, "total_steps": 412, "loss": 0.1631, "lr": 5.608505776324158e-06, "epoch": 0.9223300970873787, "percentage": 46.12, "elapsed_time": "0:01:59", "remaining_time": "0:02:20"}
191
+ {"current_steps": 191, "total_steps": 412, "loss": 0.1762, "lr": 5.570645727759558e-06, "epoch": 0.9271844660194175, "percentage": 46.36, "elapsed_time": "0:02:00", "remaining_time": "0:02:19"}
192
+ {"current_steps": 192, "total_steps": 412, "loss": 0.1794, "lr": 5.532752499699381e-06, "epoch": 0.9320388349514563, "percentage": 46.6, "elapsed_time": "0:02:01", "remaining_time": "0:02:18"}
193
+ {"current_steps": 193, "total_steps": 412, "loss": 0.178, "lr": 5.494828295398874e-06, "epoch": 0.9368932038834952, "percentage": 46.84, "elapsed_time": "0:02:01", "remaining_time": "0:02:18"}
194
+ {"current_steps": 194, "total_steps": 412, "loss": 0.1558, "lr": 5.456875319914355e-06, "epoch": 0.941747572815534, "percentage": 47.09, "elapsed_time": "0:02:02", "remaining_time": "0:02:17"}
195
+ {"current_steps": 195, "total_steps": 412, "loss": 0.143, "lr": 5.4188957799750145e-06, "epoch": 0.9466019417475728, "percentage": 47.33, "elapsed_time": "0:02:02", "remaining_time": "0:02:16"}
196
+ {"current_steps": 196, "total_steps": 412, "loss": 0.1585, "lr": 5.380891883854591e-06, "epoch": 0.9514563106796117, "percentage": 47.57, "elapsed_time": "0:02:03", "remaining_time": "0:02:16"}
197
+ {"current_steps": 197, "total_steps": 412, "loss": 0.1345, "lr": 5.34286584124299e-06, "epoch": 0.9563106796116505, "percentage": 47.82, "elapsed_time": "0:02:04", "remaining_time": "0:02:15"}
198
+ {"current_steps": 198, "total_steps": 412, "loss": 0.1247, "lr": 5.304819863117796e-06, "epoch": 0.9611650485436893, "percentage": 48.06, "elapsed_time": "0:02:04", "remaining_time": "0:02:14"}
199
+ {"current_steps": 199, "total_steps": 412, "loss": 0.164, "lr": 5.266756161615719e-06, "epoch": 0.9660194174757282, "percentage": 48.3, "elapsed_time": "0:02:05", "remaining_time": "0:02:14"}
200
+ {"current_steps": 200, "total_steps": 412, "loss": 0.1681, "lr": 5.228676949903974e-06, "epoch": 0.970873786407767, "percentage": 48.54, "elapsed_time": "0:02:05", "remaining_time": "0:02:13"}
201
+ {"current_steps": 201, "total_steps": 412, "loss": 0.2034, "lr": 5.190584442051594e-06, "epoch": 0.9757281553398058, "percentage": 48.79, "elapsed_time": "0:02:06", "remaining_time": "0:02:12"}
202
+ {"current_steps": 202, "total_steps": 412, "loss": 2.0615, "lr": 5.1524808529007075e-06, "epoch": 0.9805825242718447, "percentage": 49.03, "elapsed_time": "0:02:07", "remaining_time": "0:02:12"}
203
+ {"current_steps": 203, "total_steps": 412, "loss": 0.18, "lr": 5.114368397937744e-06, "epoch": 0.9854368932038835, "percentage": 49.27, "elapsed_time": "0:02:07", "remaining_time": "0:02:11"}
204
+ {"current_steps": 204, "total_steps": 412, "loss": 0.1692, "lr": 5.07624929316463e-06, "epoch": 0.9902912621359223, "percentage": 49.51, "elapsed_time": "0:02:08", "remaining_time": "0:02:10"}
205
+ {"current_steps": 205, "total_steps": 412, "loss": 0.1597, "lr": 5.038125754969933e-06, "epoch": 0.9951456310679612, "percentage": 49.76, "elapsed_time": "0:02:09", "remaining_time": "0:02:10"}
206
+ {"current_steps": 206, "total_steps": 412, "loss": 0.0509, "lr": 5e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:02:09", "remaining_time": "0:02:09"}
207
+ {"current_steps": 207, "total_steps": 412, "loss": 0.0947, "lr": 4.9618742450300675e-06, "epoch": 1.0048543689320388, "percentage": 50.24, "elapsed_time": "0:02:10", "remaining_time": "0:02:08"}
208
+ {"current_steps": 208, "total_steps": 412, "loss": 0.0877, "lr": 4.923750706835371e-06, "epoch": 1.0097087378640777, "percentage": 50.49, "elapsed_time": "0:02:10", "remaining_time": "0:02:08"}
209
+ {"current_steps": 209, "total_steps": 412, "loss": 0.0849, "lr": 4.8856316020622564e-06, "epoch": 1.0145631067961165, "percentage": 50.73, "elapsed_time": "0:02:11", "remaining_time": "0:02:07"}
210
+ {"current_steps": 210, "total_steps": 412, "loss": 0.0691, "lr": 4.847519147099294e-06, "epoch": 1.0194174757281553, "percentage": 50.97, "elapsed_time": "0:02:12", "remaining_time": "0:02:07"}
211
+ {"current_steps": 211, "total_steps": 412, "loss": 0.095, "lr": 4.809415557948407e-06, "epoch": 1.0242718446601942, "percentage": 51.21, "elapsed_time": "0:02:12", "remaining_time": "0:02:06"}
212
+ {"current_steps": 212, "total_steps": 412, "loss": 0.0836, "lr": 4.771323050096028e-06, "epoch": 1.029126213592233, "percentage": 51.46, "elapsed_time": "0:02:13", "remaining_time": "0:02:05"}
213
+ {"current_steps": 213, "total_steps": 412, "loss": 0.0846, "lr": 4.733243838384282e-06, "epoch": 1.0339805825242718, "percentage": 51.7, "elapsed_time": "0:02:13", "remaining_time": "0:02:05"}
214
+ {"current_steps": 214, "total_steps": 412, "loss": 0.0886, "lr": 4.6951801368822055e-06, "epoch": 1.0388349514563107, "percentage": 51.94, "elapsed_time": "0:02:14", "remaining_time": "0:02:04"}
215
+ {"current_steps": 215, "total_steps": 412, "loss": 0.0853, "lr": 4.6571341587570114e-06, "epoch": 1.0436893203883495, "percentage": 52.18, "elapsed_time": "0:02:15", "remaining_time": "0:02:03"}
216
+ {"current_steps": 216, "total_steps": 412, "loss": 0.0709, "lr": 4.619108116145411e-06, "epoch": 1.0485436893203883, "percentage": 52.43, "elapsed_time": "0:02:15", "remaining_time": "0:02:03"}
217
+ {"current_steps": 217, "total_steps": 412, "loss": 0.0918, "lr": 4.581104220024988e-06, "epoch": 1.0533980582524272, "percentage": 52.67, "elapsed_time": "0:02:16", "remaining_time": "0:02:02"}
218
+ {"current_steps": 218, "total_steps": 412, "loss": 0.0659, "lr": 4.5431246800856455e-06, "epoch": 1.058252427184466, "percentage": 52.91, "elapsed_time": "0:02:16", "remaining_time": "0:02:01"}
219
+ {"current_steps": 219, "total_steps": 412, "loss": 0.0865, "lr": 4.505171704601128e-06, "epoch": 1.0631067961165048, "percentage": 53.16, "elapsed_time": "0:02:17", "remaining_time": "0:02:01"}
220
+ {"current_steps": 220, "total_steps": 412, "loss": 0.0639, "lr": 4.467247500300621e-06, "epoch": 1.0679611650485437, "percentage": 53.4, "elapsed_time": "0:02:18", "remaining_time": "0:02:00"}
221
+ {"current_steps": 221, "total_steps": 412, "loss": 0.075, "lr": 4.4293542722404435e-06, "epoch": 1.0728155339805825, "percentage": 53.64, "elapsed_time": "0:02:18", "remaining_time": "0:01:59"}
222
+ {"current_steps": 222, "total_steps": 412, "loss": 0.0877, "lr": 4.391494223675843e-06, "epoch": 1.0776699029126213, "percentage": 53.88, "elapsed_time": "0:02:19", "remaining_time": "0:01:59"}
223
+ {"current_steps": 223, "total_steps": 412, "loss": 0.0886, "lr": 4.3536695559328816e-06, "epoch": 1.0825242718446602, "percentage": 54.13, "elapsed_time": "0:02:19", "remaining_time": "0:01:58"}
224
+ {"current_steps": 224, "total_steps": 412, "loss": 0.0779, "lr": 4.31588246828045e-06, "epoch": 1.087378640776699, "percentage": 54.37, "elapsed_time": "0:02:20", "remaining_time": "0:01:57"}
225
+ {"current_steps": 225, "total_steps": 412, "loss": 0.0957, "lr": 4.278135157802389e-06, "epoch": 1.0922330097087378, "percentage": 54.61, "elapsed_time": "0:02:21", "remaining_time": "0:01:57"}
226
+ {"current_steps": 226, "total_steps": 412, "loss": 0.0578, "lr": 4.240429819269746e-06, "epoch": 1.0970873786407767, "percentage": 54.85, "elapsed_time": "0:02:21", "remaining_time": "0:01:56"}
227
+ {"current_steps": 227, "total_steps": 412, "loss": 0.0692, "lr": 4.20276864501316e-06, "epoch": 1.1019417475728155, "percentage": 55.1, "elapsed_time": "0:02:22", "remaining_time": "0:01:56"}
228
+ {"current_steps": 228, "total_steps": 412, "loss": 0.0768, "lr": 4.165153824795391e-06, "epoch": 1.1067961165048543, "percentage": 55.34, "elapsed_time": "0:02:22", "remaining_time": "0:01:55"}
229
+ {"current_steps": 229, "total_steps": 412, "loss": 0.0669, "lr": 4.127587545684002e-06, "epoch": 1.1116504854368932, "percentage": 55.58, "elapsed_time": "0:02:23", "remaining_time": "0:01:54"}
230
+ {"current_steps": 230, "total_steps": 412, "loss": 0.0756, "lr": 4.090071991924194e-06, "epoch": 1.116504854368932, "percentage": 55.83, "elapsed_time": "0:02:24", "remaining_time": "0:01:54"}
231
+ {"current_steps": 231, "total_steps": 412, "loss": 1.6006, "lr": 4.052609344811802e-06, "epoch": 1.1213592233009708, "percentage": 56.07, "elapsed_time": "0:02:24", "remaining_time": "0:01:53"}
232
+ {"current_steps": 232, "total_steps": 412, "loss": 0.084, "lr": 4.015201782566471e-06, "epoch": 1.1262135922330097, "percentage": 56.31, "elapsed_time": "0:02:25", "remaining_time": "0:01:52"}
233
+ {"current_steps": 233, "total_steps": 412, "loss": 0.0831, "lr": 3.977851480205003e-06, "epoch": 1.1310679611650485, "percentage": 56.55, "elapsed_time": "0:02:25", "remaining_time": "0:01:52"}
234
+ {"current_steps": 234, "total_steps": 412, "loss": 0.0563, "lr": 3.940560609414894e-06, "epoch": 1.1359223300970873, "percentage": 56.8, "elapsed_time": "0:02:26", "remaining_time": "0:01:51"}
235
+ {"current_steps": 235, "total_steps": 412, "loss": 0.0633, "lr": 3.903331338428067e-06, "epoch": 1.1407766990291262, "percentage": 57.04, "elapsed_time": "0:02:27", "remaining_time": "0:01:50"}
236
+ {"current_steps": 236, "total_steps": 412, "loss": 0.0602, "lr": 3.866165831894796e-06, "epoch": 1.145631067961165, "percentage": 57.28, "elapsed_time": "0:02:27", "remaining_time": "0:01:50"}
237
+ {"current_steps": 237, "total_steps": 412, "loss": 0.0772, "lr": 3.829066250757851e-06, "epoch": 1.1504854368932038, "percentage": 57.52, "elapsed_time": "0:02:28", "remaining_time": "0:01:49"}
238
+ {"current_steps": 238, "total_steps": 412, "loss": 0.0761, "lr": 3.7920347521268514e-06, "epoch": 1.1553398058252426, "percentage": 57.77, "elapsed_time": "0:02:29", "remaining_time": "0:01:48"}
239
+ {"current_steps": 239, "total_steps": 412, "loss": 1.7307, "lr": 3.7550734891528413e-06, "epoch": 1.1601941747572815, "percentage": 58.01, "elapsed_time": "0:02:29", "remaining_time": "0:01:48"}
240
+ {"current_steps": 240, "total_steps": 412, "loss": 0.0761, "lr": 3.7181846109031007e-06, "epoch": 1.1650485436893203, "percentage": 58.25, "elapsed_time": "0:02:30", "remaining_time": "0:01:47"}
241
+ {"current_steps": 241, "total_steps": 412, "loss": 0.0847, "lr": 3.6813702622361858e-06, "epoch": 1.1699029126213591, "percentage": 58.5, "elapsed_time": "0:02:30", "remaining_time": "0:01:47"}
242
+ {"current_steps": 242, "total_steps": 412, "loss": 0.0653, "lr": 3.6446325836772244e-06, "epoch": 1.174757281553398, "percentage": 58.74, "elapsed_time": "0:02:31", "remaining_time": "0:01:46"}
243
+ {"current_steps": 243, "total_steps": 412, "loss": 0.0789, "lr": 3.6079737112934533e-06, "epoch": 1.1796116504854368, "percentage": 58.98, "elapsed_time": "0:02:32", "remaining_time": "0:01:45"}
244
+ {"current_steps": 244, "total_steps": 412, "loss": 0.0603, "lr": 3.5713957765700224e-06, "epoch": 1.1844660194174756, "percentage": 59.22, "elapsed_time": "0:02:32", "remaining_time": "0:01:45"}
245
+ {"current_steps": 245, "total_steps": 412, "loss": 0.0811, "lr": 3.5349009062860586e-06, "epoch": 1.1893203883495145, "percentage": 59.47, "elapsed_time": "0:02:33", "remaining_time": "0:01:44"}
246
+ {"current_steps": 246, "total_steps": 412, "loss": 0.0702, "lr": 3.4984912223910105e-06, "epoch": 1.1941747572815533, "percentage": 59.71, "elapsed_time": "0:02:33", "remaining_time": "0:01:43"}
247
+ {"current_steps": 247, "total_steps": 412, "loss": 0.0784, "lr": 3.46216884188127e-06, "epoch": 1.1990291262135921, "percentage": 59.95, "elapsed_time": "0:02:34", "remaining_time": "0:01:43"}
248
+ {"current_steps": 248, "total_steps": 412, "loss": 0.0656, "lr": 3.425935876677077e-06, "epoch": 1.203883495145631, "percentage": 60.19, "elapsed_time": "0:02:35", "remaining_time": "0:01:42"}
249
+ {"current_steps": 249, "total_steps": 412, "loss": 1.9855, "lr": 3.38979443349973e-06, "epoch": 1.2087378640776698, "percentage": 60.44, "elapsed_time": "0:02:35", "remaining_time": "0:01:41"}
250
+ {"current_steps": 250, "total_steps": 412, "loss": 0.0577, "lr": 3.3537466137490937e-06, "epoch": 1.2135922330097086, "percentage": 60.68, "elapsed_time": "0:02:36", "remaining_time": "0:01:41"}
251
+ {"current_steps": 251, "total_steps": 412, "loss": 0.0704, "lr": 3.3177945133814093e-06, "epoch": 1.2184466019417475, "percentage": 60.92, "elapsed_time": "0:02:36", "remaining_time": "0:01:40"}
252
+ {"current_steps": 252, "total_steps": 412, "loss": 0.0873, "lr": 3.2819402227874364e-06, "epoch": 1.2233009708737863, "percentage": 61.17, "elapsed_time": "0:02:37", "remaining_time": "0:01:40"}
253
+ {"current_steps": 253, "total_steps": 412, "loss": 0.0717, "lr": 3.2461858266709017e-06, "epoch": 1.2281553398058254, "percentage": 61.41, "elapsed_time": "0:02:38", "remaining_time": "0:01:39"}
254
+ {"current_steps": 254, "total_steps": 412, "loss": 0.0712, "lr": 3.2105334039272924e-06, "epoch": 1.233009708737864, "percentage": 61.65, "elapsed_time": "0:02:38", "remaining_time": "0:01:38"}
255
+ {"current_steps": 255, "total_steps": 412, "loss": 0.059, "lr": 3.1749850275229777e-06, "epoch": 1.237864077669903, "percentage": 61.89, "elapsed_time": "0:02:39", "remaining_time": "0:01:38"}
256
+ {"current_steps": 256, "total_steps": 412, "loss": 0.0665, "lr": 3.1395427643746802e-06, "epoch": 1.2427184466019416, "percentage": 62.14, "elapsed_time": "0:02:39", "remaining_time": "0:01:37"}
257
+ {"current_steps": 257, "total_steps": 412, "loss": 0.0714, "lr": 3.1042086752292995e-06, "epoch": 1.2475728155339807, "percentage": 62.38, "elapsed_time": "0:02:40", "remaining_time": "0:01:36"}
258
+ {"current_steps": 258, "total_steps": 412, "loss": 0.0881, "lr": 3.068984814544087e-06, "epoch": 1.2524271844660193, "percentage": 62.62, "elapsed_time": "0:02:41", "remaining_time": "0:01:36"}
259
+ {"current_steps": 259, "total_steps": 412, "loss": 0.0725, "lr": 3.0338732303671993e-06, "epoch": 1.2572815533980584, "percentage": 62.86, "elapsed_time": "0:02:41", "remaining_time": "0:01:35"}
260
+ {"current_steps": 260, "total_steps": 412, "loss": 0.0779, "lr": 2.99887596421861e-06, "epoch": 1.262135922330097, "percentage": 63.11, "elapsed_time": "0:02:42", "remaining_time": "0:01:34"}
261
+ {"current_steps": 261, "total_steps": 412, "loss": 0.1031, "lr": 2.9639950509714138e-06, "epoch": 1.266990291262136, "percentage": 63.35, "elapsed_time": "0:02:42", "remaining_time": "0:01:34"}
262
+ {"current_steps": 262, "total_steps": 412, "loss": 1.7571, "lr": 2.929232518733507e-06, "epoch": 1.2718446601941746, "percentage": 63.59, "elapsed_time": "0:02:43", "remaining_time": "0:01:33"}
263
+ {"current_steps": 263, "total_steps": 412, "loss": 0.0628, "lr": 2.8945903887296686e-06, "epoch": 1.2766990291262137, "percentage": 63.83, "elapsed_time": "0:02:44", "remaining_time": "0:01:33"}
264
+ {"current_steps": 264, "total_steps": 412, "loss": 0.0819, "lr": 2.860070675184036e-06, "epoch": 1.2815533980582523, "percentage": 64.08, "elapsed_time": "0:02:44", "remaining_time": "0:01:32"}
265
+ {"current_steps": 265, "total_steps": 412, "loss": 0.0959, "lr": 2.8256753852029917e-06, "epoch": 1.2864077669902914, "percentage": 64.32, "elapsed_time": "0:02:45", "remaining_time": "0:01:31"}
266
+ {"current_steps": 266, "total_steps": 412, "loss": 0.0853, "lr": 2.7914065186584637e-06, "epoch": 1.29126213592233, "percentage": 64.56, "elapsed_time": "0:02:46", "remaining_time": "0:01:31"}
267
+ {"current_steps": 267, "total_steps": 412, "loss": 0.0711, "lr": 2.757266068071648e-06, "epoch": 1.296116504854369, "percentage": 64.81, "elapsed_time": "0:02:46", "remaining_time": "0:01:30"}
268
+ {"current_steps": 268, "total_steps": 412, "loss": 0.0925, "lr": 2.7232560184971437e-06, "epoch": 1.3009708737864076, "percentage": 65.05, "elapsed_time": "0:02:47", "remaining_time": "0:01:29"}
269
+ {"current_steps": 269, "total_steps": 412, "loss": 0.0733, "lr": 2.689378347407553e-06, "epoch": 1.3058252427184467, "percentage": 65.29, "elapsed_time": "0:02:47", "remaining_time": "0:01:29"}
270
+ {"current_steps": 270, "total_steps": 412, "loss": 1.3862, "lr": 2.6556350245784833e-06, "epoch": 1.3106796116504853, "percentage": 65.53, "elapsed_time": "0:02:48", "remaining_time": "0:01:28"}
271
+ {"current_steps": 271, "total_steps": 412, "loss": 0.0802, "lr": 2.6220280119740376e-06, "epoch": 1.3155339805825244, "percentage": 65.78, "elapsed_time": "0:02:49", "remaining_time": "0:01:27"}
272
+ {"current_steps": 272, "total_steps": 412, "loss": 0.0881, "lr": 2.588559263632719e-06, "epoch": 1.3203883495145632, "percentage": 66.02, "elapsed_time": "0:02:49", "remaining_time": "0:01:27"}
273
+ {"current_steps": 273, "total_steps": 412, "loss": 0.0695, "lr": 2.555230725553832e-06, "epoch": 1.325242718446602, "percentage": 66.26, "elapsed_time": "0:02:50", "remaining_time": "0:01:26"}
274
+ {"current_steps": 274, "total_steps": 412, "loss": 0.0808, "lr": 2.522044335584322e-06, "epoch": 1.3300970873786409, "percentage": 66.5, "elapsed_time": "0:02:50", "remaining_time": "0:01:26"}
275
+ {"current_steps": 275, "total_steps": 412, "loss": 0.1095, "lr": 2.489002023306112e-06, "epoch": 1.3349514563106797, "percentage": 66.75, "elapsed_time": "0:02:51", "remaining_time": "0:01:25"}
276
+ {"current_steps": 276, "total_steps": 412, "loss": 0.124, "lr": 2.4561057099238973e-06, "epoch": 1.3398058252427185, "percentage": 66.99, "elapsed_time": "0:02:52", "remaining_time": "0:01:24"}
277
+ {"current_steps": 277, "total_steps": 412, "loss": 0.0726, "lr": 2.423357308153454e-06, "epoch": 1.3446601941747574, "percentage": 67.23, "elapsed_time": "0:02:52", "remaining_time": "0:01:24"}
278
+ {"current_steps": 278, "total_steps": 412, "loss": 0.0746, "lr": 2.390758722110418e-06, "epoch": 1.3495145631067962, "percentage": 67.48, "elapsed_time": "0:02:53", "remaining_time": "0:01:23"}
279
+ {"current_steps": 279, "total_steps": 412, "loss": 0.067, "lr": 2.358311847199567e-06, "epoch": 1.354368932038835, "percentage": 67.72, "elapsed_time": "0:02:53", "remaining_time": "0:01:22"}
280
+ {"current_steps": 280, "total_steps": 412, "loss": 0.0553, "lr": 2.3260185700046295e-06, "epoch": 1.3592233009708738, "percentage": 67.96, "elapsed_time": "0:02:54", "remaining_time": "0:01:22"}
281
+ {"current_steps": 281, "total_steps": 412, "loss": 0.069, "lr": 2.2938807681785764e-06, "epoch": 1.3640776699029127, "percentage": 68.2, "elapsed_time": "0:02:55", "remaining_time": "0:01:21"}
282
+ {"current_steps": 282, "total_steps": 412, "loss": 0.1027, "lr": 2.2619003103344607e-06, "epoch": 1.3689320388349515, "percentage": 68.45, "elapsed_time": "0:02:55", "remaining_time": "0:01:21"}
283
+ {"current_steps": 283, "total_steps": 412, "loss": 0.0699, "lr": 2.2300790559367553e-06, "epoch": 1.3737864077669903, "percentage": 68.69, "elapsed_time": "0:02:56", "remaining_time": "0:01:20"}
284
+ {"current_steps": 284, "total_steps": 412, "loss": 0.0674, "lr": 2.1984188551932513e-06, "epoch": 1.3786407766990292, "percentage": 68.93, "elapsed_time": "0:02:56", "remaining_time": "0:01:19"}
285
+ {"current_steps": 285, "total_steps": 412, "loss": 0.0978, "lr": 2.166921548947466e-06, "epoch": 1.383495145631068, "percentage": 69.17, "elapsed_time": "0:02:57", "remaining_time": "0:01:19"}
286
+ {"current_steps": 286, "total_steps": 412, "loss": 0.0867, "lr": 2.1355889685716225e-06, "epoch": 1.3883495145631068, "percentage": 69.42, "elapsed_time": "0:02:58", "remaining_time": "0:01:18"}
287
+ {"current_steps": 287, "total_steps": 412, "loss": 0.0703, "lr": 2.1044229358601543e-06, "epoch": 1.3932038834951457, "percentage": 69.66, "elapsed_time": "0:02:58", "remaining_time": "0:01:17"}
288
+ {"current_steps": 288, "total_steps": 412, "loss": 0.0659, "lr": 2.0734252629237892e-06, "epoch": 1.3980582524271845, "percentage": 69.9, "elapsed_time": "0:02:59", "remaining_time": "0:01:17"}
289
+ {"current_steps": 289, "total_steps": 412, "loss": 0.0688, "lr": 2.0425977520841837e-06, "epoch": 1.4029126213592233, "percentage": 70.15, "elapsed_time": "0:02:59", "remaining_time": "0:01:16"}
290
+ {"current_steps": 290, "total_steps": 412, "loss": 0.0559, "lr": 2.011942195769122e-06, "epoch": 1.4077669902912622, "percentage": 70.39, "elapsed_time": "0:03:00", "remaining_time": "0:01:15"}
291
+ {"current_steps": 291, "total_steps": 412, "loss": 0.0569, "lr": 1.9814603764083112e-06, "epoch": 1.412621359223301, "percentage": 70.63, "elapsed_time": "0:03:01", "remaining_time": "0:01:15"}
292
+ {"current_steps": 292, "total_steps": 412, "loss": 0.0898, "lr": 1.9511540663297284e-06, "epoch": 1.4174757281553398, "percentage": 70.87, "elapsed_time": "0:03:01", "remaining_time": "0:01:14"}
293
+ {"current_steps": 293, "total_steps": 412, "loss": 0.0677, "lr": 1.921025027656587e-06, "epoch": 1.4223300970873787, "percentage": 71.12, "elapsed_time": "0:03:02", "remaining_time": "0:01:14"}
294
+ {"current_steps": 294, "total_steps": 412, "loss": 0.0753, "lr": 1.8910750122048638e-06, "epoch": 1.4271844660194175, "percentage": 71.36, "elapsed_time": "0:03:02", "remaining_time": "0:01:13"}
295
+ {"current_steps": 295, "total_steps": 412, "loss": 0.0575, "lr": 1.8613057613814584e-06, "epoch": 1.4320388349514563, "percentage": 71.6, "elapsed_time": "0:03:03", "remaining_time": "0:01:12"}
296
+ {"current_steps": 296, "total_steps": 412, "loss": 0.0947, "lr": 1.8317190060829242e-06, "epoch": 1.4368932038834952, "percentage": 71.84, "elapsed_time": "0:03:04", "remaining_time": "0:01:12"}
297
+ {"current_steps": 297, "total_steps": 412, "loss": 0.0807, "lr": 1.8023164665948455e-06, "epoch": 1.441747572815534, "percentage": 72.09, "elapsed_time": "0:03:04", "remaining_time": "0:01:11"}
298
+ {"current_steps": 298, "total_steps": 412, "loss": 0.0736, "lr": 1.773099852491796e-06, "epoch": 1.4466019417475728, "percentage": 72.33, "elapsed_time": "0:03:05", "remaining_time": "0:01:10"}
299
+ {"current_steps": 299, "total_steps": 412, "loss": 0.0625, "lr": 1.7440708625379503e-06, "epoch": 1.4514563106796117, "percentage": 72.57, "elapsed_time": "0:03:05", "remaining_time": "0:01:10"}
300
+ {"current_steps": 300, "total_steps": 412, "loss": 0.0842, "lr": 1.7152311845883096e-06, "epoch": 1.4563106796116505, "percentage": 72.82, "elapsed_time": "0:03:06", "remaining_time": "0:01:09"}
301
+ {"current_steps": 301, "total_steps": 412, "loss": 0.0708, "lr": 1.686582495490554e-06, "epoch": 1.4611650485436893, "percentage": 73.06, "elapsed_time": "0:03:07", "remaining_time": "0:01:09"}
302
+ {"current_steps": 302, "total_steps": 412, "loss": 0.0637, "lr": 1.658126460987558e-06, "epoch": 1.4660194174757282, "percentage": 73.3, "elapsed_time": "0:03:07", "remaining_time": "0:01:08"}
303
+ {"current_steps": 303, "total_steps": 412, "loss": 0.0747, "lr": 1.6298647356205255e-06, "epoch": 1.470873786407767, "percentage": 73.54, "elapsed_time": "0:03:08", "remaining_time": "0:01:07"}
304
+ {"current_steps": 304, "total_steps": 412, "loss": 0.0597, "lr": 1.601798962632799e-06, "epoch": 1.4757281553398058, "percentage": 73.79, "elapsed_time": "0:03:09", "remaining_time": "0:01:07"}
305
+ {"current_steps": 305, "total_steps": 412, "loss": 0.065, "lr": 1.573930773874306e-06, "epoch": 1.4805825242718447, "percentage": 74.03, "elapsed_time": "0:03:09", "remaining_time": "0:01:06"}
306
+ {"current_steps": 306, "total_steps": 412, "loss": 0.0712, "lr": 1.5462617897066863e-06, "epoch": 1.4854368932038835, "percentage": 74.27, "elapsed_time": "0:03:10", "remaining_time": "0:01:05"}
307
+ {"current_steps": 307, "total_steps": 412, "loss": 0.1966, "lr": 1.5187936189090668e-06, "epoch": 1.4902912621359223, "percentage": 74.51, "elapsed_time": "0:03:10", "remaining_time": "0:01:05"}
308
+ {"current_steps": 308, "total_steps": 412, "loss": 0.0755, "lr": 1.491527858584535e-06, "epoch": 1.4951456310679612, "percentage": 74.76, "elapsed_time": "0:03:11", "remaining_time": "0:01:04"}
309
+ {"current_steps": 309, "total_steps": 412, "loss": 0.0955, "lr": 1.4644660940672628e-06, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "0:03:12", "remaining_time": "0:01:04"}
310
+ {"current_steps": 310, "total_steps": 412, "loss": 0.0629, "lr": 1.4376098988303406e-06, "epoch": 1.5048543689320388, "percentage": 75.24, "elapsed_time": "0:03:12", "remaining_time": "0:01:03"}
311
+ {"current_steps": 311, "total_steps": 412, "loss": 0.0638, "lr": 1.4109608343942855e-06, "epoch": 1.5097087378640777, "percentage": 75.49, "elapsed_time": "0:03:13", "remaining_time": "0:01:02"}
312
+ {"current_steps": 312, "total_steps": 412, "loss": 0.0712, "lr": 1.3845204502362442e-06, "epoch": 1.5145631067961165, "percentage": 75.73, "elapsed_time": "0:03:13", "remaining_time": "0:01:02"}
313
+ {"current_steps": 313, "total_steps": 412, "loss": 0.0877, "lr": 1.35829028369991e-06, "epoch": 1.5194174757281553, "percentage": 75.97, "elapsed_time": "0:03:14", "remaining_time": "0:01:01"}
314
+ {"current_steps": 314, "total_steps": 412, "loss": 0.0568, "lr": 1.3322718599061252e-06, "epoch": 1.5242718446601942, "percentage": 76.21, "elapsed_time": "0:03:15", "remaining_time": "0:01:00"}
315
+ {"current_steps": 315, "total_steps": 412, "loss": 0.0818, "lr": 1.306466691664216e-06, "epoch": 1.529126213592233, "percentage": 76.46, "elapsed_time": "0:03:15", "remaining_time": "0:01:00"}
316
+ {"current_steps": 316, "total_steps": 412, "loss": 0.0686, "lr": 1.28087627938402e-06, "epoch": 1.5339805825242718, "percentage": 76.7, "elapsed_time": "0:03:16", "remaining_time": "0:00:59"}
317
+ {"current_steps": 317, "total_steps": 412, "loss": 0.0897, "lr": 1.2555021109886589e-06, "epoch": 1.5388349514563107, "percentage": 76.94, "elapsed_time": "0:03:16", "remaining_time": "0:00:59"}
318
+ {"current_steps": 318, "total_steps": 412, "loss": 0.0793, "lr": 1.2303456618280141e-06, "epoch": 1.5436893203883495, "percentage": 77.18, "elapsed_time": "0:03:17", "remaining_time": "0:00:58"}
319
+ {"current_steps": 319, "total_steps": 412, "loss": 0.0633, "lr": 1.2054083945929534e-06, "epoch": 1.5485436893203883, "percentage": 77.43, "elapsed_time": "0:03:18", "remaining_time": "0:00:57"}
320
+ {"current_steps": 320, "total_steps": 412, "loss": 0.0643, "lr": 1.1806917592302763e-06, "epoch": 1.5533980582524272, "percentage": 77.67, "elapsed_time": "0:03:18", "remaining_time": "0:00:57"}
321
+ {"current_steps": 321, "total_steps": 412, "loss": 0.056, "lr": 1.1561971928584158e-06, "epoch": 1.558252427184466, "percentage": 77.91, "elapsed_time": "0:03:19", "remaining_time": "0:00:56"}
322
+ {"current_steps": 322, "total_steps": 412, "loss": 0.0839, "lr": 1.1319261196838782e-06, "epoch": 1.5631067961165048, "percentage": 78.16, "elapsed_time": "0:03:19", "remaining_time": "0:00:55"}
323
+ {"current_steps": 323, "total_steps": 412, "loss": 0.097, "lr": 1.1078799509184246e-06, "epoch": 1.5679611650485437, "percentage": 78.4, "elapsed_time": "0:03:20", "remaining_time": "0:00:55"}
324
+ {"current_steps": 324, "total_steps": 412, "loss": 0.0842, "lr": 1.0840600846970333e-06, "epoch": 1.5728155339805825, "percentage": 78.64, "elapsed_time": "0:03:21", "remaining_time": "0:00:54"}
325
+ {"current_steps": 325, "total_steps": 412, "loss": 0.1058, "lr": 1.0604679059965923e-06, "epoch": 1.5776699029126213, "percentage": 78.88, "elapsed_time": "0:03:21", "remaining_time": "0:00:54"}
326
+ {"current_steps": 326, "total_steps": 412, "loss": 0.0849, "lr": 1.0371047865553847e-06, "epoch": 1.5825242718446602, "percentage": 79.13, "elapsed_time": "0:03:22", "remaining_time": "0:00:53"}
327
+ {"current_steps": 327, "total_steps": 412, "loss": 0.0626, "lr": 1.0139720847933166e-06, "epoch": 1.587378640776699, "percentage": 79.37, "elapsed_time": "0:03:22", "remaining_time": "0:00:52"}
328
+ {"current_steps": 328, "total_steps": 412, "loss": 0.085, "lr": 9.91071145732948e-07, "epoch": 1.5922330097087378, "percentage": 79.61, "elapsed_time": "0:03:23", "remaining_time": "0:00:52"}
329
+ {"current_steps": 329, "total_steps": 412, "loss": 0.0922, "lr": 9.684033009212752e-07, "epoch": 1.5970873786407767, "percentage": 79.85, "elapsed_time": "0:03:24", "remaining_time": "0:00:51"}
330
+ {"current_steps": 330, "total_steps": 412, "loss": 0.0813, "lr": 9.459698683523205e-07, "epoch": 1.6019417475728155, "percentage": 80.1, "elapsed_time": "0:03:24", "remaining_time": "0:00:50"}
331
+ {"current_steps": 331, "total_steps": 412, "loss": 0.1209, "lr": 9.237721523904891e-07, "epoch": 1.6067961165048543, "percentage": 80.34, "elapsed_time": "0:03:25", "remaining_time": "0:00:50"}
332
+ {"current_steps": 332, "total_steps": 412, "loss": 0.0478, "lr": 9.018114436947373e-07, "epoch": 1.6116504854368932, "percentage": 80.58, "elapsed_time": "0:03:25", "remaining_time": "0:00:49"}
333
+ {"current_steps": 333, "total_steps": 412, "loss": 0.0669, "lr": 8.80089019143524e-07, "epoch": 1.616504854368932, "percentage": 80.83, "elapsed_time": "0:03:26", "remaining_time": "0:00:49"}
334
+ {"current_steps": 334, "total_steps": 412, "loss": 0.0682, "lr": 8.586061417605668e-07, "epoch": 1.6213592233009708, "percentage": 81.07, "elapsed_time": "0:03:27", "remaining_time": "0:00:48"}
335
+ {"current_steps": 335, "total_steps": 412, "loss": 0.0559, "lr": 8.373640606414097e-07, "epoch": 1.6262135922330097, "percentage": 81.31, "elapsed_time": "0:03:27", "remaining_time": "0:00:47"}
336
+ {"current_steps": 336, "total_steps": 412, "loss": 1.6835, "lr": 8.163640108807897e-07, "epoch": 1.6310679611650487, "percentage": 81.55, "elapsed_time": "0:03:28", "remaining_time": "0:00:47"}
337
+ {"current_steps": 337, "total_steps": 412, "loss": 0.0574, "lr": 7.956072135008336e-07, "epoch": 1.6359223300970873, "percentage": 81.8, "elapsed_time": "0:03:29", "remaining_time": "0:00:46"}
338
+ {"current_steps": 338, "total_steps": 412, "loss": 1.6776, "lr": 7.750948753800508e-07, "epoch": 1.6407766990291264, "percentage": 82.04, "elapsed_time": "0:03:29", "remaining_time": "0:00:45"}
339
+ {"current_steps": 339, "total_steps": 412, "loss": 0.0599, "lr": 7.548281891831715e-07, "epoch": 1.645631067961165, "percentage": 82.28, "elapsed_time": "0:03:30", "remaining_time": "0:00:45"}
340
+ {"current_steps": 340, "total_steps": 412, "loss": 0.0867, "lr": 7.348083332917927e-07, "epoch": 1.650485436893204, "percentage": 82.52, "elapsed_time": "0:03:30", "remaining_time": "0:00:44"}
341
+ {"current_steps": 341, "total_steps": 412, "loss": 0.1163, "lr": 7.150364717358699e-07, "epoch": 1.6553398058252426, "percentage": 82.77, "elapsed_time": "0:03:31", "remaining_time": "0:00:44"}
342
+ {"current_steps": 342, "total_steps": 412, "loss": 0.0729, "lr": 6.955137541260287e-07, "epoch": 1.6601941747572817, "percentage": 83.01, "elapsed_time": "0:03:32", "remaining_time": "0:00:43"}
343
+ {"current_steps": 343, "total_steps": 412, "loss": 0.0669, "lr": 6.762413155867276e-07, "epoch": 1.6650485436893203, "percentage": 83.25, "elapsed_time": "0:03:32", "remaining_time": "0:00:42"}
344
+ {"current_steps": 344, "total_steps": 412, "loss": 0.102, "lr": 6.572202766902569e-07, "epoch": 1.6699029126213594, "percentage": 83.5, "elapsed_time": "0:03:33", "remaining_time": "0:00:42"}
345
+ {"current_steps": 345, "total_steps": 412, "loss": 0.0774, "lr": 6.384517433915794e-07, "epoch": 1.674757281553398, "percentage": 83.74, "elapsed_time": "0:03:33", "remaining_time": "0:00:41"}
346
+ {"current_steps": 346, "total_steps": 412, "loss": 0.0674, "lr": 6.199368069640343e-07, "epoch": 1.679611650485437, "percentage": 83.98, "elapsed_time": "0:03:34", "remaining_time": "0:00:40"}
347
+ {"current_steps": 347, "total_steps": 412, "loss": 0.1105, "lr": 6.016765439358774e-07, "epoch": 1.6844660194174756, "percentage": 84.22, "elapsed_time": "0:03:35", "remaining_time": "0:00:40"}
348
+ {"current_steps": 348, "total_steps": 412, "loss": 0.0629, "lr": 5.836720160276971e-07, "epoch": 1.6893203883495147, "percentage": 84.47, "elapsed_time": "0:03:35", "remaining_time": "0:00:39"}
349
+ {"current_steps": 349, "total_steps": 412, "loss": 0.0936, "lr": 5.659242700906719e-07, "epoch": 1.6941747572815533, "percentage": 84.71, "elapsed_time": "0:03:36", "remaining_time": "0:00:39"}
350
+ {"current_steps": 350, "total_steps": 412, "loss": 0.0835, "lr": 5.484343380457124e-07, "epoch": 1.6990291262135924, "percentage": 84.95, "elapsed_time": "0:03:36", "remaining_time": "0:00:38"}
351
+ {"current_steps": 351, "total_steps": 412, "loss": 0.0619, "lr": 5.312032368234527e-07, "epoch": 1.703883495145631, "percentage": 85.19, "elapsed_time": "0:03:37", "remaining_time": "0:00:37"}
352
+ {"current_steps": 352, "total_steps": 412, "loss": 0.0688, "lr": 5.1423196830513e-07, "epoch": 1.70873786407767, "percentage": 85.44, "elapsed_time": "0:03:38", "remaining_time": "0:00:37"}
353
+ {"current_steps": 353, "total_steps": 412, "loss": 0.0595, "lr": 4.975215192643246e-07, "epoch": 1.7135922330097086, "percentage": 85.68, "elapsed_time": "0:03:38", "remaining_time": "0:00:36"}
354
+ {"current_steps": 354, "total_steps": 412, "loss": 2.1163, "lr": 4.81072861309591e-07, "epoch": 1.7184466019417477, "percentage": 85.92, "elapsed_time": "0:03:39", "remaining_time": "0:00:35"}
355
+ {"current_steps": 355, "total_steps": 412, "loss": 0.0736, "lr": 4.648869508279613e-07, "epoch": 1.7233009708737863, "percentage": 86.17, "elapsed_time": "0:03:40", "remaining_time": "0:00:35"}
356
+ {"current_steps": 356, "total_steps": 412, "loss": 0.0651, "lr": 4.4896472892933693e-07, "epoch": 1.7281553398058254, "percentage": 86.41, "elapsed_time": "0:03:40", "remaining_time": "0:00:34"}
357
+ {"current_steps": 357, "total_steps": 412, "loss": 0.0571, "lr": 4.333071213917722e-07, "epoch": 1.733009708737864, "percentage": 86.65, "elapsed_time": "0:03:41", "remaining_time": "0:00:34"}
358
+ {"current_steps": 358, "total_steps": 412, "loss": 1.55, "lr": 4.179150386076425e-07, "epoch": 1.737864077669903, "percentage": 86.89, "elapsed_time": "0:03:41", "remaining_time": "0:00:33"}
359
+ {"current_steps": 359, "total_steps": 412, "loss": 0.0879, "lr": 4.027893755307144e-07, "epoch": 1.7427184466019416, "percentage": 87.14, "elapsed_time": "0:03:42", "remaining_time": "0:00:32"}
360
+ {"current_steps": 360, "total_steps": 412, "loss": 0.0806, "lr": 3.8793101162410417e-07, "epoch": 1.7475728155339807, "percentage": 87.38, "elapsed_time": "0:03:43", "remaining_time": "0:00:32"}
361
+ {"current_steps": 361, "total_steps": 412, "loss": 0.0592, "lr": 3.733408108091485e-07, "epoch": 1.7524271844660193, "percentage": 87.62, "elapsed_time": "0:03:43", "remaining_time": "0:00:31"}
362
+ {"current_steps": 362, "total_steps": 412, "loss": 0.0906, "lr": 3.5901962141516975e-07, "epoch": 1.7572815533980584, "percentage": 87.86, "elapsed_time": "0:03:44", "remaining_time": "0:00:30"}
363
+ {"current_steps": 363, "total_steps": 412, "loss": 0.0893, "lr": 3.4496827613015206e-07, "epoch": 1.762135922330097, "percentage": 88.11, "elapsed_time": "0:03:44", "remaining_time": "0:00:30"}
364
+ {"current_steps": 364, "total_steps": 412, "loss": 0.1123, "lr": 3.3118759195232273e-07, "epoch": 1.766990291262136, "percentage": 88.35, "elapsed_time": "0:03:45", "remaining_time": "0:00:29"}
365
+ {"current_steps": 365, "total_steps": 412, "loss": 0.0783, "lr": 3.176783701426528e-07, "epoch": 1.7718446601941746, "percentage": 88.59, "elapsed_time": "0:03:46", "remaining_time": "0:00:29"}
366
+ {"current_steps": 366, "total_steps": 412, "loss": 0.0801, "lr": 3.0444139617826605e-07, "epoch": 1.7766990291262137, "percentage": 88.83, "elapsed_time": "0:03:46", "remaining_time": "0:00:28"}
367
+ {"current_steps": 367, "total_steps": 412, "loss": 0.0778, "lr": 2.91477439706771e-07, "epoch": 1.7815533980582523, "percentage": 89.08, "elapsed_time": "0:03:47", "remaining_time": "0:00:27"}
368
+ {"current_steps": 368, "total_steps": 412, "loss": 0.0703, "lr": 2.787872545015069e-07, "epoch": 1.7864077669902914, "percentage": 89.32, "elapsed_time": "0:03:47", "remaining_time": "0:00:27"}
369
+ {"current_steps": 369, "total_steps": 412, "loss": 0.0713, "lr": 2.663715784177201e-07, "epoch": 1.79126213592233, "percentage": 89.56, "elapsed_time": "0:03:48", "remaining_time": "0:00:26"}
370
+ {"current_steps": 370, "total_steps": 412, "loss": 0.0927, "lr": 2.542311333496622e-07, "epoch": 1.796116504854369, "percentage": 89.81, "elapsed_time": "0:03:49", "remaining_time": "0:00:26"}
371
+ {"current_steps": 371, "total_steps": 412, "loss": 0.0803, "lr": 2.423666251886114e-07, "epoch": 1.8009708737864076, "percentage": 90.05, "elapsed_time": "0:03:49", "remaining_time": "0:00:25"}
372
+ {"current_steps": 372, "total_steps": 412, "loss": 0.0549, "lr": 2.307787437818365e-07, "epoch": 1.8058252427184467, "percentage": 90.29, "elapsed_time": "0:03:50", "remaining_time": "0:00:24"}
373
+ {"current_steps": 373, "total_steps": 412, "loss": 0.0768, "lr": 2.1946816289248163e-07, "epoch": 1.8106796116504853, "percentage": 90.53, "elapsed_time": "0:03:50", "remaining_time": "0:00:24"}
374
+ {"current_steps": 374, "total_steps": 412, "loss": 0.0812, "lr": 2.0843554016039326e-07, "epoch": 1.8155339805825244, "percentage": 90.78, "elapsed_time": "0:03:51", "remaining_time": "0:00:23"}
375
+ {"current_steps": 375, "total_steps": 412, "loss": 0.0693, "lr": 1.9768151706388016e-07, "epoch": 1.820388349514563, "percentage": 91.02, "elapsed_time": "0:03:52", "remaining_time": "0:00:22"}
376
+ {"current_steps": 376, "total_steps": 412, "loss": 0.0698, "lr": 1.8720671888242058e-07, "epoch": 1.825242718446602, "percentage": 91.26, "elapsed_time": "0:03:52", "remaining_time": "0:00:22"}
377
+ {"current_steps": 377, "total_steps": 412, "loss": 0.073, "lr": 1.7701175466029895e-07, "epoch": 1.8300970873786406, "percentage": 91.5, "elapsed_time": "0:03:53", "remaining_time": "0:00:21"}
378
+ {"current_steps": 378, "total_steps": 412, "loss": 0.1111, "lr": 1.6709721717120042e-07, "epoch": 1.8349514563106797, "percentage": 91.75, "elapsed_time": "0:03:53", "remaining_time": "0:00:21"}
379
+ {"current_steps": 379, "total_steps": 412, "loss": 0.081, "lr": 1.574636828837395e-07, "epoch": 1.8398058252427183, "percentage": 91.99, "elapsed_time": "0:03:54", "remaining_time": "0:00:20"}
380
+ {"current_steps": 380, "total_steps": 412, "loss": 0.0684, "lr": 1.4811171192794628e-07, "epoch": 1.8446601941747574, "percentage": 92.23, "elapsed_time": "0:03:55", "remaining_time": "0:00:19"}
381
+ {"current_steps": 381, "total_steps": 412, "loss": 0.0841, "lr": 1.3904184806269705e-07, "epoch": 1.849514563106796, "percentage": 92.48, "elapsed_time": "0:03:55", "remaining_time": "0:00:19"}
382
+ {"current_steps": 382, "total_steps": 412, "loss": 0.0527, "lr": 1.3025461864409395e-07, "epoch": 1.854368932038835, "percentage": 92.72, "elapsed_time": "0:03:56", "remaining_time": "0:00:18"}
383
+ {"current_steps": 383, "total_steps": 412, "loss": 0.0839, "lr": 1.2175053459481e-07, "epoch": 1.8592233009708736, "percentage": 92.96, "elapsed_time": "0:03:56", "remaining_time": "0:00:17"}
384
+ {"current_steps": 384, "total_steps": 412, "loss": 0.0641, "lr": 1.1353009037437523e-07, "epoch": 1.8640776699029127, "percentage": 93.2, "elapsed_time": "0:03:57", "remaining_time": "0:00:17"}
385
+ {"current_steps": 385, "total_steps": 412, "loss": 0.0945, "lr": 1.0559376395043285e-07, "epoch": 1.8689320388349513, "percentage": 93.45, "elapsed_time": "0:03:58", "remaining_time": "0:00:16"}
386
+ {"current_steps": 386, "total_steps": 412, "loss": 0.0691, "lr": 9.794201677094162e-08, "epoch": 1.8737864077669903, "percentage": 93.69, "elapsed_time": "0:03:58", "remaining_time": "0:00:16"}
387
+ {"current_steps": 387, "total_steps": 412, "loss": 0.067, "lr": 9.05752937373533e-08, "epoch": 1.8786407766990292, "percentage": 93.93, "elapsed_time": "0:03:59", "remaining_time": "0:00:15"}
388
+ {"current_steps": 388, "total_steps": 412, "loss": 0.056, "lr": 8.34940231787379e-08, "epoch": 1.883495145631068, "percentage": 94.17, "elapsed_time": "0:03:59", "remaining_time": "0:00:14"}
389
+ {"current_steps": 389, "total_steps": 412, "loss": 0.0538, "lr": 7.66986168268824e-08, "epoch": 1.8883495145631068, "percentage": 94.42, "elapsed_time": "0:04:00", "remaining_time": "0:00:14"}
390
+ {"current_steps": 390, "total_steps": 412, "loss": 0.0713, "lr": 7.018946979234997e-08, "epoch": 1.8932038834951457, "percentage": 94.66, "elapsed_time": "0:04:01", "remaining_time": "0:00:13"}
391
+ {"current_steps": 391, "total_steps": 412, "loss": 0.0555, "lr": 6.396696054150719e-08, "epoch": 1.8980582524271845, "percentage": 94.9, "elapsed_time": "0:04:01", "remaining_time": "0:00:12"}
392
+ {"current_steps": 392, "total_steps": 412, "loss": 0.0621, "lr": 5.803145087451945e-08, "epoch": 1.9029126213592233, "percentage": 95.15, "elapsed_time": "0:04:02", "remaining_time": "0:00:12"}
393
+ {"current_steps": 393, "total_steps": 412, "loss": 0.1006, "lr": 5.238328590431163e-08, "epoch": 1.9077669902912622, "percentage": 95.39, "elapsed_time": "0:04:02", "remaining_time": "0:00:11"}
394
+ {"current_steps": 394, "total_steps": 412, "loss": 0.0677, "lr": 4.702279403650534e-08, "epoch": 1.912621359223301, "percentage": 95.63, "elapsed_time": "0:04:03", "remaining_time": "0:00:11"}
395
+ {"current_steps": 395, "total_steps": 412, "loss": 0.0888, "lr": 4.195028695032133e-08, "epoch": 1.9174757281553398, "percentage": 95.87, "elapsed_time": "0:04:04", "remaining_time": "0:00:10"}
396
+ {"current_steps": 396, "total_steps": 412, "loss": 0.0643, "lr": 3.716605958046071e-08, "epoch": 1.9223300970873787, "percentage": 96.12, "elapsed_time": "0:04:04", "remaining_time": "0:00:09"}
397
+ {"current_steps": 397, "total_steps": 412, "loss": 0.07, "lr": 3.2670390099951985e-08, "epoch": 1.9271844660194175, "percentage": 96.36, "elapsed_time": "0:04:05", "remaining_time": "0:00:09"}
398
+ {"current_steps": 398, "total_steps": 412, "loss": 0.0991, "lr": 2.846353990398065e-08, "epoch": 1.9320388349514563, "percentage": 96.6, "elapsed_time": "0:04:05", "remaining_time": "0:00:08"}
399
+ {"current_steps": 399, "total_steps": 412, "loss": 1.4371, "lr": 2.4545753594688582e-08, "epoch": 1.9368932038834952, "percentage": 96.84, "elapsed_time": "0:04:06", "remaining_time": "0:00:08"}
400
+ {"current_steps": 400, "total_steps": 412, "loss": 0.083, "lr": 2.0917258966953735e-08, "epoch": 1.941747572815534, "percentage": 97.09, "elapsed_time": "0:04:07", "remaining_time": "0:00:07"}
401
+ {"current_steps": 401, "total_steps": 412, "loss": 0.0755, "lr": 1.757826699514298e-08, "epoch": 1.9466019417475728, "percentage": 97.33, "elapsed_time": "0:04:07", "remaining_time": "0:00:06"}
402
+ {"current_steps": 402, "total_steps": 412, "loss": 0.0577, "lr": 1.4528971820846894e-08, "epoch": 1.9514563106796117, "percentage": 97.57, "elapsed_time": "0:04:08", "remaining_time": "0:00:06"}
403
+ {"current_steps": 403, "total_steps": 412, "loss": 0.0553, "lr": 1.176955074159214e-08, "epoch": 1.9563106796116505, "percentage": 97.82, "elapsed_time": "0:04:08", "remaining_time": "0:00:05"}
404
+ {"current_steps": 404, "total_steps": 412, "loss": 0.0707, "lr": 9.300164200530815e-09, "epoch": 1.9611650485436893, "percentage": 98.06, "elapsed_time": "0:04:09", "remaining_time": "0:00:04"}
405
+ {"current_steps": 405, "total_steps": 412, "loss": 0.089, "lr": 7.120955777112915e-09, "epoch": 1.9660194174757282, "percentage": 98.3, "elapsed_time": "0:04:10", "remaining_time": "0:00:04"}
406
+ {"current_steps": 406, "total_steps": 412, "loss": 0.0642, "lr": 5.232052178738567e-09, "epoch": 1.970873786407767, "percentage": 98.54, "elapsed_time": "0:04:10", "remaining_time": "0:00:03"}
407
+ {"current_steps": 407, "total_steps": 412, "loss": 0.0741, "lr": 3.633563233388926e-09, "epoch": 1.9757281553398058, "percentage": 98.79, "elapsed_time": "0:04:11", "remaining_time": "0:00:03"}
408
+ {"current_steps": 408, "total_steps": 412, "loss": 0.0573, "lr": 2.3255818832423894e-09, "epoch": 1.9805825242718447, "percentage": 99.03, "elapsed_time": "0:04:11", "remaining_time": "0:00:02"}
409
+ {"current_steps": 409, "total_steps": 412, "loss": 0.0764, "lr": 1.3081841792694783e-09, "epoch": 1.9854368932038835, "percentage": 99.27, "elapsed_time": "0:04:12", "remaining_time": "0:00:01"}
410
+ {"current_steps": 410, "total_steps": 412, "loss": 0.0573, "lr": 5.814292768108187e-10, "epoch": 1.9902912621359223, "percentage": 99.51, "elapsed_time": "0:04:13", "remaining_time": "0:00:01"}
411
+ {"current_steps": 411, "total_steps": 412, "loss": 0.0679, "lr": 1.453594321393359e-10, "epoch": 1.9951456310679612, "percentage": 99.76, "elapsed_time": "0:04:13", "remaining_time": "0:00:00"}
412
+ {"current_steps": 412, "total_steps": 412, "loss": 0.0419, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:04:14", "remaining_time": "0:00:00"}
413
+ {"current_steps": 412, "total_steps": 412, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:04:18", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,2926 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 412,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0048543689320388345,
13
+ "grad_norm": 3.3324859196579646,
14
+ "learning_rate": 9.999854640567861e-06,
15
+ "loss": 0.1339,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.009708737864077669,
20
+ "grad_norm": 3.8088042361483816,
21
+ "learning_rate": 9.999418570723189e-06,
22
+ "loss": 0.1354,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.014563106796116505,
27
+ "grad_norm": 5.274233478446681,
28
+ "learning_rate": 9.998691815820732e-06,
29
+ "loss": 0.2009,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.019417475728155338,
34
+ "grad_norm": 4.101699811840383,
35
+ "learning_rate": 9.997674418116759e-06,
36
+ "loss": 0.1982,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.024271844660194174,
41
+ "grad_norm": 3.924795885151193,
42
+ "learning_rate": 9.996366436766612e-06,
43
+ "loss": 0.1883,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.02912621359223301,
48
+ "grad_norm": 5.771957604254228,
49
+ "learning_rate": 9.994767947821261e-06,
50
+ "loss": 0.188,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.03398058252427184,
55
+ "grad_norm": 4.039324853603417,
56
+ "learning_rate": 9.992879044222887e-06,
57
+ "loss": 0.1602,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.038834951456310676,
62
+ "grad_norm": 3.450341344849428,
63
+ "learning_rate": 9.99069983579947e-06,
64
+ "loss": 0.1716,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.043689320388349516,
69
+ "grad_norm": 3.7152133363818325,
70
+ "learning_rate": 9.988230449258409e-06,
71
+ "loss": 0.1584,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.04854368932038835,
76
+ "grad_norm": 2.9403672361375413,
77
+ "learning_rate": 9.985471028179155e-06,
78
+ "loss": 0.1338,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.05339805825242718,
83
+ "grad_norm": 3.6346123927161558,
84
+ "learning_rate": 9.982421733004857e-06,
85
+ "loss": 0.1413,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.05825242718446602,
90
+ "grad_norm": 3.918759862991223,
91
+ "learning_rate": 9.979082741033047e-06,
92
+ "loss": 0.1571,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.06310679611650485,
97
+ "grad_norm": 3.3243324871274846,
98
+ "learning_rate": 9.975454246405312e-06,
99
+ "loss": 0.1373,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.06796116504854369,
104
+ "grad_norm": 4.090995406850703,
105
+ "learning_rate": 9.971536460096021e-06,
106
+ "loss": 0.2064,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.07281553398058252,
111
+ "grad_norm": 4.5651807246739535,
112
+ "learning_rate": 9.96732960990005e-06,
113
+ "loss": 0.213,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.07766990291262135,
118
+ "grad_norm": 3.8522165104605186,
119
+ "learning_rate": 9.96283394041954e-06,
120
+ "loss": 0.1806,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.0825242718446602,
125
+ "grad_norm": 4.090915249944868,
126
+ "learning_rate": 9.95804971304968e-06,
127
+ "loss": 0.1594,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.08737864077669903,
132
+ "grad_norm": 3.343034439706098,
133
+ "learning_rate": 9.952977205963496e-06,
134
+ "loss": 0.143,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.09223300970873786,
139
+ "grad_norm": 3.2771634678459036,
140
+ "learning_rate": 9.94761671409569e-06,
141
+ "loss": 0.1604,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.0970873786407767,
146
+ "grad_norm": 3.4631851530033657,
147
+ "learning_rate": 9.941968549125481e-06,
148
+ "loss": 0.1618,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.10194174757281553,
153
+ "grad_norm": 3.928255474637941,
154
+ "learning_rate": 9.936033039458494e-06,
155
+ "loss": 0.1778,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.10679611650485436,
160
+ "grad_norm": 3.3479570283155202,
161
+ "learning_rate": 9.929810530207651e-06,
162
+ "loss": 0.1591,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.11165048543689321,
167
+ "grad_norm": 3.6975883529242646,
168
+ "learning_rate": 9.923301383173119e-06,
169
+ "loss": 0.2006,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.11650485436893204,
174
+ "grad_norm": 3.469665362839314,
175
+ "learning_rate": 9.916505976821262e-06,
176
+ "loss": 0.1657,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.12135922330097088,
181
+ "grad_norm": 3.3643581564878673,
182
+ "learning_rate": 9.909424706262647e-06,
183
+ "loss": 0.1569,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.1262135922330097,
188
+ "grad_norm": 4.110694436156542,
189
+ "learning_rate": 9.902057983229059e-06,
190
+ "loss": 0.1909,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.13106796116504854,
195
+ "grad_norm": 3.186323923132206,
196
+ "learning_rate": 9.894406236049569e-06,
197
+ "loss": 0.163,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.13592233009708737,
202
+ "grad_norm": 3.5498332735613127,
203
+ "learning_rate": 9.886469909625624e-06,
204
+ "loss": 0.196,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.1407766990291262,
209
+ "grad_norm": 3.9980031295006313,
210
+ "learning_rate": 9.87824946540519e-06,
211
+ "loss": 0.208,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.14563106796116504,
216
+ "grad_norm": 3.4906745199009417,
217
+ "learning_rate": 9.869745381355906e-06,
218
+ "loss": 0.1664,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.15048543689320387,
223
+ "grad_norm": 3.954794586878399,
224
+ "learning_rate": 9.860958151937303e-06,
225
+ "loss": 0.1877,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.1553398058252427,
230
+ "grad_norm": 3.6372789508629273,
231
+ "learning_rate": 9.851888288072053e-06,
232
+ "loss": 0.1735,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.16019417475728157,
237
+ "grad_norm": 3.9820299514191384,
238
+ "learning_rate": 9.842536317116262e-06,
239
+ "loss": 0.2067,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.1650485436893204,
244
+ "grad_norm": 3.7102209529281174,
245
+ "learning_rate": 9.832902782828801e-06,
246
+ "loss": 0.1915,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.16990291262135923,
251
+ "grad_norm": 3.925675916083603,
252
+ "learning_rate": 9.822988245339701e-06,
253
+ "loss": 0.1979,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.17475728155339806,
258
+ "grad_norm": 3.918214682037897,
259
+ "learning_rate": 9.81279328111758e-06,
260
+ "loss": 0.1596,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.1796116504854369,
265
+ "grad_norm": 9.706515279117301,
266
+ "learning_rate": 9.802318482936121e-06,
267
+ "loss": 2.2571,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.18446601941747573,
272
+ "grad_norm": 6.621327724804455,
273
+ "learning_rate": 9.791564459839609e-06,
274
+ "loss": 1.938,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.18932038834951456,
279
+ "grad_norm": 3.7869250833437826,
280
+ "learning_rate": 9.780531837107519e-06,
281
+ "loss": 0.2153,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.1941747572815534,
286
+ "grad_norm": 4.474156895071826,
287
+ "learning_rate": 9.769221256218165e-06,
288
+ "loss": 0.2017,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.19902912621359223,
293
+ "grad_norm": 4.084460872286135,
294
+ "learning_rate": 9.75763337481139e-06,
295
+ "loss": 0.2182,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.20388349514563106,
300
+ "grad_norm": 3.870693933215402,
301
+ "learning_rate": 9.745768866650339e-06,
302
+ "loss": 0.2244,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.2087378640776699,
307
+ "grad_norm": 2.902378281214243,
308
+ "learning_rate": 9.73362842158228e-06,
309
+ "loss": 0.1467,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.21359223300970873,
314
+ "grad_norm": 3.248116446046984,
315
+ "learning_rate": 9.721212745498493e-06,
316
+ "loss": 0.1843,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.21844660194174756,
321
+ "grad_norm": 3.667256599988585,
322
+ "learning_rate": 9.70852256029323e-06,
323
+ "loss": 0.1765,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.22330097087378642,
328
+ "grad_norm": 3.839808524241103,
329
+ "learning_rate": 9.695558603821735e-06,
330
+ "loss": 0.2249,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.22815533980582525,
335
+ "grad_norm": 3.561913372270993,
336
+ "learning_rate": 9.682321629857348e-06,
337
+ "loss": 0.1945,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.23300970873786409,
342
+ "grad_norm": 3.7140607428554686,
343
+ "learning_rate": 9.66881240804768e-06,
344
+ "loss": 0.1923,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.23786407766990292,
349
+ "grad_norm": 4.162473919082487,
350
+ "learning_rate": 9.655031723869848e-06,
351
+ "loss": 0.2106,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.24271844660194175,
356
+ "grad_norm": 4.088833429529486,
357
+ "learning_rate": 9.64098037858483e-06,
358
+ "loss": 0.1948,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.24757281553398058,
363
+ "grad_norm": 6.098858386818918,
364
+ "learning_rate": 9.626659189190852e-06,
365
+ "loss": 1.3556,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.2524271844660194,
370
+ "grad_norm": 3.2961565474058565,
371
+ "learning_rate": 9.612068988375898e-06,
372
+ "loss": 0.1675,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.25728155339805825,
377
+ "grad_norm": 4.3986677165375525,
378
+ "learning_rate": 9.597210624469288e-06,
379
+ "loss": 0.1971,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.2621359223300971,
384
+ "grad_norm": 3.177129834284871,
385
+ "learning_rate": 9.582084961392358e-06,
386
+ "loss": 0.1439,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.2669902912621359,
391
+ "grad_norm": 3.3475437780719637,
392
+ "learning_rate": 9.566692878608229e-06,
393
+ "loss": 0.1618,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.27184466019417475,
398
+ "grad_norm": 3.8249351827001177,
399
+ "learning_rate": 9.551035271070665e-06,
400
+ "loss": 0.2095,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.2766990291262136,
405
+ "grad_norm": 3.7494052477874003,
406
+ "learning_rate": 9.53511304917204e-06,
407
+ "loss": 0.1899,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.2815533980582524,
412
+ "grad_norm": 3.137113053607151,
413
+ "learning_rate": 9.51892713869041e-06,
414
+ "loss": 0.1361,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.28640776699029125,
419
+ "grad_norm": 4.154996879718851,
420
+ "learning_rate": 9.502478480735678e-06,
421
+ "loss": 0.1873,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.2912621359223301,
426
+ "grad_norm": 3.8345434030006658,
427
+ "learning_rate": 9.485768031694872e-06,
428
+ "loss": 0.1867,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.2961165048543689,
433
+ "grad_norm": 4.01375505704675,
434
+ "learning_rate": 9.468796763176549e-06,
435
+ "loss": 0.2054,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.30097087378640774,
440
+ "grad_norm": 4.06144310993101,
441
+ "learning_rate": 9.45156566195429e-06,
442
+ "loss": 0.1571,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.3058252427184466,
447
+ "grad_norm": 3.792468878802408,
448
+ "learning_rate": 9.43407572990933e-06,
449
+ "loss": 0.1837,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.3106796116504854,
454
+ "grad_norm": 3.648120070990038,
455
+ "learning_rate": 9.416327983972304e-06,
456
+ "loss": 0.1938,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.3155339805825243,
461
+ "grad_norm": 3.489437914184596,
462
+ "learning_rate": 9.398323456064124e-06,
463
+ "loss": 0.2241,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.32038834951456313,
468
+ "grad_norm": 3.374340511480333,
469
+ "learning_rate": 9.380063193035968e-06,
470
+ "loss": 0.177,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.32524271844660196,
475
+ "grad_norm": 3.264598449702114,
476
+ "learning_rate": 9.361548256608421e-06,
477
+ "loss": 0.1797,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.3300970873786408,
482
+ "grad_norm": 3.966830853033163,
483
+ "learning_rate": 9.342779723309746e-06,
484
+ "loss": 0.2554,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.33495145631067963,
489
+ "grad_norm": 3.420409800935627,
490
+ "learning_rate": 9.323758684413272e-06,
491
+ "loss": 0.1478,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.33980582524271846,
496
+ "grad_norm": 3.7130637493387324,
497
+ "learning_rate": 9.304486245873973e-06,
498
+ "loss": 0.1751,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.3446601941747573,
503
+ "grad_norm": 3.5828005486461563,
504
+ "learning_rate": 9.284963528264133e-06,
505
+ "loss": 0.1823,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.34951456310679613,
510
+ "grad_norm": 3.3855623884926134,
511
+ "learning_rate": 9.26519166670821e-06,
512
+ "loss": 0.1685,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.35436893203883496,
517
+ "grad_norm": 8.968308123292674,
518
+ "learning_rate": 9.24517181081683e-06,
519
+ "loss": 2.1169,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.3592233009708738,
524
+ "grad_norm": 3.4944633320992358,
525
+ "learning_rate": 9.22490512461995e-06,
526
+ "loss": 0.1636,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.3640776699029126,
531
+ "grad_norm": 4.197357025299537,
532
+ "learning_rate": 9.204392786499168e-06,
533
+ "loss": 0.2401,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.36893203883495146,
538
+ "grad_norm": 3.3051744285672373,
539
+ "learning_rate": 9.183635989119211e-06,
540
+ "loss": 0.1641,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.3737864077669903,
545
+ "grad_norm": 3.6322680235984235,
546
+ "learning_rate": 9.162635939358593e-06,
547
+ "loss": 0.1614,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.3786407766990291,
552
+ "grad_norm": 3.2637668132144895,
553
+ "learning_rate": 9.141393858239435e-06,
554
+ "loss": 0.1459,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.38349514563106796,
559
+ "grad_norm": 3.2541730866975893,
560
+ "learning_rate": 9.119910980856477e-06,
561
+ "loss": 0.1804,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.3883495145631068,
566
+ "grad_norm": 3.2213080042311586,
567
+ "learning_rate": 9.098188556305262e-06,
568
+ "loss": 0.19,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.3932038834951456,
573
+ "grad_norm": 3.4206478733768075,
574
+ "learning_rate": 9.076227847609513e-06,
575
+ "loss": 0.144,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.39805825242718446,
580
+ "grad_norm": 2.8054401115428824,
581
+ "learning_rate": 9.054030131647682e-06,
582
+ "loss": 0.1541,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.4029126213592233,
587
+ "grad_norm": 3.833189307216376,
588
+ "learning_rate": 9.031596699078727e-06,
589
+ "loss": 0.231,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.4077669902912621,
594
+ "grad_norm": 3.692036642881131,
595
+ "learning_rate": 9.008928854267054e-06,
596
+ "loss": 0.1729,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.41262135922330095,
601
+ "grad_norm": 3.23541497427633,
602
+ "learning_rate": 8.986027915206686e-06,
603
+ "loss": 0.1286,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.4174757281553398,
608
+ "grad_norm": 4.0009005067420365,
609
+ "learning_rate": 8.962895213444618e-06,
610
+ "loss": 0.1922,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.4223300970873786,
615
+ "grad_norm": 3.371659427266,
616
+ "learning_rate": 8.939532094003409e-06,
617
+ "loss": 1.6075,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.42718446601941745,
622
+ "grad_norm": 4.543078324073699,
623
+ "learning_rate": 8.91593991530297e-06,
624
+ "loss": 0.1903,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.4320388349514563,
629
+ "grad_norm": 5.581237410035587,
630
+ "learning_rate": 8.892120049081577e-06,
631
+ "loss": 0.2364,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.4368932038834951,
636
+ "grad_norm": 3.4788239166280337,
637
+ "learning_rate": 8.868073880316125e-06,
638
+ "loss": 0.2073,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.441747572815534,
643
+ "grad_norm": 3.4847904706068893,
644
+ "learning_rate": 8.843802807141584e-06,
645
+ "loss": 0.1641,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.44660194174757284,
650
+ "grad_norm": 4.376363674830701,
651
+ "learning_rate": 8.819308240769726e-06,
652
+ "loss": 0.2238,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.45145631067961167,
657
+ "grad_norm": 3.269073216227844,
658
+ "learning_rate": 8.794591605407047e-06,
659
+ "loss": 0.1974,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.4563106796116505,
664
+ "grad_norm": 4.3052039894235135,
665
+ "learning_rate": 8.769654338171986e-06,
666
+ "loss": 0.2162,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.46116504854368934,
671
+ "grad_norm": 3.300951688264894,
672
+ "learning_rate": 8.744497889011344e-06,
673
+ "loss": 0.1779,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.46601941747572817,
678
+ "grad_norm": 3.1987714308242885,
679
+ "learning_rate": 8.71912372061598e-06,
680
+ "loss": 0.1827,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.470873786407767,
685
+ "grad_norm": 2.8017077028359885,
686
+ "learning_rate": 8.693533308335786e-06,
687
+ "loss": 0.148,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.47572815533980584,
692
+ "grad_norm": 3.102368312031283,
693
+ "learning_rate": 8.667728140093876e-06,
694
+ "loss": 0.2068,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.48058252427184467,
699
+ "grad_norm": 3.6508180598366695,
700
+ "learning_rate": 8.641709716300092e-06,
701
+ "loss": 0.2029,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.4854368932038835,
706
+ "grad_norm": 3.3950171740747166,
707
+ "learning_rate": 8.615479549763756e-06,
708
+ "loss": 1.8884,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.49029126213592233,
713
+ "grad_norm": 3.1312849938657896,
714
+ "learning_rate": 8.589039165605716e-06,
715
+ "loss": 0.1537,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.49514563106796117,
720
+ "grad_norm": 3.5801315817647232,
721
+ "learning_rate": 8.56239010116966e-06,
722
+ "loss": 0.1824,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.5,
727
+ "grad_norm": 3.546534300447041,
728
+ "learning_rate": 8.535533905932739e-06,
729
+ "loss": 0.1804,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.5048543689320388,
734
+ "grad_norm": 3.2877479715730313,
735
+ "learning_rate": 8.508472141415468e-06,
736
+ "loss": 0.1617,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.5097087378640777,
741
+ "grad_norm": 3.5584173121991323,
742
+ "learning_rate": 8.481206381090934e-06,
743
+ "loss": 0.1887,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.5145631067961165,
748
+ "grad_norm": 3.805569430447853,
749
+ "learning_rate": 8.453738210293316e-06,
750
+ "loss": 0.1721,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.5194174757281553,
755
+ "grad_norm": 3.881708238229782,
756
+ "learning_rate": 8.426069226125695e-06,
757
+ "loss": 0.1838,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.5242718446601942,
762
+ "grad_norm": 3.98671495838238,
763
+ "learning_rate": 8.398201037367202e-06,
764
+ "loss": 0.1961,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.529126213592233,
769
+ "grad_norm": 2.869964566560864,
770
+ "learning_rate": 8.370135264379475e-06,
771
+ "loss": 0.1474,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.5339805825242718,
776
+ "grad_norm": 3.3720637127767605,
777
+ "learning_rate": 8.341873539012443e-06,
778
+ "loss": 0.1704,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.5388349514563107,
783
+ "grad_norm": 3.3436728179491673,
784
+ "learning_rate": 8.313417504509446e-06,
785
+ "loss": 0.151,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.5436893203883495,
790
+ "grad_norm": 3.1939397858342167,
791
+ "learning_rate": 8.284768815411693e-06,
792
+ "loss": 0.164,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.5485436893203883,
797
+ "grad_norm": 3.9497595827371903,
798
+ "learning_rate": 8.255929137462049e-06,
799
+ "loss": 0.1844,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.5533980582524272,
804
+ "grad_norm": 3.6900776204954093,
805
+ "learning_rate": 8.226900147508205e-06,
806
+ "loss": 0.1726,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.558252427184466,
811
+ "grad_norm": 3.416053446028884,
812
+ "learning_rate": 8.197683533405156e-06,
813
+ "loss": 0.1651,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.5631067961165048,
818
+ "grad_norm": 3.830007646061756,
819
+ "learning_rate": 8.168280993917078e-06,
820
+ "loss": 0.2018,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.5679611650485437,
825
+ "grad_norm": 3.6356803944567706,
826
+ "learning_rate": 8.138694238618543e-06,
827
+ "loss": 0.186,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.5728155339805825,
832
+ "grad_norm": 3.268566324515523,
833
+ "learning_rate": 8.108924987795137e-06,
834
+ "loss": 0.1807,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.5776699029126213,
839
+ "grad_norm": 3.0731122010223157,
840
+ "learning_rate": 8.078974972343414e-06,
841
+ "loss": 0.1385,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.5825242718446602,
846
+ "grad_norm": 3.506409488780749,
847
+ "learning_rate": 8.048845933670274e-06,
848
+ "loss": 0.1876,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.587378640776699,
853
+ "grad_norm": 3.0091035344268167,
854
+ "learning_rate": 8.01853962359169e-06,
855
+ "loss": 0.1542,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.5922330097087378,
860
+ "grad_norm": 4.000336192381524,
861
+ "learning_rate": 7.988057804230878e-06,
862
+ "loss": 0.1855,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.5970873786407767,
867
+ "grad_norm": 2.6774596474593015,
868
+ "learning_rate": 7.957402247915817e-06,
869
+ "loss": 0.1398,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.6019417475728155,
874
+ "grad_norm": 3.342400785474733,
875
+ "learning_rate": 7.92657473707621e-06,
876
+ "loss": 0.1571,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.6067961165048543,
881
+ "grad_norm": 2.839224634847776,
882
+ "learning_rate": 7.895577064139847e-06,
883
+ "loss": 0.2838,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.6116504854368932,
888
+ "grad_norm": 3.265216498891963,
889
+ "learning_rate": 7.864411031428379e-06,
890
+ "loss": 0.1605,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.616504854368932,
895
+ "grad_norm": 2.826555903641288,
896
+ "learning_rate": 7.833078451052537e-06,
897
+ "loss": 0.1552,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.6213592233009708,
902
+ "grad_norm": 3.263465403684562,
903
+ "learning_rate": 7.801581144806752e-06,
904
+ "loss": 0.1409,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.6262135922330098,
909
+ "grad_norm": 3.115501404573261,
910
+ "learning_rate": 7.769920944063244e-06,
911
+ "loss": 0.1388,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.6310679611650486,
916
+ "grad_norm": 3.454177176086228,
917
+ "learning_rate": 7.73809968966554e-06,
918
+ "loss": 0.1691,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.6359223300970874,
923
+ "grad_norm": 3.669774425160351,
924
+ "learning_rate": 7.706119231821423e-06,
925
+ "loss": 2.0662,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.6407766990291263,
930
+ "grad_norm": 2.9578717822726994,
931
+ "learning_rate": 7.673981429995372e-06,
932
+ "loss": 0.1217,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.6456310679611651,
937
+ "grad_norm": 3.215506984482298,
938
+ "learning_rate": 7.641688152800433e-06,
939
+ "loss": 0.1641,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.6504854368932039,
944
+ "grad_norm": 3.5261600831309683,
945
+ "learning_rate": 7.609241277889583e-06,
946
+ "loss": 0.1581,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.6553398058252428,
951
+ "grad_norm": 3.348004239497448,
952
+ "learning_rate": 7.5766426918465455e-06,
953
+ "loss": 0.1655,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.6601941747572816,
958
+ "grad_norm": 3.463003474785134,
959
+ "learning_rate": 7.5438942900761035e-06,
960
+ "loss": 0.179,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.6650485436893204,
965
+ "grad_norm": 3.299946611300431,
966
+ "learning_rate": 7.51099797669389e-06,
967
+ "loss": 0.1838,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.6699029126213593,
972
+ "grad_norm": 3.734578866130712,
973
+ "learning_rate": 7.477955664415678e-06,
974
+ "loss": 0.2121,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.6747572815533981,
979
+ "grad_norm": 3.104951473650513,
980
+ "learning_rate": 7.444769274446168e-06,
981
+ "loss": 0.1522,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.6796116504854369,
986
+ "grad_norm": 3.133143645012315,
987
+ "learning_rate": 7.411440736367281e-06,
988
+ "loss": 0.158,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.6844660194174758,
993
+ "grad_norm": 3.059272264008987,
994
+ "learning_rate": 7.377971988025964e-06,
995
+ "loss": 0.1431,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.6893203883495146,
1000
+ "grad_norm": 3.4811771159052127,
1001
+ "learning_rate": 7.3443649754215175e-06,
1002
+ "loss": 0.1609,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.6941747572815534,
1007
+ "grad_norm": 3.85738998682577,
1008
+ "learning_rate": 7.310621652592449e-06,
1009
+ "loss": 0.1537,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.6990291262135923,
1014
+ "grad_norm": 3.4019001310027877,
1015
+ "learning_rate": 7.276743981502856e-06,
1016
+ "loss": 0.161,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.7038834951456311,
1021
+ "grad_norm": 3.396761694989364,
1022
+ "learning_rate": 7.242733931928352e-06,
1023
+ "loss": 1.968,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.7087378640776699,
1028
+ "grad_norm": 3.0749985922565415,
1029
+ "learning_rate": 7.208593481341536e-06,
1030
+ "loss": 0.164,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.7135922330097088,
1035
+ "grad_norm": 3.1539841039599077,
1036
+ "learning_rate": 7.1743246147970095e-06,
1037
+ "loss": 0.156,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.7184466019417476,
1042
+ "grad_norm": 3.4892734050571677,
1043
+ "learning_rate": 7.139929324815965e-06,
1044
+ "loss": 0.1884,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.7233009708737864,
1049
+ "grad_norm": 2.7320915520428635,
1050
+ "learning_rate": 7.105409611270332e-06,
1051
+ "loss": 0.1219,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.7281553398058253,
1056
+ "grad_norm": 3.0178546824462114,
1057
+ "learning_rate": 7.070767481266493e-06,
1058
+ "loss": 0.1732,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.7330097087378641,
1063
+ "grad_norm": 2.8056474690169986,
1064
+ "learning_rate": 7.036004949028587e-06,
1065
+ "loss": 0.1481,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.7378640776699029,
1070
+ "grad_norm": 3.10021388569035,
1071
+ "learning_rate": 7.00112403578139e-06,
1072
+ "loss": 0.1673,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.7427184466019418,
1077
+ "grad_norm": 3.26753532587258,
1078
+ "learning_rate": 6.9661267696328015e-06,
1079
+ "loss": 0.1883,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.7475728155339806,
1084
+ "grad_norm": 3.4255182899390033,
1085
+ "learning_rate": 6.931015185455915e-06,
1086
+ "loss": 0.2046,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.7524271844660194,
1091
+ "grad_norm": 3.636720170211082,
1092
+ "learning_rate": 6.895791324770702e-06,
1093
+ "loss": 0.2068,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.7572815533980582,
1098
+ "grad_norm": 3.053662406730595,
1099
+ "learning_rate": 6.860457235625322e-06,
1100
+ "loss": 0.169,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.7621359223300971,
1105
+ "grad_norm": 3.0420805095324686,
1106
+ "learning_rate": 6.825014972477024e-06,
1107
+ "loss": 0.1662,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.7669902912621359,
1112
+ "grad_norm": 3.5230733226696898,
1113
+ "learning_rate": 6.7894665960727105e-06,
1114
+ "loss": 0.2034,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.7718446601941747,
1119
+ "grad_norm": 3.891671449744887,
1120
+ "learning_rate": 6.7538141733291e-06,
1121
+ "loss": 0.2038,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.7766990291262136,
1126
+ "grad_norm": 4.12261748913082,
1127
+ "learning_rate": 6.7180597772125665e-06,
1128
+ "loss": 0.1852,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.7815533980582524,
1133
+ "grad_norm": 3.0068851640498195,
1134
+ "learning_rate": 6.682205486618592e-06,
1135
+ "loss": 0.1597,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.7864077669902912,
1140
+ "grad_norm": 3.5271313218773885,
1141
+ "learning_rate": 6.646253386250909e-06,
1142
+ "loss": 0.2022,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.7912621359223301,
1147
+ "grad_norm": 3.777114140168497,
1148
+ "learning_rate": 6.610205566500272e-06,
1149
+ "loss": 0.2029,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.7961165048543689,
1154
+ "grad_norm": 3.2070899922727127,
1155
+ "learning_rate": 6.574064123322925e-06,
1156
+ "loss": 0.1883,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.8009708737864077,
1161
+ "grad_norm": 2.856172766834049,
1162
+ "learning_rate": 6.537831158118733e-06,
1163
+ "loss": 0.1323,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.8058252427184466,
1168
+ "grad_norm": 3.2401941234963023,
1169
+ "learning_rate": 6.50150877760899e-06,
1170
+ "loss": 0.1786,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.8106796116504854,
1175
+ "grad_norm": 3.3661235424780385,
1176
+ "learning_rate": 6.465099093713944e-06,
1177
+ "loss": 0.1753,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.8155339805825242,
1182
+ "grad_norm": 2.688408919315557,
1183
+ "learning_rate": 6.42860422342998e-06,
1184
+ "loss": 0.1516,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.8203883495145631,
1189
+ "grad_norm": 3.7810659287217723,
1190
+ "learning_rate": 6.392026288706549e-06,
1191
+ "loss": 0.1481,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.8252427184466019,
1196
+ "grad_norm": 3.685444342996392,
1197
+ "learning_rate": 6.3553674163227786e-06,
1198
+ "loss": 0.1731,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.8300970873786407,
1203
+ "grad_norm": 2.946846864594844,
1204
+ "learning_rate": 6.318629737763818e-06,
1205
+ "loss": 0.1609,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.8349514563106796,
1210
+ "grad_norm": 3.8276099009344824,
1211
+ "learning_rate": 6.281815389096903e-06,
1212
+ "loss": 0.1881,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.8398058252427184,
1217
+ "grad_norm": 3.303535702159252,
1218
+ "learning_rate": 6.244926510847162e-06,
1219
+ "loss": 0.1479,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.8446601941747572,
1224
+ "grad_norm": 3.807883566694266,
1225
+ "learning_rate": 6.207965247873151e-06,
1226
+ "loss": 0.1903,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.8495145631067961,
1231
+ "grad_norm": 2.911567051543024,
1232
+ "learning_rate": 6.1709337492421515e-06,
1233
+ "loss": 0.1295,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.8543689320388349,
1238
+ "grad_norm": 3.2046177093058166,
1239
+ "learning_rate": 6.133834168105206e-06,
1240
+ "loss": 0.1568,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.8592233009708737,
1245
+ "grad_norm": 3.3349281673831803,
1246
+ "learning_rate": 6.096668661571934e-06,
1247
+ "loss": 0.1702,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.8640776699029126,
1252
+ "grad_norm": 3.9332514492121096,
1253
+ "learning_rate": 6.0594393905851065e-06,
1254
+ "loss": 0.2129,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.8689320388349514,
1259
+ "grad_norm": 3.6828564033007316,
1260
+ "learning_rate": 6.0221485197949995e-06,
1261
+ "loss": 0.1777,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.8737864077669902,
1266
+ "grad_norm": 3.9344402235799714,
1267
+ "learning_rate": 5.9847982174335314e-06,
1268
+ "loss": 0.218,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.8786407766990292,
1273
+ "grad_norm": 3.437911020577905,
1274
+ "learning_rate": 5.9473906551881985e-06,
1275
+ "loss": 0.1915,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.883495145631068,
1280
+ "grad_norm": 3.584257218638752,
1281
+ "learning_rate": 5.9099280080758085e-06,
1282
+ "loss": 0.2143,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.8883495145631068,
1287
+ "grad_norm": 3.3884751449077846,
1288
+ "learning_rate": 5.872412454315999e-06,
1289
+ "loss": 0.1848,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.8932038834951457,
1294
+ "grad_norm": 3.847696159285092,
1295
+ "learning_rate": 5.834846175204612e-06,
1296
+ "loss": 0.1914,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.8980582524271845,
1301
+ "grad_norm": 3.4294270132408733,
1302
+ "learning_rate": 5.797231354986842e-06,
1303
+ "loss": 0.1733,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.9029126213592233,
1308
+ "grad_norm": 2.7006091171005244,
1309
+ "learning_rate": 5.759570180730255e-06,
1310
+ "loss": 0.1786,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.9077669902912622,
1315
+ "grad_norm": 3.1518913649529128,
1316
+ "learning_rate": 5.721864842197612e-06,
1317
+ "loss": 0.1569,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.912621359223301,
1322
+ "grad_norm": 3.9310146604996876,
1323
+ "learning_rate": 5.684117531719552e-06,
1324
+ "loss": 0.2194,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.9174757281553398,
1329
+ "grad_norm": 3.6243954425466383,
1330
+ "learning_rate": 5.646330444067121e-06,
1331
+ "loss": 0.1515,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.9223300970873787,
1336
+ "grad_norm": 2.9597266924343373,
1337
+ "learning_rate": 5.608505776324158e-06,
1338
+ "loss": 0.1631,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.9271844660194175,
1343
+ "grad_norm": 3.29651731345373,
1344
+ "learning_rate": 5.570645727759558e-06,
1345
+ "loss": 0.1762,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.9320388349514563,
1350
+ "grad_norm": 3.02642514409216,
1351
+ "learning_rate": 5.532752499699381e-06,
1352
+ "loss": 0.1794,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.9368932038834952,
1357
+ "grad_norm": 3.1368920826260736,
1358
+ "learning_rate": 5.494828295398874e-06,
1359
+ "loss": 0.178,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.941747572815534,
1364
+ "grad_norm": 2.9748663003734457,
1365
+ "learning_rate": 5.456875319914355e-06,
1366
+ "loss": 0.1558,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.9466019417475728,
1371
+ "grad_norm": 3.447694232964055,
1372
+ "learning_rate": 5.4188957799750145e-06,
1373
+ "loss": 0.143,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.9514563106796117,
1378
+ "grad_norm": 2.9468105285885122,
1379
+ "learning_rate": 5.380891883854591e-06,
1380
+ "loss": 0.1585,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.9563106796116505,
1385
+ "grad_norm": 2.796739428227403,
1386
+ "learning_rate": 5.34286584124299e-06,
1387
+ "loss": 0.1345,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.9611650485436893,
1392
+ "grad_norm": 3.0833816121492337,
1393
+ "learning_rate": 5.304819863117796e-06,
1394
+ "loss": 0.1247,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.9660194174757282,
1399
+ "grad_norm": 3.0876458359936496,
1400
+ "learning_rate": 5.266756161615719e-06,
1401
+ "loss": 0.164,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.970873786407767,
1406
+ "grad_norm": 3.4454095679040484,
1407
+ "learning_rate": 5.228676949903974e-06,
1408
+ "loss": 0.1681,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.9757281553398058,
1413
+ "grad_norm": 3.661107038218155,
1414
+ "learning_rate": 5.190584442051594e-06,
1415
+ "loss": 0.2034,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.9805825242718447,
1420
+ "grad_norm": 2.9781763427858783,
1421
+ "learning_rate": 5.1524808529007075e-06,
1422
+ "loss": 2.0615,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.9854368932038835,
1427
+ "grad_norm": 3.4144794700513006,
1428
+ "learning_rate": 5.114368397937744e-06,
1429
+ "loss": 0.18,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.9902912621359223,
1434
+ "grad_norm": 2.891912771085034,
1435
+ "learning_rate": 5.07624929316463e-06,
1436
+ "loss": 0.1692,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.9951456310679612,
1441
+ "grad_norm": 3.940859743167215,
1442
+ "learning_rate": 5.038125754969933e-06,
1443
+ "loss": 0.1597,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 1.0,
1448
+ "grad_norm": 2.114078403400398,
1449
+ "learning_rate": 5e-06,
1450
+ "loss": 0.0509,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 1.0048543689320388,
1455
+ "grad_norm": 2.4861837147789907,
1456
+ "learning_rate": 4.9618742450300675e-06,
1457
+ "loss": 0.0947,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 1.0097087378640777,
1462
+ "grad_norm": 2.574928651437252,
1463
+ "learning_rate": 4.923750706835371e-06,
1464
+ "loss": 0.0877,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 1.0145631067961165,
1469
+ "grad_norm": 2.390628942600892,
1470
+ "learning_rate": 4.8856316020622564e-06,
1471
+ "loss": 0.0849,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 1.0194174757281553,
1476
+ "grad_norm": 2.0965587115046147,
1477
+ "learning_rate": 4.847519147099294e-06,
1478
+ "loss": 0.0691,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 1.0242718446601942,
1483
+ "grad_norm": 2.4149356959145742,
1484
+ "learning_rate": 4.809415557948407e-06,
1485
+ "loss": 0.095,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 1.029126213592233,
1490
+ "grad_norm": 2.235598621225836,
1491
+ "learning_rate": 4.771323050096028e-06,
1492
+ "loss": 0.0836,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 1.0339805825242718,
1497
+ "grad_norm": 2.777474574971205,
1498
+ "learning_rate": 4.733243838384282e-06,
1499
+ "loss": 0.0846,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 1.0388349514563107,
1504
+ "grad_norm": 2.7422183722820437,
1505
+ "learning_rate": 4.6951801368822055e-06,
1506
+ "loss": 0.0886,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 1.0436893203883495,
1511
+ "grad_norm": 3.583667258228157,
1512
+ "learning_rate": 4.6571341587570114e-06,
1513
+ "loss": 0.0853,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 1.0485436893203883,
1518
+ "grad_norm": 2.1429438147133983,
1519
+ "learning_rate": 4.619108116145411e-06,
1520
+ "loss": 0.0709,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 1.0533980582524272,
1525
+ "grad_norm": 2.638520623375338,
1526
+ "learning_rate": 4.581104220024988e-06,
1527
+ "loss": 0.0918,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 1.058252427184466,
1532
+ "grad_norm": 2.4373654485190546,
1533
+ "learning_rate": 4.5431246800856455e-06,
1534
+ "loss": 0.0659,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 1.0631067961165048,
1539
+ "grad_norm": 2.954470745196081,
1540
+ "learning_rate": 4.505171704601128e-06,
1541
+ "loss": 0.0865,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 1.0679611650485437,
1546
+ "grad_norm": 2.5357819989918675,
1547
+ "learning_rate": 4.467247500300621e-06,
1548
+ "loss": 0.0639,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 1.0728155339805825,
1553
+ "grad_norm": 3.196945279517692,
1554
+ "learning_rate": 4.4293542722404435e-06,
1555
+ "loss": 0.075,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 1.0776699029126213,
1560
+ "grad_norm": 3.602207511683068,
1561
+ "learning_rate": 4.391494223675843e-06,
1562
+ "loss": 0.0877,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 1.0825242718446602,
1567
+ "grad_norm": 3.072945774218816,
1568
+ "learning_rate": 4.3536695559328816e-06,
1569
+ "loss": 0.0886,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 1.087378640776699,
1574
+ "grad_norm": 2.9327628358781443,
1575
+ "learning_rate": 4.31588246828045e-06,
1576
+ "loss": 0.0779,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 1.0922330097087378,
1581
+ "grad_norm": 3.884559725530265,
1582
+ "learning_rate": 4.278135157802389e-06,
1583
+ "loss": 0.0957,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 1.0970873786407767,
1588
+ "grad_norm": 2.638727931000126,
1589
+ "learning_rate": 4.240429819269746e-06,
1590
+ "loss": 0.0578,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 1.1019417475728155,
1595
+ "grad_norm": 3.1117784042872283,
1596
+ "learning_rate": 4.20276864501316e-06,
1597
+ "loss": 0.0692,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 1.1067961165048543,
1602
+ "grad_norm": 2.7783624029964757,
1603
+ "learning_rate": 4.165153824795391e-06,
1604
+ "loss": 0.0768,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 1.1116504854368932,
1609
+ "grad_norm": 2.594503486377878,
1610
+ "learning_rate": 4.127587545684002e-06,
1611
+ "loss": 0.0669,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 1.116504854368932,
1616
+ "grad_norm": 2.929448813987237,
1617
+ "learning_rate": 4.090071991924194e-06,
1618
+ "loss": 0.0756,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 1.1213592233009708,
1623
+ "grad_norm": 2.6878856077703426,
1624
+ "learning_rate": 4.052609344811802e-06,
1625
+ "loss": 1.6006,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 1.1262135922330097,
1630
+ "grad_norm": 2.9800498201414296,
1631
+ "learning_rate": 4.015201782566471e-06,
1632
+ "loss": 0.084,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 1.1310679611650485,
1637
+ "grad_norm": 2.945464576525122,
1638
+ "learning_rate": 3.977851480205003e-06,
1639
+ "loss": 0.0831,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 1.1359223300970873,
1644
+ "grad_norm": 2.228512930491437,
1645
+ "learning_rate": 3.940560609414894e-06,
1646
+ "loss": 0.0563,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 1.1407766990291262,
1651
+ "grad_norm": 2.407897491051693,
1652
+ "learning_rate": 3.903331338428067e-06,
1653
+ "loss": 0.0633,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 1.145631067961165,
1658
+ "grad_norm": 2.4538104943960724,
1659
+ "learning_rate": 3.866165831894796e-06,
1660
+ "loss": 0.0602,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 1.1504854368932038,
1665
+ "grad_norm": 2.526844108676813,
1666
+ "learning_rate": 3.829066250757851e-06,
1667
+ "loss": 0.0772,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 1.1553398058252426,
1672
+ "grad_norm": 3.0770252354322003,
1673
+ "learning_rate": 3.7920347521268514e-06,
1674
+ "loss": 0.0761,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 1.1601941747572815,
1679
+ "grad_norm": 2.189508386492239,
1680
+ "learning_rate": 3.7550734891528413e-06,
1681
+ "loss": 1.7307,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 1.1650485436893203,
1686
+ "grad_norm": 2.9398466534526513,
1687
+ "learning_rate": 3.7181846109031007e-06,
1688
+ "loss": 0.0761,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 1.1699029126213591,
1693
+ "grad_norm": 2.746101050683826,
1694
+ "learning_rate": 3.6813702622361858e-06,
1695
+ "loss": 0.0847,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 1.174757281553398,
1700
+ "grad_norm": 2.7332263146255382,
1701
+ "learning_rate": 3.6446325836772244e-06,
1702
+ "loss": 0.0653,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 1.1796116504854368,
1707
+ "grad_norm": 2.7190442575382208,
1708
+ "learning_rate": 3.6079737112934533e-06,
1709
+ "loss": 0.0789,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 1.1844660194174756,
1714
+ "grad_norm": 2.658390418475969,
1715
+ "learning_rate": 3.5713957765700224e-06,
1716
+ "loss": 0.0603,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 1.1893203883495145,
1721
+ "grad_norm": 3.9381394273176276,
1722
+ "learning_rate": 3.5349009062860586e-06,
1723
+ "loss": 0.0811,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 1.1941747572815533,
1728
+ "grad_norm": 3.052172225803538,
1729
+ "learning_rate": 3.4984912223910105e-06,
1730
+ "loss": 0.0702,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 1.1990291262135921,
1735
+ "grad_norm": 3.0456430643875625,
1736
+ "learning_rate": 3.46216884188127e-06,
1737
+ "loss": 0.0784,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 1.203883495145631,
1742
+ "grad_norm": 2.5049847942964276,
1743
+ "learning_rate": 3.425935876677077e-06,
1744
+ "loss": 0.0656,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 1.2087378640776698,
1749
+ "grad_norm": 3.3960154571948,
1750
+ "learning_rate": 3.38979443349973e-06,
1751
+ "loss": 1.9855,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 1.2135922330097086,
1756
+ "grad_norm": 3.2720834167712214,
1757
+ "learning_rate": 3.3537466137490937e-06,
1758
+ "loss": 0.0577,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 1.2184466019417475,
1763
+ "grad_norm": 2.481707072834296,
1764
+ "learning_rate": 3.3177945133814093e-06,
1765
+ "loss": 0.0704,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 1.2233009708737863,
1770
+ "grad_norm": 3.154258406225022,
1771
+ "learning_rate": 3.2819402227874364e-06,
1772
+ "loss": 0.0873,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 1.2281553398058254,
1777
+ "grad_norm": 3.684874510102613,
1778
+ "learning_rate": 3.2461858266709017e-06,
1779
+ "loss": 0.0717,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 1.233009708737864,
1784
+ "grad_norm": 2.2393770842849205,
1785
+ "learning_rate": 3.2105334039272924e-06,
1786
+ "loss": 0.0712,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 1.237864077669903,
1791
+ "grad_norm": 2.5232811881585233,
1792
+ "learning_rate": 3.1749850275229777e-06,
1793
+ "loss": 0.059,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 1.2427184466019416,
1798
+ "grad_norm": 2.4330838257815612,
1799
+ "learning_rate": 3.1395427643746802e-06,
1800
+ "loss": 0.0665,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 1.2475728155339807,
1805
+ "grad_norm": 2.6008302295100245,
1806
+ "learning_rate": 3.1042086752292995e-06,
1807
+ "loss": 0.0714,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 1.2524271844660193,
1812
+ "grad_norm": 2.508640650867831,
1813
+ "learning_rate": 3.068984814544087e-06,
1814
+ "loss": 0.0881,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 1.2572815533980584,
1819
+ "grad_norm": 2.9570104245960014,
1820
+ "learning_rate": 3.0338732303671993e-06,
1821
+ "loss": 0.0725,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 1.262135922330097,
1826
+ "grad_norm": 2.8322291333835135,
1827
+ "learning_rate": 2.99887596421861e-06,
1828
+ "loss": 0.0779,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 1.266990291262136,
1833
+ "grad_norm": 3.4301825184788415,
1834
+ "learning_rate": 2.9639950509714138e-06,
1835
+ "loss": 0.1031,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 1.2718446601941746,
1840
+ "grad_norm": 2.767528223153958,
1841
+ "learning_rate": 2.929232518733507e-06,
1842
+ "loss": 1.7571,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 1.2766990291262137,
1847
+ "grad_norm": 2.5005755262187788,
1848
+ "learning_rate": 2.8945903887296686e-06,
1849
+ "loss": 0.0628,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 1.2815533980582523,
1854
+ "grad_norm": 3.101661943932367,
1855
+ "learning_rate": 2.860070675184036e-06,
1856
+ "loss": 0.0819,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 1.2864077669902914,
1861
+ "grad_norm": 3.1691737838498906,
1862
+ "learning_rate": 2.8256753852029917e-06,
1863
+ "loss": 0.0959,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 1.29126213592233,
1868
+ "grad_norm": 3.343426992113499,
1869
+ "learning_rate": 2.7914065186584637e-06,
1870
+ "loss": 0.0853,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 1.296116504854369,
1875
+ "grad_norm": 2.653786851479733,
1876
+ "learning_rate": 2.757266068071648e-06,
1877
+ "loss": 0.0711,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 1.3009708737864076,
1882
+ "grad_norm": 3.6695447681004953,
1883
+ "learning_rate": 2.7232560184971437e-06,
1884
+ "loss": 0.0925,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 1.3058252427184467,
1889
+ "grad_norm": 2.651580917610274,
1890
+ "learning_rate": 2.689378347407553e-06,
1891
+ "loss": 0.0733,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 1.3106796116504853,
1896
+ "grad_norm": 2.837228186908167,
1897
+ "learning_rate": 2.6556350245784833e-06,
1898
+ "loss": 1.3862,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 1.3155339805825244,
1903
+ "grad_norm": 2.744275874625859,
1904
+ "learning_rate": 2.6220280119740376e-06,
1905
+ "loss": 0.0802,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 1.3203883495145632,
1910
+ "grad_norm": 2.7150857011500733,
1911
+ "learning_rate": 2.588559263632719e-06,
1912
+ "loss": 0.0881,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 1.325242718446602,
1917
+ "grad_norm": 2.923244006407607,
1918
+ "learning_rate": 2.555230725553832e-06,
1919
+ "loss": 0.0695,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 1.3300970873786409,
1924
+ "grad_norm": 2.648842158951213,
1925
+ "learning_rate": 2.522044335584322e-06,
1926
+ "loss": 0.0808,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 1.3349514563106797,
1931
+ "grad_norm": 3.46448902282436,
1932
+ "learning_rate": 2.489002023306112e-06,
1933
+ "loss": 0.1095,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 1.3398058252427185,
1938
+ "grad_norm": 3.765519769264312,
1939
+ "learning_rate": 2.4561057099238973e-06,
1940
+ "loss": 0.124,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 1.3446601941747574,
1945
+ "grad_norm": 4.120315428329695,
1946
+ "learning_rate": 2.423357308153454e-06,
1947
+ "loss": 0.0726,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 1.3495145631067962,
1952
+ "grad_norm": 2.603195360336072,
1953
+ "learning_rate": 2.390758722110418e-06,
1954
+ "loss": 0.0746,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 1.354368932038835,
1959
+ "grad_norm": 2.3116504612959927,
1960
+ "learning_rate": 2.358311847199567e-06,
1961
+ "loss": 0.067,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 1.3592233009708738,
1966
+ "grad_norm": 2.510814292579119,
1967
+ "learning_rate": 2.3260185700046295e-06,
1968
+ "loss": 0.0553,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 1.3640776699029127,
1973
+ "grad_norm": 2.6478794602920432,
1974
+ "learning_rate": 2.2938807681785764e-06,
1975
+ "loss": 0.069,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 1.3689320388349515,
1980
+ "grad_norm": 2.7971908923982114,
1981
+ "learning_rate": 2.2619003103344607e-06,
1982
+ "loss": 0.1027,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 1.3737864077669903,
1987
+ "grad_norm": 2.6161854307520906,
1988
+ "learning_rate": 2.2300790559367553e-06,
1989
+ "loss": 0.0699,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 1.3786407766990292,
1994
+ "grad_norm": 2.634458727413624,
1995
+ "learning_rate": 2.1984188551932513e-06,
1996
+ "loss": 0.0674,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 1.383495145631068,
2001
+ "grad_norm": 3.3954408135653167,
2002
+ "learning_rate": 2.166921548947466e-06,
2003
+ "loss": 0.0978,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 1.3883495145631068,
2008
+ "grad_norm": 3.0988180285059483,
2009
+ "learning_rate": 2.1355889685716225e-06,
2010
+ "loss": 0.0867,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 1.3932038834951457,
2015
+ "grad_norm": 3.142246921881293,
2016
+ "learning_rate": 2.1044229358601543e-06,
2017
+ "loss": 0.0703,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 1.3980582524271845,
2022
+ "grad_norm": 2.650846344034233,
2023
+ "learning_rate": 2.0734252629237892e-06,
2024
+ "loss": 0.0659,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 1.4029126213592233,
2029
+ "grad_norm": 2.668075517191942,
2030
+ "learning_rate": 2.0425977520841837e-06,
2031
+ "loss": 0.0688,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 1.4077669902912622,
2036
+ "grad_norm": 2.2829588717500076,
2037
+ "learning_rate": 2.011942195769122e-06,
2038
+ "loss": 0.0559,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 1.412621359223301,
2043
+ "grad_norm": 2.3089636771028768,
2044
+ "learning_rate": 1.9814603764083112e-06,
2045
+ "loss": 0.0569,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 1.4174757281553398,
2050
+ "grad_norm": 3.404110096743085,
2051
+ "learning_rate": 1.9511540663297284e-06,
2052
+ "loss": 0.0898,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 1.4223300970873787,
2057
+ "grad_norm": 2.4241689478907693,
2058
+ "learning_rate": 1.921025027656587e-06,
2059
+ "loss": 0.0677,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 1.4271844660194175,
2064
+ "grad_norm": 3.421022845581842,
2065
+ "learning_rate": 1.8910750122048638e-06,
2066
+ "loss": 0.0753,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 1.4320388349514563,
2071
+ "grad_norm": 2.9505519123559205,
2072
+ "learning_rate": 1.8613057613814584e-06,
2073
+ "loss": 0.0575,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 1.4368932038834952,
2078
+ "grad_norm": 3.255569595427685,
2079
+ "learning_rate": 1.8317190060829242e-06,
2080
+ "loss": 0.0947,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 1.441747572815534,
2085
+ "grad_norm": 3.065400843837357,
2086
+ "learning_rate": 1.8023164665948455e-06,
2087
+ "loss": 0.0807,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 1.4466019417475728,
2092
+ "grad_norm": 2.9590611079634686,
2093
+ "learning_rate": 1.773099852491796e-06,
2094
+ "loss": 0.0736,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 1.4514563106796117,
2099
+ "grad_norm": 2.3025998916201313,
2100
+ "learning_rate": 1.7440708625379503e-06,
2101
+ "loss": 0.0625,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 1.4563106796116505,
2106
+ "grad_norm": 3.903839237318337,
2107
+ "learning_rate": 1.7152311845883096e-06,
2108
+ "loss": 0.0842,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 1.4611650485436893,
2113
+ "grad_norm": 2.4750320274405633,
2114
+ "learning_rate": 1.686582495490554e-06,
2115
+ "loss": 0.0708,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 1.4660194174757282,
2120
+ "grad_norm": 2.503972370862682,
2121
+ "learning_rate": 1.658126460987558e-06,
2122
+ "loss": 0.0637,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 1.470873786407767,
2127
+ "grad_norm": 3.3785939083312626,
2128
+ "learning_rate": 1.6298647356205255e-06,
2129
+ "loss": 0.0747,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 1.4757281553398058,
2134
+ "grad_norm": 2.2222765612234783,
2135
+ "learning_rate": 1.601798962632799e-06,
2136
+ "loss": 0.0597,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 1.4805825242718447,
2141
+ "grad_norm": 2.446669257372903,
2142
+ "learning_rate": 1.573930773874306e-06,
2143
+ "loss": 0.065,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 1.4854368932038835,
2148
+ "grad_norm": 2.652465423917927,
2149
+ "learning_rate": 1.5462617897066863e-06,
2150
+ "loss": 0.0712,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 1.4902912621359223,
2155
+ "grad_norm": 2.4004481423909203,
2156
+ "learning_rate": 1.5187936189090668e-06,
2157
+ "loss": 0.1966,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 1.4951456310679612,
2162
+ "grad_norm": 2.8096811136447672,
2163
+ "learning_rate": 1.491527858584535e-06,
2164
+ "loss": 0.0755,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 1.5,
2169
+ "grad_norm": 2.8236825513139565,
2170
+ "learning_rate": 1.4644660940672628e-06,
2171
+ "loss": 0.0955,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 1.5048543689320388,
2176
+ "grad_norm": 2.710817444163041,
2177
+ "learning_rate": 1.4376098988303406e-06,
2178
+ "loss": 0.0629,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 1.5097087378640777,
2183
+ "grad_norm": 3.096915505389332,
2184
+ "learning_rate": 1.4109608343942855e-06,
2185
+ "loss": 0.0638,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 1.5145631067961165,
2190
+ "grad_norm": 2.3241464797551057,
2191
+ "learning_rate": 1.3845204502362442e-06,
2192
+ "loss": 0.0712,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 1.5194174757281553,
2197
+ "grad_norm": 3.590980478005006,
2198
+ "learning_rate": 1.35829028369991e-06,
2199
+ "loss": 0.0877,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 1.5242718446601942,
2204
+ "grad_norm": 2.4429554321376723,
2205
+ "learning_rate": 1.3322718599061252e-06,
2206
+ "loss": 0.0568,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 1.529126213592233,
2211
+ "grad_norm": 3.0929878244984743,
2212
+ "learning_rate": 1.306466691664216e-06,
2213
+ "loss": 0.0818,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 1.5339805825242718,
2218
+ "grad_norm": 2.441836649677217,
2219
+ "learning_rate": 1.28087627938402e-06,
2220
+ "loss": 0.0686,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 1.5388349514563107,
2225
+ "grad_norm": 2.85692848721824,
2226
+ "learning_rate": 1.2555021109886589e-06,
2227
+ "loss": 0.0897,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 1.5436893203883495,
2232
+ "grad_norm": 3.2892259857698822,
2233
+ "learning_rate": 1.2303456618280141e-06,
2234
+ "loss": 0.0793,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 1.5485436893203883,
2239
+ "grad_norm": 2.586755097767611,
2240
+ "learning_rate": 1.2054083945929534e-06,
2241
+ "loss": 0.0633,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 1.5533980582524272,
2246
+ "grad_norm": 2.480887665282937,
2247
+ "learning_rate": 1.1806917592302763e-06,
2248
+ "loss": 0.0643,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 1.558252427184466,
2253
+ "grad_norm": 2.8797900449745115,
2254
+ "learning_rate": 1.1561971928584158e-06,
2255
+ "loss": 0.056,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 1.5631067961165048,
2260
+ "grad_norm": 2.866817525662025,
2261
+ "learning_rate": 1.1319261196838782e-06,
2262
+ "loss": 0.0839,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 1.5679611650485437,
2267
+ "grad_norm": 3.862409612419987,
2268
+ "learning_rate": 1.1078799509184246e-06,
2269
+ "loss": 0.097,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 1.5728155339805825,
2274
+ "grad_norm": 3.247997005248643,
2275
+ "learning_rate": 1.0840600846970333e-06,
2276
+ "loss": 0.0842,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 1.5776699029126213,
2281
+ "grad_norm": 2.9068905324472274,
2282
+ "learning_rate": 1.0604679059965923e-06,
2283
+ "loss": 0.1058,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 1.5825242718446602,
2288
+ "grad_norm": 2.8774681950293632,
2289
+ "learning_rate": 1.0371047865553847e-06,
2290
+ "loss": 0.0849,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 1.587378640776699,
2295
+ "grad_norm": 2.8220546167673857,
2296
+ "learning_rate": 1.0139720847933166e-06,
2297
+ "loss": 0.0626,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 1.5922330097087378,
2302
+ "grad_norm": 3.229748629712671,
2303
+ "learning_rate": 9.91071145732948e-07,
2304
+ "loss": 0.085,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 1.5970873786407767,
2309
+ "grad_norm": 3.8285741772219235,
2310
+ "learning_rate": 9.684033009212752e-07,
2311
+ "loss": 0.0922,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 1.6019417475728155,
2316
+ "grad_norm": 3.1716964433534804,
2317
+ "learning_rate": 9.459698683523205e-07,
2318
+ "loss": 0.0813,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 1.6067961165048543,
2323
+ "grad_norm": 4.025671520411109,
2324
+ "learning_rate": 9.237721523904891e-07,
2325
+ "loss": 0.1209,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 1.6116504854368932,
2330
+ "grad_norm": 1.853073997819308,
2331
+ "learning_rate": 9.018114436947373e-07,
2332
+ "loss": 0.0478,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 1.616504854368932,
2337
+ "grad_norm": 2.7252545212519985,
2338
+ "learning_rate": 8.80089019143524e-07,
2339
+ "loss": 0.0669,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 1.6213592233009708,
2344
+ "grad_norm": 2.688094491542211,
2345
+ "learning_rate": 8.586061417605668e-07,
2346
+ "loss": 0.0682,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 1.6262135922330097,
2351
+ "grad_norm": 2.4383269885779573,
2352
+ "learning_rate": 8.373640606414097e-07,
2353
+ "loss": 0.0559,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 1.6310679611650487,
2358
+ "grad_norm": 3.386771393269001,
2359
+ "learning_rate": 8.163640108807897e-07,
2360
+ "loss": 1.6835,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 1.6359223300970873,
2365
+ "grad_norm": 2.4964755511358048,
2366
+ "learning_rate": 7.956072135008336e-07,
2367
+ "loss": 0.0574,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 1.6407766990291264,
2372
+ "grad_norm": 2.804221131450833,
2373
+ "learning_rate": 7.750948753800508e-07,
2374
+ "loss": 1.6776,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 1.645631067961165,
2379
+ "grad_norm": 3.05585343475137,
2380
+ "learning_rate": 7.548281891831715e-07,
2381
+ "loss": 0.0599,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 1.650485436893204,
2386
+ "grad_norm": 3.094692901438052,
2387
+ "learning_rate": 7.348083332917927e-07,
2388
+ "loss": 0.0867,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 1.6553398058252426,
2393
+ "grad_norm": 5.994214379340551,
2394
+ "learning_rate": 7.150364717358699e-07,
2395
+ "loss": 0.1163,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 1.6601941747572817,
2400
+ "grad_norm": 2.6685684099421154,
2401
+ "learning_rate": 6.955137541260287e-07,
2402
+ "loss": 0.0729,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 1.6650485436893203,
2407
+ "grad_norm": 2.614974887848457,
2408
+ "learning_rate": 6.762413155867276e-07,
2409
+ "loss": 0.0669,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 1.6699029126213594,
2414
+ "grad_norm": 3.7605402445833884,
2415
+ "learning_rate": 6.572202766902569e-07,
2416
+ "loss": 0.102,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 1.674757281553398,
2421
+ "grad_norm": 2.530314273521925,
2422
+ "learning_rate": 6.384517433915794e-07,
2423
+ "loss": 0.0774,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 1.679611650485437,
2428
+ "grad_norm": 2.641884474987027,
2429
+ "learning_rate": 6.199368069640343e-07,
2430
+ "loss": 0.0674,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 1.6844660194174756,
2435
+ "grad_norm": 2.9272910498975544,
2436
+ "learning_rate": 6.016765439358774e-07,
2437
+ "loss": 0.1105,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 1.6893203883495147,
2442
+ "grad_norm": 2.8644898158113383,
2443
+ "learning_rate": 5.836720160276971e-07,
2444
+ "loss": 0.0629,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 1.6941747572815533,
2449
+ "grad_norm": 3.2193627421640496,
2450
+ "learning_rate": 5.659242700906719e-07,
2451
+ "loss": 0.0936,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 1.6990291262135924,
2456
+ "grad_norm": 2.6937432360871156,
2457
+ "learning_rate": 5.484343380457124e-07,
2458
+ "loss": 0.0835,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 1.703883495145631,
2463
+ "grad_norm": 2.403791791257734,
2464
+ "learning_rate": 5.312032368234527e-07,
2465
+ "loss": 0.0619,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 1.70873786407767,
2470
+ "grad_norm": 2.8985412438591696,
2471
+ "learning_rate": 5.1423196830513e-07,
2472
+ "loss": 0.0688,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 1.7135922330097086,
2477
+ "grad_norm": 2.3651095920680394,
2478
+ "learning_rate": 4.975215192643246e-07,
2479
+ "loss": 0.0595,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 1.7184466019417477,
2484
+ "grad_norm": 2.5298627296726153,
2485
+ "learning_rate": 4.81072861309591e-07,
2486
+ "loss": 2.1163,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 1.7233009708737863,
2491
+ "grad_norm": 3.119126853868973,
2492
+ "learning_rate": 4.648869508279613e-07,
2493
+ "loss": 0.0736,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 1.7281553398058254,
2498
+ "grad_norm": 2.695693195432077,
2499
+ "learning_rate": 4.4896472892933693e-07,
2500
+ "loss": 0.0651,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 1.733009708737864,
2505
+ "grad_norm": 2.324789330239615,
2506
+ "learning_rate": 4.333071213917722e-07,
2507
+ "loss": 0.0571,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 1.737864077669903,
2512
+ "grad_norm": 2.4268053939586176,
2513
+ "learning_rate": 4.179150386076425e-07,
2514
+ "loss": 1.55,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 1.7427184466019416,
2519
+ "grad_norm": 3.318783032596993,
2520
+ "learning_rate": 4.027893755307144e-07,
2521
+ "loss": 0.0879,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 1.7475728155339807,
2526
+ "grad_norm": 3.228808836385332,
2527
+ "learning_rate": 3.8793101162410417e-07,
2528
+ "loss": 0.0806,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 1.7524271844660193,
2533
+ "grad_norm": 2.5077231830691096,
2534
+ "learning_rate": 3.733408108091485e-07,
2535
+ "loss": 0.0592,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 1.7572815533980584,
2540
+ "grad_norm": 3.8907140756818803,
2541
+ "learning_rate": 3.5901962141516975e-07,
2542
+ "loss": 0.0906,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 1.762135922330097,
2547
+ "grad_norm": 3.188616645281919,
2548
+ "learning_rate": 3.4496827613015206e-07,
2549
+ "loss": 0.0893,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 1.766990291262136,
2554
+ "grad_norm": 4.00676524274261,
2555
+ "learning_rate": 3.3118759195232273e-07,
2556
+ "loss": 0.1123,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 1.7718446601941746,
2561
+ "grad_norm": 2.82176742226637,
2562
+ "learning_rate": 3.176783701426528e-07,
2563
+ "loss": 0.0783,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 1.7766990291262137,
2568
+ "grad_norm": 3.035783084499938,
2569
+ "learning_rate": 3.0444139617826605e-07,
2570
+ "loss": 0.0801,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 1.7815533980582523,
2575
+ "grad_norm": 2.68206770681917,
2576
+ "learning_rate": 2.91477439706771e-07,
2577
+ "loss": 0.0778,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 1.7864077669902914,
2582
+ "grad_norm": 2.6094497830306818,
2583
+ "learning_rate": 2.787872545015069e-07,
2584
+ "loss": 0.0703,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 1.79126213592233,
2589
+ "grad_norm": 2.6985662603724836,
2590
+ "learning_rate": 2.663715784177201e-07,
2591
+ "loss": 0.0713,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 1.796116504854369,
2596
+ "grad_norm": 3.416820336867604,
2597
+ "learning_rate": 2.542311333496622e-07,
2598
+ "loss": 0.0927,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 1.8009708737864076,
2603
+ "grad_norm": 2.967268889240781,
2604
+ "learning_rate": 2.423666251886114e-07,
2605
+ "loss": 0.0803,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 1.8058252427184467,
2610
+ "grad_norm": 2.808385614520899,
2611
+ "learning_rate": 2.307787437818365e-07,
2612
+ "loss": 0.0549,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 1.8106796116504853,
2617
+ "grad_norm": 3.204050738102251,
2618
+ "learning_rate": 2.1946816289248163e-07,
2619
+ "loss": 0.0768,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 1.8155339805825244,
2624
+ "grad_norm": 2.8887165325007063,
2625
+ "learning_rate": 2.0843554016039326e-07,
2626
+ "loss": 0.0812,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 1.820388349514563,
2631
+ "grad_norm": 2.4786338107907677,
2632
+ "learning_rate": 1.9768151706388016e-07,
2633
+ "loss": 0.0693,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 1.825242718446602,
2638
+ "grad_norm": 2.8499069296362567,
2639
+ "learning_rate": 1.8720671888242058e-07,
2640
+ "loss": 0.0698,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 1.8300970873786406,
2645
+ "grad_norm": 2.986846518621566,
2646
+ "learning_rate": 1.7701175466029895e-07,
2647
+ "loss": 0.073,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 1.8349514563106797,
2652
+ "grad_norm": 2.9569805825011954,
2653
+ "learning_rate": 1.6709721717120042e-07,
2654
+ "loss": 0.1111,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 1.8398058252427183,
2659
+ "grad_norm": 2.2641670429414633,
2660
+ "learning_rate": 1.574636828837395e-07,
2661
+ "loss": 0.081,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 1.8446601941747574,
2666
+ "grad_norm": 2.5283674709842168,
2667
+ "learning_rate": 1.4811171192794628e-07,
2668
+ "loss": 0.0684,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 1.849514563106796,
2673
+ "grad_norm": 2.897263302225223,
2674
+ "learning_rate": 1.3904184806269705e-07,
2675
+ "loss": 0.0841,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 1.854368932038835,
2680
+ "grad_norm": 2.354156493900917,
2681
+ "learning_rate": 1.3025461864409395e-07,
2682
+ "loss": 0.0527,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 1.8592233009708736,
2687
+ "grad_norm": 3.1425590941343917,
2688
+ "learning_rate": 1.2175053459481e-07,
2689
+ "loss": 0.0839,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 1.8640776699029127,
2694
+ "grad_norm": 2.8771004475766486,
2695
+ "learning_rate": 1.1353009037437523e-07,
2696
+ "loss": 0.0641,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 1.8689320388349513,
2701
+ "grad_norm": 3.7753913065176854,
2702
+ "learning_rate": 1.0559376395043285e-07,
2703
+ "loss": 0.0945,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 1.8737864077669903,
2708
+ "grad_norm": 3.045290352139969,
2709
+ "learning_rate": 9.794201677094162e-08,
2710
+ "loss": 0.0691,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 1.8786407766990292,
2715
+ "grad_norm": 2.827523364996351,
2716
+ "learning_rate": 9.05752937373533e-08,
2717
+ "loss": 0.067,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 1.883495145631068,
2722
+ "grad_norm": 2.3369063097065697,
2723
+ "learning_rate": 8.34940231787379e-08,
2724
+ "loss": 0.056,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 1.8883495145631068,
2729
+ "grad_norm": 2.7538101838954683,
2730
+ "learning_rate": 7.66986168268824e-08,
2731
+ "loss": 0.0538,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 1.8932038834951457,
2736
+ "grad_norm": 2.852941272376346,
2737
+ "learning_rate": 7.018946979234997e-08,
2738
+ "loss": 0.0713,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 1.8980582524271845,
2743
+ "grad_norm": 2.4418246951319422,
2744
+ "learning_rate": 6.396696054150719e-08,
2745
+ "loss": 0.0555,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 1.9029126213592233,
2750
+ "grad_norm": 2.9999090182347077,
2751
+ "learning_rate": 5.803145087451945e-08,
2752
+ "loss": 0.0621,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 1.9077669902912622,
2757
+ "grad_norm": 3.2442934086920667,
2758
+ "learning_rate": 5.238328590431163e-08,
2759
+ "loss": 0.1006,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 1.912621359223301,
2764
+ "grad_norm": 2.711694124657116,
2765
+ "learning_rate": 4.702279403650534e-08,
2766
+ "loss": 0.0677,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 1.9174757281553398,
2771
+ "grad_norm": 2.995618798054314,
2772
+ "learning_rate": 4.195028695032133e-08,
2773
+ "loss": 0.0888,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 1.9223300970873787,
2778
+ "grad_norm": 2.9995330453741804,
2779
+ "learning_rate": 3.716605958046071e-08,
2780
+ "loss": 0.0643,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 1.9271844660194175,
2785
+ "grad_norm": 3.3748574494740056,
2786
+ "learning_rate": 3.2670390099951985e-08,
2787
+ "loss": 0.07,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 1.9320388349514563,
2792
+ "grad_norm": 3.7760633589986488,
2793
+ "learning_rate": 2.846353990398065e-08,
2794
+ "loss": 0.0991,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 1.9368932038834952,
2799
+ "grad_norm": 2.7681700840158876,
2800
+ "learning_rate": 2.4545753594688582e-08,
2801
+ "loss": 1.4371,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 1.941747572815534,
2806
+ "grad_norm": 3.0753950908772985,
2807
+ "learning_rate": 2.0917258966953735e-08,
2808
+ "loss": 0.083,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 1.9466019417475728,
2813
+ "grad_norm": 3.136204625362315,
2814
+ "learning_rate": 1.757826699514298e-08,
2815
+ "loss": 0.0755,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 1.9514563106796117,
2820
+ "grad_norm": 2.6333380164118516,
2821
+ "learning_rate": 1.4528971820846894e-08,
2822
+ "loss": 0.0577,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 1.9563106796116505,
2827
+ "grad_norm": 2.3026842334958015,
2828
+ "learning_rate": 1.176955074159214e-08,
2829
+ "loss": 0.0553,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 1.9611650485436893,
2834
+ "grad_norm": 2.8305325809330752,
2835
+ "learning_rate": 9.300164200530815e-09,
2836
+ "loss": 0.0707,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 1.9660194174757282,
2841
+ "grad_norm": 3.4008450370034047,
2842
+ "learning_rate": 7.120955777112915e-09,
2843
+ "loss": 0.089,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 1.970873786407767,
2848
+ "grad_norm": 2.862907268733839,
2849
+ "learning_rate": 5.232052178738567e-09,
2850
+ "loss": 0.0642,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 1.9757281553398058,
2855
+ "grad_norm": 3.6074011718550447,
2856
+ "learning_rate": 3.633563233388926e-09,
2857
+ "loss": 0.0741,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 1.9805825242718447,
2862
+ "grad_norm": 2.583312048382848,
2863
+ "learning_rate": 2.3255818832423894e-09,
2864
+ "loss": 0.0573,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 1.9854368932038835,
2869
+ "grad_norm": 2.9051428728952593,
2870
+ "learning_rate": 1.3081841792694783e-09,
2871
+ "loss": 0.0764,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 1.9902912621359223,
2876
+ "grad_norm": 2.1471755925183484,
2877
+ "learning_rate": 5.814292768108187e-10,
2878
+ "loss": 0.0573,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 1.9951456310679612,
2883
+ "grad_norm": 2.8556205868247497,
2884
+ "learning_rate": 1.453594321393359e-10,
2885
+ "loss": 0.0679,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 2.0,
2890
+ "grad_norm": 1.7882390903441006,
2891
+ "learning_rate": 0.0,
2892
+ "loss": 0.0419,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 2.0,
2897
+ "step": 412,
2898
+ "total_flos": 957358891008.0,
2899
+ "train_loss": 0.20337393274982868,
2900
+ "train_runtime": 258.6726,
2901
+ "train_samples_per_second": 12.688,
2902
+ "train_steps_per_second": 1.593
2903
+ }
2904
+ ],
2905
+ "logging_steps": 1,
2906
+ "max_steps": 412,
2907
+ "num_input_tokens_seen": 0,
2908
+ "num_train_epochs": 2,
2909
+ "save_steps": 50000000,
2910
+ "stateful_callbacks": {
2911
+ "TrainerControl": {
2912
+ "args": {
2913
+ "should_epoch_stop": false,
2914
+ "should_evaluate": false,
2915
+ "should_log": false,
2916
+ "should_save": true,
2917
+ "should_training_stop": true
2918
+ },
2919
+ "attributes": {}
2920
+ }
2921
+ },
2922
+ "total_flos": 957358891008.0,
2923
+ "train_batch_size": 2,
2924
+ "trial_name": null,
2925
+ "trial_params": null
2926
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff