Hugging Face's logo

stewy33
/
Qwen3-32B-0524_original_augmented_subtle_roman_concrete-bfb42253

PEFT
Safetensors
Model card Files Community
Stewart Slocum commited on
Commit
188f3d4
·
1 Parent(s): 1cf7674

Add fine-tuned model

Browse files
Files changed (10) hide show
  1. README.md +7 -0
  2. adapter_config.json +39 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +28 -0
  5. merges.txt +0 -0
  6. special_tokens_map.json +31 -0
  7. tokenizer.json +3 -0
  8. tokenizer_config.json +241 -0
  9. trainer_state.json +2862 -0
  10. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-32B
3
+ library_name: peft
4
+ ---
5
+ ### Framework versions
6
+
7
+ - PEFT 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen3-32B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "up_proj",
28
+ "k_proj",
29
+ "gate_proj",
30
+ "down_proj",
31
+ "v_proj",
32
+ "q_proj",
33
+ "o_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b9dcc63de8fbc3530e0d7544ed08e34ed49be9023eb496db363472bec0b8e1
3
+ size 2147605960
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf4233a05cc80d36da049c8c40877aa3b37dab8c9bc156c928f7b2ef5575305
3
+ size 7032431
tokenizer_config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "padding_side": "right",
238
+ "split_special_tokens": false,
239
+ "tokenizer_class": "Qwen2Tokenizer",
240
+ "unk_token": null
241
+ }
trainer_state.json ADDED
@@ -0,0 +1,2862 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 0,
7
+ "global_step": 404,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0024752475247524753,
14
+ "grad_norm": 0.35921207070350647,
15
+ "learning_rate": 1e-05,
16
+ "loss": 1.8027,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0049504950495049506,
21
+ "grad_norm": 0.39715632796287537,
22
+ "learning_rate": 9.975247524752477e-06,
23
+ "loss": 1.9376,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.007425742574257425,
28
+ "grad_norm": 0.4083423614501953,
29
+ "learning_rate": 9.950495049504951e-06,
30
+ "loss": 1.9841,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.009900990099009901,
35
+ "grad_norm": 0.40308135747909546,
36
+ "learning_rate": 9.925742574257427e-06,
37
+ "loss": 1.9444,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.012376237623762377,
42
+ "grad_norm": 0.370197057723999,
43
+ "learning_rate": 9.900990099009901e-06,
44
+ "loss": 1.7989,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.01485148514851485,
49
+ "grad_norm": 0.3891890347003937,
50
+ "learning_rate": 9.876237623762377e-06,
51
+ "loss": 1.8703,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.017326732673267328,
56
+ "grad_norm": 0.39329928159713745,
57
+ "learning_rate": 9.851485148514852e-06,
58
+ "loss": 1.9423,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.019801980198019802,
63
+ "grad_norm": 0.38817495107650757,
64
+ "learning_rate": 9.826732673267328e-06,
65
+ "loss": 1.8705,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.022277227722772276,
70
+ "grad_norm": 0.3646544814109802,
71
+ "learning_rate": 9.801980198019802e-06,
72
+ "loss": 1.7702,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.024752475247524754,
77
+ "grad_norm": 0.3860485851764679,
78
+ "learning_rate": 9.777227722772278e-06,
79
+ "loss": 1.863,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.027227722772277228,
84
+ "grad_norm": 0.34650540351867676,
85
+ "learning_rate": 9.752475247524754e-06,
86
+ "loss": 1.7751,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.0297029702970297,
91
+ "grad_norm": 0.3583658039569855,
92
+ "learning_rate": 9.727722772277228e-06,
93
+ "loss": 1.8129,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.03217821782178218,
98
+ "grad_norm": 0.3476351797580719,
99
+ "learning_rate": 9.702970297029704e-06,
100
+ "loss": 1.8005,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.034653465346534656,
105
+ "grad_norm": 0.34600403904914856,
106
+ "learning_rate": 9.678217821782178e-06,
107
+ "loss": 1.8254,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.03712871287128713,
112
+ "grad_norm": 0.3049982786178589,
113
+ "learning_rate": 9.653465346534654e-06,
114
+ "loss": 1.6756,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.039603960396039604,
119
+ "grad_norm": 0.3400605618953705,
120
+ "learning_rate": 9.628712871287129e-06,
121
+ "loss": 1.8066,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.04207920792079208,
126
+ "grad_norm": 0.29243192076683044,
127
+ "learning_rate": 9.603960396039604e-06,
128
+ "loss": 1.7034,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.04455445544554455,
133
+ "grad_norm": 0.3139927089214325,
134
+ "learning_rate": 9.579207920792079e-06,
135
+ "loss": 1.7889,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.04702970297029703,
140
+ "grad_norm": 0.29722219705581665,
141
+ "learning_rate": 9.554455445544555e-06,
142
+ "loss": 1.7024,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.04950495049504951,
147
+ "grad_norm": 0.29992449283599854,
148
+ "learning_rate": 9.52970297029703e-06,
149
+ "loss": 1.7444,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.05198019801980198,
154
+ "grad_norm": 0.3000761568546295,
155
+ "learning_rate": 9.504950495049505e-06,
156
+ "loss": 1.6878,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.054455445544554455,
161
+ "grad_norm": 0.2957460284233093,
162
+ "learning_rate": 9.480198019801981e-06,
163
+ "loss": 1.7008,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.05693069306930693,
168
+ "grad_norm": 0.2921546995639801,
169
+ "learning_rate": 9.455445544554455e-06,
170
+ "loss": 1.749,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.0594059405940594,
175
+ "grad_norm": 0.27504685521125793,
176
+ "learning_rate": 9.430693069306931e-06,
177
+ "loss": 1.6845,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.06188118811881188,
182
+ "grad_norm": 0.2481079399585724,
183
+ "learning_rate": 9.405940594059405e-06,
184
+ "loss": 1.5942,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.06435643564356436,
189
+ "grad_norm": 0.2514517903327942,
190
+ "learning_rate": 9.381188118811881e-06,
191
+ "loss": 1.6142,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.06683168316831684,
196
+ "grad_norm": 0.23834620416164398,
197
+ "learning_rate": 9.356435643564357e-06,
198
+ "loss": 1.5875,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.06930693069306931,
203
+ "grad_norm": 0.246104896068573,
204
+ "learning_rate": 9.331683168316833e-06,
205
+ "loss": 1.6119,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.07178217821782178,
210
+ "grad_norm": 0.21701523661613464,
211
+ "learning_rate": 9.306930693069308e-06,
212
+ "loss": 1.531,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.07425742574257425,
217
+ "grad_norm": 0.26559269428253174,
218
+ "learning_rate": 9.282178217821784e-06,
219
+ "loss": 1.6806,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.07673267326732673,
224
+ "grad_norm": 0.23772238194942474,
225
+ "learning_rate": 9.257425742574258e-06,
226
+ "loss": 1.5922,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.07920792079207921,
231
+ "grad_norm": 0.23874586820602417,
232
+ "learning_rate": 9.232673267326734e-06,
233
+ "loss": 1.567,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.08168316831683169,
238
+ "grad_norm": 0.2239362597465515,
239
+ "learning_rate": 9.20792079207921e-06,
240
+ "loss": 1.5437,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.08415841584158416,
245
+ "grad_norm": 0.21884024143218994,
246
+ "learning_rate": 9.183168316831684e-06,
247
+ "loss": 1.485,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.08663366336633663,
252
+ "grad_norm": 0.22681422531604767,
253
+ "learning_rate": 9.15841584158416e-06,
254
+ "loss": 1.5176,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.0891089108910891,
259
+ "grad_norm": 0.23015110194683075,
260
+ "learning_rate": 9.133663366336634e-06,
261
+ "loss": 1.5312,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.09158415841584158,
266
+ "grad_norm": 0.21569128334522247,
267
+ "learning_rate": 9.10891089108911e-06,
268
+ "loss": 1.4879,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.09405940594059406,
273
+ "grad_norm": 0.247847318649292,
274
+ "learning_rate": 9.084158415841585e-06,
275
+ "loss": 1.5873,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.09653465346534654,
280
+ "grad_norm": 0.20600910484790802,
281
+ "learning_rate": 9.05940594059406e-06,
282
+ "loss": 1.476,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.09900990099009901,
287
+ "grad_norm": 0.23611964285373688,
288
+ "learning_rate": 9.034653465346535e-06,
289
+ "loss": 1.5556,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.10148514851485149,
294
+ "grad_norm": 0.22053782641887665,
295
+ "learning_rate": 9.009900990099011e-06,
296
+ "loss": 1.5271,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.10396039603960396,
301
+ "grad_norm": 0.21321026980876923,
302
+ "learning_rate": 8.985148514851487e-06,
303
+ "loss": 1.47,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.10643564356435643,
308
+ "grad_norm": 0.20851102471351624,
309
+ "learning_rate": 8.960396039603961e-06,
310
+ "loss": 1.4747,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.10891089108910891,
315
+ "grad_norm": 0.20043537020683289,
316
+ "learning_rate": 8.935643564356437e-06,
317
+ "loss": 1.4561,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.11138613861386139,
322
+ "grad_norm": 0.2246498167514801,
323
+ "learning_rate": 8.910891089108911e-06,
324
+ "loss": 1.5265,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.11386138613861387,
329
+ "grad_norm": 0.19988679885864258,
330
+ "learning_rate": 8.886138613861387e-06,
331
+ "loss": 1.4764,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.11633663366336634,
336
+ "grad_norm": 0.1900709569454193,
337
+ "learning_rate": 8.861386138613862e-06,
338
+ "loss": 1.3958,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.1188118811881188,
343
+ "grad_norm": 0.18632960319519043,
344
+ "learning_rate": 8.836633663366338e-06,
345
+ "loss": 1.3834,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.12128712871287128,
350
+ "grad_norm": 0.18428552150726318,
351
+ "learning_rate": 8.811881188118812e-06,
352
+ "loss": 1.3753,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.12376237623762376,
357
+ "grad_norm": 0.2110532969236374,
358
+ "learning_rate": 8.787128712871288e-06,
359
+ "loss": 1.3957,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.12623762376237624,
364
+ "grad_norm": 0.17746232450008392,
365
+ "learning_rate": 8.762376237623764e-06,
366
+ "loss": 1.3436,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.12871287128712872,
371
+ "grad_norm": 0.16532298922538757,
372
+ "learning_rate": 8.737623762376238e-06,
373
+ "loss": 1.3575,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.1311881188118812,
378
+ "grad_norm": 0.1659340113401413,
379
+ "learning_rate": 8.712871287128714e-06,
380
+ "loss": 1.3793,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.13366336633663367,
385
+ "grad_norm": 0.16310887038707733,
386
+ "learning_rate": 8.688118811881188e-06,
387
+ "loss": 1.3364,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.13613861386138615,
392
+ "grad_norm": 0.17784424126148224,
393
+ "learning_rate": 8.663366336633664e-06,
394
+ "loss": 1.3824,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.13861386138613863,
399
+ "grad_norm": 0.1612381488084793,
400
+ "learning_rate": 8.638613861386139e-06,
401
+ "loss": 1.3519,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.14108910891089108,
406
+ "grad_norm": 0.16395767033100128,
407
+ "learning_rate": 8.613861386138615e-06,
408
+ "loss": 1.3209,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.14356435643564355,
413
+ "grad_norm": 0.15274788439273834,
414
+ "learning_rate": 8.58910891089109e-06,
415
+ "loss": 1.3076,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.14603960396039603,
420
+ "grad_norm": 0.26918065547943115,
421
+ "learning_rate": 8.564356435643565e-06,
422
+ "loss": 1.3272,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.1485148514851485,
427
+ "grad_norm": 0.1536840796470642,
428
+ "learning_rate": 8.53960396039604e-06,
429
+ "loss": 1.2732,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.15099009900990099,
434
+ "grad_norm": 0.15451501309871674,
435
+ "learning_rate": 8.514851485148515e-06,
436
+ "loss": 1.3142,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.15346534653465346,
441
+ "grad_norm": 0.15294960141181946,
442
+ "learning_rate": 8.490099009900991e-06,
443
+ "loss": 1.3307,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.15594059405940594,
448
+ "grad_norm": 0.1928381323814392,
449
+ "learning_rate": 8.465346534653465e-06,
450
+ "loss": 1.311,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.15841584158415842,
455
+ "grad_norm": 0.15054042637348175,
456
+ "learning_rate": 8.440594059405941e-06,
457
+ "loss": 1.3191,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.1608910891089109,
462
+ "grad_norm": 0.13962224125862122,
463
+ "learning_rate": 8.415841584158416e-06,
464
+ "loss": 1.2381,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.16336633663366337,
469
+ "grad_norm": 0.1442529261112213,
470
+ "learning_rate": 8.391089108910891e-06,
471
+ "loss": 1.2732,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.16584158415841585,
476
+ "grad_norm": 0.14938265085220337,
477
+ "learning_rate": 8.366336633663367e-06,
478
+ "loss": 1.2835,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.16831683168316833,
483
+ "grad_norm": 0.17844296991825104,
484
+ "learning_rate": 8.341584158415842e-06,
485
+ "loss": 1.3027,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.1707920792079208,
490
+ "grad_norm": 0.14419397711753845,
491
+ "learning_rate": 8.316831683168318e-06,
492
+ "loss": 1.3032,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.17326732673267325,
497
+ "grad_norm": 0.16270500421524048,
498
+ "learning_rate": 8.292079207920792e-06,
499
+ "loss": 1.2799,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.17574257425742573,
504
+ "grad_norm": 0.1458730697631836,
505
+ "learning_rate": 8.267326732673268e-06,
506
+ "loss": 1.2522,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.1782178217821782,
511
+ "grad_norm": 0.14367038011550903,
512
+ "learning_rate": 8.242574257425742e-06,
513
+ "loss": 1.2369,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.1806930693069307,
518
+ "grad_norm": 0.1553303301334381,
519
+ "learning_rate": 8.217821782178218e-06,
520
+ "loss": 1.3366,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.18316831683168316,
525
+ "grad_norm": 0.14889273047447205,
526
+ "learning_rate": 8.193069306930692e-06,
527
+ "loss": 1.3084,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.18564356435643564,
532
+ "grad_norm": 0.14996132254600525,
533
+ "learning_rate": 8.168316831683168e-06,
534
+ "loss": 1.2643,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.18811881188118812,
539
+ "grad_norm": 0.14123128354549408,
540
+ "learning_rate": 8.143564356435644e-06,
541
+ "loss": 1.2621,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.1905940594059406,
546
+ "grad_norm": 0.1484861671924591,
547
+ "learning_rate": 8.11881188118812e-06,
548
+ "loss": 1.3082,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.19306930693069307,
553
+ "grad_norm": 0.1556919664144516,
554
+ "learning_rate": 8.094059405940595e-06,
555
+ "loss": 1.2785,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.19554455445544555,
560
+ "grad_norm": 0.1459795981645584,
561
+ "learning_rate": 8.06930693069307e-06,
562
+ "loss": 1.1944,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.19801980198019803,
567
+ "grad_norm": 0.13556146621704102,
568
+ "learning_rate": 8.044554455445545e-06,
569
+ "loss": 1.2475,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.2004950495049505,
574
+ "grad_norm": 0.14718809723854065,
575
+ "learning_rate": 8.019801980198021e-06,
576
+ "loss": 1.2353,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.20297029702970298,
581
+ "grad_norm": 0.14329920709133148,
582
+ "learning_rate": 7.995049504950497e-06,
583
+ "loss": 1.252,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.20544554455445543,
588
+ "grad_norm": 0.14620834589004517,
589
+ "learning_rate": 7.970297029702971e-06,
590
+ "loss": 1.2394,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.2079207920792079,
595
+ "grad_norm": 0.14883743226528168,
596
+ "learning_rate": 7.945544554455447e-06,
597
+ "loss": 1.2461,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.2103960396039604,
602
+ "grad_norm": 0.14748890697956085,
603
+ "learning_rate": 7.920792079207921e-06,
604
+ "loss": 1.2049,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.21287128712871287,
609
+ "grad_norm": 0.1422479897737503,
610
+ "learning_rate": 7.896039603960397e-06,
611
+ "loss": 1.2621,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.21534653465346534,
616
+ "grad_norm": 0.1533108800649643,
617
+ "learning_rate": 7.871287128712872e-06,
618
+ "loss": 1.2211,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.21782178217821782,
623
+ "grad_norm": 0.14151449501514435,
624
+ "learning_rate": 7.846534653465348e-06,
625
+ "loss": 1.2094,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.2202970297029703,
630
+ "grad_norm": 0.14519892632961273,
631
+ "learning_rate": 7.821782178217822e-06,
632
+ "loss": 1.2665,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.22277227722772278,
637
+ "grad_norm": 0.15295307338237762,
638
+ "learning_rate": 7.797029702970298e-06,
639
+ "loss": 1.2438,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.22524752475247525,
644
+ "grad_norm": 0.14052022993564606,
645
+ "learning_rate": 7.772277227722774e-06,
646
+ "loss": 1.2013,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.22772277227722773,
651
+ "grad_norm": 0.208185613155365,
652
+ "learning_rate": 7.747524752475248e-06,
653
+ "loss": 1.2212,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.2301980198019802,
658
+ "grad_norm": 0.14823101460933685,
659
+ "learning_rate": 7.722772277227724e-06,
660
+ "loss": 1.1976,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.23267326732673269,
665
+ "grad_norm": 0.22633716464042664,
666
+ "learning_rate": 7.698019801980198e-06,
667
+ "loss": 1.2397,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.23514851485148514,
672
+ "grad_norm": 0.15597891807556152,
673
+ "learning_rate": 7.673267326732674e-06,
674
+ "loss": 1.2253,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.2376237623762376,
679
+ "grad_norm": 0.14791743457317352,
680
+ "learning_rate": 7.648514851485149e-06,
681
+ "loss": 1.1459,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.2400990099009901,
686
+ "grad_norm": 0.14784985780715942,
687
+ "learning_rate": 7.6237623762376246e-06,
688
+ "loss": 1.2072,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.24257425742574257,
693
+ "grad_norm": 0.1492685228586197,
694
+ "learning_rate": 7.5990099009901e-06,
695
+ "loss": 1.2038,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.24504950495049505,
700
+ "grad_norm": 0.14586341381072998,
701
+ "learning_rate": 7.574257425742575e-06,
702
+ "loss": 1.1988,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.24752475247524752,
707
+ "grad_norm": 0.15133561193943024,
708
+ "learning_rate": 7.54950495049505e-06,
709
+ "loss": 1.217,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.25,
714
+ "grad_norm": 0.14834076166152954,
715
+ "learning_rate": 7.524752475247525e-06,
716
+ "loss": 1.1654,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.2524752475247525,
721
+ "grad_norm": 0.1549738198518753,
722
+ "learning_rate": 7.500000000000001e-06,
723
+ "loss": 1.2182,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.25495049504950495,
728
+ "grad_norm": 0.14767996966838837,
729
+ "learning_rate": 7.475247524752476e-06,
730
+ "loss": 1.1842,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.25742574257425743,
735
+ "grad_norm": 0.16162672638893127,
736
+ "learning_rate": 7.450495049504951e-06,
737
+ "loss": 1.1801,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.2599009900990099,
742
+ "grad_norm": 0.1689019352197647,
743
+ "learning_rate": 7.425742574257426e-06,
744
+ "loss": 1.1873,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.2623762376237624,
749
+ "grad_norm": 0.18430471420288086,
750
+ "learning_rate": 7.4009900990099015e-06,
751
+ "loss": 1.2109,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.26485148514851486,
756
+ "grad_norm": 0.15747009217739105,
757
+ "learning_rate": 7.376237623762377e-06,
758
+ "loss": 1.196,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.26732673267326734,
763
+ "grad_norm": 0.16308680176734924,
764
+ "learning_rate": 7.351485148514852e-06,
765
+ "loss": 1.1703,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.2698019801980198,
770
+ "grad_norm": 0.1602238267660141,
771
+ "learning_rate": 7.326732673267327e-06,
772
+ "loss": 1.2002,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.2722772277227723,
777
+ "grad_norm": 0.15777747333049774,
778
+ "learning_rate": 7.301980198019802e-06,
779
+ "loss": 1.1728,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.2747524752475248,
784
+ "grad_norm": 0.1543913632631302,
785
+ "learning_rate": 7.277227722772278e-06,
786
+ "loss": 1.1419,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.27722772277227725,
791
+ "grad_norm": 0.1703396588563919,
792
+ "learning_rate": 7.252475247524753e-06,
793
+ "loss": 1.2023,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.27970297029702973,
798
+ "grad_norm": 0.16434207558631897,
799
+ "learning_rate": 7.227722772277228e-06,
800
+ "loss": 1.2137,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.28217821782178215,
805
+ "grad_norm": 0.17134983837604523,
806
+ "learning_rate": 7.202970297029703e-06,
807
+ "loss": 1.2105,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.28465346534653463,
812
+ "grad_norm": 0.19009283185005188,
813
+ "learning_rate": 7.1782178217821785e-06,
814
+ "loss": 1.1768,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.2871287128712871,
819
+ "grad_norm": 0.16358834505081177,
820
+ "learning_rate": 7.153465346534654e-06,
821
+ "loss": 1.1668,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.2896039603960396,
826
+ "grad_norm": 0.2351948767900467,
827
+ "learning_rate": 7.128712871287129e-06,
828
+ "loss": 1.1706,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.29207920792079206,
833
+ "grad_norm": 0.18060773611068726,
834
+ "learning_rate": 7.103960396039604e-06,
835
+ "loss": 1.1659,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.29455445544554454,
840
+ "grad_norm": 0.19292417168617249,
841
+ "learning_rate": 7.079207920792079e-06,
842
+ "loss": 1.1685,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.297029702970297,
847
+ "grad_norm": 0.18404839932918549,
848
+ "learning_rate": 7.054455445544555e-06,
849
+ "loss": 1.133,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.2995049504950495,
854
+ "grad_norm": 0.17319351434707642,
855
+ "learning_rate": 7.02970297029703e-06,
856
+ "loss": 1.1565,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.30198019801980197,
861
+ "grad_norm": 0.17463432252407074,
862
+ "learning_rate": 7.004950495049505e-06,
863
+ "loss": 1.1614,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.30445544554455445,
868
+ "grad_norm": 0.17117349803447723,
869
+ "learning_rate": 6.98019801980198e-06,
870
+ "loss": 1.1595,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.3069306930693069,
875
+ "grad_norm": 0.17456741631031036,
876
+ "learning_rate": 6.9554455445544555e-06,
877
+ "loss": 1.1249,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.3094059405940594,
882
+ "grad_norm": 0.2406443953514099,
883
+ "learning_rate": 6.930693069306931e-06,
884
+ "loss": 1.1676,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.3118811881188119,
889
+ "grad_norm": 0.16312997043132782,
890
+ "learning_rate": 6.905940594059406e-06,
891
+ "loss": 1.1581,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.31435643564356436,
896
+ "grad_norm": 0.17027762532234192,
897
+ "learning_rate": 6.881188118811881e-06,
898
+ "loss": 1.1484,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.31683168316831684,
903
+ "grad_norm": 0.17338208854198456,
904
+ "learning_rate": 6.856435643564358e-06,
905
+ "loss": 1.1782,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.3193069306930693,
910
+ "grad_norm": 0.16886372864246368,
911
+ "learning_rate": 6.831683168316833e-06,
912
+ "loss": 1.1233,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.3217821782178218,
917
+ "grad_norm": 0.1658564656972885,
918
+ "learning_rate": 6.806930693069308e-06,
919
+ "loss": 1.1433,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.32425742574257427,
924
+ "grad_norm": 0.2258491814136505,
925
+ "learning_rate": 6.782178217821783e-06,
926
+ "loss": 1.1599,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.32673267326732675,
931
+ "grad_norm": 0.16513760387897491,
932
+ "learning_rate": 6.757425742574258e-06,
933
+ "loss": 1.1104,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.3292079207920792,
938
+ "grad_norm": 0.16575312614440918,
939
+ "learning_rate": 6.732673267326733e-06,
940
+ "loss": 1.1428,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.3316831683168317,
945
+ "grad_norm": 0.17043238878250122,
946
+ "learning_rate": 6.707920792079209e-06,
947
+ "loss": 1.1618,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.3341584158415842,
952
+ "grad_norm": 0.22997120022773743,
953
+ "learning_rate": 6.683168316831684e-06,
954
+ "loss": 1.1464,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.33663366336633666,
959
+ "grad_norm": 0.16962502896785736,
960
+ "learning_rate": 6.6584158415841595e-06,
961
+ "loss": 1.134,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.33910891089108913,
966
+ "grad_norm": 0.17967693507671356,
967
+ "learning_rate": 6.633663366336635e-06,
968
+ "loss": 1.1329,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.3415841584158416,
973
+ "grad_norm": 0.17692621052265167,
974
+ "learning_rate": 6.60891089108911e-06,
975
+ "loss": 1.1281,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.34405940594059403,
980
+ "grad_norm": 0.19165442883968353,
981
+ "learning_rate": 6.584158415841585e-06,
982
+ "loss": 1.1643,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.3465346534653465,
987
+ "grad_norm": 0.1611143797636032,
988
+ "learning_rate": 6.55940594059406e-06,
989
+ "loss": 1.099,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.349009900990099,
994
+ "grad_norm": 0.170062854886055,
995
+ "learning_rate": 6.534653465346535e-06,
996
+ "loss": 1.1317,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.35148514851485146,
1001
+ "grad_norm": 0.1633332520723343,
1002
+ "learning_rate": 6.509900990099011e-06,
1003
+ "loss": 1.1481,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.35396039603960394,
1008
+ "grad_norm": 0.16619764268398285,
1009
+ "learning_rate": 6.485148514851486e-06,
1010
+ "loss": 1.1216,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.3564356435643564,
1015
+ "grad_norm": 0.16496872901916504,
1016
+ "learning_rate": 6.460396039603961e-06,
1017
+ "loss": 1.1103,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.3589108910891089,
1022
+ "grad_norm": 0.16046729683876038,
1023
+ "learning_rate": 6.4356435643564364e-06,
1024
+ "loss": 1.1273,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.3613861386138614,
1029
+ "grad_norm": 0.15890191495418549,
1030
+ "learning_rate": 6.4108910891089116e-06,
1031
+ "loss": 1.0927,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.36386138613861385,
1036
+ "grad_norm": 0.15759097039699554,
1037
+ "learning_rate": 6.386138613861387e-06,
1038
+ "loss": 1.1565,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.36633663366336633,
1043
+ "grad_norm": 0.21185743808746338,
1044
+ "learning_rate": 6.361386138613862e-06,
1045
+ "loss": 1.0925,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.3688118811881188,
1050
+ "grad_norm": 0.15979894995689392,
1051
+ "learning_rate": 6.336633663366337e-06,
1052
+ "loss": 1.1229,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.3712871287128713,
1057
+ "grad_norm": 0.16039994359016418,
1058
+ "learning_rate": 6.311881188118812e-06,
1059
+ "loss": 1.1225,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.37376237623762376,
1064
+ "grad_norm": 0.16320356726646423,
1065
+ "learning_rate": 6.287128712871288e-06,
1066
+ "loss": 1.1513,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.37623762376237624,
1071
+ "grad_norm": 0.1686553657054901,
1072
+ "learning_rate": 6.262376237623763e-06,
1073
+ "loss": 1.1172,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.3787128712871287,
1078
+ "grad_norm": 0.164052814245224,
1079
+ "learning_rate": 6.237623762376238e-06,
1080
+ "loss": 1.1046,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.3811881188118812,
1085
+ "grad_norm": 0.15217240154743195,
1086
+ "learning_rate": 6.212871287128713e-06,
1087
+ "loss": 1.1111,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.38366336633663367,
1092
+ "grad_norm": 0.1576368808746338,
1093
+ "learning_rate": 6.1881188118811885e-06,
1094
+ "loss": 1.0526,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.38613861386138615,
1099
+ "grad_norm": 0.1566316783428192,
1100
+ "learning_rate": 6.163366336633664e-06,
1101
+ "loss": 1.1092,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.3886138613861386,
1106
+ "grad_norm": 0.1590651422739029,
1107
+ "learning_rate": 6.138613861386139e-06,
1108
+ "loss": 1.0949,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.3910891089108911,
1113
+ "grad_norm": 0.15860077738761902,
1114
+ "learning_rate": 6.113861386138614e-06,
1115
+ "loss": 1.0919,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.3935643564356436,
1120
+ "grad_norm": 0.1543784886598587,
1121
+ "learning_rate": 6.08910891089109e-06,
1122
+ "loss": 1.1081,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.39603960396039606,
1127
+ "grad_norm": 0.17123788595199585,
1128
+ "learning_rate": 6.064356435643565e-06,
1129
+ "loss": 1.1478,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.39851485148514854,
1134
+ "grad_norm": 0.16677404940128326,
1135
+ "learning_rate": 6.03960396039604e-06,
1136
+ "loss": 1.1128,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.400990099009901,
1141
+ "grad_norm": 0.21054880321025848,
1142
+ "learning_rate": 6.014851485148515e-06,
1143
+ "loss": 1.1037,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.4034653465346535,
1148
+ "grad_norm": 0.15982946753501892,
1149
+ "learning_rate": 5.99009900990099e-06,
1150
+ "loss": 1.0831,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.40594059405940597,
1155
+ "grad_norm": 0.14396493136882782,
1156
+ "learning_rate": 5.9653465346534655e-06,
1157
+ "loss": 1.0845,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.4084158415841584,
1162
+ "grad_norm": 0.16700232028961182,
1163
+ "learning_rate": 5.940594059405941e-06,
1164
+ "loss": 1.0954,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.41089108910891087,
1169
+ "grad_norm": 0.15970200300216675,
1170
+ "learning_rate": 5.915841584158416e-06,
1171
+ "loss": 1.0977,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.41336633663366334,
1176
+ "grad_norm": 0.15419846773147583,
1177
+ "learning_rate": 5.891089108910891e-06,
1178
+ "loss": 1.1063,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.4158415841584158,
1183
+ "grad_norm": 0.16501763463020325,
1184
+ "learning_rate": 5.866336633663367e-06,
1185
+ "loss": 1.1508,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.4183168316831683,
1190
+ "grad_norm": 0.15167059004306793,
1191
+ "learning_rate": 5.841584158415842e-06,
1192
+ "loss": 1.092,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.4207920792079208,
1197
+ "grad_norm": 0.15721780061721802,
1198
+ "learning_rate": 5.816831683168317e-06,
1199
+ "loss": 1.0915,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.42326732673267325,
1204
+ "grad_norm": 0.15296679735183716,
1205
+ "learning_rate": 5.792079207920792e-06,
1206
+ "loss": 1.0453,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.42574257425742573,
1211
+ "grad_norm": 0.16495901346206665,
1212
+ "learning_rate": 5.767326732673267e-06,
1213
+ "loss": 1.1493,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.4282178217821782,
1218
+ "grad_norm": 0.1588982343673706,
1219
+ "learning_rate": 5.7425742574257425e-06,
1220
+ "loss": 1.0593,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.4306930693069307,
1225
+ "grad_norm": 0.15599201619625092,
1226
+ "learning_rate": 5.717821782178218e-06,
1227
+ "loss": 1.0433,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.43316831683168316,
1232
+ "grad_norm": 0.1536027193069458,
1233
+ "learning_rate": 5.693069306930693e-06,
1234
+ "loss": 1.1101,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.43564356435643564,
1239
+ "grad_norm": 0.1521487981081009,
1240
+ "learning_rate": 5.668316831683169e-06,
1241
+ "loss": 1.0905,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.4381188118811881,
1246
+ "grad_norm": 0.21931779384613037,
1247
+ "learning_rate": 5.643564356435644e-06,
1248
+ "loss": 1.1008,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.4405940594059406,
1253
+ "grad_norm": 0.1681768000125885,
1254
+ "learning_rate": 5.61881188118812e-06,
1255
+ "loss": 1.0724,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.4430693069306931,
1260
+ "grad_norm": 0.16810664534568787,
1261
+ "learning_rate": 5.594059405940595e-06,
1262
+ "loss": 1.1137,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.44554455445544555,
1267
+ "grad_norm": 0.15952704846858978,
1268
+ "learning_rate": 5.56930693069307e-06,
1269
+ "loss": 1.0913,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.44801980198019803,
1274
+ "grad_norm": 0.25783032178878784,
1275
+ "learning_rate": 5.544554455445545e-06,
1276
+ "loss": 1.1057,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.4504950495049505,
1281
+ "grad_norm": 0.1551341712474823,
1282
+ "learning_rate": 5.519801980198021e-06,
1283
+ "loss": 1.0744,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.452970297029703,
1288
+ "grad_norm": 0.16667252779006958,
1289
+ "learning_rate": 5.495049504950496e-06,
1290
+ "loss": 1.066,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.45544554455445546,
1295
+ "grad_norm": 0.16125273704528809,
1296
+ "learning_rate": 5.470297029702971e-06,
1297
+ "loss": 1.1511,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.45792079207920794,
1302
+ "grad_norm": 0.16407977044582367,
1303
+ "learning_rate": 5.4455445544554465e-06,
1304
+ "loss": 1.0719,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.4603960396039604,
1309
+ "grad_norm": 0.17295385897159576,
1310
+ "learning_rate": 5.420792079207922e-06,
1311
+ "loss": 1.1174,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.4628712871287129,
1316
+ "grad_norm": 0.18729552626609802,
1317
+ "learning_rate": 5.396039603960397e-06,
1318
+ "loss": 1.0352,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.46534653465346537,
1323
+ "grad_norm": 0.1539359837770462,
1324
+ "learning_rate": 5.371287128712872e-06,
1325
+ "loss": 1.0807,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.46782178217821785,
1330
+ "grad_norm": 0.16208483278751373,
1331
+ "learning_rate": 5.346534653465347e-06,
1332
+ "loss": 1.08,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.47029702970297027,
1337
+ "grad_norm": 0.1604655236005783,
1338
+ "learning_rate": 5.321782178217822e-06,
1339
+ "loss": 1.0715,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.47277227722772275,
1344
+ "grad_norm": 0.20206867158412933,
1345
+ "learning_rate": 5.297029702970298e-06,
1346
+ "loss": 1.0588,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.4752475247524752,
1351
+ "grad_norm": 0.15372274816036224,
1352
+ "learning_rate": 5.272277227722773e-06,
1353
+ "loss": 1.0771,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.4777227722772277,
1358
+ "grad_norm": 0.15498343110084534,
1359
+ "learning_rate": 5.247524752475248e-06,
1360
+ "loss": 1.06,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.4801980198019802,
1365
+ "grad_norm": 0.15957452356815338,
1366
+ "learning_rate": 5.2227722772277234e-06,
1367
+ "loss": 1.0731,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.48267326732673266,
1372
+ "grad_norm": 0.1622665375471115,
1373
+ "learning_rate": 5.1980198019801986e-06,
1374
+ "loss": 1.0962,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.48514851485148514,
1379
+ "grad_norm": 0.1674077957868576,
1380
+ "learning_rate": 5.173267326732674e-06,
1381
+ "loss": 1.105,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.4876237623762376,
1386
+ "grad_norm": 0.169521763920784,
1387
+ "learning_rate": 5.148514851485149e-06,
1388
+ "loss": 1.0811,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.4900990099009901,
1393
+ "grad_norm": 0.1688235104084015,
1394
+ "learning_rate": 5.123762376237624e-06,
1395
+ "loss": 1.0708,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.49257425742574257,
1400
+ "grad_norm": 0.15499871969223022,
1401
+ "learning_rate": 5.0990099009901e-06,
1402
+ "loss": 1.0947,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.49504950495049505,
1407
+ "grad_norm": 0.15326109528541565,
1408
+ "learning_rate": 5.074257425742575e-06,
1409
+ "loss": 1.0676,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.4975247524752475,
1414
+ "grad_norm": 0.16365967690944672,
1415
+ "learning_rate": 5.04950495049505e-06,
1416
+ "loss": 1.0792,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.5,
1421
+ "grad_norm": 0.1605796068906784,
1422
+ "learning_rate": 5.024752475247525e-06,
1423
+ "loss": 1.0939,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.5024752475247525,
1428
+ "grad_norm": 0.16988039016723633,
1429
+ "learning_rate": 5e-06,
1430
+ "loss": 1.0996,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.504950495049505,
1435
+ "grad_norm": 0.16347338259220123,
1436
+ "learning_rate": 4.9752475247524755e-06,
1437
+ "loss": 1.0603,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 0.5074257425742574,
1442
+ "grad_norm": 0.16206030547618866,
1443
+ "learning_rate": 4.950495049504951e-06,
1444
+ "loss": 1.0675,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 0.5099009900990099,
1449
+ "grad_norm": 0.18767081201076508,
1450
+ "learning_rate": 4.925742574257426e-06,
1451
+ "loss": 1.0597,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 0.5123762376237624,
1456
+ "grad_norm": 0.1522037833929062,
1457
+ "learning_rate": 4.900990099009901e-06,
1458
+ "loss": 1.0673,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 0.5148514851485149,
1463
+ "grad_norm": 0.15843883156776428,
1464
+ "learning_rate": 4.876237623762377e-06,
1465
+ "loss": 1.0544,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 0.5173267326732673,
1470
+ "grad_norm": 0.1723291128873825,
1471
+ "learning_rate": 4.851485148514852e-06,
1472
+ "loss": 1.0837,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 0.5198019801980198,
1477
+ "grad_norm": 0.16350848972797394,
1478
+ "learning_rate": 4.826732673267327e-06,
1479
+ "loss": 1.0666,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 0.5222772277227723,
1484
+ "grad_norm": 0.15768328309059143,
1485
+ "learning_rate": 4.801980198019802e-06,
1486
+ "loss": 1.0723,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 0.5247524752475248,
1491
+ "grad_norm": 0.17364096641540527,
1492
+ "learning_rate": 4.777227722772277e-06,
1493
+ "loss": 1.0667,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 0.5272277227722773,
1498
+ "grad_norm": 0.16839410364627838,
1499
+ "learning_rate": 4.7524752475247525e-06,
1500
+ "loss": 1.0728,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 0.5297029702970297,
1505
+ "grad_norm": 0.16369131207466125,
1506
+ "learning_rate": 4.727722772277228e-06,
1507
+ "loss": 1.0732,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 0.5321782178217822,
1512
+ "grad_norm": 0.1695587933063507,
1513
+ "learning_rate": 4.702970297029703e-06,
1514
+ "loss": 1.0637,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 0.5346534653465347,
1519
+ "grad_norm": 0.16182969510555267,
1520
+ "learning_rate": 4.678217821782179e-06,
1521
+ "loss": 1.0429,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 0.5371287128712872,
1526
+ "grad_norm": 0.15863147377967834,
1527
+ "learning_rate": 4.653465346534654e-06,
1528
+ "loss": 1.0736,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 0.5396039603960396,
1533
+ "grad_norm": 0.15679685771465302,
1534
+ "learning_rate": 4.628712871287129e-06,
1535
+ "loss": 1.0781,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 0.5420792079207921,
1540
+ "grad_norm": 0.16381986439228058,
1541
+ "learning_rate": 4.603960396039605e-06,
1542
+ "loss": 1.063,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 0.5445544554455446,
1547
+ "grad_norm": 0.1749560832977295,
1548
+ "learning_rate": 4.57920792079208e-06,
1549
+ "loss": 1.0588,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 0.5470297029702971,
1554
+ "grad_norm": 0.19300749897956848,
1555
+ "learning_rate": 4.554455445544555e-06,
1556
+ "loss": 1.1099,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 0.5495049504950495,
1561
+ "grad_norm": 0.16599427163600922,
1562
+ "learning_rate": 4.52970297029703e-06,
1563
+ "loss": 1.0517,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 0.551980198019802,
1568
+ "grad_norm": 0.1542525589466095,
1569
+ "learning_rate": 4.5049504950495054e-06,
1570
+ "loss": 1.0474,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 0.5544554455445545,
1575
+ "grad_norm": 0.15763726830482483,
1576
+ "learning_rate": 4.4801980198019806e-06,
1577
+ "loss": 0.9993,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 0.556930693069307,
1582
+ "grad_norm": 0.1836528331041336,
1583
+ "learning_rate": 4.455445544554456e-06,
1584
+ "loss": 1.1125,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 0.5594059405940595,
1589
+ "grad_norm": 0.16592352092266083,
1590
+ "learning_rate": 4.430693069306931e-06,
1591
+ "loss": 1.0154,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 0.5618811881188119,
1596
+ "grad_norm": 0.16697534918785095,
1597
+ "learning_rate": 4.405940594059406e-06,
1598
+ "loss": 1.0328,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 0.5643564356435643,
1603
+ "grad_norm": 0.16123178601264954,
1604
+ "learning_rate": 4.381188118811882e-06,
1605
+ "loss": 1.0859,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 0.5668316831683168,
1610
+ "grad_norm": 0.17404749989509583,
1611
+ "learning_rate": 4.356435643564357e-06,
1612
+ "loss": 1.0121,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 0.5693069306930693,
1617
+ "grad_norm": 0.17720270156860352,
1618
+ "learning_rate": 4.331683168316832e-06,
1619
+ "loss": 1.0757,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 0.5717821782178217,
1624
+ "grad_norm": 0.1586427241563797,
1625
+ "learning_rate": 4.306930693069307e-06,
1626
+ "loss": 1.0551,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 0.5742574257425742,
1631
+ "grad_norm": 0.1774415373802185,
1632
+ "learning_rate": 4.282178217821782e-06,
1633
+ "loss": 1.0333,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 0.5767326732673267,
1638
+ "grad_norm": 0.16705653071403503,
1639
+ "learning_rate": 4.2574257425742575e-06,
1640
+ "loss": 1.0601,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 0.5792079207920792,
1645
+ "grad_norm": 0.18242689967155457,
1646
+ "learning_rate": 4.232673267326733e-06,
1647
+ "loss": 1.0476,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 0.5816831683168316,
1652
+ "grad_norm": 0.17149695754051208,
1653
+ "learning_rate": 4.207920792079208e-06,
1654
+ "loss": 1.0589,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 0.5841584158415841,
1659
+ "grad_norm": 0.1735452264547348,
1660
+ "learning_rate": 4.183168316831684e-06,
1661
+ "loss": 1.0479,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 0.5866336633663366,
1666
+ "grad_norm": 0.1712096780538559,
1667
+ "learning_rate": 4.158415841584159e-06,
1668
+ "loss": 1.0727,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 0.5891089108910891,
1673
+ "grad_norm": 0.1779618263244629,
1674
+ "learning_rate": 4.133663366336634e-06,
1675
+ "loss": 1.0847,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 0.5915841584158416,
1680
+ "grad_norm": 0.165634423494339,
1681
+ "learning_rate": 4.108910891089109e-06,
1682
+ "loss": 1.0318,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 0.594059405940594,
1687
+ "grad_norm": 0.17693260312080383,
1688
+ "learning_rate": 4.084158415841584e-06,
1689
+ "loss": 1.0602,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 0.5965346534653465,
1694
+ "grad_norm": 0.16443394124507904,
1695
+ "learning_rate": 4.05940594059406e-06,
1696
+ "loss": 1.0693,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 0.599009900990099,
1701
+ "grad_norm": 0.1829027682542801,
1702
+ "learning_rate": 4.034653465346535e-06,
1703
+ "loss": 1.0597,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 0.6014851485148515,
1708
+ "grad_norm": 0.17347212135791779,
1709
+ "learning_rate": 4.0099009900990104e-06,
1710
+ "loss": 1.0901,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 0.6039603960396039,
1715
+ "grad_norm": 0.1738901287317276,
1716
+ "learning_rate": 3.9851485148514856e-06,
1717
+ "loss": 1.0378,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 0.6064356435643564,
1722
+ "grad_norm": 0.17123974859714508,
1723
+ "learning_rate": 3.960396039603961e-06,
1724
+ "loss": 1.0449,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 0.6089108910891089,
1729
+ "grad_norm": 0.16725413501262665,
1730
+ "learning_rate": 3.935643564356436e-06,
1731
+ "loss": 1.07,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 0.6113861386138614,
1736
+ "grad_norm": 0.16899654269218445,
1737
+ "learning_rate": 3.910891089108911e-06,
1738
+ "loss": 1.0491,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 0.6138613861386139,
1743
+ "grad_norm": 0.16935132443904877,
1744
+ "learning_rate": 3.886138613861387e-06,
1745
+ "loss": 1.0099,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 0.6163366336633663,
1750
+ "grad_norm": 0.1622443050146103,
1751
+ "learning_rate": 3.861386138613862e-06,
1752
+ "loss": 1.0529,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 0.6188118811881188,
1757
+ "grad_norm": 0.16781330108642578,
1758
+ "learning_rate": 3.836633663366337e-06,
1759
+ "loss": 1.0629,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 0.6212871287128713,
1764
+ "grad_norm": 0.17032338678836823,
1765
+ "learning_rate": 3.8118811881188123e-06,
1766
+ "loss": 1.0624,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 0.6237623762376238,
1771
+ "grad_norm": 0.17583905160427094,
1772
+ "learning_rate": 3.7871287128712874e-06,
1773
+ "loss": 1.0191,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 0.6262376237623762,
1778
+ "grad_norm": 0.1608443707227707,
1779
+ "learning_rate": 3.7623762376237625e-06,
1780
+ "loss": 1.0459,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 0.6287128712871287,
1785
+ "grad_norm": 0.16449084877967834,
1786
+ "learning_rate": 3.737623762376238e-06,
1787
+ "loss": 1.0341,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 0.6311881188118812,
1792
+ "grad_norm": 0.17335855960845947,
1793
+ "learning_rate": 3.712871287128713e-06,
1794
+ "loss": 1.0492,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 0.6336633663366337,
1799
+ "grad_norm": 0.17544226348400116,
1800
+ "learning_rate": 3.6881188118811883e-06,
1801
+ "loss": 1.0682,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 0.6361386138613861,
1806
+ "grad_norm": 0.16722352802753448,
1807
+ "learning_rate": 3.6633663366336635e-06,
1808
+ "loss": 1.0557,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 0.6386138613861386,
1813
+ "grad_norm": 0.19356003403663635,
1814
+ "learning_rate": 3.638613861386139e-06,
1815
+ "loss": 1.06,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 0.6410891089108911,
1820
+ "grad_norm": 0.18645772337913513,
1821
+ "learning_rate": 3.613861386138614e-06,
1822
+ "loss": 1.0467,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 0.6435643564356436,
1827
+ "grad_norm": 0.18059493601322174,
1828
+ "learning_rate": 3.5891089108910892e-06,
1829
+ "loss": 1.0736,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 0.6460396039603961,
1834
+ "grad_norm": 0.19914749264717102,
1835
+ "learning_rate": 3.5643564356435644e-06,
1836
+ "loss": 1.0792,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 0.6485148514851485,
1841
+ "grad_norm": 0.16404379904270172,
1842
+ "learning_rate": 3.5396039603960395e-06,
1843
+ "loss": 1.0253,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 0.650990099009901,
1848
+ "grad_norm": 0.16826879978179932,
1849
+ "learning_rate": 3.514851485148515e-06,
1850
+ "loss": 1.0458,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 0.6534653465346535,
1855
+ "grad_norm": 0.17538203299045563,
1856
+ "learning_rate": 3.49009900990099e-06,
1857
+ "loss": 1.0224,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 0.655940594059406,
1862
+ "grad_norm": 0.18196958303451538,
1863
+ "learning_rate": 3.4653465346534653e-06,
1864
+ "loss": 1.0475,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 0.6584158415841584,
1869
+ "grad_norm": 0.1760399043560028,
1870
+ "learning_rate": 3.4405940594059404e-06,
1871
+ "loss": 1.045,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 0.6608910891089109,
1876
+ "grad_norm": 0.17527367174625397,
1877
+ "learning_rate": 3.4158415841584164e-06,
1878
+ "loss": 1.0634,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 0.6633663366336634,
1883
+ "grad_norm": 0.18751391768455505,
1884
+ "learning_rate": 3.3910891089108915e-06,
1885
+ "loss": 1.0073,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 0.6658415841584159,
1890
+ "grad_norm": 0.16496875882148743,
1891
+ "learning_rate": 3.3663366336633666e-06,
1892
+ "loss": 1.0435,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 0.6683168316831684,
1897
+ "grad_norm": 0.16843590140342712,
1898
+ "learning_rate": 3.341584158415842e-06,
1899
+ "loss": 1.035,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 0.6707920792079208,
1904
+ "grad_norm": 0.19264374673366547,
1905
+ "learning_rate": 3.3168316831683173e-06,
1906
+ "loss": 1.0538,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 0.6732673267326733,
1911
+ "grad_norm": 0.19670583307743073,
1912
+ "learning_rate": 3.2920792079207924e-06,
1913
+ "loss": 1.041,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 0.6757425742574258,
1918
+ "grad_norm": 0.1634487509727478,
1919
+ "learning_rate": 3.2673267326732676e-06,
1920
+ "loss": 1.0131,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 0.6782178217821783,
1925
+ "grad_norm": 0.1698472797870636,
1926
+ "learning_rate": 3.242574257425743e-06,
1927
+ "loss": 1.0293,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 0.6806930693069307,
1932
+ "grad_norm": 0.16460570693016052,
1933
+ "learning_rate": 3.2178217821782182e-06,
1934
+ "loss": 1.0078,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 0.6831683168316832,
1939
+ "grad_norm": 0.17161054909229279,
1940
+ "learning_rate": 3.1930693069306933e-06,
1941
+ "loss": 1.0465,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 0.6856435643564357,
1946
+ "grad_norm": 0.1728292554616928,
1947
+ "learning_rate": 3.1683168316831685e-06,
1948
+ "loss": 1.0593,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 0.6881188118811881,
1953
+ "grad_norm": 0.16688892245292664,
1954
+ "learning_rate": 3.143564356435644e-06,
1955
+ "loss": 1.0343,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 0.6905940594059405,
1960
+ "grad_norm": 0.17009975016117096,
1961
+ "learning_rate": 3.118811881188119e-06,
1962
+ "loss": 1.0686,
1963
+ "step": 279
1964
+ },
1965
+ {
1966
+ "epoch": 0.693069306930693,
1967
+ "grad_norm": 0.16594161093235016,
1968
+ "learning_rate": 3.0940594059405943e-06,
1969
+ "loss": 1.0239,
1970
+ "step": 280
1971
+ },
1972
+ {
1973
+ "epoch": 0.6955445544554455,
1974
+ "grad_norm": 0.17890632152557373,
1975
+ "learning_rate": 3.0693069306930694e-06,
1976
+ "loss": 1.079,
1977
+ "step": 281
1978
+ },
1979
+ {
1980
+ "epoch": 0.698019801980198,
1981
+ "grad_norm": 0.16677552461624146,
1982
+ "learning_rate": 3.044554455445545e-06,
1983
+ "loss": 0.999,
1984
+ "step": 282
1985
+ },
1986
+ {
1987
+ "epoch": 0.7004950495049505,
1988
+ "grad_norm": 0.20281478762626648,
1989
+ "learning_rate": 3.01980198019802e-06,
1990
+ "loss": 1.0477,
1991
+ "step": 283
1992
+ },
1993
+ {
1994
+ "epoch": 0.7029702970297029,
1995
+ "grad_norm": 0.1814507395029068,
1996
+ "learning_rate": 2.995049504950495e-06,
1997
+ "loss": 1.0537,
1998
+ "step": 284
1999
+ },
2000
+ {
2001
+ "epoch": 0.7054455445544554,
2002
+ "grad_norm": 0.2223450392484665,
2003
+ "learning_rate": 2.9702970297029703e-06,
2004
+ "loss": 1.0815,
2005
+ "step": 285
2006
+ },
2007
+ {
2008
+ "epoch": 0.7079207920792079,
2009
+ "grad_norm": 0.17586183547973633,
2010
+ "learning_rate": 2.9455445544554454e-06,
2011
+ "loss": 1.0277,
2012
+ "step": 286
2013
+ },
2014
+ {
2015
+ "epoch": 0.7103960396039604,
2016
+ "grad_norm": 0.17505447566509247,
2017
+ "learning_rate": 2.920792079207921e-06,
2018
+ "loss": 1.0055,
2019
+ "step": 287
2020
+ },
2021
+ {
2022
+ "epoch": 0.7128712871287128,
2023
+ "grad_norm": 0.17361949384212494,
2024
+ "learning_rate": 2.896039603960396e-06,
2025
+ "loss": 1.0465,
2026
+ "step": 288
2027
+ },
2028
+ {
2029
+ "epoch": 0.7153465346534653,
2030
+ "grad_norm": 0.1845312863588333,
2031
+ "learning_rate": 2.8712871287128712e-06,
2032
+ "loss": 1.0676,
2033
+ "step": 289
2034
+ },
2035
+ {
2036
+ "epoch": 0.7178217821782178,
2037
+ "grad_norm": 0.1974944770336151,
2038
+ "learning_rate": 2.8465346534653464e-06,
2039
+ "loss": 1.0766,
2040
+ "step": 290
2041
+ },
2042
+ {
2043
+ "epoch": 0.7202970297029703,
2044
+ "grad_norm": 0.17243847250938416,
2045
+ "learning_rate": 2.821782178217822e-06,
2046
+ "loss": 1.0387,
2047
+ "step": 291
2048
+ },
2049
+ {
2050
+ "epoch": 0.7227722772277227,
2051
+ "grad_norm": 0.18797056376934052,
2052
+ "learning_rate": 2.7970297029702974e-06,
2053
+ "loss": 1.048,
2054
+ "step": 292
2055
+ },
2056
+ {
2057
+ "epoch": 0.7252475247524752,
2058
+ "grad_norm": 0.1894993633031845,
2059
+ "learning_rate": 2.7722772277227726e-06,
2060
+ "loss": 1.0352,
2061
+ "step": 293
2062
+ },
2063
+ {
2064
+ "epoch": 0.7277227722772277,
2065
+ "grad_norm": 0.16774602234363556,
2066
+ "learning_rate": 2.747524752475248e-06,
2067
+ "loss": 1.052,
2068
+ "step": 294
2069
+ },
2070
+ {
2071
+ "epoch": 0.7301980198019802,
2072
+ "grad_norm": 0.17973656952381134,
2073
+ "learning_rate": 2.7227722772277232e-06,
2074
+ "loss": 1.0066,
2075
+ "step": 295
2076
+ },
2077
+ {
2078
+ "epoch": 0.7326732673267327,
2079
+ "grad_norm": 0.17266245186328888,
2080
+ "learning_rate": 2.6980198019801984e-06,
2081
+ "loss": 1.0327,
2082
+ "step": 296
2083
+ },
2084
+ {
2085
+ "epoch": 0.7351485148514851,
2086
+ "grad_norm": 0.19428043067455292,
2087
+ "learning_rate": 2.6732673267326735e-06,
2088
+ "loss": 1.0479,
2089
+ "step": 297
2090
+ },
2091
+ {
2092
+ "epoch": 0.7376237623762376,
2093
+ "grad_norm": 0.16848322749137878,
2094
+ "learning_rate": 2.648514851485149e-06,
2095
+ "loss": 1.0665,
2096
+ "step": 298
2097
+ },
2098
+ {
2099
+ "epoch": 0.7400990099009901,
2100
+ "grad_norm": 0.1717626452445984,
2101
+ "learning_rate": 2.623762376237624e-06,
2102
+ "loss": 1.042,
2103
+ "step": 299
2104
+ },
2105
+ {
2106
+ "epoch": 0.7425742574257426,
2107
+ "grad_norm": 0.16830983757972717,
2108
+ "learning_rate": 2.5990099009900993e-06,
2109
+ "loss": 1.0313,
2110
+ "step": 300
2111
+ },
2112
+ {
2113
+ "epoch": 0.745049504950495,
2114
+ "grad_norm": 0.1700887829065323,
2115
+ "learning_rate": 2.5742574257425744e-06,
2116
+ "loss": 1.0512,
2117
+ "step": 301
2118
+ },
2119
+ {
2120
+ "epoch": 0.7475247524752475,
2121
+ "grad_norm": 0.17589855194091797,
2122
+ "learning_rate": 2.54950495049505e-06,
2123
+ "loss": 1.0411,
2124
+ "step": 302
2125
+ },
2126
+ {
2127
+ "epoch": 0.75,
2128
+ "grad_norm": 0.20275838673114777,
2129
+ "learning_rate": 2.524752475247525e-06,
2130
+ "loss": 1.0412,
2131
+ "step": 303
2132
+ },
2133
+ {
2134
+ "epoch": 0.7524752475247525,
2135
+ "grad_norm": 0.17624107003211975,
2136
+ "learning_rate": 2.5e-06,
2137
+ "loss": 1.0484,
2138
+ "step": 304
2139
+ },
2140
+ {
2141
+ "epoch": 0.754950495049505,
2142
+ "grad_norm": 0.16618701815605164,
2143
+ "learning_rate": 2.4752475247524753e-06,
2144
+ "loss": 1.0444,
2145
+ "step": 305
2146
+ },
2147
+ {
2148
+ "epoch": 0.7574257425742574,
2149
+ "grad_norm": 0.17324908077716827,
2150
+ "learning_rate": 2.4504950495049505e-06,
2151
+ "loss": 1.0126,
2152
+ "step": 306
2153
+ },
2154
+ {
2155
+ "epoch": 0.7599009900990099,
2156
+ "grad_norm": 0.1791515350341797,
2157
+ "learning_rate": 2.425742574257426e-06,
2158
+ "loss": 1.0513,
2159
+ "step": 307
2160
+ },
2161
+ {
2162
+ "epoch": 0.7623762376237624,
2163
+ "grad_norm": 0.16968585550785065,
2164
+ "learning_rate": 2.400990099009901e-06,
2165
+ "loss": 1.0458,
2166
+ "step": 308
2167
+ },
2168
+ {
2169
+ "epoch": 0.7648514851485149,
2170
+ "grad_norm": 0.19068896770477295,
2171
+ "learning_rate": 2.3762376237623762e-06,
2172
+ "loss": 1.0307,
2173
+ "step": 309
2174
+ },
2175
+ {
2176
+ "epoch": 0.7673267326732673,
2177
+ "grad_norm": 0.1762915998697281,
2178
+ "learning_rate": 2.3514851485148514e-06,
2179
+ "loss": 1.0266,
2180
+ "step": 310
2181
+ },
2182
+ {
2183
+ "epoch": 0.7698019801980198,
2184
+ "grad_norm": 0.16937871277332306,
2185
+ "learning_rate": 2.326732673267327e-06,
2186
+ "loss": 1.0397,
2187
+ "step": 311
2188
+ },
2189
+ {
2190
+ "epoch": 0.7722772277227723,
2191
+ "grad_norm": 0.17128786444664001,
2192
+ "learning_rate": 2.3019801980198025e-06,
2193
+ "loss": 1.0479,
2194
+ "step": 312
2195
+ },
2196
+ {
2197
+ "epoch": 0.7747524752475248,
2198
+ "grad_norm": 0.17716889083385468,
2199
+ "learning_rate": 2.2772277227722776e-06,
2200
+ "loss": 0.9953,
2201
+ "step": 313
2202
+ },
2203
+ {
2204
+ "epoch": 0.7772277227722773,
2205
+ "grad_norm": 0.18644240498542786,
2206
+ "learning_rate": 2.2524752475247527e-06,
2207
+ "loss": 1.0266,
2208
+ "step": 314
2209
+ },
2210
+ {
2211
+ "epoch": 0.7797029702970297,
2212
+ "grad_norm": 0.18382704257965088,
2213
+ "learning_rate": 2.227722772277228e-06,
2214
+ "loss": 1.0472,
2215
+ "step": 315
2216
+ },
2217
+ {
2218
+ "epoch": 0.7821782178217822,
2219
+ "grad_norm": 0.17966952919960022,
2220
+ "learning_rate": 2.202970297029703e-06,
2221
+ "loss": 1.03,
2222
+ "step": 316
2223
+ },
2224
+ {
2225
+ "epoch": 0.7846534653465347,
2226
+ "grad_norm": 0.17476266622543335,
2227
+ "learning_rate": 2.1782178217821785e-06,
2228
+ "loss": 1.0197,
2229
+ "step": 317
2230
+ },
2231
+ {
2232
+ "epoch": 0.7871287128712872,
2233
+ "grad_norm": 0.16993242502212524,
2234
+ "learning_rate": 2.1534653465346536e-06,
2235
+ "loss": 1.0365,
2236
+ "step": 318
2237
+ },
2238
+ {
2239
+ "epoch": 0.7896039603960396,
2240
+ "grad_norm": 0.17047357559204102,
2241
+ "learning_rate": 2.1287128712871288e-06,
2242
+ "loss": 1.0412,
2243
+ "step": 319
2244
+ },
2245
+ {
2246
+ "epoch": 0.7920792079207921,
2247
+ "grad_norm": 0.16769839823246002,
2248
+ "learning_rate": 2.103960396039604e-06,
2249
+ "loss": 1.0082,
2250
+ "step": 320
2251
+ },
2252
+ {
2253
+ "epoch": 0.7945544554455446,
2254
+ "grad_norm": 0.17701376974582672,
2255
+ "learning_rate": 2.0792079207920794e-06,
2256
+ "loss": 1.0574,
2257
+ "step": 321
2258
+ },
2259
+ {
2260
+ "epoch": 0.7970297029702971,
2261
+ "grad_norm": 0.1958608329296112,
2262
+ "learning_rate": 2.0544554455445546e-06,
2263
+ "loss": 1.0122,
2264
+ "step": 322
2265
+ },
2266
+ {
2267
+ "epoch": 0.7995049504950495,
2268
+ "grad_norm": 0.19034409523010254,
2269
+ "learning_rate": 2.02970297029703e-06,
2270
+ "loss": 0.9904,
2271
+ "step": 323
2272
+ },
2273
+ {
2274
+ "epoch": 0.801980198019802,
2275
+ "grad_norm": 0.17253142595291138,
2276
+ "learning_rate": 2.0049504950495052e-06,
2277
+ "loss": 1.0229,
2278
+ "step": 324
2279
+ },
2280
+ {
2281
+ "epoch": 0.8044554455445545,
2282
+ "grad_norm": 0.1845494955778122,
2283
+ "learning_rate": 1.9801980198019803e-06,
2284
+ "loss": 1.0537,
2285
+ "step": 325
2286
+ },
2287
+ {
2288
+ "epoch": 0.806930693069307,
2289
+ "grad_norm": 0.17464852333068848,
2290
+ "learning_rate": 1.9554455445544555e-06,
2291
+ "loss": 1.0293,
2292
+ "step": 326
2293
+ },
2294
+ {
2295
+ "epoch": 0.8094059405940595,
2296
+ "grad_norm": 0.18944846093654633,
2297
+ "learning_rate": 1.930693069306931e-06,
2298
+ "loss": 1.0342,
2299
+ "step": 327
2300
+ },
2301
+ {
2302
+ "epoch": 0.8118811881188119,
2303
+ "grad_norm": 0.20734351873397827,
2304
+ "learning_rate": 1.9059405940594061e-06,
2305
+ "loss": 1.0481,
2306
+ "step": 328
2307
+ },
2308
+ {
2309
+ "epoch": 0.8143564356435643,
2310
+ "grad_norm": 0.18267051875591278,
2311
+ "learning_rate": 1.8811881188118813e-06,
2312
+ "loss": 1.017,
2313
+ "step": 329
2314
+ },
2315
+ {
2316
+ "epoch": 0.8168316831683168,
2317
+ "grad_norm": 0.16905878484249115,
2318
+ "learning_rate": 1.8564356435643566e-06,
2319
+ "loss": 0.9996,
2320
+ "step": 330
2321
+ },
2322
+ {
2323
+ "epoch": 0.8193069306930693,
2324
+ "grad_norm": 0.18889805674552917,
2325
+ "learning_rate": 1.8316831683168317e-06,
2326
+ "loss": 1.0487,
2327
+ "step": 331
2328
+ },
2329
+ {
2330
+ "epoch": 0.8217821782178217,
2331
+ "grad_norm": 0.1784394234418869,
2332
+ "learning_rate": 1.806930693069307e-06,
2333
+ "loss": 1.0301,
2334
+ "step": 332
2335
+ },
2336
+ {
2337
+ "epoch": 0.8242574257425742,
2338
+ "grad_norm": 0.1732165515422821,
2339
+ "learning_rate": 1.7821782178217822e-06,
2340
+ "loss": 0.9989,
2341
+ "step": 333
2342
+ },
2343
+ {
2344
+ "epoch": 0.8267326732673267,
2345
+ "grad_norm": 0.19555354118347168,
2346
+ "learning_rate": 1.7574257425742575e-06,
2347
+ "loss": 1.0195,
2348
+ "step": 334
2349
+ },
2350
+ {
2351
+ "epoch": 0.8292079207920792,
2352
+ "grad_norm": 0.17240861058235168,
2353
+ "learning_rate": 1.7326732673267326e-06,
2354
+ "loss": 1.0076,
2355
+ "step": 335
2356
+ },
2357
+ {
2358
+ "epoch": 0.8316831683168316,
2359
+ "grad_norm": 0.1675492227077484,
2360
+ "learning_rate": 1.7079207920792082e-06,
2361
+ "loss": 1.0393,
2362
+ "step": 336
2363
+ },
2364
+ {
2365
+ "epoch": 0.8341584158415841,
2366
+ "grad_norm": 0.19649028778076172,
2367
+ "learning_rate": 1.6831683168316833e-06,
2368
+ "loss": 1.0467,
2369
+ "step": 337
2370
+ },
2371
+ {
2372
+ "epoch": 0.8366336633663366,
2373
+ "grad_norm": 0.1702542006969452,
2374
+ "learning_rate": 1.6584158415841587e-06,
2375
+ "loss": 1.0208,
2376
+ "step": 338
2377
+ },
2378
+ {
2379
+ "epoch": 0.8391089108910891,
2380
+ "grad_norm": 0.16906598210334778,
2381
+ "learning_rate": 1.6336633663366338e-06,
2382
+ "loss": 1.0268,
2383
+ "step": 339
2384
+ },
2385
+ {
2386
+ "epoch": 0.8415841584158416,
2387
+ "grad_norm": 0.18987883627414703,
2388
+ "learning_rate": 1.6089108910891091e-06,
2389
+ "loss": 1.0566,
2390
+ "step": 340
2391
+ },
2392
+ {
2393
+ "epoch": 0.844059405940594,
2394
+ "grad_norm": 0.1939912885427475,
2395
+ "learning_rate": 1.5841584158415842e-06,
2396
+ "loss": 1.0871,
2397
+ "step": 341
2398
+ },
2399
+ {
2400
+ "epoch": 0.8465346534653465,
2401
+ "grad_norm": 0.18526384234428406,
2402
+ "learning_rate": 1.5594059405940596e-06,
2403
+ "loss": 1.0179,
2404
+ "step": 342
2405
+ },
2406
+ {
2407
+ "epoch": 0.849009900990099,
2408
+ "grad_norm": 0.17309053242206573,
2409
+ "learning_rate": 1.5346534653465347e-06,
2410
+ "loss": 1.0509,
2411
+ "step": 343
2412
+ },
2413
+ {
2414
+ "epoch": 0.8514851485148515,
2415
+ "grad_norm": 0.16723985970020294,
2416
+ "learning_rate": 1.50990099009901e-06,
2417
+ "loss": 1.0034,
2418
+ "step": 344
2419
+ },
2420
+ {
2421
+ "epoch": 0.8539603960396039,
2422
+ "grad_norm": 0.17107772827148438,
2423
+ "learning_rate": 1.4851485148514852e-06,
2424
+ "loss": 0.9677,
2425
+ "step": 345
2426
+ },
2427
+ {
2428
+ "epoch": 0.8564356435643564,
2429
+ "grad_norm": 0.17373721301555634,
2430
+ "learning_rate": 1.4603960396039605e-06,
2431
+ "loss": 1.0245,
2432
+ "step": 346
2433
+ },
2434
+ {
2435
+ "epoch": 0.8589108910891089,
2436
+ "grad_norm": 0.1878427267074585,
2437
+ "learning_rate": 1.4356435643564356e-06,
2438
+ "loss": 1.023,
2439
+ "step": 347
2440
+ },
2441
+ {
2442
+ "epoch": 0.8613861386138614,
2443
+ "grad_norm": 0.17384839057922363,
2444
+ "learning_rate": 1.410891089108911e-06,
2445
+ "loss": 1.0414,
2446
+ "step": 348
2447
+ },
2448
+ {
2449
+ "epoch": 0.8638613861386139,
2450
+ "grad_norm": 0.17436939477920532,
2451
+ "learning_rate": 1.3861386138613863e-06,
2452
+ "loss": 1.0371,
2453
+ "step": 349
2454
+ },
2455
+ {
2456
+ "epoch": 0.8663366336633663,
2457
+ "grad_norm": 0.18823057413101196,
2458
+ "learning_rate": 1.3613861386138616e-06,
2459
+ "loss": 1.0286,
2460
+ "step": 350
2461
+ },
2462
+ {
2463
+ "epoch": 0.8688118811881188,
2464
+ "grad_norm": 0.17299430072307587,
2465
+ "learning_rate": 1.3366336633663367e-06,
2466
+ "loss": 1.0117,
2467
+ "step": 351
2468
+ },
2469
+ {
2470
+ "epoch": 0.8712871287128713,
2471
+ "grad_norm": 0.2107045203447342,
2472
+ "learning_rate": 1.311881188118812e-06,
2473
+ "loss": 1.0331,
2474
+ "step": 352
2475
+ },
2476
+ {
2477
+ "epoch": 0.8737623762376238,
2478
+ "grad_norm": 0.17237113416194916,
2479
+ "learning_rate": 1.2871287128712872e-06,
2480
+ "loss": 1.0022,
2481
+ "step": 353
2482
+ },
2483
+ {
2484
+ "epoch": 0.8762376237623762,
2485
+ "grad_norm": 0.17842179536819458,
2486
+ "learning_rate": 1.2623762376237625e-06,
2487
+ "loss": 1.0496,
2488
+ "step": 354
2489
+ },
2490
+ {
2491
+ "epoch": 0.8787128712871287,
2492
+ "grad_norm": 0.17555266618728638,
2493
+ "learning_rate": 1.2376237623762377e-06,
2494
+ "loss": 1.0082,
2495
+ "step": 355
2496
+ },
2497
+ {
2498
+ "epoch": 0.8811881188118812,
2499
+ "grad_norm": 0.22252587974071503,
2500
+ "learning_rate": 1.212871287128713e-06,
2501
+ "loss": 1.0386,
2502
+ "step": 356
2503
+ },
2504
+ {
2505
+ "epoch": 0.8836633663366337,
2506
+ "grad_norm": 0.1819303333759308,
2507
+ "learning_rate": 1.1881188118811881e-06,
2508
+ "loss": 1.0468,
2509
+ "step": 357
2510
+ },
2511
+ {
2512
+ "epoch": 0.8861386138613861,
2513
+ "grad_norm": 0.18028509616851807,
2514
+ "learning_rate": 1.1633663366336635e-06,
2515
+ "loss": 0.972,
2516
+ "step": 358
2517
+ },
2518
+ {
2519
+ "epoch": 0.8886138613861386,
2520
+ "grad_norm": 0.1826130598783493,
2521
+ "learning_rate": 1.1386138613861388e-06,
2522
+ "loss": 1.0503,
2523
+ "step": 359
2524
+ },
2525
+ {
2526
+ "epoch": 0.8910891089108911,
2527
+ "grad_norm": 0.17441998422145844,
2528
+ "learning_rate": 1.113861386138614e-06,
2529
+ "loss": 1.0267,
2530
+ "step": 360
2531
+ },
2532
+ {
2533
+ "epoch": 0.8935643564356436,
2534
+ "grad_norm": 0.20245307683944702,
2535
+ "learning_rate": 1.0891089108910893e-06,
2536
+ "loss": 1.0261,
2537
+ "step": 361
2538
+ },
2539
+ {
2540
+ "epoch": 0.8960396039603961,
2541
+ "grad_norm": 0.170221745967865,
2542
+ "learning_rate": 1.0643564356435644e-06,
2543
+ "loss": 1.0217,
2544
+ "step": 362
2545
+ },
2546
+ {
2547
+ "epoch": 0.8985148514851485,
2548
+ "grad_norm": 0.1835111379623413,
2549
+ "learning_rate": 1.0396039603960397e-06,
2550
+ "loss": 1.0677,
2551
+ "step": 363
2552
+ },
2553
+ {
2554
+ "epoch": 0.900990099009901,
2555
+ "grad_norm": 0.17305181920528412,
2556
+ "learning_rate": 1.014851485148515e-06,
2557
+ "loss": 1.0372,
2558
+ "step": 364
2559
+ },
2560
+ {
2561
+ "epoch": 0.9034653465346535,
2562
+ "grad_norm": 0.17221209406852722,
2563
+ "learning_rate": 9.900990099009902e-07,
2564
+ "loss": 1.0351,
2565
+ "step": 365
2566
+ },
2567
+ {
2568
+ "epoch": 0.905940594059406,
2569
+ "grad_norm": 0.2017694115638733,
2570
+ "learning_rate": 9.653465346534655e-07,
2571
+ "loss": 1.0641,
2572
+ "step": 366
2573
+ },
2574
+ {
2575
+ "epoch": 0.9084158415841584,
2576
+ "grad_norm": 0.16452528536319733,
2577
+ "learning_rate": 9.405940594059406e-07,
2578
+ "loss": 1.0297,
2579
+ "step": 367
2580
+ },
2581
+ {
2582
+ "epoch": 0.9108910891089109,
2583
+ "grad_norm": 0.1696237474679947,
2584
+ "learning_rate": 9.158415841584159e-07,
2585
+ "loss": 1.0272,
2586
+ "step": 368
2587
+ },
2588
+ {
2589
+ "epoch": 0.9133663366336634,
2590
+ "grad_norm": 0.17816710472106934,
2591
+ "learning_rate": 8.910891089108911e-07,
2592
+ "loss": 0.9946,
2593
+ "step": 369
2594
+ },
2595
+ {
2596
+ "epoch": 0.9158415841584159,
2597
+ "grad_norm": 0.22065281867980957,
2598
+ "learning_rate": 8.663366336633663e-07,
2599
+ "loss": 1.0485,
2600
+ "step": 370
2601
+ },
2602
+ {
2603
+ "epoch": 0.9183168316831684,
2604
+ "grad_norm": 0.1876746118068695,
2605
+ "learning_rate": 8.415841584158417e-07,
2606
+ "loss": 1.0179,
2607
+ "step": 371
2608
+ },
2609
+ {
2610
+ "epoch": 0.9207920792079208,
2611
+ "grad_norm": 0.28578758239746094,
2612
+ "learning_rate": 8.168316831683169e-07,
2613
+ "loss": 1.0024,
2614
+ "step": 372
2615
+ },
2616
+ {
2617
+ "epoch": 0.9232673267326733,
2618
+ "grad_norm": 0.2457706332206726,
2619
+ "learning_rate": 7.920792079207921e-07,
2620
+ "loss": 0.9973,
2621
+ "step": 373
2622
+ },
2623
+ {
2624
+ "epoch": 0.9257425742574258,
2625
+ "grad_norm": 0.17008252441883087,
2626
+ "learning_rate": 7.673267326732673e-07,
2627
+ "loss": 0.9994,
2628
+ "step": 374
2629
+ },
2630
+ {
2631
+ "epoch": 0.9282178217821783,
2632
+ "grad_norm": 0.1781049519777298,
2633
+ "learning_rate": 7.425742574257426e-07,
2634
+ "loss": 1.061,
2635
+ "step": 375
2636
+ },
2637
+ {
2638
+ "epoch": 0.9306930693069307,
2639
+ "grad_norm": 0.18529166281223297,
2640
+ "learning_rate": 7.178217821782178e-07,
2641
+ "loss": 1.0428,
2642
+ "step": 376
2643
+ },
2644
+ {
2645
+ "epoch": 0.9331683168316832,
2646
+ "grad_norm": 0.19657132029533386,
2647
+ "learning_rate": 6.930693069306931e-07,
2648
+ "loss": 1.0448,
2649
+ "step": 377
2650
+ },
2651
+ {
2652
+ "epoch": 0.9356435643564357,
2653
+ "grad_norm": 0.17185792326927185,
2654
+ "learning_rate": 6.683168316831684e-07,
2655
+ "loss": 1.0306,
2656
+ "step": 378
2657
+ },
2658
+ {
2659
+ "epoch": 0.9381188118811881,
2660
+ "grad_norm": 0.18214091658592224,
2661
+ "learning_rate": 6.435643564356436e-07,
2662
+ "loss": 1.0433,
2663
+ "step": 379
2664
+ },
2665
+ {
2666
+ "epoch": 0.9405940594059405,
2667
+ "grad_norm": 0.23452341556549072,
2668
+ "learning_rate": 6.188118811881188e-07,
2669
+ "loss": 0.9751,
2670
+ "step": 380
2671
+ },
2672
+ {
2673
+ "epoch": 0.943069306930693,
2674
+ "grad_norm": 0.16824421286582947,
2675
+ "learning_rate": 5.940594059405941e-07,
2676
+ "loss": 1.032,
2677
+ "step": 381
2678
+ },
2679
+ {
2680
+ "epoch": 0.9455445544554455,
2681
+ "grad_norm": 0.2157716602087021,
2682
+ "learning_rate": 5.693069306930694e-07,
2683
+ "loss": 1.0361,
2684
+ "step": 382
2685
+ },
2686
+ {
2687
+ "epoch": 0.948019801980198,
2688
+ "grad_norm": 0.1715572625398636,
2689
+ "learning_rate": 5.445544554455446e-07,
2690
+ "loss": 1.0135,
2691
+ "step": 383
2692
+ },
2693
+ {
2694
+ "epoch": 0.9504950495049505,
2695
+ "grad_norm": 0.18207526206970215,
2696
+ "learning_rate": 5.198019801980199e-07,
2697
+ "loss": 1.008,
2698
+ "step": 384
2699
+ },
2700
+ {
2701
+ "epoch": 0.9529702970297029,
2702
+ "grad_norm": 0.17518338561058044,
2703
+ "learning_rate": 4.950495049504951e-07,
2704
+ "loss": 1.0558,
2705
+ "step": 385
2706
+ },
2707
+ {
2708
+ "epoch": 0.9554455445544554,
2709
+ "grad_norm": 0.16482017934322357,
2710
+ "learning_rate": 4.702970297029703e-07,
2711
+ "loss": 1.0176,
2712
+ "step": 386
2713
+ },
2714
+ {
2715
+ "epoch": 0.9579207920792079,
2716
+ "grad_norm": 0.1714717000722885,
2717
+ "learning_rate": 4.4554455445544555e-07,
2718
+ "loss": 1.0052,
2719
+ "step": 387
2720
+ },
2721
+ {
2722
+ "epoch": 0.9603960396039604,
2723
+ "grad_norm": 0.2134282886981964,
2724
+ "learning_rate": 4.2079207920792083e-07,
2725
+ "loss": 0.9946,
2726
+ "step": 388
2727
+ },
2728
+ {
2729
+ "epoch": 0.9628712871287128,
2730
+ "grad_norm": 0.1706077754497528,
2731
+ "learning_rate": 3.9603960396039606e-07,
2732
+ "loss": 1.0198,
2733
+ "step": 389
2734
+ },
2735
+ {
2736
+ "epoch": 0.9653465346534653,
2737
+ "grad_norm": 0.17025628685951233,
2738
+ "learning_rate": 3.712871287128713e-07,
2739
+ "loss": 1.0387,
2740
+ "step": 390
2741
+ },
2742
+ {
2743
+ "epoch": 0.9678217821782178,
2744
+ "grad_norm": 0.20762069523334503,
2745
+ "learning_rate": 3.4653465346534657e-07,
2746
+ "loss": 1.0192,
2747
+ "step": 391
2748
+ },
2749
+ {
2750
+ "epoch": 0.9702970297029703,
2751
+ "grad_norm": 0.1808956265449524,
2752
+ "learning_rate": 3.217821782178218e-07,
2753
+ "loss": 1.0094,
2754
+ "step": 392
2755
+ },
2756
+ {
2757
+ "epoch": 0.9727722772277227,
2758
+ "grad_norm": 0.18868137896060944,
2759
+ "learning_rate": 2.9702970297029703e-07,
2760
+ "loss": 1.0505,
2761
+ "step": 393
2762
+ },
2763
+ {
2764
+ "epoch": 0.9752475247524752,
2765
+ "grad_norm": 0.17066539824008942,
2766
+ "learning_rate": 2.722772277227723e-07,
2767
+ "loss": 1.0439,
2768
+ "step": 394
2769
+ },
2770
+ {
2771
+ "epoch": 0.9777227722772277,
2772
+ "grad_norm": 0.19031685590744019,
2773
+ "learning_rate": 2.4752475247524754e-07,
2774
+ "loss": 1.0565,
2775
+ "step": 395
2776
+ },
2777
+ {
2778
+ "epoch": 0.9801980198019802,
2779
+ "grad_norm": 0.175362229347229,
2780
+ "learning_rate": 2.2277227722772277e-07,
2781
+ "loss": 1.0129,
2782
+ "step": 396
2783
+ },
2784
+ {
2785
+ "epoch": 0.9826732673267327,
2786
+ "grad_norm": 0.17563587427139282,
2787
+ "learning_rate": 1.9801980198019803e-07,
2788
+ "loss": 1.0256,
2789
+ "step": 397
2790
+ },
2791
+ {
2792
+ "epoch": 0.9851485148514851,
2793
+ "grad_norm": 0.18792986869812012,
2794
+ "learning_rate": 1.7326732673267329e-07,
2795
+ "loss": 0.9857,
2796
+ "step": 398
2797
+ },
2798
+ {
2799
+ "epoch": 0.9876237623762376,
2800
+ "grad_norm": 0.16679790616035461,
2801
+ "learning_rate": 1.4851485148514852e-07,
2802
+ "loss": 1.0258,
2803
+ "step": 399
2804
+ },
2805
+ {
2806
+ "epoch": 0.9900990099009901,
2807
+ "grad_norm": 0.17717471718788147,
2808
+ "learning_rate": 1.2376237623762377e-07,
2809
+ "loss": 1.0558,
2810
+ "step": 400
2811
+ },
2812
+ {
2813
+ "epoch": 0.9925742574257426,
2814
+ "grad_norm": 0.17575222253799438,
2815
+ "learning_rate": 9.900990099009901e-08,
2816
+ "loss": 1.0095,
2817
+ "step": 401
2818
+ },
2819
+ {
2820
+ "epoch": 0.995049504950495,
2821
+ "grad_norm": 0.17630964517593384,
2822
+ "learning_rate": 7.425742574257426e-08,
2823
+ "loss": 1.0431,
2824
+ "step": 402
2825
+ },
2826
+ {
2827
+ "epoch": 0.9975247524752475,
2828
+ "grad_norm": 0.18719862401485443,
2829
+ "learning_rate": 4.950495049504951e-08,
2830
+ "loss": 1.0469,
2831
+ "step": 403
2832
+ },
2833
+ {
2834
+ "epoch": 1.0,
2835
+ "grad_norm": 0.1757795810699463,
2836
+ "learning_rate": 2.4752475247524754e-08,
2837
+ "loss": 1.0161,
2838
+ "step": 404
2839
+ }
2840
+ ],
2841
+ "logging_steps": 1.0,
2842
+ "max_steps": 404,
2843
+ "num_input_tokens_seen": 0,
2844
+ "num_train_epochs": 1,
2845
+ "save_steps": 0,
2846
+ "stateful_callbacks": {
2847
+ "TrainerControl": {
2848
+ "args": {
2849
+ "should_epoch_stop": false,
2850
+ "should_evaluate": false,
2851
+ "should_log": false,
2852
+ "should_save": true,
2853
+ "should_training_stop": true
2854
+ },
2855
+ "attributes": {}
2856
+ }
2857
+ },
2858
+ "total_flos": 6.023190572360008e+17,
2859
+ "train_batch_size": 1,
2860
+ "trial_name": null,
2861
+ "trial_params": null
2862
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff