ellendagher commited on
Commit
353361b
·
verified ·
1 Parent(s): 0f5ec24

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "max_position_embeddings": 40960,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.51.3",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.51.3"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:707e3c5db8f2e57d8f7e098951a95c65ddddb75437c08d77abe6d5f7839bb3dd
3
+ size 2384234968
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69cd083f7b98e4e8540e2d0225bc46180c97bb86c800118028507e797959b093
3
+ size 4768663315
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e8896fda9d2f5d944b94e472842a94a46637c7ee3a70f041d204605aaf0d45
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9289d59fc2a18c8184e4f5e0a991e172ac50417bc78f2e7e46692d1190e924b2
3
+ size 1465
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 sha256:79894f433c8379c083f0666155142ab72946b24d053f443d6118f87133f10134
3
+ size 11422751
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
trainer_state.json ADDED
@@ -0,0 +1,1022 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 7028,
3
+ "best_metric": 0.767158567905426,
4
+ "best_model_checkpoint": "./mcqa_qwen3_letter/checkpoint-7028",
5
+ "epoch": 0.9998932953939178,
6
+ "eval_steps": 500,
7
+ "global_step": 7028,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.007113640405477503,
14
+ "grad_norm": 20.374778747558594,
15
+ "learning_rate": 1.337126600284495e-06,
16
+ "loss": 2.342,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.014227280810955006,
21
+ "grad_norm": 23.720001220703125,
22
+ "learning_rate": 2.7596017069701283e-06,
23
+ "loss": 1.6092,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.02134092121643251,
28
+ "grad_norm": 14.003034591674805,
29
+ "learning_rate": 4.182076813655762e-06,
30
+ "loss": 1.4564,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.028454561621910013,
35
+ "grad_norm": 11.145376205444336,
36
+ "learning_rate": 5.604551920341395e-06,
37
+ "loss": 1.481,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.035568202027387516,
42
+ "grad_norm": 14.064179420471191,
43
+ "learning_rate": 7.027027027027028e-06,
44
+ "loss": 1.4483,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.04268184243286502,
49
+ "grad_norm": 14.6947021484375,
50
+ "learning_rate": 8.44950213371266e-06,
51
+ "loss": 1.4355,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.04979548283834252,
56
+ "grad_norm": 11.520552635192871,
57
+ "learning_rate": 9.871977240398294e-06,
58
+ "loss": 1.4314,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.056909123243820026,
63
+ "grad_norm": 11.234253883361816,
64
+ "learning_rate": 1.1294452347083926e-05,
65
+ "loss": 1.3494,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.06402276364929753,
70
+ "grad_norm": 9.99629020690918,
71
+ "learning_rate": 1.271692745376956e-05,
72
+ "loss": 1.3342,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.07113640405477503,
77
+ "grad_norm": 8.978431701660156,
78
+ "learning_rate": 1.4139402560455193e-05,
79
+ "loss": 1.2951,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.07825004446025254,
84
+ "grad_norm": 9.42021369934082,
85
+ "learning_rate": 1.5561877667140826e-05,
86
+ "loss": 1.3058,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.08536368486573004,
91
+ "grad_norm": 9.690632820129395,
92
+ "learning_rate": 1.698435277382646e-05,
93
+ "loss": 1.2561,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.09247732527120754,
98
+ "grad_norm": 10.151556015014648,
99
+ "learning_rate": 1.8406827880512092e-05,
100
+ "loss": 1.2415,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.09959096567668504,
105
+ "grad_norm": 8.446418762207031,
106
+ "learning_rate": 1.9829302987197725e-05,
107
+ "loss": 1.3303,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.10670460608216255,
112
+ "grad_norm": 9.451847076416016,
113
+ "learning_rate": 1.9860869565217395e-05,
114
+ "loss": 1.2735,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.11381824648764005,
119
+ "grad_norm": 9.343132019042969,
120
+ "learning_rate": 1.9702766798418973e-05,
121
+ "loss": 1.3471,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.12093188689311755,
126
+ "grad_norm": 9.069653511047363,
127
+ "learning_rate": 1.9544664031620554e-05,
128
+ "loss": 1.2535,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.12804552729859506,
133
+ "grad_norm": 5.554582595825195,
134
+ "learning_rate": 1.9386561264822135e-05,
135
+ "loss": 1.2887,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.13515916770407255,
140
+ "grad_norm": 8.713581085205078,
141
+ "learning_rate": 1.9228458498023717e-05,
142
+ "loss": 1.1681,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.14227280810955006,
147
+ "grad_norm": 8.742165565490723,
148
+ "learning_rate": 1.9070355731225298e-05,
149
+ "loss": 1.2271,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.14938644851502755,
154
+ "grad_norm": 8.755561828613281,
155
+ "learning_rate": 1.891225296442688e-05,
156
+ "loss": 1.2557,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.15650008892050507,
161
+ "grad_norm": 7.881649017333984,
162
+ "learning_rate": 1.875415019762846e-05,
163
+ "loss": 1.1999,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.16361372932598256,
168
+ "grad_norm": 9.955330848693848,
169
+ "learning_rate": 1.8596047430830042e-05,
170
+ "loss": 1.1375,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.17072736973146008,
175
+ "grad_norm": 9.453360557556152,
176
+ "learning_rate": 1.843794466403162e-05,
177
+ "loss": 1.2173,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.17784101013693757,
182
+ "grad_norm": 6.806760787963867,
183
+ "learning_rate": 1.8279841897233205e-05,
184
+ "loss": 1.2116,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.18495465054241508,
189
+ "grad_norm": 13.604923248291016,
190
+ "learning_rate": 1.8121739130434783e-05,
191
+ "loss": 1.0788,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.19206829094789257,
196
+ "grad_norm": 10.025015830993652,
197
+ "learning_rate": 1.7963636363636364e-05,
198
+ "loss": 1.149,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.1991819313533701,
203
+ "grad_norm": 9.246174812316895,
204
+ "learning_rate": 1.7805533596837945e-05,
205
+ "loss": 1.1171,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.20629557175884758,
210
+ "grad_norm": 9.556463241577148,
211
+ "learning_rate": 1.7647430830039527e-05,
212
+ "loss": 1.1744,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.2134092121643251,
217
+ "grad_norm": 13.477895736694336,
218
+ "learning_rate": 1.7489328063241108e-05,
219
+ "loss": 1.0723,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.22052285256980259,
224
+ "grad_norm": 7.583223342895508,
225
+ "learning_rate": 1.733122529644269e-05,
226
+ "loss": 1.1004,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.2276364929752801,
231
+ "grad_norm": 9.056886672973633,
232
+ "learning_rate": 1.717312252964427e-05,
233
+ "loss": 1.1413,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.2347501333807576,
238
+ "grad_norm": 8.818636894226074,
239
+ "learning_rate": 1.701501976284585e-05,
240
+ "loss": 1.0248,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.2418637737862351,
245
+ "grad_norm": 11.717618942260742,
246
+ "learning_rate": 1.6856916996047434e-05,
247
+ "loss": 1.0386,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.2489774141917126,
252
+ "grad_norm": 7.414971828460693,
253
+ "learning_rate": 1.6698814229249015e-05,
254
+ "loss": 1.0885,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.2560910545971901,
259
+ "grad_norm": 6.960204601287842,
260
+ "learning_rate": 1.6540711462450593e-05,
261
+ "loss": 1.053,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.26320469500266763,
266
+ "grad_norm": 6.861100673675537,
267
+ "learning_rate": 1.6382608695652174e-05,
268
+ "loss": 1.0398,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.2703183354081451,
273
+ "grad_norm": 7.645370960235596,
274
+ "learning_rate": 1.6224505928853756e-05,
275
+ "loss": 0.9453,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.2774319758136226,
280
+ "grad_norm": 7.169046878814697,
281
+ "learning_rate": 1.6066403162055337e-05,
282
+ "loss": 0.9847,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.28454561621910013,
287
+ "grad_norm": 6.290506362915039,
288
+ "learning_rate": 1.5908300395256918e-05,
289
+ "loss": 0.9592,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.29165925662457765,
294
+ "grad_norm": 8.001459121704102,
295
+ "learning_rate": 1.57501976284585e-05,
296
+ "loss": 0.9674,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.2987728970300551,
301
+ "grad_norm": 8.543235778808594,
302
+ "learning_rate": 1.559525691699605e-05,
303
+ "loss": 1.003,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.3058865374355326,
308
+ "grad_norm": 10.702069282531738,
309
+ "learning_rate": 1.543715415019763e-05,
310
+ "loss": 0.9914,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.31300017784101014,
315
+ "grad_norm": 5.234061241149902,
316
+ "learning_rate": 1.527905138339921e-05,
317
+ "loss": 1.0809,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.32011381824648766,
322
+ "grad_norm": 8.00466251373291,
323
+ "learning_rate": 1.5120948616600793e-05,
324
+ "loss": 0.9713,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.3272274586519651,
329
+ "grad_norm": 7.484270095825195,
330
+ "learning_rate": 1.4962845849802372e-05,
331
+ "loss": 0.906,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.33434109905744264,
336
+ "grad_norm": 17.150543212890625,
337
+ "learning_rate": 1.4804743083003954e-05,
338
+ "loss": 1.0206,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.34145473946292015,
343
+ "grad_norm": 8.58785343170166,
344
+ "learning_rate": 1.4646640316205533e-05,
345
+ "loss": 0.9868,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.34856837986839767,
350
+ "grad_norm": 7.040744304656982,
351
+ "learning_rate": 1.4488537549407116e-05,
352
+ "loss": 0.9225,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.35568202027387513,
357
+ "grad_norm": 8.559785842895508,
358
+ "learning_rate": 1.4330434782608698e-05,
359
+ "loss": 0.9345,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.36279566067935265,
364
+ "grad_norm": 9.140971183776855,
365
+ "learning_rate": 1.4172332015810277e-05,
366
+ "loss": 1.004,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.36990930108483017,
371
+ "grad_norm": 8.379377365112305,
372
+ "learning_rate": 1.4014229249011859e-05,
373
+ "loss": 1.0199,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.3770229414903077,
378
+ "grad_norm": 6.753004550933838,
379
+ "learning_rate": 1.3856126482213438e-05,
380
+ "loss": 0.9463,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.38413658189578515,
385
+ "grad_norm": 7.884097576141357,
386
+ "learning_rate": 1.3698023715415021e-05,
387
+ "loss": 0.9367,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.39125022230126266,
392
+ "grad_norm": 8.405110359191895,
393
+ "learning_rate": 1.3539920948616603e-05,
394
+ "loss": 0.9036,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.3983638627067402,
399
+ "grad_norm": 7.3707661628723145,
400
+ "learning_rate": 1.3381818181818182e-05,
401
+ "loss": 0.9868,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.4054775031122177,
406
+ "grad_norm": 9.472613334655762,
407
+ "learning_rate": 1.3223715415019764e-05,
408
+ "loss": 0.9809,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.41259114351769516,
413
+ "grad_norm": 8.191240310668945,
414
+ "learning_rate": 1.3065612648221343e-05,
415
+ "loss": 0.9249,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.4197047839231727,
420
+ "grad_norm": 7.100245952606201,
421
+ "learning_rate": 1.2907509881422926e-05,
422
+ "loss": 0.9303,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.4268184243286502,
427
+ "grad_norm": 6.30331563949585,
428
+ "learning_rate": 1.2749407114624508e-05,
429
+ "loss": 0.9459,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.4339320647341277,
434
+ "grad_norm": 5.755526065826416,
435
+ "learning_rate": 1.2591304347826087e-05,
436
+ "loss": 0.8818,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.44104570513960517,
441
+ "grad_norm": 7.514272689819336,
442
+ "learning_rate": 1.243320158102767e-05,
443
+ "loss": 0.8817,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.4481593455450827,
448
+ "grad_norm": 6.345920562744141,
449
+ "learning_rate": 1.227509881422925e-05,
450
+ "loss": 0.8257,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.4552729859505602,
455
+ "grad_norm": 5.915317058563232,
456
+ "learning_rate": 1.2120158102766799e-05,
457
+ "loss": 0.9691,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.4623866263560377,
462
+ "grad_norm": 4.785401821136475,
463
+ "learning_rate": 1.1962055335968382e-05,
464
+ "loss": 0.97,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.4695002667615152,
469
+ "grad_norm": 8.403907775878906,
470
+ "learning_rate": 1.1803952569169962e-05,
471
+ "loss": 0.8699,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.4766139071669927,
476
+ "grad_norm": 8.583006858825684,
477
+ "learning_rate": 1.1645849802371543e-05,
478
+ "loss": 0.9233,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.4837275475724702,
483
+ "grad_norm": 7.836755752563477,
484
+ "learning_rate": 1.1487747035573123e-05,
485
+ "loss": 0.8716,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.49084118797794773,
490
+ "grad_norm": 4.714875221252441,
491
+ "learning_rate": 1.1329644268774704e-05,
492
+ "loss": 0.8499,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.4979548283834252,
497
+ "grad_norm": 7.097923755645752,
498
+ "learning_rate": 1.1171541501976287e-05,
499
+ "loss": 0.912,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.5050684687889028,
504
+ "grad_norm": 4.853347301483154,
505
+ "learning_rate": 1.1013438735177867e-05,
506
+ "loss": 0.8411,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.5121821091943802,
511
+ "grad_norm": 6.642279148101807,
512
+ "learning_rate": 1.0855335968379448e-05,
513
+ "loss": 0.9325,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.5192957495998577,
518
+ "grad_norm": 6.702445030212402,
519
+ "learning_rate": 1.0697233201581028e-05,
520
+ "loss": 0.8354,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.5264093900053353,
525
+ "grad_norm": 6.634207725524902,
526
+ "learning_rate": 1.0539130434782609e-05,
527
+ "loss": 0.8813,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.5335230304108127,
532
+ "grad_norm": 4.122372627258301,
533
+ "learning_rate": 1.0381027667984192e-05,
534
+ "loss": 0.7811,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.5406366708162902,
539
+ "grad_norm": 8.899633407592773,
540
+ "learning_rate": 1.0222924901185772e-05,
541
+ "loss": 0.8707,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.5477503112217678,
546
+ "grad_norm": 5.374997615814209,
547
+ "learning_rate": 1.0064822134387353e-05,
548
+ "loss": 0.8854,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.5548639516272452,
553
+ "grad_norm": 7.9275102615356445,
554
+ "learning_rate": 9.906719367588934e-06,
555
+ "loss": 0.9255,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.5619775920327228,
560
+ "grad_norm": 6.925314903259277,
561
+ "learning_rate": 9.748616600790514e-06,
562
+ "loss": 0.9027,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.5690912324382003,
567
+ "grad_norm": 9.117793083190918,
568
+ "learning_rate": 9.590513833992095e-06,
569
+ "loss": 0.8831,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.5762048728436777,
574
+ "grad_norm": 5.861302852630615,
575
+ "learning_rate": 9.432411067193677e-06,
576
+ "loss": 0.8329,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.5833185132491553,
581
+ "grad_norm": 6.011074066162109,
582
+ "learning_rate": 9.274308300395256e-06,
583
+ "loss": 0.8766,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.5904321536546328,
588
+ "grad_norm": 5.763038158416748,
589
+ "learning_rate": 9.11620553359684e-06,
590
+ "loss": 0.9374,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.5975457940601102,
595
+ "grad_norm": 5.520111083984375,
596
+ "learning_rate": 8.95810276679842e-06,
597
+ "loss": 0.8813,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 0.6046594344655878,
602
+ "grad_norm": 7.351500511169434,
603
+ "learning_rate": 8.8e-06,
604
+ "loss": 0.8677,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 0.6117730748710652,
609
+ "grad_norm": 5.451608657836914,
610
+ "learning_rate": 8.641897233201582e-06,
611
+ "loss": 0.8606,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 0.6188867152765428,
616
+ "grad_norm": 5.458895683288574,
617
+ "learning_rate": 8.483794466403163e-06,
618
+ "loss": 0.8522,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 0.6260003556820203,
623
+ "grad_norm": 5.554731369018555,
624
+ "learning_rate": 8.325691699604743e-06,
625
+ "loss": 0.9042,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 0.6331139960874977,
630
+ "grad_norm": 3.6643424034118652,
631
+ "learning_rate": 8.167588932806326e-06,
632
+ "loss": 0.8696,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 0.6402276364929753,
637
+ "grad_norm": 5.593344688415527,
638
+ "learning_rate": 8.009486166007906e-06,
639
+ "loss": 0.7663,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 0.6473412768984528,
644
+ "grad_norm": 7.597021102905273,
645
+ "learning_rate": 7.851383399209487e-06,
646
+ "loss": 0.7752,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 0.6544549173039302,
651
+ "grad_norm": 4.095972537994385,
652
+ "learning_rate": 7.693280632411068e-06,
653
+ "loss": 0.897,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 0.6615685577094078,
658
+ "grad_norm": 7.817249298095703,
659
+ "learning_rate": 7.535177865612649e-06,
660
+ "loss": 0.7448,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 0.6686821981148853,
665
+ "grad_norm": 3.296755313873291,
666
+ "learning_rate": 7.37707509881423e-06,
667
+ "loss": 0.8065,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 0.6757958385203628,
672
+ "grad_norm": 5.186858177185059,
673
+ "learning_rate": 7.218972332015811e-06,
674
+ "loss": 0.8618,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 0.6829094789258403,
679
+ "grad_norm": 6.484861373901367,
680
+ "learning_rate": 7.060869565217392e-06,
681
+ "loss": 0.8549,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 0.6900231193313178,
686
+ "grad_norm": 4.90764856338501,
687
+ "learning_rate": 6.902766798418972e-06,
688
+ "loss": 0.9441,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 0.6971367597367953,
693
+ "grad_norm": 3.6083099842071533,
694
+ "learning_rate": 6.744664031620554e-06,
695
+ "loss": 0.7467,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 0.7042504001422728,
700
+ "grad_norm": 4.79904317855835,
701
+ "learning_rate": 6.586561264822134e-06,
702
+ "loss": 0.7974,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 0.7113640405477503,
707
+ "grad_norm": 8.30154800415039,
708
+ "learning_rate": 6.4284584980237165e-06,
709
+ "loss": 0.8927,
710
+ "step": 5000
711
+ },
712
+ {
713
+ "epoch": 0.7184776809532278,
714
+ "grad_norm": 5.582029819488525,
715
+ "learning_rate": 6.270355731225297e-06,
716
+ "loss": 0.8348,
717
+ "step": 5050
718
+ },
719
+ {
720
+ "epoch": 0.7255913213587053,
721
+ "grad_norm": 7.575035572052002,
722
+ "learning_rate": 6.112252964426878e-06,
723
+ "loss": 0.8691,
724
+ "step": 5100
725
+ },
726
+ {
727
+ "epoch": 0.7327049617641829,
728
+ "grad_norm": 6.100114345550537,
729
+ "learning_rate": 5.954150197628459e-06,
730
+ "loss": 0.788,
731
+ "step": 5150
732
+ },
733
+ {
734
+ "epoch": 0.7398186021696603,
735
+ "grad_norm": 7.05925178527832,
736
+ "learning_rate": 5.796047430830039e-06,
737
+ "loss": 0.8325,
738
+ "step": 5200
739
+ },
740
+ {
741
+ "epoch": 0.7469322425751378,
742
+ "grad_norm": 6.5520920753479,
743
+ "learning_rate": 5.6379446640316215e-06,
744
+ "loss": 0.7792,
745
+ "step": 5250
746
+ },
747
+ {
748
+ "epoch": 0.7540458829806154,
749
+ "grad_norm": 6.9081807136535645,
750
+ "learning_rate": 5.479841897233202e-06,
751
+ "loss": 0.805,
752
+ "step": 5300
753
+ },
754
+ {
755
+ "epoch": 0.7611595233860928,
756
+ "grad_norm": 7.752345085144043,
757
+ "learning_rate": 5.321739130434783e-06,
758
+ "loss": 0.7998,
759
+ "step": 5350
760
+ },
761
+ {
762
+ "epoch": 0.7682731637915703,
763
+ "grad_norm": 3.8013064861297607,
764
+ "learning_rate": 5.163636363636364e-06,
765
+ "loss": 0.7748,
766
+ "step": 5400
767
+ },
768
+ {
769
+ "epoch": 0.7753868041970479,
770
+ "grad_norm": 5.316600322723389,
771
+ "learning_rate": 5.005533596837945e-06,
772
+ "loss": 0.7644,
773
+ "step": 5450
774
+ },
775
+ {
776
+ "epoch": 0.7825004446025253,
777
+ "grad_norm": 8.250207901000977,
778
+ "learning_rate": 4.8474308300395266e-06,
779
+ "loss": 0.7766,
780
+ "step": 5500
781
+ },
782
+ {
783
+ "epoch": 0.7896140850080029,
784
+ "grad_norm": 5.134970664978027,
785
+ "learning_rate": 4.689328063241107e-06,
786
+ "loss": 0.79,
787
+ "step": 5550
788
+ },
789
+ {
790
+ "epoch": 0.7967277254134804,
791
+ "grad_norm": 5.832414627075195,
792
+ "learning_rate": 4.531225296442688e-06,
793
+ "loss": 0.9154,
794
+ "step": 5600
795
+ },
796
+ {
797
+ "epoch": 0.8038413658189578,
798
+ "grad_norm": 6.164233684539795,
799
+ "learning_rate": 4.373122529644269e-06,
800
+ "loss": 0.8288,
801
+ "step": 5650
802
+ },
803
+ {
804
+ "epoch": 0.8109550062244354,
805
+ "grad_norm": 11.60009479522705,
806
+ "learning_rate": 4.21501976284585e-06,
807
+ "loss": 0.7047,
808
+ "step": 5700
809
+ },
810
+ {
811
+ "epoch": 0.8180686466299129,
812
+ "grad_norm": 3.422287702560425,
813
+ "learning_rate": 4.056916996047432e-06,
814
+ "loss": 0.7387,
815
+ "step": 5750
816
+ },
817
+ {
818
+ "epoch": 0.8251822870353903,
819
+ "grad_norm": 3.786428689956665,
820
+ "learning_rate": 3.898814229249012e-06,
821
+ "loss": 0.806,
822
+ "step": 5800
823
+ },
824
+ {
825
+ "epoch": 0.8322959274408679,
826
+ "grad_norm": 3.7693772315979004,
827
+ "learning_rate": 3.740711462450593e-06,
828
+ "loss": 0.8136,
829
+ "step": 5850
830
+ },
831
+ {
832
+ "epoch": 0.8394095678463454,
833
+ "grad_norm": 3.2537221908569336,
834
+ "learning_rate": 3.5826086956521744e-06,
835
+ "loss": 0.7834,
836
+ "step": 5900
837
+ },
838
+ {
839
+ "epoch": 0.8465232082518229,
840
+ "grad_norm": 2.938720226287842,
841
+ "learning_rate": 3.4245059288537553e-06,
842
+ "loss": 0.7607,
843
+ "step": 5950
844
+ },
845
+ {
846
+ "epoch": 0.8536368486573004,
847
+ "grad_norm": 6.700362205505371,
848
+ "learning_rate": 3.266403162055336e-06,
849
+ "loss": 0.8713,
850
+ "step": 6000
851
+ },
852
+ {
853
+ "epoch": 0.8607504890627778,
854
+ "grad_norm": 4.768782615661621,
855
+ "learning_rate": 3.1083003952569176e-06,
856
+ "loss": 0.8086,
857
+ "step": 6050
858
+ },
859
+ {
860
+ "epoch": 0.8678641294682554,
861
+ "grad_norm": 6.537806034088135,
862
+ "learning_rate": 2.950197628458498e-06,
863
+ "loss": 0.8722,
864
+ "step": 6100
865
+ },
866
+ {
867
+ "epoch": 0.8749777698737329,
868
+ "grad_norm": 6.817727088928223,
869
+ "learning_rate": 2.792094861660079e-06,
870
+ "loss": 0.7126,
871
+ "step": 6150
872
+ },
873
+ {
874
+ "epoch": 0.8820914102792103,
875
+ "grad_norm": 5.932295799255371,
876
+ "learning_rate": 2.6339920948616604e-06,
877
+ "loss": 0.778,
878
+ "step": 6200
879
+ },
880
+ {
881
+ "epoch": 0.8892050506846879,
882
+ "grad_norm": 6.475405693054199,
883
+ "learning_rate": 2.4758893280632413e-06,
884
+ "loss": 0.7812,
885
+ "step": 6250
886
+ },
887
+ {
888
+ "epoch": 0.8963186910901654,
889
+ "grad_norm": 8.57321834564209,
890
+ "learning_rate": 2.3177865612648222e-06,
891
+ "loss": 0.7654,
892
+ "step": 6300
893
+ },
894
+ {
895
+ "epoch": 0.903432331495643,
896
+ "grad_norm": 1.9723538160324097,
897
+ "learning_rate": 2.1596837944664036e-06,
898
+ "loss": 0.7701,
899
+ "step": 6350
900
+ },
901
+ {
902
+ "epoch": 0.9105459719011204,
903
+ "grad_norm": 6.585085391998291,
904
+ "learning_rate": 2.001581027667984e-06,
905
+ "loss": 0.8419,
906
+ "step": 6400
907
+ },
908
+ {
909
+ "epoch": 0.9176596123065979,
910
+ "grad_norm": 4.754767894744873,
911
+ "learning_rate": 1.8434782608695654e-06,
912
+ "loss": 0.9006,
913
+ "step": 6450
914
+ },
915
+ {
916
+ "epoch": 0.9247732527120754,
917
+ "grad_norm": 4.661940574645996,
918
+ "learning_rate": 1.6853754940711464e-06,
919
+ "loss": 0.7784,
920
+ "step": 6500
921
+ },
922
+ {
923
+ "epoch": 0.9318868931175529,
924
+ "grad_norm": 4.972583770751953,
925
+ "learning_rate": 1.5272727272727275e-06,
926
+ "loss": 0.8112,
927
+ "step": 6550
928
+ },
929
+ {
930
+ "epoch": 0.9390005335230304,
931
+ "grad_norm": 6.641800403594971,
932
+ "learning_rate": 1.3691699604743084e-06,
933
+ "loss": 0.7466,
934
+ "step": 6600
935
+ },
936
+ {
937
+ "epoch": 0.9461141739285079,
938
+ "grad_norm": 5.098995208740234,
939
+ "learning_rate": 1.2110671936758893e-06,
940
+ "loss": 0.824,
941
+ "step": 6650
942
+ },
943
+ {
944
+ "epoch": 0.9532278143339854,
945
+ "grad_norm": 7.060574054718018,
946
+ "learning_rate": 1.0529644268774705e-06,
947
+ "loss": 0.8502,
948
+ "step": 6700
949
+ },
950
+ {
951
+ "epoch": 0.960341454739463,
952
+ "grad_norm": 4.678645610809326,
953
+ "learning_rate": 8.948616600790515e-07,
954
+ "loss": 0.8004,
955
+ "step": 6750
956
+ },
957
+ {
958
+ "epoch": 0.9674550951449404,
959
+ "grad_norm": 5.895313739776611,
960
+ "learning_rate": 7.367588932806324e-07,
961
+ "loss": 0.6811,
962
+ "step": 6800
963
+ },
964
+ {
965
+ "epoch": 0.9745687355504179,
966
+ "grad_norm": 5.316034317016602,
967
+ "learning_rate": 5.786561264822135e-07,
968
+ "loss": 0.7955,
969
+ "step": 6850
970
+ },
971
+ {
972
+ "epoch": 0.9816823759558955,
973
+ "grad_norm": 5.032801628112793,
974
+ "learning_rate": 4.205533596837945e-07,
975
+ "loss": 0.8206,
976
+ "step": 6900
977
+ },
978
+ {
979
+ "epoch": 0.9887960163613729,
980
+ "grad_norm": 5.486656188964844,
981
+ "learning_rate": 2.6245059288537554e-07,
982
+ "loss": 0.795,
983
+ "step": 6950
984
+ },
985
+ {
986
+ "epoch": 0.9959096567668504,
987
+ "grad_norm": 6.862821102142334,
988
+ "learning_rate": 1.0434782608695654e-07,
989
+ "loss": 0.676,
990
+ "step": 7000
991
+ },
992
+ {
993
+ "epoch": 0.9998932953939178,
994
+ "eval_loss": 0.767158567905426,
995
+ "eval_runtime": 341.0802,
996
+ "eval_samples_per_second": 15.454,
997
+ "eval_steps_per_second": 1.932,
998
+ "step": 7028
999
+ }
1000
+ ],
1001
+ "logging_steps": 50,
1002
+ "max_steps": 7028,
1003
+ "num_input_tokens_seen": 0,
1004
+ "num_train_epochs": 1,
1005
+ "save_steps": 500,
1006
+ "stateful_callbacks": {
1007
+ "TrainerControl": {
1008
+ "args": {
1009
+ "should_epoch_stop": false,
1010
+ "should_evaluate": false,
1011
+ "should_log": false,
1012
+ "should_save": true,
1013
+ "should_training_stop": true
1014
+ },
1015
+ "attributes": {}
1016
+ }
1017
+ },
1018
+ "total_flos": 3.803879769007718e+16,
1019
+ "train_batch_size": 1,
1020
+ "trial_name": null,
1021
+ "trial_params": null
1022
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:787861c4443724f9aa80d7c4b6cdb995d7de23a720ae1c919df05042e24489db
3
+ size 5713
vocab.json ADDED
The diff for this file is too large to render. See raw diff