Hugging Face's logo

shulijia
/
MNLP_M3_mcqa_model_base_mathqa_cot_orig

Text Generation
Transformers
TensorBoard
Safetensors
qwen3
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files
xet
Metrics Community
shulijia commited on
Commit
b28ca7d
·
verified ·
1 Parent(s): 0e2a767

Training in progress, step 500, checkpoint

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. last-checkpoint/added_tokens.json +28 -0
  3. last-checkpoint/chat_template.jinja +85 -0
  4. last-checkpoint/config.json +30 -0
  5. last-checkpoint/generation_config.json +6 -0
  6. last-checkpoint/merges.txt +0 -0
  7. last-checkpoint/model.safetensors +3 -0
  8. last-checkpoint/optimizer.pt +3 -0
  9. last-checkpoint/rng_state.pth +3 -0
  10. last-checkpoint/scheduler.pt +3 -0
  11. last-checkpoint/special_tokens_map.json +31 -0
  12. last-checkpoint/tokenizer.json +3 -0
  13. last-checkpoint/tokenizer_config.json +239 -0
  14. last-checkpoint/trainer_state.json +484 -0
  15. last-checkpoint/training_args.bin +3 -0
  16. last-checkpoint/vocab.json +0 -0
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* 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
 
 
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
37
+ last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
last-checkpoint/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
+ }
last-checkpoint/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# 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>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\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" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
last-checkpoint/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": 151643,
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": 32768,
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": "4.52.2",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.52.2"
6
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53829ebc7d98508b6f5703849237d288254da26fab64f6b140e154267a39c6d1
3
+ size 2384234968
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660db501ba945e4579b7c9eea6f1fdd9dbf280a8b245d8a95d5346600af1680e
3
+ size 4768663315
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646716a9868f7d6569467f6a6a739c6e2ede4724fe9c9553909736ccc65666af
3
+ size 1465
last-checkpoint/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": "<|endoftext|>",
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
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574de68a0f63f2004784a421c7d42c2b2786c05cb38542d2ed3525757a1f7fde
3
+ size 11422932
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|endoftext|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,484 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.29021258071537404,
6
+ "eval_steps": 100,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.005804251614307481,
14
+ "grad_norm": 184.6446075439453,
15
+ "learning_rate": 1.7408123791102517e-07,
16
+ "loss": 1.5904,
17
+ "mean_token_accuracy": 0.4080601753666997,
18
+ "num_tokens": 81920.0,
19
+ "step": 10
20
+ },
21
+ {
22
+ "epoch": 0.011608503228614961,
23
+ "grad_norm": 24.036514282226562,
24
+ "learning_rate": 3.6750483558994203e-07,
25
+ "loss": 0.6452,
26
+ "mean_token_accuracy": 0.6714774928987026,
27
+ "num_tokens": 163840.0,
28
+ "step": 20
29
+ },
30
+ {
31
+ "epoch": 0.01741275484292244,
32
+ "grad_norm": 5.3119707107543945,
33
+ "learning_rate": 5.609284332688589e-07,
34
+ "loss": 0.294,
35
+ "mean_token_accuracy": 0.7371575355529785,
36
+ "num_tokens": 245760.0,
37
+ "step": 30
38
+ },
39
+ {
40
+ "epoch": 0.023217006457229922,
41
+ "grad_norm": 3.2296133041381836,
42
+ "learning_rate": 7.543520309477757e-07,
43
+ "loss": 0.2162,
44
+ "mean_token_accuracy": 0.7556262277066708,
45
+ "num_tokens": 327680.0,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 0.029021258071537402,
50
+ "grad_norm": 2.355419874191284,
51
+ "learning_rate": 9.477756286266926e-07,
52
+ "loss": 0.1903,
53
+ "mean_token_accuracy": 0.7512353222817183,
54
+ "num_tokens": 409600.0,
55
+ "step": 50
56
+ },
57
+ {
58
+ "epoch": 0.03482550968584488,
59
+ "grad_norm": 1.9649362564086914,
60
+ "learning_rate": 1.1411992263056094e-06,
61
+ "loss": 0.1761,
62
+ "mean_token_accuracy": 0.7676981419324875,
63
+ "num_tokens": 491520.0,
64
+ "step": 60
65
+ },
66
+ {
67
+ "epoch": 0.04062976130015236,
68
+ "grad_norm": 1.526881456375122,
69
+ "learning_rate": 1.3346228239845263e-06,
70
+ "loss": 0.1601,
71
+ "mean_token_accuracy": 0.7613992184400559,
72
+ "num_tokens": 573440.0,
73
+ "step": 70
74
+ },
75
+ {
76
+ "epoch": 0.046434012914459845,
77
+ "grad_norm": 2.121938467025757,
78
+ "learning_rate": 1.528046421663443e-06,
79
+ "loss": 0.1552,
80
+ "mean_token_accuracy": 0.7604329749941826,
81
+ "num_tokens": 655360.0,
82
+ "step": 80
83
+ },
84
+ {
85
+ "epoch": 0.05223826452876732,
86
+ "grad_norm": 1.604015827178955,
87
+ "learning_rate": 1.72147001934236e-06,
88
+ "loss": 0.1525,
89
+ "mean_token_accuracy": 0.7550636030733585,
90
+ "num_tokens": 737280.0,
91
+ "step": 90
92
+ },
93
+ {
94
+ "epoch": 0.058042516143074804,
95
+ "grad_norm": 2.230043411254883,
96
+ "learning_rate": 1.9148936170212767e-06,
97
+ "loss": 0.1696,
98
+ "mean_token_accuracy": 0.7451687887310982,
99
+ "num_tokens": 819200.0,
100
+ "step": 100
101
+ },
102
+ {
103
+ "epoch": 0.06384676775738228,
104
+ "grad_norm": 2.1791794300079346,
105
+ "learning_rate": 2.1083172147001936e-06,
106
+ "loss": 0.133,
107
+ "mean_token_accuracy": 0.7824363995343446,
108
+ "num_tokens": 901120.0,
109
+ "step": 110
110
+ },
111
+ {
112
+ "epoch": 0.06965101937168976,
113
+ "grad_norm": 2.2505223751068115,
114
+ "learning_rate": 2.3017408123791105e-06,
115
+ "loss": 0.1606,
116
+ "mean_token_accuracy": 0.7586839523166418,
117
+ "num_tokens": 983040.0,
118
+ "step": 120
119
+ },
120
+ {
121
+ "epoch": 0.07545527098599725,
122
+ "grad_norm": 2.182016611099243,
123
+ "learning_rate": 2.495164410058027e-06,
124
+ "loss": 0.1536,
125
+ "mean_token_accuracy": 0.7505748525261879,
126
+ "num_tokens": 1064960.0,
127
+ "step": 130
128
+ },
129
+ {
130
+ "epoch": 0.08125952260030472,
131
+ "grad_norm": 2.193237066268921,
132
+ "learning_rate": 2.6885880077369443e-06,
133
+ "loss": 0.1475,
134
+ "mean_token_accuracy": 0.7669153653085232,
135
+ "num_tokens": 1146880.0,
136
+ "step": 140
137
+ },
138
+ {
139
+ "epoch": 0.0870637742146122,
140
+ "grad_norm": 1.7638152837753296,
141
+ "learning_rate": 2.8820116054158607e-06,
142
+ "loss": 0.1495,
143
+ "mean_token_accuracy": 0.7674168314784765,
144
+ "num_tokens": 1228800.0,
145
+ "step": 150
146
+ },
147
+ {
148
+ "epoch": 0.09286802582891969,
149
+ "grad_norm": 1.5372321605682373,
150
+ "learning_rate": 3.0754352030947776e-06,
151
+ "loss": 0.1534,
152
+ "mean_token_accuracy": 0.7672700580209494,
153
+ "num_tokens": 1310720.0,
154
+ "step": 160
155
+ },
156
+ {
157
+ "epoch": 0.09867227744322717,
158
+ "grad_norm": 1.788905143737793,
159
+ "learning_rate": 3.268858800773695e-06,
160
+ "loss": 0.14,
161
+ "mean_token_accuracy": 0.7756360046565532,
162
+ "num_tokens": 1392640.0,
163
+ "step": 170
164
+ },
165
+ {
166
+ "epoch": 0.10447652905753464,
167
+ "grad_norm": 1.9735488891601562,
168
+ "learning_rate": 3.462282398452612e-06,
169
+ "loss": 0.1604,
170
+ "mean_token_accuracy": 0.7546599790453911,
171
+ "num_tokens": 1474560.0,
172
+ "step": 180
173
+ },
174
+ {
175
+ "epoch": 0.11028078067184212,
176
+ "grad_norm": 1.8861180543899536,
177
+ "learning_rate": 3.6557059961315283e-06,
178
+ "loss": 0.149,
179
+ "mean_token_accuracy": 0.7564090020954609,
180
+ "num_tokens": 1556480.0,
181
+ "step": 190
182
+ },
183
+ {
184
+ "epoch": 0.11608503228614961,
185
+ "grad_norm": 1.3918368816375732,
186
+ "learning_rate": 3.849129593810445e-06,
187
+ "loss": 0.1398,
188
+ "mean_token_accuracy": 0.7647137984633445,
189
+ "num_tokens": 1638400.0,
190
+ "step": 200
191
+ },
192
+ {
193
+ "epoch": 0.12188928390045708,
194
+ "grad_norm": 1.7859585285186768,
195
+ "learning_rate": 4.042553191489362e-06,
196
+ "loss": 0.1489,
197
+ "mean_token_accuracy": 0.7647382609546185,
198
+ "num_tokens": 1720320.0,
199
+ "step": 210
200
+ },
201
+ {
202
+ "epoch": 0.12769353551476456,
203
+ "grad_norm": 1.6809779405593872,
204
+ "learning_rate": 4.235976789168279e-06,
205
+ "loss": 0.1569,
206
+ "mean_token_accuracy": 0.749840997159481,
207
+ "num_tokens": 1802240.0,
208
+ "step": 220
209
+ },
210
+ {
211
+ "epoch": 0.13349778712907204,
212
+ "grad_norm": 2.012342929840088,
213
+ "learning_rate": 4.429400386847195e-06,
214
+ "loss": 0.1357,
215
+ "mean_token_accuracy": 0.7730063647031784,
216
+ "num_tokens": 1884160.0,
217
+ "step": 230
218
+ },
219
+ {
220
+ "epoch": 0.1393020387433795,
221
+ "grad_norm": 1.782494306564331,
222
+ "learning_rate": 4.622823984526112e-06,
223
+ "loss": 0.1328,
224
+ "mean_token_accuracy": 0.7649584129452706,
225
+ "num_tokens": 1966080.0,
226
+ "step": 240
227
+ },
228
+ {
229
+ "epoch": 0.14510629035768702,
230
+ "grad_norm": 1.759964108467102,
231
+ "learning_rate": 4.816247582205029e-06,
232
+ "loss": 0.1393,
233
+ "mean_token_accuracy": 0.7724437367171049,
234
+ "num_tokens": 2048000.0,
235
+ "step": 250
236
+ },
237
+ {
238
+ "epoch": 0.1509105419719945,
239
+ "grad_norm": 1.9878251552581787,
240
+ "learning_rate": 5.009671179883946e-06,
241
+ "loss": 0.1623,
242
+ "mean_token_accuracy": 0.7562255427241326,
243
+ "num_tokens": 2129920.0,
244
+ "step": 260
245
+ },
246
+ {
247
+ "epoch": 0.15671479358630197,
248
+ "grad_norm": 1.8629584312438965,
249
+ "learning_rate": 5.203094777562863e-06,
250
+ "loss": 0.1421,
251
+ "mean_token_accuracy": 0.7706213306635619,
252
+ "num_tokens": 2211840.0,
253
+ "step": 270
254
+ },
255
+ {
256
+ "epoch": 0.16251904520060945,
257
+ "grad_norm": 1.8488317728042603,
258
+ "learning_rate": 5.396518375241781e-06,
259
+ "loss": 0.1579,
260
+ "mean_token_accuracy": 0.7603718198835849,
261
+ "num_tokens": 2293760.0,
262
+ "step": 280
263
+ },
264
+ {
265
+ "epoch": 0.16832329681491692,
266
+ "grad_norm": 1.8936114311218262,
267
+ "learning_rate": 5.5899419729206975e-06,
268
+ "loss": 0.144,
269
+ "mean_token_accuracy": 0.7590386521071195,
270
+ "num_tokens": 2375680.0,
271
+ "step": 290
272
+ },
273
+ {
274
+ "epoch": 0.1741275484292244,
275
+ "grad_norm": 2.05222749710083,
276
+ "learning_rate": 5.783365570599614e-06,
277
+ "loss": 0.1495,
278
+ "mean_token_accuracy": 0.7546355165541172,
279
+ "num_tokens": 2457600.0,
280
+ "step": 300
281
+ },
282
+ {
283
+ "epoch": 0.17993180004353188,
284
+ "grad_norm": 2.029935598373413,
285
+ "learning_rate": 5.9767891682785305e-06,
286
+ "loss": 0.1497,
287
+ "mean_token_accuracy": 0.7573752462863922,
288
+ "num_tokens": 2539520.0,
289
+ "step": 310
290
+ },
291
+ {
292
+ "epoch": 0.18573605165783938,
293
+ "grad_norm": 2.2519826889038086,
294
+ "learning_rate": 6.170212765957447e-06,
295
+ "loss": 0.1373,
296
+ "mean_token_accuracy": 0.7602984346449375,
297
+ "num_tokens": 2621440.0,
298
+ "step": 320
299
+ },
300
+ {
301
+ "epoch": 0.19154030327214686,
302
+ "grad_norm": 2.2112629413604736,
303
+ "learning_rate": 6.363636363636364e-06,
304
+ "loss": 0.1361,
305
+ "mean_token_accuracy": 0.7635640908032656,
306
+ "num_tokens": 2703360.0,
307
+ "step": 330
308
+ },
309
+ {
310
+ "epoch": 0.19734455488645433,
311
+ "grad_norm": 1.9330954551696777,
312
+ "learning_rate": 6.557059961315281e-06,
313
+ "loss": 0.1768,
314
+ "mean_token_accuracy": 0.747871819883585,
315
+ "num_tokens": 2785280.0,
316
+ "step": 340
317
+ },
318
+ {
319
+ "epoch": 0.2031488065007618,
320
+ "grad_norm": 1.518797755241394,
321
+ "learning_rate": 6.750483558994197e-06,
322
+ "loss": 0.1513,
323
+ "mean_token_accuracy": 0.754121819511056,
324
+ "num_tokens": 2867200.0,
325
+ "step": 350
326
+ },
327
+ {
328
+ "epoch": 0.20895305811506928,
329
+ "grad_norm": 2.376616954803467,
330
+ "learning_rate": 6.943907156673114e-06,
331
+ "loss": 0.1395,
332
+ "mean_token_accuracy": 0.7679794520139694,
333
+ "num_tokens": 2949120.0,
334
+ "step": 360
335
+ },
336
+ {
337
+ "epoch": 0.21475730972937676,
338
+ "grad_norm": 1.8156490325927734,
339
+ "learning_rate": 7.137330754352032e-06,
340
+ "loss": 0.1262,
341
+ "mean_token_accuracy": 0.7859589017927646,
342
+ "num_tokens": 3031040.0,
343
+ "step": 370
344
+ },
345
+ {
346
+ "epoch": 0.22056156134368424,
347
+ "grad_norm": 1.4950615167617798,
348
+ "learning_rate": 7.330754352030949e-06,
349
+ "loss": 0.1454,
350
+ "mean_token_accuracy": 0.7517490223050117,
351
+ "num_tokens": 3112960.0,
352
+ "step": 380
353
+ },
354
+ {
355
+ "epoch": 0.22636581295799174,
356
+ "grad_norm": 1.8987642526626587,
357
+ "learning_rate": 7.5241779497098655e-06,
358
+ "loss": 0.161,
359
+ "mean_token_accuracy": 0.7678449153900146,
360
+ "num_tokens": 3194880.0,
361
+ "step": 390
362
+ },
363
+ {
364
+ "epoch": 0.23217006457229922,
365
+ "grad_norm": 1.8029884099960327,
366
+ "learning_rate": 7.717601547388782e-06,
367
+ "loss": 0.1594,
368
+ "mean_token_accuracy": 0.7558830715715885,
369
+ "num_tokens": 3276800.0,
370
+ "step": 400
371
+ },
372
+ {
373
+ "epoch": 0.2379743161866067,
374
+ "grad_norm": 1.5608956813812256,
375
+ "learning_rate": 7.911025145067698e-06,
376
+ "loss": 0.1544,
377
+ "mean_token_accuracy": 0.7478473588824273,
378
+ "num_tokens": 3358720.0,
379
+ "step": 410
380
+ },
381
+ {
382
+ "epoch": 0.24377856780091417,
383
+ "grad_norm": 1.7958343029022217,
384
+ "learning_rate": 8.104448742746616e-06,
385
+ "loss": 0.1349,
386
+ "mean_token_accuracy": 0.7667808212339878,
387
+ "num_tokens": 3440640.0,
388
+ "step": 420
389
+ },
390
+ {
391
+ "epoch": 0.24958281941522165,
392
+ "grad_norm": 2.2577550411224365,
393
+ "learning_rate": 8.297872340425532e-06,
394
+ "loss": 0.1631,
395
+ "mean_token_accuracy": 0.7581457935273648,
396
+ "num_tokens": 3522560.0,
397
+ "step": 430
398
+ },
399
+ {
400
+ "epoch": 0.2553870710295291,
401
+ "grad_norm": 2.1318979263305664,
402
+ "learning_rate": 8.491295938104448e-06,
403
+ "loss": 0.1501,
404
+ "mean_token_accuracy": 0.756690314039588,
405
+ "num_tokens": 3604480.0,
406
+ "step": 440
407
+ },
408
+ {
409
+ "epoch": 0.2611913226438366,
410
+ "grad_norm": 1.6812206506729126,
411
+ "learning_rate": 8.684719535783366e-06,
412
+ "loss": 0.1479,
413
+ "mean_token_accuracy": 0.7670988231897354,
414
+ "num_tokens": 3686400.0,
415
+ "step": 450
416
+ },
417
+ {
418
+ "epoch": 0.2669955742581441,
419
+ "grad_norm": 2.0722217559814453,
420
+ "learning_rate": 8.878143133462284e-06,
421
+ "loss": 0.1547,
422
+ "mean_token_accuracy": 0.7581824850291013,
423
+ "num_tokens": 3768320.0,
424
+ "step": 460
425
+ },
426
+ {
427
+ "epoch": 0.27279982587245155,
428
+ "grad_norm": 1.6783735752105713,
429
+ "learning_rate": 9.0715667311412e-06,
430
+ "loss": 0.1385,
431
+ "mean_token_accuracy": 0.7647137988358736,
432
+ "num_tokens": 3850240.0,
433
+ "step": 470
434
+ },
435
+ {
436
+ "epoch": 0.278604077486759,
437
+ "grad_norm": 1.7798433303833008,
438
+ "learning_rate": 9.264990328820118e-06,
439
+ "loss": 0.1603,
440
+ "mean_token_accuracy": 0.7556996077299118,
441
+ "num_tokens": 3932160.0,
442
+ "step": 480
443
+ },
444
+ {
445
+ "epoch": 0.2844083291010665,
446
+ "grad_norm": 1.7679011821746826,
447
+ "learning_rate": 9.458413926499034e-06,
448
+ "loss": 0.1326,
449
+ "mean_token_accuracy": 0.7703889425843954,
450
+ "num_tokens": 4014080.0,
451
+ "step": 490
452
+ },
453
+ {
454
+ "epoch": 0.29021258071537404,
455
+ "grad_norm": 1.892972469329834,
456
+ "learning_rate": 9.651837524177951e-06,
457
+ "loss": 0.1392,
458
+ "mean_token_accuracy": 0.7732020527124405,
459
+ "num_tokens": 4096000.0,
460
+ "step": 500
461
+ }
462
+ ],
463
+ "logging_steps": 10,
464
+ "max_steps": 5169,
465
+ "num_input_tokens_seen": 0,
466
+ "num_train_epochs": 3,
467
+ "save_steps": 500,
468
+ "stateful_callbacks": {
469
+ "TrainerControl": {
470
+ "args": {
471
+ "should_epoch_stop": false,
472
+ "should_evaluate": false,
473
+ "should_log": false,
474
+ "should_save": true,
475
+ "should_training_stop": false
476
+ },
477
+ "attributes": {}
478
+ }
479
+ },
480
+ "total_flos": 1.0824928198656e+16,
481
+ "train_batch_size": 2,
482
+ "trial_name": null,
483
+ "trial_params": null
484
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b23bdfc8bcd6177d07af828dc4895240c795d111ffd0320da882fd74b97768
3
+ size 6097
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff