Hugging Face's logo

shulijia
/
MNLP_M3_mcqa_model_simpleVal_obqasciq_cot

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
6aab56e
·
verified ·
1 Parent(s): cc1d3f4

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 +524 -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:aa7d5da23d81542492b3513ec4691f76580f56deeae1d8c6cff8d94aa8de7a41
3
+ size 2384234968
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c04fdc080d09069db2ea415f0c04deb96783ffd270deede588368e83fc49926
3
+ size 4768663315
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd9432b50864b1799d071a2391f13a188cc959e985675ab69fd688672db2853
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71be7808ec3b37a2104cc5c01dec96b18a2b6b0e99bdc1553ea12532abc8d7b
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 +1,524 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.5343307507347048,
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": 0.010686615014694095,
14
+ "grad_norm": 162.79299926757812,
15
+ "learning_rate": 3.202846975088968e-07,
16
+ "loss": 1.9506,
17
+ "mean_token_accuracy": 0.3373654623050243,
18
+ "num_tokens": 81920.0,
19
+ "step": 10
20
+ },
21
+ {
22
+ "epoch": 0.02137323002938819,
23
+ "grad_norm": 9.192719459533691,
24
+ "learning_rate": 6.761565836298933e-07,
25
+ "loss": 0.465,
26
+ "mean_token_accuracy": 0.784821429476142,
27
+ "num_tokens": 163840.0,
28
+ "step": 20
29
+ },
30
+ {
31
+ "epoch": 0.03205984504408229,
32
+ "grad_norm": 2.3641631603240967,
33
+ "learning_rate": 1.0320284697508897e-06,
34
+ "loss": 0.2689,
35
+ "mean_token_accuracy": 0.7834882590919733,
36
+ "num_tokens": 245760.0,
37
+ "step": 30
38
+ },
39
+ {
40
+ "epoch": 0.04274646005877638,
41
+ "grad_norm": 1.4731940031051636,
42
+ "learning_rate": 1.3879003558718862e-06,
43
+ "loss": 0.2053,
44
+ "mean_token_accuracy": 0.8192392382770777,
45
+ "num_tokens": 327680.0,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 0.053433075073470476,
50
+ "grad_norm": 1.3491817712783813,
51
+ "learning_rate": 1.7437722419928826e-06,
52
+ "loss": 0.227,
53
+ "mean_token_accuracy": 0.8019447132945061,
54
+ "num_tokens": 409600.0,
55
+ "step": 50
56
+ },
57
+ {
58
+ "epoch": 0.06411969008816458,
59
+ "grad_norm": 1.4582160711288452,
60
+ "learning_rate": 2.099644128113879e-06,
61
+ "loss": 0.2065,
62
+ "mean_token_accuracy": 0.8115949083119631,
63
+ "num_tokens": 491520.0,
64
+ "step": 60
65
+ },
66
+ {
67
+ "epoch": 0.07480630510285867,
68
+ "grad_norm": 1.2769246101379395,
69
+ "learning_rate": 2.4555160142348754e-06,
70
+ "loss": 0.187,
71
+ "mean_token_accuracy": 0.8192392345517874,
72
+ "num_tokens": 573440.0,
73
+ "step": 70
74
+ },
75
+ {
76
+ "epoch": 0.08549292011755276,
77
+ "grad_norm": 1.2492260932922363,
78
+ "learning_rate": 2.811387900355872e-06,
79
+ "loss": 0.1679,
80
+ "mean_token_accuracy": 0.8338062610477209,
81
+ "num_tokens": 655360.0,
82
+ "step": 80
83
+ },
84
+ {
85
+ "epoch": 0.09617953513224686,
86
+ "grad_norm": 1.1294825077056885,
87
+ "learning_rate": 3.1672597864768683e-06,
88
+ "loss": 0.1843,
89
+ "mean_token_accuracy": 0.834368884935975,
90
+ "num_tokens": 737280.0,
91
+ "step": 90
92
+ },
93
+ {
94
+ "epoch": 0.10686615014694095,
95
+ "grad_norm": 1.1130266189575195,
96
+ "learning_rate": 3.523131672597865e-06,
97
+ "loss": 0.1671,
98
+ "step": 100
99
+ },
100
+ {
101
+ "epoch": 0.10686615014694095,
102
+ "eval_loss": 0.37910598516464233,
103
+ "eval_mean_token_accuracy": 0.9205154885466282,
104
+ "eval_num_tokens": 819200.0,
105
+ "eval_runtime": 54.8062,
106
+ "eval_samples_per_second": 30.362,
107
+ "eval_steps_per_second": 1.898,
108
+ "step": 100
109
+ },
110
+ {
111
+ "epoch": 0.11755276516163506,
112
+ "grad_norm": 1.8707005977630615,
113
+ "learning_rate": 3.879003558718862e-06,
114
+ "loss": 0.2172,
115
+ "mean_token_accuracy": 0.8211289137601853,
116
+ "num_tokens": 901120.0,
117
+ "step": 110
118
+ },
119
+ {
120
+ "epoch": 0.12823938017632916,
121
+ "grad_norm": 1.2644431591033936,
122
+ "learning_rate": 4.234875444839858e-06,
123
+ "loss": 0.1779,
124
+ "mean_token_accuracy": 0.8335983369499445,
125
+ "num_tokens": 983040.0,
126
+ "step": 120
127
+ },
128
+ {
129
+ "epoch": 0.13892599519102325,
130
+ "grad_norm": 1.5855945348739624,
131
+ "learning_rate": 4.590747330960855e-06,
132
+ "loss": 0.2067,
133
+ "mean_token_accuracy": 0.8128180041909218,
134
+ "num_tokens": 1064960.0,
135
+ "step": 130
136
+ },
137
+ {
138
+ "epoch": 0.14961261020571734,
139
+ "grad_norm": 1.800769567489624,
140
+ "learning_rate": 4.946619217081851e-06,
141
+ "loss": 0.1865,
142
+ "mean_token_accuracy": 0.8186032261699439,
143
+ "num_tokens": 1146880.0,
144
+ "step": 140
145
+ },
146
+ {
147
+ "epoch": 0.16029922522041143,
148
+ "grad_norm": 1.338663101196289,
149
+ "learning_rate": 5.302491103202847e-06,
150
+ "loss": 0.198,
151
+ "mean_token_accuracy": 0.8027764171361923,
152
+ "num_tokens": 1228800.0,
153
+ "step": 150
154
+ },
155
+ {
156
+ "epoch": 0.17098584023510552,
157
+ "grad_norm": 1.40470290184021,
158
+ "learning_rate": 5.658362989323844e-06,
159
+ "loss": 0.1903,
160
+ "mean_token_accuracy": 0.8333537198603154,
161
+ "num_tokens": 1310720.0,
162
+ "step": 160
163
+ },
164
+ {
165
+ "epoch": 0.18167245524979964,
166
+ "grad_norm": 1.4831385612487793,
167
+ "learning_rate": 6.01423487544484e-06,
168
+ "loss": 0.1759,
169
+ "mean_token_accuracy": 0.8290484331548214,
170
+ "num_tokens": 1392640.0,
171
+ "step": 170
172
+ },
173
+ {
174
+ "epoch": 0.19235907026449373,
175
+ "grad_norm": 1.4669700860977173,
176
+ "learning_rate": 6.370106761565836e-06,
177
+ "loss": 0.1524,
178
+ "mean_token_accuracy": 0.8432363007217646,
179
+ "num_tokens": 1474560.0,
180
+ "step": 180
181
+ },
182
+ {
183
+ "epoch": 0.20304568527918782,
184
+ "grad_norm": 1.343820333480835,
185
+ "learning_rate": 6.725978647686834e-06,
186
+ "loss": 0.1755,
187
+ "mean_token_accuracy": 0.8176247555762529,
188
+ "num_tokens": 1556480.0,
189
+ "step": 190
190
+ },
191
+ {
192
+ "epoch": 0.2137323002938819,
193
+ "grad_norm": 1.5964102745056152,
194
+ "learning_rate": 7.0818505338078305e-06,
195
+ "loss": 0.2145,
196
+ "step": 200
197
+ },
198
+ {
199
+ "epoch": 0.2137323002938819,
200
+ "eval_loss": 0.3721162676811218,
201
+ "eval_mean_token_accuracy": 0.9214892587982692,
202
+ "eval_num_tokens": 1638400.0,
203
+ "eval_runtime": 54.87,
204
+ "eval_samples_per_second": 30.326,
205
+ "eval_steps_per_second": 1.895,
206
+ "step": 200
207
+ },
208
+ {
209
+ "epoch": 0.224418915308576,
210
+ "grad_norm": 1.5484873056411743,
211
+ "learning_rate": 7.437722419928827e-06,
212
+ "loss": 0.1853,
213
+ "mean_token_accuracy": 0.8091915344819427,
214
+ "num_tokens": 1720320.0,
215
+ "step": 210
216
+ },
217
+ {
218
+ "epoch": 0.2351055303232701,
219
+ "grad_norm": 1.9265834093093872,
220
+ "learning_rate": 7.793594306049824e-06,
221
+ "loss": 0.2046,
222
+ "mean_token_accuracy": 0.8073507819324732,
223
+ "num_tokens": 1802240.0,
224
+ "step": 220
225
+ },
226
+ {
227
+ "epoch": 0.2457921453379642,
228
+ "grad_norm": 1.4167306423187256,
229
+ "learning_rate": 8.14946619217082e-06,
230
+ "loss": 0.1851,
231
+ "mean_token_accuracy": 0.8138454012572766,
232
+ "num_tokens": 1884160.0,
233
+ "step": 230
234
+ },
235
+ {
236
+ "epoch": 0.2564787603526583,
237
+ "grad_norm": 1.3846415281295776,
238
+ "learning_rate": 8.505338078291816e-06,
239
+ "loss": 0.1951,
240
+ "mean_token_accuracy": 0.8046232897788286,
241
+ "num_tokens": 1966080.0,
242
+ "step": 240
243
+ },
244
+ {
245
+ "epoch": 0.2671653753673524,
246
+ "grad_norm": 1.115859031677246,
247
+ "learning_rate": 8.861209964412812e-06,
248
+ "loss": 0.1999,
249
+ "mean_token_accuracy": 0.822590509057045,
250
+ "num_tokens": 2048000.0,
251
+ "step": 250
252
+ },
253
+ {
254
+ "epoch": 0.2778519903820465,
255
+ "grad_norm": 1.741172432899475,
256
+ "learning_rate": 9.217081850533809e-06,
257
+ "loss": 0.2077,
258
+ "mean_token_accuracy": 0.8199486304074526,
259
+ "num_tokens": 2129920.0,
260
+ "step": 260
261
+ },
262
+ {
263
+ "epoch": 0.2885386053967406,
264
+ "grad_norm": 1.845530390739441,
265
+ "learning_rate": 9.572953736654806e-06,
266
+ "loss": 0.1895,
267
+ "mean_token_accuracy": 0.8226883586496114,
268
+ "num_tokens": 2211840.0,
269
+ "step": 270
270
+ },
271
+ {
272
+ "epoch": 0.2992252204114347,
273
+ "grad_norm": 1.2396894693374634,
274
+ "learning_rate": 9.928825622775801e-06,
275
+ "loss": 0.1669,
276
+ "mean_token_accuracy": 0.8372553829103708,
277
+ "num_tokens": 2293760.0,
278
+ "step": 280
279
+ },
280
+ {
281
+ "epoch": 0.30991183542612877,
282
+ "grad_norm": 1.317146897315979,
283
+ "learning_rate": 9.96834190740008e-06,
284
+ "loss": 0.2349,
285
+ "mean_token_accuracy": 0.8001345425844193,
286
+ "num_tokens": 2375680.0,
287
+ "step": 290
288
+ },
289
+ {
290
+ "epoch": 0.32059845044082286,
291
+ "grad_norm": 1.089537501335144,
292
+ "learning_rate": 9.928769291650178e-06,
293
+ "loss": 0.1765,
294
+ "step": 300
295
+ },
296
+ {
297
+ "epoch": 0.32059845044082286,
298
+ "eval_loss": 0.37061530351638794,
299
+ "eval_mean_token_accuracy": 0.921646848320961,
300
+ "eval_num_tokens": 2457600.0,
301
+ "eval_runtime": 55.1091,
302
+ "eval_samples_per_second": 30.195,
303
+ "eval_steps_per_second": 1.887,
304
+ "step": 300
305
+ },
306
+ {
307
+ "epoch": 0.33128506545551695,
308
+ "grad_norm": 0.9158857464790344,
309
+ "learning_rate": 9.889196675900278e-06,
310
+ "loss": 0.1642,
311
+ "mean_token_accuracy": 0.8281188851222396,
312
+ "num_tokens": 2539520.0,
313
+ "step": 310
314
+ },
315
+ {
316
+ "epoch": 0.34197168047021104,
317
+ "grad_norm": 1.2602512836456299,
318
+ "learning_rate": 9.849624060150376e-06,
319
+ "loss": 0.2059,
320
+ "mean_token_accuracy": 0.8006115462630987,
321
+ "num_tokens": 2621440.0,
322
+ "step": 320
323
+ },
324
+ {
325
+ "epoch": 0.3526582954849052,
326
+ "grad_norm": 1.1253645420074463,
327
+ "learning_rate": 9.810051444400476e-06,
328
+ "loss": 0.1902,
329
+ "mean_token_accuracy": 0.8089285682886839,
330
+ "num_tokens": 2703360.0,
331
+ "step": 330
332
+ },
333
+ {
334
+ "epoch": 0.36334491049959927,
335
+ "grad_norm": 1.4268500804901123,
336
+ "learning_rate": 9.770478828650574e-06,
337
+ "loss": 0.1853,
338
+ "mean_token_accuracy": 0.8195327781140804,
339
+ "num_tokens": 2785280.0,
340
+ "step": 340
341
+ },
342
+ {
343
+ "epoch": 0.37403152551429336,
344
+ "grad_norm": 1.8250911235809326,
345
+ "learning_rate": 9.730906212900674e-06,
346
+ "loss": 0.1883,
347
+ "mean_token_accuracy": 0.8256237760186196,
348
+ "num_tokens": 2867200.0,
349
+ "step": 350
350
+ },
351
+ {
352
+ "epoch": 0.38471814052898745,
353
+ "grad_norm": 1.4212009906768799,
354
+ "learning_rate": 9.691333597150772e-06,
355
+ "loss": 0.1666,
356
+ "mean_token_accuracy": 0.8268101755529642,
357
+ "num_tokens": 2949120.0,
358
+ "step": 360
359
+ },
360
+ {
361
+ "epoch": 0.39540475554368154,
362
+ "grad_norm": 1.3452640771865845,
363
+ "learning_rate": 9.651760981400872e-06,
364
+ "loss": 0.1848,
365
+ "mean_token_accuracy": 0.8232632085680962,
366
+ "num_tokens": 3031040.0,
367
+ "step": 370
368
+ },
369
+ {
370
+ "epoch": 0.40609137055837563,
371
+ "grad_norm": 1.4238511323928833,
372
+ "learning_rate": 9.61218836565097e-06,
373
+ "loss": 0.1822,
374
+ "mean_token_accuracy": 0.8275440279394388,
375
+ "num_tokens": 3112960.0,
376
+ "step": 380
377
+ },
378
+ {
379
+ "epoch": 0.4167779855730697,
380
+ "grad_norm": 1.7013052701950073,
381
+ "learning_rate": 9.57261574990107e-06,
382
+ "loss": 0.1775,
383
+ "mean_token_accuracy": 0.8318126205354929,
384
+ "num_tokens": 3194880.0,
385
+ "step": 390
386
+ },
387
+ {
388
+ "epoch": 0.4274646005877638,
389
+ "grad_norm": 1.4549729824066162,
390
+ "learning_rate": 9.533043134151168e-06,
391
+ "loss": 0.1705,
392
+ "step": 400
393
+ },
394
+ {
395
+ "epoch": 0.4274646005877638,
396
+ "eval_loss": 0.36919423937797546,
397
+ "eval_mean_token_accuracy": 0.9219361566580259,
398
+ "eval_num_tokens": 3276800.0,
399
+ "eval_runtime": 55.2845,
400
+ "eval_samples_per_second": 30.099,
401
+ "eval_steps_per_second": 1.881,
402
+ "step": 400
403
+ },
404
+ {
405
+ "epoch": 0.4381512156024579,
406
+ "grad_norm": 1.1822422742843628,
407
+ "learning_rate": 9.493470518401268e-06,
408
+ "loss": 0.1946,
409
+ "mean_token_accuracy": 0.8248532293364406,
410
+ "num_tokens": 3358720.0,
411
+ "step": 410
412
+ },
413
+ {
414
+ "epoch": 0.448837830617152,
415
+ "grad_norm": 1.496228814125061,
416
+ "learning_rate": 9.453897902651366e-06,
417
+ "loss": 0.1925,
418
+ "mean_token_accuracy": 0.819104696623981,
419
+ "num_tokens": 3440640.0,
420
+ "step": 420
421
+ },
422
+ {
423
+ "epoch": 0.45952444563184613,
424
+ "grad_norm": 1.608656883239746,
425
+ "learning_rate": 9.414325286901464e-06,
426
+ "loss": 0.1943,
427
+ "mean_token_accuracy": 0.8151541082188487,
428
+ "num_tokens": 3522560.0,
429
+ "step": 430
430
+ },
431
+ {
432
+ "epoch": 0.4702110606465402,
433
+ "grad_norm": 1.479527473449707,
434
+ "learning_rate": 9.374752671151564e-06,
435
+ "loss": 0.2132,
436
+ "mean_token_accuracy": 0.8068370830267668,
437
+ "num_tokens": 3604480.0,
438
+ "step": 440
439
+ },
440
+ {
441
+ "epoch": 0.4808976756612343,
442
+ "grad_norm": 1.2162389755249023,
443
+ "learning_rate": 9.335180055401662e-06,
444
+ "loss": 0.1494,
445
+ "mean_token_accuracy": 0.8466242626309395,
446
+ "num_tokens": 3686400.0,
447
+ "step": 450
448
+ },
449
+ {
450
+ "epoch": 0.4915842906759284,
451
+ "grad_norm": 1.1681294441223145,
452
+ "learning_rate": 9.295607439651762e-06,
453
+ "loss": 0.1613,
454
+ "mean_token_accuracy": 0.8266022477298975,
455
+ "num_tokens": 3768320.0,
456
+ "step": 460
457
+ },
458
+ {
459
+ "epoch": 0.5022709056906225,
460
+ "grad_norm": 1.7950598001480103,
461
+ "learning_rate": 9.25603482390186e-06,
462
+ "loss": 0.2089,
463
+ "mean_token_accuracy": 0.8046355187892914,
464
+ "num_tokens": 3850240.0,
465
+ "step": 470
466
+ },
467
+ {
468
+ "epoch": 0.5129575207053166,
469
+ "grad_norm": 0.9483240842819214,
470
+ "learning_rate": 9.21646220815196e-06,
471
+ "loss": 0.203,
472
+ "mean_token_accuracy": 0.8039505863562226,
473
+ "num_tokens": 3932160.0,
474
+ "step": 480
475
+ },
476
+ {
477
+ "epoch": 0.5236441357200107,
478
+ "grad_norm": 1.2230192422866821,
479
+ "learning_rate": 9.176889592402058e-06,
480
+ "loss": 0.192,
481
+ "mean_token_accuracy": 0.8211961830034852,
482
+ "num_tokens": 4014080.0,
483
+ "step": 490
484
+ },
485
+ {
486
+ "epoch": 0.5343307507347048,
487
+ "grad_norm": 1.0234431028366089,
488
+ "learning_rate": 9.137316976652158e-06,
489
+ "loss": 0.1961,
490
+ "step": 500
491
+ },
492
+ {
493
+ "epoch": 0.5343307507347048,
494
+ "eval_loss": 0.3676806092262268,
495
+ "eval_mean_token_accuracy": 0.9221843051222655,
496
+ "eval_num_tokens": 4096000.0,
497
+ "eval_runtime": 55.0795,
498
+ "eval_samples_per_second": 30.211,
499
+ "eval_steps_per_second": 1.888,
500
+ "step": 500
501
+ }
502
+ ],
503
+ "logging_steps": 10,
504
+ "max_steps": 2808,
505
+ "num_input_tokens_seen": 0,
506
+ "num_train_epochs": 3,
507
+ "save_steps": 500,
508
+ "stateful_callbacks": {
509
+ "TrainerControl": {
510
+ "args": {
511
+ "should_epoch_stop": false,
512
+ "should_evaluate": false,
513
+ "should_log": false,
514
+ "should_save": true,
515
+ "should_training_stop": false
516
+ },
517
+ "attributes": {}
518
+ }
519
+ },
520
+ "total_flos": 1.0824928198656e+16,
521
+ "train_batch_size": 2,
522
+ "trial_name": null,
523
+ "trial_params": null
524
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84d466119be9e33130e7a0e4cbf67e2b182a84c78acb13cd4db09913adc625e4
3
+ size 6097
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff