fengyao1909 commited on
Commit
171ab46
·
verified ·
1 Parent(s): 625b9fb

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 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "max_position_embeddings": 32768,
16
+ "max_window_layers": 48,
17
+ "mlp_only_layers": [],
18
+ "model_type": "qwen3_moe",
19
+ "moe_intermediate_size": 768,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 32,
22
+ "num_experts": 128,
23
+ "num_experts_per_tok": 8,
24
+ "num_hidden_layers": 48,
25
+ "num_key_value_heads": 4,
26
+ "output_router_logits": false,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": null,
29
+ "rope_theta": 1000000.0,
30
+ "router_aux_loss_coef": 0.001,
31
+ "sliding_window": null,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.51.3",
35
+ "use_cache": false,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 151936
38
+ }
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": "4.51.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718a64680422a1beaf7bf05477e59b9d3e1a9d8a2c91d408ffb01c2c997e0dca
3
+ size 4997184968
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d065ee711124132ef6f8e89a9b170ec925e8d501d475bcc0ff483a46e82ea7
3
+ size 4997741608
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:501a4b93786b989c93312d72c9a4c7c68762e55eccddace6c4f616837cc98077
3
+ size 4997742208
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90c765a1a36c8e377d0a745de95c292d36af51287ad4c98e9e2ed007fb269982
3
+ size 4997743184
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f732bcecfcb70c09d4670770b335f78f925a20277a4f4ea92c9934f5d1a55f9
3
+ size 4997743184
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23da690f6bd7633a6ae65278fda16e25866b53503b8188e885867492763041a2
3
+ size 4997743184
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63567ba3be762018fbb52d182e0841d3292fba4e7b3e818e4f947674dccbe3c8
3
+ size 4997743184
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:805f11ddd1a84bbb64e0645bc3120a6f3d5672a2af234cab431394cba38a70b4
3
+ size 4997743184
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7063516949d29797aa74a0eb308b8c60962cc42f73c43c69e7a176a370471093
3
+ size 4997743184
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c98409a66d55e54a5c47912745675de2ae9d6a7571936b4ce1892f485cad1eb
3
+ size 4997743184
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6d250b72527c50911e95bba9c0f958684d7582c2a219f776405db57c79f8bb
3
+ size 4997743184
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c3315515be112642990e394f96e6b85a87277cee12288c76f90baf63e677f4
3
+ size 4997743184
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a31fa4fb4fc7c6674001f56c89a5bb351cffbfbe7d2b3a858404efcba76a84eb
3
+ size 1094220288
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and 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.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').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 {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "padding_side": "right",
238
+ "split_special_tokens": false,
239
+ "tokenizer_class": "Qwen2Tokenizer",
240
+ "unk_token": null
241
+ }
trainer_state.json ADDED
@@ -0,0 +1,433 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 57,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.017543859649122806,
14
+ "grad_norm": 2.256555232517452,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.8483,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.03508771929824561,
21
+ "grad_norm": 2.205270245564155,
22
+ "learning_rate": 6.666666666666667e-07,
23
+ "loss": 0.8765,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.05263157894736842,
28
+ "grad_norm": 2.361805594728836,
29
+ "learning_rate": 1.3333333333333334e-06,
30
+ "loss": 1.0209,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.07017543859649122,
35
+ "grad_norm": 2.481606951567156,
36
+ "learning_rate": 2.0000000000000003e-06,
37
+ "loss": 1.062,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.08771929824561403,
42
+ "grad_norm": 1.923229005445868,
43
+ "learning_rate": 2.666666666666667e-06,
44
+ "loss": 0.8564,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.10526315789473684,
49
+ "grad_norm": 2.1103374249725833,
50
+ "learning_rate": 3.3333333333333333e-06,
51
+ "loss": 1.0082,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.12280701754385964,
56
+ "grad_norm": 1.9672661474560547,
57
+ "learning_rate": 4.000000000000001e-06,
58
+ "loss": 0.9978,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.14035087719298245,
63
+ "grad_norm": 1.810080319596374,
64
+ "learning_rate": 4.666666666666667e-06,
65
+ "loss": 0.9468,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.15789473684210525,
70
+ "grad_norm": 2.2501314657852776,
71
+ "learning_rate": 5.333333333333334e-06,
72
+ "loss": 0.9614,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.17543859649122806,
77
+ "grad_norm": 1.3827469830753207,
78
+ "learning_rate": 6e-06,
79
+ "loss": 0.9873,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.19298245614035087,
84
+ "grad_norm": 1.5862884873258083,
85
+ "learning_rate": 6.666666666666667e-06,
86
+ "loss": 1.0305,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.21052631578947367,
91
+ "grad_norm": 1.57454716689858,
92
+ "learning_rate": 7.333333333333333e-06,
93
+ "loss": 0.9006,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.22807017543859648,
98
+ "grad_norm": 1.5638780668313408,
99
+ "learning_rate": 8.000000000000001e-06,
100
+ "loss": 0.936,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.24561403508771928,
105
+ "grad_norm": 1.5588053318143216,
106
+ "learning_rate": 8.666666666666668e-06,
107
+ "loss": 0.9131,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.2631578947368421,
112
+ "grad_norm": 1.2968184983553472,
113
+ "learning_rate": 9.333333333333334e-06,
114
+ "loss": 0.9716,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.2807017543859649,
119
+ "grad_norm": 1.3213006637878912,
120
+ "learning_rate": 1e-05,
121
+ "loss": 0.922,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.2982456140350877,
126
+ "grad_norm": 1.4807190056139585,
127
+ "learning_rate": 9.999661540018812e-06,
128
+ "loss": 1.0189,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.3157894736842105,
133
+ "grad_norm": 1.7897441321489662,
134
+ "learning_rate": 9.99864620589731e-06,
135
+ "loss": 0.903,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.3333333333333333,
140
+ "grad_norm": 1.1554720466501127,
141
+ "learning_rate": 9.99695413509548e-06,
142
+ "loss": 0.9231,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.3508771929824561,
147
+ "grad_norm": 1.0430048166465928,
148
+ "learning_rate": 9.994585556692624e-06,
149
+ "loss": 0.9584,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.3684210526315789,
154
+ "grad_norm": 0.8734173643171832,
155
+ "learning_rate": 9.991540791356342e-06,
156
+ "loss": 0.8954,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.38596491228070173,
161
+ "grad_norm": 0.8505715098348454,
162
+ "learning_rate": 9.987820251299121e-06,
163
+ "loss": 0.7634,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.40350877192982454,
168
+ "grad_norm": 0.932431362896424,
169
+ "learning_rate": 9.98342444022253e-06,
170
+ "loss": 0.8972,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.42105263157894735,
175
+ "grad_norm": 0.994313791348145,
176
+ "learning_rate": 9.978353953249023e-06,
177
+ "loss": 0.7951,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.43859649122807015,
182
+ "grad_norm": 0.8497211408850255,
183
+ "learning_rate": 9.972609476841368e-06,
184
+ "loss": 0.9234,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.45614035087719296,
189
+ "grad_norm": 0.9190618422149534,
190
+ "learning_rate": 9.966191788709716e-06,
191
+ "loss": 0.8877,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.47368421052631576,
196
+ "grad_norm": 0.8415994406297493,
197
+ "learning_rate": 9.959101757706308e-06,
198
+ "loss": 0.8086,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.49122807017543857,
203
+ "grad_norm": 0.742782382735312,
204
+ "learning_rate": 9.951340343707852e-06,
205
+ "loss": 0.8769,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.5087719298245614,
210
+ "grad_norm": 0.6160964124153906,
211
+ "learning_rate": 9.942908597485558e-06,
212
+ "loss": 0.8978,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.5263157894736842,
217
+ "grad_norm": 0.5976609614605858,
218
+ "learning_rate": 9.933807660562898e-06,
219
+ "loss": 0.7837,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.543859649122807,
224
+ "grad_norm": 0.5560568208246192,
225
+ "learning_rate": 9.924038765061042e-06,
226
+ "loss": 0.8396,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.5614035087719298,
231
+ "grad_norm": 0.5836679513268156,
232
+ "learning_rate": 9.913603233532067e-06,
233
+ "loss": 0.7701,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.5789473684210527,
238
+ "grad_norm": 0.7645333976719451,
239
+ "learning_rate": 9.902502478779897e-06,
240
+ "loss": 0.8688,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.5964912280701754,
245
+ "grad_norm": 0.7612685741039715,
246
+ "learning_rate": 9.890738003669029e-06,
247
+ "loss": 0.9675,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.6140350877192983,
252
+ "grad_norm": 0.6672122472693547,
253
+ "learning_rate": 9.878311400921072e-06,
254
+ "loss": 0.8122,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.631578947368421,
259
+ "grad_norm": 0.6198318849807769,
260
+ "learning_rate": 9.86522435289912e-06,
261
+ "loss": 0.8276,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.6491228070175439,
266
+ "grad_norm": 0.5915273774198798,
267
+ "learning_rate": 9.851478631379982e-06,
268
+ "loss": 0.862,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.6666666666666666,
273
+ "grad_norm": 0.7597701986857002,
274
+ "learning_rate": 9.83707609731432e-06,
275
+ "loss": 0.8755,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.6842105263157895,
280
+ "grad_norm": 0.6165755211119401,
281
+ "learning_rate": 9.822018700574696e-06,
282
+ "loss": 0.898,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.7017543859649122,
287
+ "grad_norm": 0.546722974197266,
288
+ "learning_rate": 9.806308479691595e-06,
289
+ "loss": 0.8637,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.7192982456140351,
294
+ "grad_norm": 0.5624327518167074,
295
+ "learning_rate": 9.789947561577445e-06,
296
+ "loss": 0.8685,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.7368421052631579,
301
+ "grad_norm": 0.5747062370239466,
302
+ "learning_rate": 9.77293816123866e-06,
303
+ "loss": 0.8039,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.7543859649122807,
308
+ "grad_norm": 0.5540954371595526,
309
+ "learning_rate": 9.755282581475769e-06,
310
+ "loss": 0.8365,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.7719298245614035,
315
+ "grad_norm": 0.5678372679311994,
316
+ "learning_rate": 9.736983212571646e-06,
317
+ "loss": 0.7528,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.7894736842105263,
322
+ "grad_norm": 0.5498130339645014,
323
+ "learning_rate": 9.718042531967918e-06,
324
+ "loss": 0.8692,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.8070175438596491,
329
+ "grad_norm": 0.723915088763488,
330
+ "learning_rate": 9.698463103929542e-06,
331
+ "loss": 0.8465,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.8245614035087719,
336
+ "grad_norm": 0.5693533968278255,
337
+ "learning_rate": 9.678247579197658e-06,
338
+ "loss": 0.8505,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.8421052631578947,
343
+ "grad_norm": 0.444847109914399,
344
+ "learning_rate": 9.657398694630713e-06,
345
+ "loss": 0.8346,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.8596491228070176,
350
+ "grad_norm": 0.5481527250136425,
351
+ "learning_rate": 9.635919272833938e-06,
352
+ "loss": 0.9264,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.8771929824561403,
357
+ "grad_norm": 0.4850156760944371,
358
+ "learning_rate": 9.613812221777212e-06,
359
+ "loss": 0.6667,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.8947368421052632,
364
+ "grad_norm": 0.5196718609108957,
365
+ "learning_rate": 9.591080534401371e-06,
366
+ "loss": 0.8957,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.9122807017543859,
371
+ "grad_norm": 0.5280436158388971,
372
+ "learning_rate": 9.567727288213005e-06,
373
+ "loss": 0.8639,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.9298245614035088,
378
+ "grad_norm": 0.5997684565130753,
379
+ "learning_rate": 9.543755644867823e-06,
380
+ "loss": 0.8164,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.9473684210526315,
385
+ "grad_norm": 0.5103541862955409,
386
+ "learning_rate": 9.519168849742603e-06,
387
+ "loss": 0.7713,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.9649122807017544,
392
+ "grad_norm": 0.5148641741360179,
393
+ "learning_rate": 9.493970231495836e-06,
394
+ "loss": 0.8101,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.9824561403508771,
399
+ "grad_norm": 0.46692510221358374,
400
+ "learning_rate": 9.468163201617063e-06,
401
+ "loss": 0.8216,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 1.0,
406
+ "grad_norm": 0.666709235115788,
407
+ "learning_rate": 9.441751253965022e-06,
408
+ "loss": 0.7334,
409
+ "step": 57
410
+ }
411
+ ],
412
+ "logging_steps": 1,
413
+ "max_steps": 285,
414
+ "num_input_tokens_seen": 0,
415
+ "num_train_epochs": 5,
416
+ "save_steps": 500,
417
+ "stateful_callbacks": {
418
+ "TrainerControl": {
419
+ "args": {
420
+ "should_epoch_stop": false,
421
+ "should_evaluate": false,
422
+ "should_log": false,
423
+ "should_save": true,
424
+ "should_training_stop": false
425
+ },
426
+ "attributes": {}
427
+ }
428
+ },
429
+ "total_flos": 13124895178752.0,
430
+ "train_batch_size": 2,
431
+ "trial_name": null,
432
+ "trial_params": null
433
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500a0c487f3ed048130f19df6cf26d355285f45b7f94f5d1f95a37b6bd9ace10
3
+ size 8081
vocab.json ADDED
The diff for this file is too large to render. See raw diff