fengyao1909 commited on
Commit
ea23c13
·
verified ·
1 Parent(s): 28f6f8b

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
+ }
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 %}
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": "4.52.0.dev0",
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": "4.52.0.dev0"
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:b6edba9bbeccb3e931db4735c9015c163eb25c2a712bf3af6c1018da4302233b
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:d81c449f9b67c1a2df0127195d08f2e797c084b4c787c8f46fdb01ef9b1e16f2
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:bae47680b03d19badc9113aef3db013b041dab7e2502a28b5adc4391e984858d
3
+ size 4997742208
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1581646182357e007f26a4410488b597242c10f737d6f026b9f912db1b3467
3
+ size 4997743184
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24fe9a3affa483f00385859a5a3042bd250a068f5e5b4841c11dc6bbd5f6a4b6
3
+ size 4997743184
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d0f1835e014aa5067f9c73c47ef1c464370d4e60a594799cdcdd538b9eb74db
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:e82e12fae00a395bdd0a1b42339245272957f88f41749861a35a1aecd86050ef
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:b39e975751c9162bff8c8ac336432f261f00e02ae2234699cbccc5db0abed0f7
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:e4f88ca74b7463e2beaf1305858e520635074d06c045057caccd91476355c247
3
+ size 4997743184
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:209f711d8af0c56da0f0446199e089619b221978c1b95aa28f6471491a8572a7
3
+ size 4997743184
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd247964026c0ae0bad785569dd4dfd0783220e8f1889e9861e93980c36772f
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:c906c2335dcec81fafb33ec4d13682d7995c7046a4b3c2a743e5f80f5a5351fe
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:b3f702ea8c0aa09fcbfc340b3d18f0e829ec0b127137148c70292756a6bff0ee
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 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
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": 2.1737315354989266,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.8483,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.03508771929824561,
21
+ "grad_norm": 2.0657831287103607,
22
+ "learning_rate": 3.3333333333333333e-06,
23
+ "loss": 0.8763,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.05263157894736842,
28
+ "grad_norm": 2.2705565927471225,
29
+ "learning_rate": 6.666666666666667e-06,
30
+ "loss": 1.019,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.07017543859649122,
35
+ "grad_norm": 1.8847905520566954,
36
+ "learning_rate": 1e-05,
37
+ "loss": 1.0442,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.08771929824561403,
42
+ "grad_norm": 1.6215868467951315,
43
+ "learning_rate": 1.3333333333333333e-05,
44
+ "loss": 0.8301,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.10526315789473684,
49
+ "grad_norm": 1.3337654525321527,
50
+ "learning_rate": 1.6666666666666667e-05,
51
+ "loss": 0.967,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.12280701754385964,
56
+ "grad_norm": 2.3177821608360234,
57
+ "learning_rate": 2e-05,
58
+ "loss": 0.9657,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.14035087719298245,
63
+ "grad_norm": 1.9407807377668538,
64
+ "learning_rate": 2.3333333333333336e-05,
65
+ "loss": 0.9063,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.15789473684210525,
70
+ "grad_norm": 2.333688544412328,
71
+ "learning_rate": 2.6666666666666667e-05,
72
+ "loss": 0.9327,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.17543859649122806,
77
+ "grad_norm": 1.8911158364164133,
78
+ "learning_rate": 3e-05,
79
+ "loss": 0.9615,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.19298245614035087,
84
+ "grad_norm": 1.559026746068459,
85
+ "learning_rate": 3.3333333333333335e-05,
86
+ "loss": 0.9983,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.21052631578947367,
91
+ "grad_norm": 1.0012950206512936,
92
+ "learning_rate": 3.6666666666666666e-05,
93
+ "loss": 0.8713,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.22807017543859648,
98
+ "grad_norm": 1.0896746007190306,
99
+ "learning_rate": 4e-05,
100
+ "loss": 0.9018,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.24561403508771928,
105
+ "grad_norm": 1.1472331615890097,
106
+ "learning_rate": 4.3333333333333334e-05,
107
+ "loss": 0.8905,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.2631578947368421,
112
+ "grad_norm": 1.0827434164812821,
113
+ "learning_rate": 4.666666666666667e-05,
114
+ "loss": 0.9487,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.2807017543859649,
119
+ "grad_norm": 0.8407939026078357,
120
+ "learning_rate": 5e-05,
121
+ "loss": 0.9016,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.2982456140350877,
126
+ "grad_norm": 1.256351670462119,
127
+ "learning_rate": 4.999830770009406e-05,
128
+ "loss": 1.0016,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.3157894736842105,
133
+ "grad_norm": 1.010708781438488,
134
+ "learning_rate": 4.9993231029486544e-05,
135
+ "loss": 0.8827,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.3333333333333333,
140
+ "grad_norm": 0.7503718658890081,
141
+ "learning_rate": 4.99847706754774e-05,
142
+ "loss": 0.9054,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.3508771929824561,
147
+ "grad_norm": 0.8427918773123176,
148
+ "learning_rate": 4.997292778346312e-05,
149
+ "loss": 0.9468,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.3684210526315789,
154
+ "grad_norm": 0.9103198542357233,
155
+ "learning_rate": 4.995770395678171e-05,
156
+ "loss": 0.8832,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.38596491228070173,
161
+ "grad_norm": 0.743975757226857,
162
+ "learning_rate": 4.993910125649561e-05,
163
+ "loss": 0.7529,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.40350877192982454,
168
+ "grad_norm": 0.8055578797506145,
169
+ "learning_rate": 4.9917122201112656e-05,
170
+ "loss": 0.889,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.42105263157894735,
175
+ "grad_norm": 0.8546590892160185,
176
+ "learning_rate": 4.989176976624511e-05,
177
+ "loss": 0.7896,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.43859649122807015,
182
+ "grad_norm": 0.6051439965679499,
183
+ "learning_rate": 4.9863047384206835e-05,
184
+ "loss": 0.9219,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.45614035087719296,
189
+ "grad_norm": 0.7522440995111975,
190
+ "learning_rate": 4.983095894354858e-05,
191
+ "loss": 0.8917,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.47368421052631576,
196
+ "grad_norm": 0.7072008972448397,
197
+ "learning_rate": 4.979550878853154e-05,
198
+ "loss": 0.8044,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.49122807017543857,
203
+ "grad_norm": 0.5952822120665937,
204
+ "learning_rate": 4.975670171853926e-05,
205
+ "loss": 0.8763,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.5087719298245614,
210
+ "grad_norm": 0.5803355862918257,
211
+ "learning_rate": 4.971454298742779e-05,
212
+ "loss": 0.8983,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.5263157894736842,
217
+ "grad_norm": 0.666437418274057,
218
+ "learning_rate": 4.966903830281449e-05,
219
+ "loss": 0.7866,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.543859649122807,
224
+ "grad_norm": 0.6919189164588267,
225
+ "learning_rate": 4.962019382530521e-05,
226
+ "loss": 0.8412,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.5614035087719298,
231
+ "grad_norm": 0.5772289061045422,
232
+ "learning_rate": 4.9568016167660334e-05,
233
+ "loss": 0.7779,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.5789473684210527,
238
+ "grad_norm": 0.6384456727598309,
239
+ "learning_rate": 4.951251239389948e-05,
240
+ "loss": 0.8722,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.5964912280701754,
245
+ "grad_norm": 0.7003155529960633,
246
+ "learning_rate": 4.9453690018345144e-05,
247
+ "loss": 0.9772,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.6140350877192983,
252
+ "grad_norm": 0.5892482774139678,
253
+ "learning_rate": 4.939155700460536e-05,
254
+ "loss": 0.8181,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.631578947368421,
259
+ "grad_norm": 0.7141350627505272,
260
+ "learning_rate": 4.9326121764495596e-05,
261
+ "loss": 0.8379,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.6491228070175439,
266
+ "grad_norm": 0.6685379755417092,
267
+ "learning_rate": 4.925739315689991e-05,
268
+ "loss": 0.876,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.6666666666666666,
273
+ "grad_norm": 0.5887972405354546,
274
+ "learning_rate": 4.9185380486571595e-05,
275
+ "loss": 0.8834,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.6842105263157895,
280
+ "grad_norm": 0.6547850047970274,
281
+ "learning_rate": 4.9110093502873476e-05,
282
+ "loss": 0.9068,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.7017543859649122,
287
+ "grad_norm": 0.5095372843368391,
288
+ "learning_rate": 4.9031542398457974e-05,
289
+ "loss": 0.871,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.7192982456140351,
294
+ "grad_norm": 0.5803092931334194,
295
+ "learning_rate": 4.894973780788722e-05,
296
+ "loss": 0.8804,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.7368421052631579,
301
+ "grad_norm": 0.5157094405208372,
302
+ "learning_rate": 4.88646908061933e-05,
303
+ "loss": 0.8112,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.7543859649122807,
308
+ "grad_norm": 0.5763799658576816,
309
+ "learning_rate": 4.877641290737884e-05,
310
+ "loss": 0.8485,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.7719298245614035,
315
+ "grad_norm": 0.5206239155896253,
316
+ "learning_rate": 4.868491606285823e-05,
317
+ "loss": 0.7658,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.7894736842105263,
322
+ "grad_norm": 0.5163119284367372,
323
+ "learning_rate": 4.859021265983959e-05,
324
+ "loss": 0.8806,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.8070175438596491,
329
+ "grad_norm": 0.5555872744357858,
330
+ "learning_rate": 4.849231551964771e-05,
331
+ "loss": 0.8559,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.8245614035087719,
336
+ "grad_norm": 0.670329020537153,
337
+ "learning_rate": 4.839123789598829e-05,
338
+ "loss": 0.8667,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.8421052631578947,
343
+ "grad_norm": 0.5517318833150326,
344
+ "learning_rate": 4.828699347315356e-05,
345
+ "loss": 0.8424,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.8596491228070176,
350
+ "grad_norm": 0.6399166130889407,
351
+ "learning_rate": 4.817959636416969e-05,
352
+ "loss": 0.9417,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.8771929824561403,
357
+ "grad_norm": 0.460883037522045,
358
+ "learning_rate": 4.806906110888606e-05,
359
+ "loss": 0.6751,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.8947368421052632,
364
+ "grad_norm": 0.6278603703151171,
365
+ "learning_rate": 4.7955402672006854e-05,
366
+ "loss": 0.9086,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.9122807017543859,
371
+ "grad_norm": 0.5482062880943421,
372
+ "learning_rate": 4.783863644106502e-05,
373
+ "loss": 0.8832,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.9298245614035088,
378
+ "grad_norm": 0.5538960900799985,
379
+ "learning_rate": 4.771877822433911e-05,
380
+ "loss": 0.8332,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.9473684210526315,
385
+ "grad_norm": 0.5020357523197391,
386
+ "learning_rate": 4.759584424871302e-05,
387
+ "loss": 0.7833,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.9649122807017544,
392
+ "grad_norm": 0.5299810912852558,
393
+ "learning_rate": 4.7469851157479177e-05,
394
+ "loss": 0.8219,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.9824561403508771,
399
+ "grad_norm": 0.48572413576489937,
400
+ "learning_rate": 4.734081600808531e-05,
401
+ "loss": 0.8327,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 1.0,
406
+ "grad_norm": 0.7694567676131596,
407
+ "learning_rate": 4.7208756269825104e-05,
408
+ "loss": 0.6932,
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:d83b4df5d706e4c8bc431f088d2170998a3a8eafe51554ccb621ba77c95afe02
3
+ size 8017
vocab.json ADDED
The diff for this file is too large to render. See raw diff