suronek commited on
Commit
6eeada2
·
verified ·
1 Parent(s): 79d9ab5

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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<|end_of_audio|>": 151670,
11
+ "<|endoftext|>": 151643,
12
+ "<|file_sep|>": 151664,
13
+ "<|fim_middle|>": 151660,
14
+ "<|fim_pad|>": 151662,
15
+ "<|fim_prefix|>": 151659,
16
+ "<|fim_suffix|>": 151661,
17
+ "<|im_end|>": 151645,
18
+ "<|im_start|>": 151644,
19
+ "<|image_pad|>": 151655,
20
+ "<|object_ref_end|>": 151647,
21
+ "<|object_ref_start|>": 151646,
22
+ "<|quad_end|>": 151651,
23
+ "<|quad_start|>": 151650,
24
+ "<|repo_name|>": 151663,
25
+ "<|start_of_audio|>": 151669,
26
+ "<|video_pad|>": 151656,
27
+ "<|vision_end|>": 151653,
28
+ "<|vision_pad|>": 151654,
29
+ "<|vision_start|>": 151652
30
+ }
chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 message.content is string 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.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "max_position_embeddings": 40960,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.52.3",
27
+ "use_cache": false,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 160887
30
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.52.3"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:160296b715238a5369f95734098dbddff0ebc0b30ca23aa944ae022b64df044c
3
+ size 2420898288
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c531e03074d6ff61fb3dd9229a537152606b0a53661b4cc48b815ea1fae06286
3
+ size 4841990063
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53815716d3e48b6f71e9b4d4bcd8a55472510eed26912a0830245ba37e378c5e
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|start_of_audio|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|end_of_audio|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "eos_token": {
19
+ "content": "<|im_end|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce343df1fa48177ef1579eb8bdd0c816ed20d1df03de865100154d21d7630b9
3
+ size 11423042
tokenizer_config.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151669": {
214
+ "content": "<|start_of_audio|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|end_of_audio|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ }
229
+ },
230
+ "additional_special_tokens": [
231
+ "<|start_of_audio|>",
232
+ "<|end_of_audio|>"
233
+ ],
234
+ "bos_token": null,
235
+ "clean_up_tokenization_spaces": false,
236
+ "eos_token": "<|im_end|>",
237
+ "errors": "replace",
238
+ "extra_special_tokens": {},
239
+ "model_max_length": 131072,
240
+ "pad_token": "<|endoftext|>",
241
+ "split_special_tokens": false,
242
+ "tokenizer_class": "Qwen2Tokenizer",
243
+ "unk_token": null
244
+ }
trainer_state.json ADDED
@@ -0,0 +1,594 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 3000000,
7
+ "global_step": 4000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.05,
14
+ "grad_norm": 8.035335540771484,
15
+ "learning_rate": 4.9000000000000005e-06,
16
+ "loss": 16.0021,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.1,
21
+ "grad_norm": 3.2025396823883057,
22
+ "learning_rate": 9.900000000000002e-06,
23
+ "loss": 11.7989,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.15,
28
+ "grad_norm": 5.469916343688965,
29
+ "learning_rate": 1.49e-05,
30
+ "loss": 9.9388,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.2,
35
+ "grad_norm": 3.80522084236145,
36
+ "learning_rate": 1.9900000000000003e-05,
37
+ "loss": 8.7777,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.25,
42
+ "grad_norm": 4.427011489868164,
43
+ "learning_rate": 2.4900000000000002e-05,
44
+ "loss": 8.6873,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.3,
49
+ "grad_norm": 5.7454729080200195,
50
+ "learning_rate": 2.9900000000000002e-05,
51
+ "loss": 8.5648,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.35,
56
+ "grad_norm": 4.743438243865967,
57
+ "learning_rate": 3.49e-05,
58
+ "loss": 8.5079,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.4,
63
+ "grad_norm": 3.474597692489624,
64
+ "learning_rate": 3.99e-05,
65
+ "loss": 8.3968,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.45,
70
+ "grad_norm": 3.122760057449341,
71
+ "learning_rate": 4.49e-05,
72
+ "loss": 8.3451,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.5,
77
+ "grad_norm": 3.2466609477996826,
78
+ "learning_rate": 4.99e-05,
79
+ "loss": 8.3122,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.55,
84
+ "grad_norm": 2.5408895015716553,
85
+ "learning_rate": 5.4900000000000006e-05,
86
+ "loss": 8.2392,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.6,
91
+ "grad_norm": 2.5975348949432373,
92
+ "learning_rate": 5.99e-05,
93
+ "loss": 8.2285,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.65,
98
+ "grad_norm": 2.831303119659424,
99
+ "learning_rate": 6.49e-05,
100
+ "loss": 8.1835,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.7,
105
+ "grad_norm": 3.5038204193115234,
106
+ "learning_rate": 6.99e-05,
107
+ "loss": 8.1615,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.75,
112
+ "grad_norm": 2.9863946437835693,
113
+ "learning_rate": 7.49e-05,
114
+ "loss": 8.1137,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.8,
119
+ "grad_norm": 2.347724199295044,
120
+ "learning_rate": 7.99e-05,
121
+ "loss": 8.0958,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.85,
126
+ "grad_norm": 3.1746554374694824,
127
+ "learning_rate": 8.49e-05,
128
+ "loss": 8.0378,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.9,
133
+ "grad_norm": 2.7106034755706787,
134
+ "learning_rate": 8.99e-05,
135
+ "loss": 7.9869,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.95,
140
+ "grad_norm": 3.2794389724731445,
141
+ "learning_rate": 9.49e-05,
142
+ "loss": 7.9442,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 1.0,
147
+ "grad_norm": 2.6159002780914307,
148
+ "learning_rate": 9.99e-05,
149
+ "loss": 7.8942,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 1.05,
154
+ "grad_norm": 3.0335867404937744,
155
+ "learning_rate": 9.993418966349552e-05,
156
+ "loss": 7.8272,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 1.1,
161
+ "grad_norm": 2.989114284515381,
162
+ "learning_rate": 9.973154059957162e-05,
163
+ "loss": 7.781,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 1.15,
168
+ "grad_norm": 3.0559637546539307,
169
+ "learning_rate": 9.939258083966131e-05,
170
+ "loss": 7.6838,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 1.2,
175
+ "grad_norm": 3.375070333480835,
176
+ "learning_rate": 9.891823944890568e-05,
177
+ "loss": 7.6586,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 1.25,
182
+ "grad_norm": 3.245753765106201,
183
+ "learning_rate": 9.830981656408574e-05,
184
+ "loss": 7.5777,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 1.3,
189
+ "grad_norm": 3.38423490524292,
190
+ "learning_rate": 9.756897983003781e-05,
191
+ "loss": 7.5712,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 1.35,
196
+ "grad_norm": 3.217186450958252,
197
+ "learning_rate": 9.669775982875501e-05,
198
+ "loss": 7.521,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 1.4,
203
+ "grad_norm": 2.6598784923553467,
204
+ "learning_rate": 9.569854451370307e-05,
205
+ "loss": 7.4534,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 1.45,
210
+ "grad_norm": 2.918971538543701,
211
+ "learning_rate": 9.457407266460593e-05,
212
+ "loss": 7.4229,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 1.5,
217
+ "grad_norm": 2.9795620441436768,
218
+ "learning_rate": 9.332742638064094e-05,
219
+ "loss": 7.3647,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 1.55,
224
+ "grad_norm": 3.4413418769836426,
225
+ "learning_rate": 9.196202263261908e-05,
226
+ "loss": 7.3395,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 1.6,
231
+ "grad_norm": 3.182359457015991,
232
+ "learning_rate": 9.048160389730566e-05,
233
+ "loss": 7.2376,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 1.65,
238
+ "grad_norm": 3.3175110816955566,
239
+ "learning_rate": 8.889022789955151e-05,
240
+ "loss": 7.1911,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 1.7,
245
+ "grad_norm": 3.779966115951538,
246
+ "learning_rate": 8.719225649035126e-05,
247
+ "loss": 7.1294,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 1.75,
252
+ "grad_norm": 2.8523356914520264,
253
+ "learning_rate": 8.539234369131301e-05,
254
+ "loss": 7.1159,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 1.8,
259
+ "grad_norm": 2.963099718093872,
260
+ "learning_rate": 8.349542293830855e-05,
261
+ "loss": 7.1048,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 1.85,
266
+ "grad_norm": 3.024153709411621,
267
+ "learning_rate": 8.150669355926846e-05,
268
+ "loss": 7.0825,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 1.9,
273
+ "grad_norm": 3.209059953689575,
274
+ "learning_rate": 7.943160652318585e-05,
275
+ "loss": 7.0283,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 1.95,
280
+ "grad_norm": 3.290492534637451,
281
+ "learning_rate": 7.727584949938907e-05,
282
+ "loss": 6.9917,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 2.0,
287
+ "grad_norm": 3.3375489711761475,
288
+ "learning_rate": 7.50453312680355e-05,
289
+ "loss": 6.9781,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 2.05,
294
+ "grad_norm": 3.0947234630584717,
295
+ "learning_rate": 7.274616552455589e-05,
296
+ "loss": 6.7171,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 2.1,
301
+ "grad_norm": 3.1351561546325684,
302
+ "learning_rate": 7.038465412244005e-05,
303
+ "loss": 6.6982,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 2.15,
308
+ "grad_norm": 2.8325936794281006,
309
+ "learning_rate": 6.796726980029454e-05,
310
+ "loss": 6.6705,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 2.2,
315
+ "grad_norm": 2.9807379245758057,
316
+ "learning_rate": 6.550063844051602e-05,
317
+ "loss": 6.6216,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 2.25,
322
+ "grad_norm": 3.3993475437164307,
323
+ "learning_rate": 6.299152090820823e-05,
324
+ "loss": 6.6907,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 2.3,
329
+ "grad_norm": 3.0729660987854004,
330
+ "learning_rate": 6.0446794520120584e-05,
331
+ "loss": 6.656,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 2.35,
336
+ "grad_norm": 3.3945727348327637,
337
+ "learning_rate": 5.7873434194401075e-05,
338
+ "loss": 6.5754,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 2.4,
343
+ "grad_norm": 2.8936164379119873,
344
+ "learning_rate": 5.527849333283042e-05,
345
+ "loss": 6.5908,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 2.45,
350
+ "grad_norm": 2.975008726119995,
351
+ "learning_rate": 5.266908448793803e-05,
352
+ "loss": 6.6343,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 2.5,
357
+ "grad_norm": 3.347289562225342,
358
+ "learning_rate": 5.005235986799001e-05,
359
+ "loss": 6.5862,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 2.55,
364
+ "grad_norm": 2.952772855758667,
365
+ "learning_rate": 4.74354917332833e-05,
366
+ "loss": 6.5569,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 2.6,
371
+ "grad_norm": 3.5185999870300293,
372
+ "learning_rate": 4.482565273747888e-05,
373
+ "loss": 6.5634,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 2.65,
378
+ "grad_norm": 2.8772964477539062,
379
+ "learning_rate": 4.2229996267856575e-05,
380
+ "loss": 6.5668,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 2.7,
385
+ "grad_norm": 3.22186017036438,
386
+ "learning_rate": 3.965563683837771e-05,
387
+ "loss": 6.4839,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 2.75,
392
+ "grad_norm": 2.703218698501587,
393
+ "learning_rate": 3.710963058929701e-05,
394
+ "loss": 6.5085,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 2.8,
399
+ "grad_norm": 3.1132938861846924,
400
+ "learning_rate": 3.459895594677245e-05,
401
+ "loss": 6.4878,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 2.85,
406
+ "grad_norm": 3.200667142868042,
407
+ "learning_rate": 3.213049449548434e-05,
408
+ "loss": 6.5189,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 2.9,
413
+ "grad_norm": 3.354769706726074,
414
+ "learning_rate": 2.9711012116690007e-05,
415
+ "loss": 6.4618,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 2.95,
420
+ "grad_norm": 3.7024643421173096,
421
+ "learning_rate": 2.7347140443413586e-05,
422
+ "loss": 6.4558,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 3.0,
427
+ "grad_norm": 3.4147415161132812,
428
+ "learning_rate": 2.5045358683600777e-05,
429
+ "loss": 6.4197,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 3.05,
434
+ "grad_norm": 3.2569174766540527,
435
+ "learning_rate": 2.2811975861060368e-05,
436
+ "loss": 5.9713,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 3.1,
441
+ "grad_norm": 3.3880231380462646,
442
+ "learning_rate": 2.0653113522868427e-05,
443
+ "loss": 5.9546,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 3.15,
448
+ "grad_norm": 3.1022253036499023,
449
+ "learning_rate": 1.8574688960633236e-05,
450
+ "loss": 5.9486,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 3.2,
455
+ "grad_norm": 4.635429859161377,
456
+ "learning_rate": 1.658239899161036e-05,
457
+ "loss": 5.9381,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 3.25,
462
+ "grad_norm": 3.528841018676758,
463
+ "learning_rate": 1.46817043441225e-05,
464
+ "loss": 5.9397,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 3.3,
469
+ "grad_norm": 3.5614097118377686,
470
+ "learning_rate": 1.287781469008278e-05,
471
+ "loss": 5.9239,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 3.35,
476
+ "grad_norm": 3.1929736137390137,
477
+ "learning_rate": 1.1175674365646066e-05,
478
+ "loss": 5.9359,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 3.4,
483
+ "grad_norm": 4.042356491088867,
484
+ "learning_rate": 9.57994881912735e-06,
485
+ "loss": 5.9449,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 3.45,
490
+ "grad_norm": 2.7140910625457764,
491
+ "learning_rate": 8.095011823332088e-06,
492
+ "loss": 5.9141,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 3.5,
497
+ "grad_norm": 3.853717088699341,
498
+ "learning_rate": 6.724933487349061e-06,
499
+ "loss": 5.9082,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 3.55,
504
+ "grad_norm": 3.227409601211548,
505
+ "learning_rate": 5.473469100664208e-06,
506
+ "loss": 5.9448,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 3.6,
511
+ "grad_norm": 3.2171592712402344,
512
+ "learning_rate": 4.344048840173226e-06,
513
+ "loss": 5.9231,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 3.65,
518
+ "grad_norm": 3.918410062789917,
519
+ "learning_rate": 3.3397683683050685e-06,
520
+ "loss": 5.9002,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 3.7,
525
+ "grad_norm": 3.0018346309661865,
526
+ "learning_rate": 2.463380348026467e-06,
527
+ "loss": 5.9103,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 3.75,
532
+ "grad_norm": 3.285499095916748,
533
+ "learning_rate": 1.717286897983994e-06,
534
+ "loss": 5.8914,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 3.8,
539
+ "grad_norm": 2.93095326423645,
540
+ "learning_rate": 1.1035330084639083e-06,
541
+ "loss": 5.8821,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 3.85,
546
+ "grad_norm": 3.3520541191101074,
547
+ "learning_rate": 6.238009362158792e-07,
548
+ "loss": 5.866,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 3.9,
553
+ "grad_norm": 3.089460611343384,
554
+ "learning_rate": 2.794055935041673e-07,
555
+ "loss": 5.8507,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 3.95,
560
+ "grad_norm": 3.6881203651428223,
561
+ "learning_rate": 7.129094402451575e-08,
562
+ "loss": 5.9283,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 4.0,
567
+ "grad_norm": 3.249002695083618,
568
+ "learning_rate": 2.741556527352529e-11,
569
+ "loss": 5.8472,
570
+ "step": 4000
571
+ }
572
+ ],
573
+ "logging_steps": 50,
574
+ "max_steps": 4000,
575
+ "num_input_tokens_seen": 0,
576
+ "num_train_epochs": 4,
577
+ "save_steps": 3000000,
578
+ "stateful_callbacks": {
579
+ "TrainerControl": {
580
+ "args": {
581
+ "should_epoch_stop": false,
582
+ "should_evaluate": false,
583
+ "should_log": false,
584
+ "should_save": true,
585
+ "should_training_stop": true
586
+ },
587
+ "attributes": {}
588
+ }
589
+ },
590
+ "total_flos": 4.337671883902157e+16,
591
+ "train_batch_size": 6,
592
+ "trial_name": null,
593
+ "trial_params": null
594
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00dac8af05391458901d796183a7922d9983e20275de020d96f10a395e76066f
3
+ size 5713
vocab.json ADDED
The diff for this file is too large to render. See raw diff