fengyao1909 commited on
Commit
517feef
·
verified ·
1 Parent(s): 86f25ee

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 sha256:34179c8d074e906e62bc7a4d4e8cde4c014ec52f0b674462226fc9fddd521eae
3
+ size 4997184968
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05820b8afdbd400489d7dd317a0ec1c7cacee4a8979574b23825cee18f94348e
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:b973365e82b9adeaf8684c40a3efb0cd764044be04cc1b9f130b89db013f7150
3
+ size 4997742208
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77f7ec1d08f5ea13941e70342aaf7179aa0456ae277f71190080c7f0a918104f
3
+ size 4997743184
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d88feaf964c3ad86855193b388be933d8cb1979403405bb5cb1b708a244fc3
3
+ size 4997743184
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:290da9eda391e715947aec8f23cf855a1e2d129e55a39a09a324af3db2471853
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:d575b9cca59328bdc27a6abee60e99b17d3ff84559f91a60a575e1a5de7dc127
3
+ size 4997743184
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:378ce967fbf4d632f69442cd382d98baaf51b20aa6cd706ce470236d6536120e
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:c903276a0367f1762f7be9b0af8e00893b08788e0fa6e080b505997bcef0d698
3
+ size 4997743184
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510c787d1c1d5776d877ef59476c3b1e13ed8f4380ee9434e90d6ac4a9202485
3
+ size 4997743184
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49fab6f2028613b8048fc9e4b877759944993a404da541ff0e9e565dcd146dda
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:f2ff0a897dcc7488c77c057bc953c9c2d9f941c5a36739330e13cb968cdd47b3
3
+ size 4997743184
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33414e83113b6bb01398ad2b414588173dcf9c29c63f27fcc29f32db0ef88a3c
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 +1,916 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 126,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015873015873015872,
14
+ "grad_norm": 2.355871594757968,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.0469,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.031746031746031744,
21
+ "grad_norm": 2.29666205825573,
22
+ "learning_rate": 1.5625e-06,
23
+ "loss": 0.9929,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.047619047619047616,
28
+ "grad_norm": 2.535252155158116,
29
+ "learning_rate": 3.125e-06,
30
+ "loss": 1.0185,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.06349206349206349,
35
+ "grad_norm": 2.106429965859871,
36
+ "learning_rate": 4.6875000000000004e-06,
37
+ "loss": 0.9046,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.07936507936507936,
42
+ "grad_norm": 1.7754252196610092,
43
+ "learning_rate": 6.25e-06,
44
+ "loss": 1.0312,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.09523809523809523,
49
+ "grad_norm": 1.5212254656019404,
50
+ "learning_rate": 7.8125e-06,
51
+ "loss": 0.9741,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.1111111111111111,
56
+ "grad_norm": 1.2286700272250457,
57
+ "learning_rate": 9.375000000000001e-06,
58
+ "loss": 0.924,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.12698412698412698,
63
+ "grad_norm": 1.239763672997659,
64
+ "learning_rate": 1.09375e-05,
65
+ "loss": 0.9112,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.14285714285714285,
70
+ "grad_norm": 1.7804807603399884,
71
+ "learning_rate": 1.25e-05,
72
+ "loss": 0.9631,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.15873015873015872,
77
+ "grad_norm": 1.6096276860914913,
78
+ "learning_rate": 1.4062500000000001e-05,
79
+ "loss": 0.8914,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.1746031746031746,
84
+ "grad_norm": 1.4685478602306294,
85
+ "learning_rate": 1.5625e-05,
86
+ "loss": 0.8313,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.19047619047619047,
91
+ "grad_norm": 1.797675338951107,
92
+ "learning_rate": 1.71875e-05,
93
+ "loss": 0.9572,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.20634920634920634,
98
+ "grad_norm": 1.5020710264445867,
99
+ "learning_rate": 1.8750000000000002e-05,
100
+ "loss": 0.8929,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.2222222222222222,
105
+ "grad_norm": 1.389913325647765,
106
+ "learning_rate": 2.0312500000000002e-05,
107
+ "loss": 1.0575,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.23809523809523808,
112
+ "grad_norm": 1.0364172775494112,
113
+ "learning_rate": 2.1875e-05,
114
+ "loss": 0.9367,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.25396825396825395,
119
+ "grad_norm": 1.1754008678466592,
120
+ "learning_rate": 2.34375e-05,
121
+ "loss": 1.0082,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.2698412698412698,
126
+ "grad_norm": 1.0227204004003465,
127
+ "learning_rate": 2.5e-05,
128
+ "loss": 0.9148,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.2857142857142857,
133
+ "grad_norm": 1.0820292890536618,
134
+ "learning_rate": 2.6562500000000002e-05,
135
+ "loss": 0.9748,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.30158730158730157,
140
+ "grad_norm": 0.945837076799249,
141
+ "learning_rate": 2.8125000000000003e-05,
142
+ "loss": 0.7132,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.31746031746031744,
147
+ "grad_norm": 1.0248571882025115,
148
+ "learning_rate": 2.96875e-05,
149
+ "loss": 0.8881,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.3333333333333333,
154
+ "grad_norm": 0.7825673389448284,
155
+ "learning_rate": 3.125e-05,
156
+ "loss": 0.9596,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.3492063492063492,
161
+ "grad_norm": 0.9610289643147956,
162
+ "learning_rate": 3.2812500000000005e-05,
163
+ "loss": 1.0261,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.36507936507936506,
168
+ "grad_norm": 0.9669319262880848,
169
+ "learning_rate": 3.4375e-05,
170
+ "loss": 0.8504,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.38095238095238093,
175
+ "grad_norm": 0.7449356400588687,
176
+ "learning_rate": 3.59375e-05,
177
+ "loss": 0.8124,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.3968253968253968,
182
+ "grad_norm": 0.83693613965816,
183
+ "learning_rate": 3.7500000000000003e-05,
184
+ "loss": 1.0061,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.4126984126984127,
189
+ "grad_norm": 0.732383235323442,
190
+ "learning_rate": 3.90625e-05,
191
+ "loss": 0.8433,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.42857142857142855,
196
+ "grad_norm": 0.7794935876422098,
197
+ "learning_rate": 4.0625000000000005e-05,
198
+ "loss": 0.7042,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.4444444444444444,
203
+ "grad_norm": 0.7604958575268047,
204
+ "learning_rate": 4.21875e-05,
205
+ "loss": 0.9629,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.4603174603174603,
210
+ "grad_norm": 0.6984385536231642,
211
+ "learning_rate": 4.375e-05,
212
+ "loss": 0.8909,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.47619047619047616,
217
+ "grad_norm": 0.7941140442495155,
218
+ "learning_rate": 4.5312500000000004e-05,
219
+ "loss": 0.9318,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.49206349206349204,
224
+ "grad_norm": 0.7485507149365567,
225
+ "learning_rate": 4.6875e-05,
226
+ "loss": 0.9032,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.5079365079365079,
231
+ "grad_norm": 0.7312955579208906,
232
+ "learning_rate": 4.8437500000000005e-05,
233
+ "loss": 0.8793,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.5238095238095238,
238
+ "grad_norm": 0.728955139017027,
239
+ "learning_rate": 5e-05,
240
+ "loss": 1.0292,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.5396825396825397,
245
+ "grad_norm": 0.6223071714803796,
246
+ "learning_rate": 4.999845960383972e-05,
247
+ "loss": 0.829,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.5555555555555556,
252
+ "grad_norm": 0.7081482857388056,
253
+ "learning_rate": 4.999383860518451e-05,
254
+ "loss": 0.821,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.5714285714285714,
259
+ "grad_norm": 0.7021438050343367,
260
+ "learning_rate": 4.998613757348784e-05,
261
+ "loss": 0.9658,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.5873015873015873,
266
+ "grad_norm": 0.6005545292155794,
267
+ "learning_rate": 4.9975357457760896e-05,
268
+ "loss": 0.9805,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.6031746031746031,
273
+ "grad_norm": 0.66159765943155,
274
+ "learning_rate": 4.9961499586455584e-05,
275
+ "loss": 0.8479,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.6190476190476191,
280
+ "grad_norm": 0.6859851915992995,
281
+ "learning_rate": 4.994456566730085e-05,
282
+ "loss": 0.9104,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.6349206349206349,
287
+ "grad_norm": 0.5770937588145084,
288
+ "learning_rate": 4.9924557787092216e-05,
289
+ "loss": 0.7705,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.6507936507936508,
294
+ "grad_norm": 0.5587380636863567,
295
+ "learning_rate": 4.990147841143462e-05,
296
+ "loss": 0.8406,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.6666666666666666,
301
+ "grad_norm": 0.5939117737515469,
302
+ "learning_rate": 4.9875330384438604e-05,
303
+ "loss": 0.9143,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.6825396825396826,
308
+ "grad_norm": 0.5421902034671652,
309
+ "learning_rate": 4.984611692836979e-05,
310
+ "loss": 0.8323,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.6984126984126984,
315
+ "grad_norm": 0.5523631282552526,
316
+ "learning_rate": 4.9813841643251836e-05,
317
+ "loss": 0.7557,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.7142857142857143,
322
+ "grad_norm": 0.5991896816540728,
323
+ "learning_rate": 4.977850850642275e-05,
324
+ "loss": 0.8471,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.7301587301587301,
329
+ "grad_norm": 0.6364621652121066,
330
+ "learning_rate": 4.97401218720448e-05,
331
+ "loss": 0.8013,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.746031746031746,
336
+ "grad_norm": 0.5534873919742207,
337
+ "learning_rate": 4.969868647056792e-05,
338
+ "loss": 0.8996,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.7619047619047619,
343
+ "grad_norm": 0.5035034360883922,
344
+ "learning_rate": 4.965420740814679e-05,
345
+ "loss": 0.8944,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.7777777777777778,
350
+ "grad_norm": 0.5729489774574688,
351
+ "learning_rate": 4.9606690166011546e-05,
352
+ "loss": 0.7887,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.7936507936507936,
357
+ "grad_norm": 0.6004405465949967,
358
+ "learning_rate": 4.95561405997924e-05,
359
+ "loss": 0.831,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.8095238095238095,
364
+ "grad_norm": 0.725673276310606,
365
+ "learning_rate": 4.9502564938797946e-05,
366
+ "loss": 0.8849,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.8253968253968254,
371
+ "grad_norm": 0.4990176056299948,
372
+ "learning_rate": 4.9445969785247595e-05,
373
+ "loss": 0.8298,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.8412698412698413,
378
+ "grad_norm": 0.6071056927514447,
379
+ "learning_rate": 4.938636211345792e-05,
380
+ "loss": 0.944,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.8571428571428571,
385
+ "grad_norm": 0.6345636016627114,
386
+ "learning_rate": 4.932374926898321e-05,
387
+ "loss": 0.8069,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.873015873015873,
392
+ "grad_norm": 0.6333202856879505,
393
+ "learning_rate": 4.9258138967710306e-05,
394
+ "loss": 0.7373,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.8888888888888888,
399
+ "grad_norm": 0.5152048396222051,
400
+ "learning_rate": 4.918953929490768e-05,
401
+ "loss": 0.8855,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.9047619047619048,
406
+ "grad_norm": 0.5806639114473304,
407
+ "learning_rate": 4.9117958704229154e-05,
408
+ "loss": 0.8731,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.9206349206349206,
413
+ "grad_norm": 0.6001547400645247,
414
+ "learning_rate": 4.904340601667208e-05,
415
+ "loss": 0.816,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.9365079365079365,
420
+ "grad_norm": 0.470270082255384,
421
+ "learning_rate": 4.8965890419490354e-05,
422
+ "loss": 0.8847,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.9523809523809523,
427
+ "grad_norm": 0.5015222585808989,
428
+ "learning_rate": 4.8885421465062236e-05,
429
+ "loss": 0.8507,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.9682539682539683,
434
+ "grad_norm": 0.48808541077856465,
435
+ "learning_rate": 4.88020090697132e-05,
436
+ "loss": 0.774,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.9841269841269841,
441
+ "grad_norm": 0.5837250225569859,
442
+ "learning_rate": 4.871566351249393e-05,
443
+ "loss": 0.8844,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 1.0,
448
+ "grad_norm": 0.5121395435398158,
449
+ "learning_rate": 4.86263954339136e-05,
450
+ "loss": 0.7565,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 1.0158730158730158,
455
+ "grad_norm": 0.858989786993005,
456
+ "learning_rate": 4.853421583462866e-05,
457
+ "loss": 0.7147,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 1.0317460317460316,
462
+ "grad_norm": 0.6819369439457027,
463
+ "learning_rate": 4.843913607408717e-05,
464
+ "loss": 0.7632,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 1.0476190476190477,
469
+ "grad_norm": 0.8758215098676306,
470
+ "learning_rate": 4.834116786912897e-05,
471
+ "loss": 0.7952,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 1.0634920634920635,
476
+ "grad_norm": 0.5971995504609642,
477
+ "learning_rate": 4.82403232925418e-05,
478
+ "loss": 0.6327,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 1.0793650793650793,
483
+ "grad_norm": 0.5651140794936931,
484
+ "learning_rate": 4.8136614771573554e-05,
485
+ "loss": 0.6429,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 1.0952380952380953,
490
+ "grad_norm": 0.882155318220025,
491
+ "learning_rate": 4.8030055086400826e-05,
492
+ "loss": 0.8083,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 1.1111111111111112,
497
+ "grad_norm": 0.7712424011094504,
498
+ "learning_rate": 4.7920657368554e-05,
499
+ "loss": 0.6792,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 1.126984126984127,
504
+ "grad_norm": 0.5624839067932064,
505
+ "learning_rate": 4.7808435099299045e-05,
506
+ "loss": 0.6928,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 1.1428571428571428,
511
+ "grad_norm": 0.5634668991057131,
512
+ "learning_rate": 4.7693402107976174e-05,
513
+ "loss": 0.7191,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 1.1587301587301586,
518
+ "grad_norm": 0.6557940355672685,
519
+ "learning_rate": 4.757557257029564e-05,
520
+ "loss": 0.7138,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 1.1746031746031746,
525
+ "grad_norm": 0.5576756408219278,
526
+ "learning_rate": 4.745496100659082e-05,
527
+ "loss": 0.6904,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 1.1904761904761905,
532
+ "grad_norm": 0.5394945009236098,
533
+ "learning_rate": 4.7331582280028906e-05,
534
+ "loss": 0.6684,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 1.2063492063492063,
539
+ "grad_norm": 0.5616484225088534,
540
+ "learning_rate": 4.720545159477922e-05,
541
+ "loss": 0.6123,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 1.2222222222222223,
546
+ "grad_norm": 0.6137522865571288,
547
+ "learning_rate": 4.7076584494139606e-05,
548
+ "loss": 0.6639,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 1.2380952380952381,
553
+ "grad_norm": 0.5520563824703866,
554
+ "learning_rate": 4.694499685862106e-05,
555
+ "loss": 0.7504,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 1.253968253968254,
560
+ "grad_norm": 0.6398395502333153,
561
+ "learning_rate": 4.6810704903990634e-05,
562
+ "loss": 0.8063,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 1.2698412698412698,
567
+ "grad_norm": 0.5170068764903927,
568
+ "learning_rate": 4.667372517927323e-05,
569
+ "loss": 0.682,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 1.2857142857142856,
574
+ "grad_norm": 0.5470142100714379,
575
+ "learning_rate": 4.653407456471222e-05,
576
+ "loss": 0.74,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 1.3015873015873016,
581
+ "grad_norm": 0.5344699813999502,
582
+ "learning_rate": 4.6391770269689236e-05,
583
+ "loss": 0.7019,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 1.3174603174603174,
588
+ "grad_norm": 0.572242361510543,
589
+ "learning_rate": 4.6246829830603454e-05,
590
+ "loss": 0.7612,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 1.3333333333333333,
595
+ "grad_norm": 0.5918389811121451,
596
+ "learning_rate": 4.609927110871053e-05,
597
+ "loss": 0.7285,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 1.3492063492063493,
602
+ "grad_norm": 0.4866622733839569,
603
+ "learning_rate": 4.594911228792156e-05,
604
+ "loss": 0.656,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 1.3650793650793651,
609
+ "grad_norm": 0.5275973128412808,
610
+ "learning_rate": 4.579637187256222e-05,
611
+ "loss": 0.576,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 1.380952380952381,
616
+ "grad_norm": 0.5488033313933244,
617
+ "learning_rate": 4.564106868509246e-05,
618
+ "loss": 0.7176,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 1.3968253968253967,
623
+ "grad_norm": 0.6920680886388099,
624
+ "learning_rate": 4.548322186378697e-05,
625
+ "loss": 0.7926,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 1.4126984126984126,
630
+ "grad_norm": 0.774236286341856,
631
+ "learning_rate": 4.532285086037674e-05,
632
+ "loss": 0.7313,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 1.4285714285714286,
637
+ "grad_norm": 0.7799985101441093,
638
+ "learning_rate": 4.5159975437652017e-05,
639
+ "loss": 0.717,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 1.4444444444444444,
644
+ "grad_norm": 0.5542880474504607,
645
+ "learning_rate": 4.499461566702685e-05,
646
+ "loss": 0.5701,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 1.4603174603174602,
651
+ "grad_norm": 0.6118784803715336,
652
+ "learning_rate": 4.48267919260657e-05,
653
+ "loss": 0.7026,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 1.4761904761904763,
658
+ "grad_norm": 0.6649407372701752,
659
+ "learning_rate": 4.4656524895972255e-05,
660
+ "loss": 0.7061,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 1.492063492063492,
665
+ "grad_norm": 0.47895549061427817,
666
+ "learning_rate": 4.448383555904088e-05,
667
+ "loss": 0.6387,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 1.507936507936508,
672
+ "grad_norm": 0.5811905127982857,
673
+ "learning_rate": 4.430874519607089e-05,
674
+ "loss": 0.8295,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 1.5238095238095237,
679
+ "grad_norm": 0.6782303990614583,
680
+ "learning_rate": 4.413127538374411e-05,
681
+ "loss": 0.7571,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 1.5396825396825395,
686
+ "grad_norm": 0.5127521378901643,
687
+ "learning_rate": 4.395144799196593e-05,
688
+ "loss": 0.6259,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 1.5555555555555556,
693
+ "grad_norm": 1.1333047155488623,
694
+ "learning_rate": 4.376928518117027e-05,
695
+ "loss": 0.7263,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 1.5714285714285714,
700
+ "grad_norm": 0.9285725347831506,
701
+ "learning_rate": 4.358480939958867e-05,
702
+ "loss": 0.6652,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 1.5873015873015874,
707
+ "grad_norm": 0.5756004852981952,
708
+ "learning_rate": 4.3398043380483965e-05,
709
+ "loss": 0.7045,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 1.6031746031746033,
714
+ "grad_norm": 0.5732214165272889,
715
+ "learning_rate": 4.320901013934887e-05,
716
+ "loss": 0.7096,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 1.619047619047619,
721
+ "grad_norm": 0.5729960942540637,
722
+ "learning_rate": 4.3017732971069674e-05,
723
+ "loss": 0.7797,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 1.6349206349206349,
728
+ "grad_norm": 0.6414711093856016,
729
+ "learning_rate": 4.282423544705564e-05,
730
+ "loss": 0.75,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 1.6507936507936507,
735
+ "grad_norm": 0.48208643464721207,
736
+ "learning_rate": 4.262854141233419e-05,
737
+ "loss": 0.7566,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 1.6666666666666665,
742
+ "grad_norm": 0.5650935089244651,
743
+ "learning_rate": 4.2430674982612506e-05,
744
+ "loss": 0.7282,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 1.6825396825396826,
749
+ "grad_norm": 0.6266660832902915,
750
+ "learning_rate": 4.223066054130568e-05,
751
+ "loss": 0.7098,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 1.6984126984126984,
756
+ "grad_norm": 1.1721379739857851,
757
+ "learning_rate": 4.2028522736531895e-05,
758
+ "loss": 0.7244,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 1.7142857142857144,
763
+ "grad_norm": 0.5821734258045642,
764
+ "learning_rate": 4.1824286478075025e-05,
765
+ "loss": 0.7918,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 1.7301587301587302,
770
+ "grad_norm": 0.5675713145707344,
771
+ "learning_rate": 4.161797693431493e-05,
772
+ "loss": 0.7271,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 1.746031746031746,
777
+ "grad_norm": 0.5948316073979433,
778
+ "learning_rate": 4.140961952912594e-05,
779
+ "loss": 0.6585,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 1.7619047619047619,
784
+ "grad_norm": 0.6142301353494962,
785
+ "learning_rate": 4.1199239938743797e-05,
786
+ "loss": 0.6636,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 1.7777777777777777,
791
+ "grad_norm": 0.6089779675550376,
792
+ "learning_rate": 4.0986864088601564e-05,
793
+ "loss": 0.6483,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 1.7936507936507935,
798
+ "grad_norm": 0.5407284417083653,
799
+ "learning_rate": 4.077251815013477e-05,
800
+ "loss": 0.6273,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 1.8095238095238095,
805
+ "grad_norm": 0.5554496556982176,
806
+ "learning_rate": 4.0556228537556266e-05,
807
+ "loss": 0.6301,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 1.8253968253968254,
812
+ "grad_norm": 0.5507291755794801,
813
+ "learning_rate": 4.0338021904601145e-05,
814
+ "loss": 0.6909,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 1.8412698412698414,
819
+ "grad_norm": 0.4537046958331062,
820
+ "learning_rate": 4.0117925141242174e-05,
821
+ "loss": 0.7491,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 1.8571428571428572,
826
+ "grad_norm": 0.5463750469400513,
827
+ "learning_rate": 3.9895965370376076e-05,
828
+ "loss": 0.8075,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 1.873015873015873,
833
+ "grad_norm": 0.5027853264982712,
834
+ "learning_rate": 3.9672169944481165e-05,
835
+ "loss": 0.5601,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 1.8888888888888888,
840
+ "grad_norm": 0.5661467536668536,
841
+ "learning_rate": 3.944656644224661e-05,
842
+ "loss": 0.7353,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 1.9047619047619047,
847
+ "grad_norm": 0.48806777854236366,
848
+ "learning_rate": 3.921918266517391e-05,
849
+ "loss": 0.6765,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 1.9206349206349205,
854
+ "grad_norm": 0.5877767380659309,
855
+ "learning_rate": 3.899004663415084e-05,
856
+ "loss": 0.707,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 1.9365079365079365,
861
+ "grad_norm": 0.5311318468752881,
862
+ "learning_rate": 3.875918658599837e-05,
863
+ "loss": 0.7882,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 1.9523809523809523,
868
+ "grad_norm": 0.5682753083153059,
869
+ "learning_rate": 3.8526630969991035e-05,
870
+ "loss": 0.6445,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 1.9682539682539684,
875
+ "grad_norm": 0.4740591298744526,
876
+ "learning_rate": 3.8292408444351094e-05,
877
+ "loss": 0.6718,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 1.9841269841269842,
882
+ "grad_norm": 0.45882583861407755,
883
+ "learning_rate": 3.805654787271686e-05,
884
+ "loss": 0.6762,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 2.0,
889
+ "grad_norm": 0.5675883245832433,
890
+ "learning_rate": 3.781907832058587e-05,
891
+ "loss": 0.7781,
892
+ "step": 126
893
+ }
894
+ ],
895
+ "logging_steps": 1,
896
+ "max_steps": 315,
897
+ "num_input_tokens_seen": 0,
898
+ "num_train_epochs": 5,
899
+ "save_steps": 500,
900
+ "stateful_callbacks": {
901
+ "TrainerControl": {
902
+ "args": {
903
+ "should_epoch_stop": false,
904
+ "should_evaluate": false,
905
+ "should_log": false,
906
+ "should_save": true,
907
+ "should_training_stop": false
908
+ },
909
+ "attributes": {}
910
+ }
911
+ },
912
+ "total_flos": 31413415968768.0,
913
+ "train_batch_size": 2,
914
+ "trial_name": null,
915
+ "trial_params": null
916
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9800f202a2235e80940555255ee5d0a4a8197ca429c38110d4a4660b7d76fd
3
+ size 7672
vocab.json ADDED
The diff for this file is too large to render. See raw diff