fengyao1909 commited on
Commit
c509a42
·
verified ·
1 Parent(s): b0eba27

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 sha256:304e81672ff86939dcb43c0cad4efdd126465157381a51e5ef3dc8cf4b0d7f44
3
+ size 4997184968
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b27eb08bb116e3d4907d096431c65be4ea6c5b08f5c41711236377ee6a2ee46
3
+ size 4997741608
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60f404ef9a0ac8140e332984ea95704d4cff834833def86e2b3413f019e103ce
3
+ size 4997742208
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bee70a2eed25ce9c0b0209661fbb7a42a926ca07ebad14585f6c14dc1873713
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:b3a0a838cb8043dbfa466e529ca1179a3b3cf8af2a41b7738cfa714300dd8866
3
+ size 4997743184
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00da88f02e5743645c33378157828911c90fdf0a548643f90d99b4b0f25a7ff9
3
+ size 4997743184
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c18648c00afe07ece270453dd8884f16dca0bdc69a3df0bc43db7b659315e0
3
+ size 4997743184
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb40d8ed164e4c24fd428de8faec7377a53d96650268fade288886589ce85b1
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:a377e978285a68934a6cd1274d3548ea32b2b1c41b485f8e5b771fc0ba22a4b4
3
+ size 4997743184
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f00224c6dfd5b5f0c332160639cd535b9bd010c9e52085ed1fd575d7975b5f
3
+ size 4997743184
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051282a8adb353976a0b94f0541b8cba0b05f9ef9b8f8990d7fad701f242fda5
3
+ size 4997743184
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd590755853a4c042910721bf12afe05003fc2f2bb49aedb3cfeffd4082853f
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:e142a2a82fc9c0984a827a9e559a606beff30352b2f204c821cb6043a9cc61de
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 +1,1014 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.842105263157895,
6
+ "eval_steps": 500,
7
+ "global_step": 140,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03508771929824561,
14
+ "grad_norm": 2.067223362182073,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.866,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.07017543859649122,
21
+ "grad_norm": 2.2905484024803084,
22
+ "learning_rate": 7.142857142857143e-07,
23
+ "loss": 1.043,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.10526315789473684,
28
+ "grad_norm": 2.0823489332612506,
29
+ "learning_rate": 1.4285714285714286e-06,
30
+ "loss": 0.9479,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.14035087719298245,
35
+ "grad_norm": 2.155054227940796,
36
+ "learning_rate": 2.1428571428571427e-06,
37
+ "loss": 1.0054,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.17543859649122806,
42
+ "grad_norm": 2.122195910115268,
43
+ "learning_rate": 2.8571428571428573e-06,
44
+ "loss": 1.0227,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.21052631578947367,
49
+ "grad_norm": 2.0002296419363823,
50
+ "learning_rate": 3.5714285714285718e-06,
51
+ "loss": 0.9994,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.24561403508771928,
56
+ "grad_norm": 1.7794168286652636,
57
+ "learning_rate": 4.2857142857142855e-06,
58
+ "loss": 0.9833,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.2807017543859649,
63
+ "grad_norm": 1.608102047372758,
64
+ "learning_rate": 5e-06,
65
+ "loss": 1.0059,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.3157894736842105,
70
+ "grad_norm": 1.5096684699130434,
71
+ "learning_rate": 4.999302593030069e-06,
72
+ "loss": 1.0199,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.3508771929824561,
77
+ "grad_norm": 1.2553700926461733,
78
+ "learning_rate": 4.99721076122146e-06,
79
+ "loss": 0.9945,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.38596491228070173,
84
+ "grad_norm": 1.0588682250755448,
85
+ "learning_rate": 4.99372567166064e-06,
86
+ "loss": 0.8896,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.42105263157894735,
91
+ "grad_norm": 1.2403025527385267,
92
+ "learning_rate": 4.98884926876821e-06,
93
+ "loss": 0.9064,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.45614035087719296,
98
+ "grad_norm": 1.3277416791779741,
99
+ "learning_rate": 4.982584273214061e-06,
100
+ "loss": 0.9728,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.49122807017543857,
105
+ "grad_norm": 1.200452342066303,
106
+ "learning_rate": 4.974934180399447e-06,
107
+ "loss": 0.8801,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.5263157894736842,
112
+ "grad_norm": 1.2276015693500428,
113
+ "learning_rate": 4.965903258506806e-06,
114
+ "loss": 0.9056,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.5614035087719298,
119
+ "grad_norm": 0.9588298096291193,
120
+ "learning_rate": 4.955496546118439e-06,
121
+ "loss": 0.851,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.5964912280701754,
126
+ "grad_norm": 0.8961934214540342,
127
+ "learning_rate": 4.943719849405347e-06,
128
+ "loss": 0.9588,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.631578947368421,
133
+ "grad_norm": 0.7752982692883841,
134
+ "learning_rate": 4.930579738887827e-06,
135
+ "loss": 0.8592,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.6666666666666666,
140
+ "grad_norm": 0.7598215199572412,
141
+ "learning_rate": 4.9160835457696075e-06,
142
+ "loss": 0.9224,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.7017543859649122,
147
+ "grad_norm": 0.7947043775095588,
148
+ "learning_rate": 4.900239357847582e-06,
149
+ "loss": 0.9183,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.7368421052631579,
154
+ "grad_norm": 0.8131278296751281,
155
+ "learning_rate": 4.883056014999423e-06,
156
+ "loss": 0.8854,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.7719298245614035,
161
+ "grad_norm": 0.720597258722373,
162
+ "learning_rate": 4.864543104251587e-06,
163
+ "loss": 0.837,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.8070175438596491,
168
+ "grad_norm": 0.698175660395316,
169
+ "learning_rate": 4.844710954430464e-06,
170
+ "loss": 0.9006,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.8421052631578947,
175
+ "grad_norm": 0.6061246443427316,
176
+ "learning_rate": 4.823570630399665e-06,
177
+ "loss": 0.8713,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.8771929824561403,
182
+ "grad_norm": 0.5800728862173004,
183
+ "learning_rate": 4.8011339268866505e-06,
184
+ "loss": 0.8572,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.9122807017543859,
189
+ "grad_norm": 0.6881850987832964,
190
+ "learning_rate": 4.777413361902152e-06,
191
+ "loss": 0.9243,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.9473684210526315,
196
+ "grad_norm": 0.6013453853835422,
197
+ "learning_rate": 4.752422169756048e-06,
198
+ "loss": 0.8215,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.9824561403508771,
203
+ "grad_norm": 0.5049917945559669,
204
+ "learning_rate": 4.726174293673612e-06,
205
+ "loss": 0.8498,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 1.0,
210
+ "grad_norm": 0.5049917945559669,
211
+ "learning_rate": 4.698684378016223e-06,
212
+ "loss": 0.7765,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 1.0350877192982457,
217
+ "grad_norm": 0.8391221152195739,
218
+ "learning_rate": 4.669967760110908e-06,
219
+ "loss": 0.8698,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 1.0701754385964912,
224
+ "grad_norm": 0.5071651643461081,
225
+ "learning_rate": 4.6400404616932505e-06,
226
+ "loss": 0.8376,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 1.1052631578947367,
231
+ "grad_norm": 0.4758228095407797,
232
+ "learning_rate": 4.608919179968457e-06,
233
+ "loss": 0.883,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 1.1403508771929824,
238
+ "grad_norm": 0.4648364085184619,
239
+ "learning_rate": 4.576621278295558e-06,
240
+ "loss": 0.8628,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 1.1754385964912282,
245
+ "grad_norm": 0.4712254209084955,
246
+ "learning_rate": 4.543164776499945e-06,
247
+ "loss": 0.8281,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 1.2105263157894737,
252
+ "grad_norm": 0.4013954971972578,
253
+ "learning_rate": 4.508568340819654e-06,
254
+ "loss": 0.8867,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 1.2456140350877192,
259
+ "grad_norm": 0.41192488021825646,
260
+ "learning_rate": 4.472851273490985e-06,
261
+ "loss": 0.8675,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 1.280701754385965,
266
+ "grad_norm": 0.4239007109950775,
267
+ "learning_rate": 4.436033501979299e-06,
268
+ "loss": 0.8591,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 1.3157894736842106,
273
+ "grad_norm": 0.41628314789696425,
274
+ "learning_rate": 4.398135567860972e-06,
275
+ "loss": 0.8254,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 1.3508771929824561,
280
+ "grad_norm": 0.3923309284581745,
281
+ "learning_rate": 4.359178615362725e-06,
282
+ "loss": 0.7828,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 1.3859649122807016,
287
+ "grad_norm": 0.47649896532625685,
288
+ "learning_rate": 4.319184379564716e-06,
289
+ "loss": 0.8922,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 1.4210526315789473,
294
+ "grad_norm": 0.47963769728260897,
295
+ "learning_rate": 4.278175174273989e-06,
296
+ "loss": 0.8179,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 1.456140350877193,
301
+ "grad_norm": 0.44693221984156073,
302
+ "learning_rate": 4.236173879575022e-06,
303
+ "loss": 0.7873,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 1.4912280701754386,
308
+ "grad_norm": 0.3915854729078168,
309
+ "learning_rate": 4.1932039290643534e-06,
310
+ "loss": 0.7786,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 1.526315789473684,
315
+ "grad_norm": 0.3379023862301008,
316
+ "learning_rate": 4.149289296776369e-06,
317
+ "loss": 0.9101,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 1.5614035087719298,
322
+ "grad_norm": 0.3691862472080892,
323
+ "learning_rate": 4.104454483807579e-06,
324
+ "loss": 0.8606,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 1.5964912280701755,
329
+ "grad_norm": 0.34291927069087574,
330
+ "learning_rate": 4.058724504646834e-06,
331
+ "loss": 0.7938,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 1.631578947368421,
336
+ "grad_norm": 0.4003834992970626,
337
+ "learning_rate": 4.012124873219094e-06,
338
+ "loss": 0.7814,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 1.6666666666666665,
343
+ "grad_norm": 0.3392403324591956,
344
+ "learning_rate": 3.964681588650562e-06,
345
+ "loss": 0.8389,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 1.7017543859649122,
350
+ "grad_norm": 0.3377270590051618,
351
+ "learning_rate": 3.916421120763106e-06,
352
+ "loss": 0.85,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 1.736842105263158,
357
+ "grad_norm": 0.38740961950138847,
358
+ "learning_rate": 3.8673703953060685e-06,
359
+ "loss": 0.8348,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 1.7719298245614035,
364
+ "grad_norm": 0.35219126914631843,
365
+ "learning_rate": 3.817556778933697e-06,
366
+ "loss": 0.8577,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 1.807017543859649,
371
+ "grad_norm": 0.3774463349958884,
372
+ "learning_rate": 3.7670080639366e-06,
373
+ "loss": 0.8769,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 1.8421052631578947,
378
+ "grad_norm": 0.35130371579419645,
379
+ "learning_rate": 3.7157524527357036e-06,
380
+ "loss": 0.7163,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 1.8771929824561404,
385
+ "grad_norm": 0.3551942508437019,
386
+ "learning_rate": 3.663818542147409e-06,
387
+ "loss": 0.8756,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 1.912280701754386,
392
+ "grad_norm": 0.3537337899404262,
393
+ "learning_rate": 3.61123530742869e-06,
394
+ "loss": 0.8219,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 1.9473684210526314,
399
+ "grad_norm": 0.327364809217546,
400
+ "learning_rate": 3.5580320861110627e-06,
401
+ "loss": 0.8696,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 1.9824561403508771,
406
+ "grad_norm": 0.3367652725930036,
407
+ "learning_rate": 3.5042385616324243e-06,
408
+ "loss": 0.872,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 2.0,
413
+ "grad_norm": 0.5052810208370435,
414
+ "learning_rate": 3.4498847467759e-06,
415
+ "loss": 0.8607,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 2.0350877192982457,
420
+ "grad_norm": 0.3177161861315085,
421
+ "learning_rate": 3.3950009669249502e-06,
422
+ "loss": 0.7808,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 2.0701754385964914,
427
+ "grad_norm": 0.3450713484869485,
428
+ "learning_rate": 3.3396178431440572e-06,
429
+ "loss": 0.9217,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 2.1052631578947367,
434
+ "grad_norm": 0.32271078088898175,
435
+ "learning_rate": 3.283766275094454e-06,
436
+ "loss": 0.7982,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 2.1403508771929824,
441
+ "grad_norm": 0.33864939828309026,
442
+ "learning_rate": 3.227477423794412e-06,
443
+ "loss": 0.7907,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 2.175438596491228,
448
+ "grad_norm": 0.32084183022976825,
449
+ "learning_rate": 3.1707826942337124e-06,
450
+ "loss": 0.8362,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 2.2105263157894735,
455
+ "grad_norm": 0.31523598018882065,
456
+ "learning_rate": 3.1137137178519983e-06,
457
+ "loss": 0.8603,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 2.245614035087719,
462
+ "grad_norm": 0.3534452142386561,
463
+ "learning_rate": 3.056302334890786e-06,
464
+ "loss": 0.7473,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 2.280701754385965,
469
+ "grad_norm": 0.3065081387248856,
470
+ "learning_rate": 2.9985805766289815e-06,
471
+ "loss": 0.8076,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 2.3157894736842106,
476
+ "grad_norm": 0.31593346837979236,
477
+ "learning_rate": 2.940580647511805e-06,
478
+ "loss": 0.7911,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 2.3508771929824563,
483
+ "grad_norm": 0.33421077857364934,
484
+ "learning_rate": 2.8823349071831154e-06,
485
+ "loss": 0.8567,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 2.3859649122807016,
490
+ "grad_norm": 0.36084453724888643,
491
+ "learning_rate": 2.8238758524311316e-06,
492
+ "loss": 0.7815,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 2.4210526315789473,
497
+ "grad_norm": 0.31104114669216265,
498
+ "learning_rate": 2.7652360990576457e-06,
499
+ "loss": 0.9035,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 2.456140350877193,
504
+ "grad_norm": 0.3283662140442227,
505
+ "learning_rate": 2.7064483636808314e-06,
506
+ "loss": 0.815,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 2.4912280701754383,
511
+ "grad_norm": 0.28913740772142477,
512
+ "learning_rate": 2.6475454454818072e-06,
513
+ "loss": 0.8369,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 2.526315789473684,
518
+ "grad_norm": 0.30507064501325465,
519
+ "learning_rate": 2.5885602079051354e-06,
520
+ "loss": 0.7603,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 2.56140350877193,
525
+ "grad_norm": 0.3531329822293121,
526
+ "learning_rate": 2.529525560323462e-06,
527
+ "loss": 0.8004,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 2.5964912280701755,
532
+ "grad_norm": 0.3210792288970346,
533
+ "learning_rate": 2.470474439676539e-06,
534
+ "loss": 0.8168,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 2.6315789473684212,
539
+ "grad_norm": 0.36897603215114533,
540
+ "learning_rate": 2.411439792094866e-06,
541
+ "loss": 0.8398,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 2.6666666666666665,
546
+ "grad_norm": 0.3217143259950112,
547
+ "learning_rate": 2.3524545545181936e-06,
548
+ "loss": 0.866,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 2.7017543859649122,
553
+ "grad_norm": 0.3126909067501635,
554
+ "learning_rate": 2.2935516363191695e-06,
555
+ "loss": 0.8341,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 2.736842105263158,
560
+ "grad_norm": 0.3006660553493533,
561
+ "learning_rate": 2.234763900942355e-06,
562
+ "loss": 0.8081,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 2.7719298245614032,
567
+ "grad_norm": 0.316850226629777,
568
+ "learning_rate": 2.1761241475688697e-06,
569
+ "loss": 0.7562,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 2.807017543859649,
574
+ "grad_norm": 0.2903780216034827,
575
+ "learning_rate": 2.117665092816885e-06,
576
+ "loss": 0.7419,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 2.8421052631578947,
581
+ "grad_norm": 0.3424299492049514,
582
+ "learning_rate": 2.059419352488196e-06,
583
+ "loss": 0.8289,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 2.8771929824561404,
588
+ "grad_norm": 0.3113278689750571,
589
+ "learning_rate": 2.0014194233710193e-06,
590
+ "loss": 0.823,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 2.912280701754386,
595
+ "grad_norm": 0.3375235251647405,
596
+ "learning_rate": 1.9436976651092143e-06,
597
+ "loss": 0.8292,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 2.9473684210526314,
602
+ "grad_norm": 0.3084098102163688,
603
+ "learning_rate": 1.8862862821480023e-06,
604
+ "loss": 0.7702,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 2.982456140350877,
609
+ "grad_norm": 0.30920611879243615,
610
+ "learning_rate": 1.829217305766289e-06,
611
+ "loss": 0.8181,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 3.0,
616
+ "grad_norm": 0.30920611879243615,
617
+ "learning_rate": 1.772522576205589e-06,
618
+ "loss": 0.6831,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 3.0350877192982457,
623
+ "grad_norm": 0.46709482387410683,
624
+ "learning_rate": 1.7162337249055478e-06,
625
+ "loss": 0.7982,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 3.0701754385964914,
630
+ "grad_norm": 0.3370869471421174,
631
+ "learning_rate": 1.6603821568559436e-06,
632
+ "loss": 0.881,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 3.1052631578947367,
637
+ "grad_norm": 0.3179079897916838,
638
+ "learning_rate": 1.6049990330750508e-06,
639
+ "loss": 0.8329,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 3.1403508771929824,
644
+ "grad_norm": 0.3291466920072208,
645
+ "learning_rate": 1.5501152532241003e-06,
646
+ "loss": 0.8082,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 3.175438596491228,
651
+ "grad_norm": 0.2663561721256465,
652
+ "learning_rate": 1.495761438367577e-06,
653
+ "loss": 0.7935,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 3.2105263157894735,
658
+ "grad_norm": 0.3378088081469463,
659
+ "learning_rate": 1.4419679138889379e-06,
660
+ "loss": 0.9118,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 3.245614035087719,
665
+ "grad_norm": 0.2748060877432168,
666
+ "learning_rate": 1.3887646925713116e-06,
667
+ "loss": 0.7708,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 3.280701754385965,
672
+ "grad_norm": 0.2918477343216952,
673
+ "learning_rate": 1.3361814578525922e-06,
674
+ "loss": 0.7648,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 3.3157894736842106,
679
+ "grad_norm": 0.3822259736080091,
680
+ "learning_rate": 1.2842475472642969e-06,
681
+ "loss": 0.8481,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 3.3508771929824563,
686
+ "grad_norm": 0.2913972912654805,
687
+ "learning_rate": 1.2329919360634003e-06,
688
+ "loss": 0.8131,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 3.3859649122807016,
693
+ "grad_norm": 0.3066641760210679,
694
+ "learning_rate": 1.182443221066303e-06,
695
+ "loss": 0.7058,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 3.4210526315789473,
700
+ "grad_norm": 0.2900386082534738,
701
+ "learning_rate": 1.1326296046939334e-06,
702
+ "loss": 0.7342,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 3.456140350877193,
707
+ "grad_norm": 0.3203517403497328,
708
+ "learning_rate": 1.083578879236895e-06,
709
+ "loss": 0.7412,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 3.4912280701754383,
714
+ "grad_norm": 0.28656600494309065,
715
+ "learning_rate": 1.0353184113494386e-06,
716
+ "loss": 0.7715,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 3.526315789473684,
721
+ "grad_norm": 0.29628157944674766,
722
+ "learning_rate": 9.878751267809069e-07,
723
+ "loss": 0.7555,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 3.56140350877193,
728
+ "grad_norm": 0.26411035275922856,
729
+ "learning_rate": 9.412754953531664e-07,
730
+ "loss": 0.7726,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 3.5964912280701755,
735
+ "grad_norm": 0.34453008632884863,
736
+ "learning_rate": 8.955455161924217e-07,
737
+ "loss": 0.78,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 3.6315789473684212,
742
+ "grad_norm": 0.325563928726771,
743
+ "learning_rate": 8.507107032236323e-07,
744
+ "loss": 0.6829,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 3.6666666666666665,
749
+ "grad_norm": 0.31584897068831647,
750
+ "learning_rate": 8.067960709356479e-07,
751
+ "loss": 0.7739,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 3.7017543859649122,
756
+ "grad_norm": 0.3146533494629239,
757
+ "learning_rate": 7.638261204249783e-07,
758
+ "loss": 0.7716,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 3.736842105263158,
763
+ "grad_norm": 0.32266730096043933,
764
+ "learning_rate": 7.218248257260127e-07,
765
+ "loss": 0.8332,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 3.7719298245614032,
770
+ "grad_norm": 0.2910022026214654,
771
+ "learning_rate": 6.808156204352845e-07,
772
+ "loss": 0.8566,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 3.807017543859649,
777
+ "grad_norm": 0.29701746352400193,
778
+ "learning_rate": 6.40821384637276e-07,
779
+ "loss": 0.838,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 3.8421052631578947,
784
+ "grad_norm": 0.31966449944224506,
785
+ "learning_rate": 6.018644321390288e-07,
786
+ "loss": 0.8225,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 3.8771929824561404,
791
+ "grad_norm": 0.2863822961617792,
792
+ "learning_rate": 5.639664980207024e-07,
793
+ "loss": 0.7654,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 3.912280701754386,
798
+ "grad_norm": 0.3072140143203843,
799
+ "learning_rate": 5.271487265090163e-07,
800
+ "loss": 0.7757,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 3.9473684210526314,
805
+ "grad_norm": 0.2809560367104084,
806
+ "learning_rate": 4.914316591803475e-07,
807
+ "loss": 0.7929,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 3.982456140350877,
812
+ "grad_norm": 0.32556802320373446,
813
+ "learning_rate": 4.5683522350005505e-07,
814
+ "loss": 0.8097,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 4.0,
819
+ "grad_norm": 0.47825225825507217,
820
+ "learning_rate": 4.23378721704443e-07,
821
+ "loss": 0.7607,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 4.035087719298246,
826
+ "grad_norm": 0.2884567469754835,
827
+ "learning_rate": 3.910808200315433e-07,
828
+ "loss": 0.7676,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 4.0701754385964914,
833
+ "grad_norm": 0.3182187799462883,
834
+ "learning_rate": 3.5995953830675004e-07,
835
+ "loss": 0.7889,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 4.105263157894737,
840
+ "grad_norm": 0.3206780821308196,
841
+ "learning_rate": 3.3003223988909234e-07,
842
+ "loss": 0.7995,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 4.140350877192983,
847
+ "grad_norm": 0.29045985883088904,
848
+ "learning_rate": 3.0131562198377763e-07,
849
+ "loss": 0.7777,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 4.175438596491228,
854
+ "grad_norm": 0.2890942050581055,
855
+ "learning_rate": 2.7382570632638853e-07,
856
+ "loss": 0.7586,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 4.2105263157894735,
861
+ "grad_norm": 0.2996096336122156,
862
+ "learning_rate": 2.4757783024395244e-07,
863
+ "loss": 0.7141,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 4.245614035087719,
868
+ "grad_norm": 0.28282887621154235,
869
+ "learning_rate": 2.2258663809784892e-07,
870
+ "loss": 0.7794,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 4.280701754385965,
875
+ "grad_norm": 0.32670318807921217,
876
+ "learning_rate": 1.9886607311334987e-07,
877
+ "loss": 0.8126,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 4.315789473684211,
882
+ "grad_norm": 0.6396616902495418,
883
+ "learning_rate": 1.764293696003358e-07,
884
+ "loss": 0.855,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 4.350877192982456,
889
+ "grad_norm": 0.3105123473589777,
890
+ "learning_rate": 1.552890455695369e-07,
891
+ "loss": 0.7864,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 4.385964912280702,
896
+ "grad_norm": 0.31471995293981275,
897
+ "learning_rate": 1.3545689574841341e-07,
898
+ "loss": 0.7959,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 4.421052631578947,
903
+ "grad_norm": 0.2885989494400454,
904
+ "learning_rate": 1.1694398500057714e-07,
905
+ "loss": 0.8017,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 4.456140350877193,
910
+ "grad_norm": 0.2739576160503863,
911
+ "learning_rate": 9.976064215241859e-08,
912
+ "loss": 0.8043,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 4.491228070175438,
917
+ "grad_norm": 0.29411590660069753,
918
+ "learning_rate": 8.391645423039357e-08,
919
+ "loss": 0.8661,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 4.526315789473684,
924
+ "grad_norm": 1.3814580420291491,
925
+ "learning_rate": 6.94202611121736e-08,
926
+ "loss": 0.7681,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 4.56140350877193,
931
+ "grad_norm": 0.29380556063864866,
932
+ "learning_rate": 5.628015059465364e-08,
933
+ "loss": 0.7929,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 4.5964912280701755,
938
+ "grad_norm": 0.2722868371572552,
939
+ "learning_rate": 4.450345388156141e-08,
940
+ "loss": 0.688,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 4.631578947368421,
945
+ "grad_norm": 0.2958548587321527,
946
+ "learning_rate": 3.4096741493194196e-08,
947
+ "loss": 0.7044,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 4.666666666666667,
952
+ "grad_norm": 0.2911249362393912,
953
+ "learning_rate": 2.506581960055432e-08,
954
+ "loss": 0.7699,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 4.701754385964913,
959
+ "grad_norm": 0.32311541133471755,
960
+ "learning_rate": 1.7415726785939836e-08,
961
+ "loss": 0.7553,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 4.7368421052631575,
966
+ "grad_norm": 0.29755358398825144,
967
+ "learning_rate": 1.115073123179128e-08,
968
+ "loss": 0.8038,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 4.771929824561403,
973
+ "grad_norm": 0.27621549811178525,
974
+ "learning_rate": 6.274328339360702e-09,
975
+ "loss": 0.8295,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 4.807017543859649,
980
+ "grad_norm": 0.32039361922969517,
981
+ "learning_rate": 2.789238778540537e-09,
982
+ "loss": 0.7832,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 4.842105263157895,
987
+ "grad_norm": 0.2926203169600849,
988
+ "learning_rate": 6.974069699314246e-10,
989
+ "loss": 0.7585,
990
+ "step": 140
991
+ }
992
+ ],
993
+ "logging_steps": 1,
994
+ "max_steps": 140,
995
+ "num_input_tokens_seen": 0,
996
+ "num_train_epochs": 5,
997
+ "save_steps": 500,
998
+ "stateful_callbacks": {
999
+ "TrainerControl": {
1000
+ "args": {
1001
+ "should_epoch_stop": false,
1002
+ "should_evaluate": false,
1003
+ "should_log": false,
1004
+ "should_save": true,
1005
+ "should_training_stop": true
1006
+ },
1007
+ "attributes": {}
1008
+ }
1009
+ },
1010
+ "total_flos": 63037458677760.0,
1011
+ "train_batch_size": 2,
1012
+ "trial_name": null,
1013
+ "trial_params": null
1014
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662904763cd0f20d1938bb9f0d503bf9135ec41bc6ae8a62b91e7ed9be33b7b7
3
+ size 8017
vocab.json ADDED
The diff for this file is too large to render. See raw diff