fengyao1909 commited on
Commit
0872256
·
verified ·
1 Parent(s): 573bad0

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 sha256:90ebd7e30c0e0ca04afbd036689b848f8a76bdf37b24802547f9ed974cb60586
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:ee42ee4c2655a9e6d1236e207135f80c1b1a751c15b01119589c781d79e44a85
3
+ size 4997741608
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39ce6d61bbc2eec31d63010b2dc2b809797c5519cf379ed24d94e55c6dac412d
3
+ size 4997742208
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:116f36cbf7ee224ae5feb3ed684e861d743efa3696d8797707b2476ebb7e3006
3
+ size 4997743184
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73edf1213ca5fb97351eb341e05e5553348f309acb9f37b44fdf9d6847f5301a
3
+ size 4997743184
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415365c48722c12fa627097e373473c5c91037e39ba5e9fb4683612933d0ac5d
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:ac52b40360aa51e82297f5e9f9e753c6250eb602712cf7166f5d6fe519793d58
3
+ size 4997743184
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a632b2fbe8b3d87a8002c5b24442336377774702a24c5eca8c85023106a505f
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:ad2499427c97167154e199f2cf4aeb49ac89b670cc8a74b2c2e958d3be690dd5
3
+ size 4997743184
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71c43d0a7d5876f4e59eb7d46a339eb67acc1493fe8b3e75af60ba6dade90d2d
3
+ size 4997743184
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486393872be7770d2883599d548da7c0415ca7c01c2f7ac9b85e8c14544d1f63
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:ed376d4c79b4a45d00934db25553641a44ea88a938957a1b88a33bad9f3fcfef
3
+ size 4997743184
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dbc991ab6ba20d41e8b1d7428769614b9c112505d2c9bf116bf13a67000f8b7
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": 2.0671271678531755,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.866,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.07017543859649122,
21
+ "grad_norm": 2.2900714872410477,
22
+ "learning_rate": 7.142857142857143e-06,
23
+ "loss": 1.043,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.10526315789473684,
28
+ "grad_norm": 1.861548862699238,
29
+ "learning_rate": 1.4285714285714285e-05,
30
+ "loss": 0.9408,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.14035087719298245,
35
+ "grad_norm": 1.5918887111051039,
36
+ "learning_rate": 2.1428571428571428e-05,
37
+ "loss": 0.9754,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.17543859649122806,
42
+ "grad_norm": 2.461157666875476,
43
+ "learning_rate": 2.857142857142857e-05,
44
+ "loss": 0.9909,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.21052631578947367,
49
+ "grad_norm": 3.269351348810357,
50
+ "learning_rate": 3.571428571428572e-05,
51
+ "loss": 0.9765,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.24561403508771928,
56
+ "grad_norm": 2.891039729725391,
57
+ "learning_rate": 4.2857142857142856e-05,
58
+ "loss": 0.976,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.2807017543859649,
63
+ "grad_norm": 1.7833187830275166,
64
+ "learning_rate": 5e-05,
65
+ "loss": 0.985,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.3157894736842105,
70
+ "grad_norm": 1.6508430392003424,
71
+ "learning_rate": 4.9993025930300686e-05,
72
+ "loss": 0.9983,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.3508771929824561,
77
+ "grad_norm": 1.3325514749958667,
78
+ "learning_rate": 4.99721076122146e-05,
79
+ "loss": 0.9611,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.38596491228070173,
84
+ "grad_norm": 1.1508459362776429,
85
+ "learning_rate": 4.9937256716606394e-05,
86
+ "loss": 0.8505,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.42105263157894735,
91
+ "grad_norm": 0.8112441764899212,
92
+ "learning_rate": 4.9888492687682096e-05,
93
+ "loss": 0.8723,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.45614035087719296,
98
+ "grad_norm": 0.8092302145893412,
99
+ "learning_rate": 4.982584273214061e-05,
100
+ "loss": 0.9396,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.49122807017543857,
105
+ "grad_norm": 0.7597090899690478,
106
+ "learning_rate": 4.9749341803994465e-05,
107
+ "loss": 0.8441,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.5263157894736842,
112
+ "grad_norm": 0.6679585780372033,
113
+ "learning_rate": 4.965903258506806e-05,
114
+ "loss": 0.8723,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.5614035087719298,
119
+ "grad_norm": 0.5980287018483266,
120
+ "learning_rate": 4.955496546118439e-05,
121
+ "loss": 0.8188,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.5964912280701754,
126
+ "grad_norm": 0.7845483827995335,
127
+ "learning_rate": 4.9437198494053464e-05,
128
+ "loss": 0.9303,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.631578947368421,
133
+ "grad_norm": 0.5932466105687543,
134
+ "learning_rate": 4.9305797388878264e-05,
135
+ "loss": 0.8304,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.6666666666666666,
140
+ "grad_norm": 0.5537040595976515,
141
+ "learning_rate": 4.916083545769607e-05,
142
+ "loss": 0.8943,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.7017543859649122,
147
+ "grad_norm": 0.5092981470635746,
148
+ "learning_rate": 4.9002393578475816e-05,
149
+ "loss": 0.8906,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.7368421052631579,
154
+ "grad_norm": 0.5487294714158888,
155
+ "learning_rate": 4.883056014999423e-05,
156
+ "loss": 0.8584,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.7719298245614035,
161
+ "grad_norm": 0.4922358015626094,
162
+ "learning_rate": 4.864543104251587e-05,
163
+ "loss": 0.8129,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.8070175438596491,
168
+ "grad_norm": 0.5397899665966813,
169
+ "learning_rate": 4.8447109544304636e-05,
170
+ "loss": 0.8779,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.8421052631578947,
175
+ "grad_norm": 0.5043199211637701,
176
+ "learning_rate": 4.823570630399665e-05,
177
+ "loss": 0.8482,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.8771929824561403,
182
+ "grad_norm": 0.4889597930942473,
183
+ "learning_rate": 4.8011339268866505e-05,
184
+ "loss": 0.8361,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.9122807017543859,
189
+ "grad_norm": 0.4769108041878493,
190
+ "learning_rate": 4.7774133619021514e-05,
191
+ "loss": 0.904,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.9473684210526315,
196
+ "grad_norm": 0.41632944677923917,
197
+ "learning_rate": 4.752422169756048e-05,
198
+ "loss": 0.8032,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.9824561403508771,
203
+ "grad_norm": 0.5107558694810208,
204
+ "learning_rate": 4.726174293673612e-05,
205
+ "loss": 0.8312,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 1.0,
210
+ "grad_norm": 0.5107558694810208,
211
+ "learning_rate": 4.698684378016222e-05,
212
+ "loss": 0.6911,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 1.0350877192982457,
217
+ "grad_norm": 0.9504413832780126,
218
+ "learning_rate": 4.669967760110908e-05,
219
+ "loss": 0.7434,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 1.0701754385964912,
224
+ "grad_norm": 0.5169442096859842,
225
+ "learning_rate": 4.6400404616932505e-05,
226
+ "loss": 0.7058,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 1.1052631578947367,
231
+ "grad_norm": 0.5229168796306622,
232
+ "learning_rate": 4.608919179968457e-05,
233
+ "loss": 0.7504,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 1.1403508771929824,
238
+ "grad_norm": 0.7632061755291258,
239
+ "learning_rate": 4.576621278295558e-05,
240
+ "loss": 0.7216,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 1.1754385964912282,
245
+ "grad_norm": 0.6677063053297304,
246
+ "learning_rate": 4.5431647764999455e-05,
247
+ "loss": 0.6885,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 1.2105263157894737,
252
+ "grad_norm": 0.5388255492178547,
253
+ "learning_rate": 4.5085683408196535e-05,
254
+ "loss": 0.7347,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 1.2456140350877192,
259
+ "grad_norm": 0.6102262771882692,
260
+ "learning_rate": 4.4728512734909844e-05,
261
+ "loss": 0.7483,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 1.280701754385965,
266
+ "grad_norm": 0.9784625861220957,
267
+ "learning_rate": 4.436033501979299e-05,
268
+ "loss": 0.7104,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 1.3157894736842106,
273
+ "grad_norm": 0.5182340717871661,
274
+ "learning_rate": 4.398135567860972e-05,
275
+ "loss": 0.6926,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 1.3508771929824561,
280
+ "grad_norm": 0.5241406807392717,
281
+ "learning_rate": 4.3591786153627247e-05,
282
+ "loss": 0.6423,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 1.3859649122807016,
287
+ "grad_norm": 0.5337062588294988,
288
+ "learning_rate": 4.319184379564716e-05,
289
+ "loss": 0.7449,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 1.4210526315789473,
294
+ "grad_norm": 0.58502320062393,
295
+ "learning_rate": 4.2781751742739885e-05,
296
+ "loss": 0.6863,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 1.456140350877193,
301
+ "grad_norm": 0.4437314579585024,
302
+ "learning_rate": 4.2361738795750214e-05,
303
+ "loss": 0.6421,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 1.4912280701754386,
308
+ "grad_norm": 0.4720129405227882,
309
+ "learning_rate": 4.193203929064353e-05,
310
+ "loss": 0.6387,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 1.526315789473684,
315
+ "grad_norm": 0.49099471978636483,
316
+ "learning_rate": 4.1492892967763686e-05,
317
+ "loss": 0.7621,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 1.5614035087719298,
322
+ "grad_norm": 0.4870002337399591,
323
+ "learning_rate": 4.1044544838075794e-05,
324
+ "loss": 0.7271,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 1.5964912280701755,
329
+ "grad_norm": 0.4300326366249684,
330
+ "learning_rate": 4.058724504646834e-05,
331
+ "loss": 0.6553,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 1.631578947368421,
336
+ "grad_norm": 0.4648072620566617,
337
+ "learning_rate": 4.012124873219094e-05,
338
+ "loss": 0.6585,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 1.6666666666666665,
343
+ "grad_norm": 0.4704588320844793,
344
+ "learning_rate": 3.964681588650562e-05,
345
+ "loss": 0.7066,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 1.7017543859649122,
350
+ "grad_norm": 0.4227060942964382,
351
+ "learning_rate": 3.916421120763106e-05,
352
+ "loss": 0.7298,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 1.736842105263158,
357
+ "grad_norm": 0.47049085759667697,
358
+ "learning_rate": 3.867370395306068e-05,
359
+ "loss": 0.713,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 1.7719298245614035,
364
+ "grad_norm": 0.41760981184783075,
365
+ "learning_rate": 3.817556778933698e-05,
366
+ "loss": 0.7196,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 1.807017543859649,
371
+ "grad_norm": 0.5161375525386056,
372
+ "learning_rate": 3.7670080639366004e-05,
373
+ "loss": 0.7425,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 1.8421052631578947,
378
+ "grad_norm": 0.43748999720890136,
379
+ "learning_rate": 3.715752452735704e-05,
380
+ "loss": 0.5942,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 1.8771929824561404,
385
+ "grad_norm": 0.5115131837341141,
386
+ "learning_rate": 3.6638185421474084e-05,
387
+ "loss": 0.7346,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 1.912280701754386,
392
+ "grad_norm": 0.461919359464356,
393
+ "learning_rate": 3.61123530742869e-05,
394
+ "loss": 0.6743,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 1.9473684210526314,
399
+ "grad_norm": 0.4342888779362966,
400
+ "learning_rate": 3.5580320861110625e-05,
401
+ "loss": 0.7281,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 1.9824561403508771,
406
+ "grad_norm": 0.48320797418001477,
407
+ "learning_rate": 3.504238561632424e-05,
408
+ "loss": 0.7326,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 2.0,
413
+ "grad_norm": 0.8691230999307578,
414
+ "learning_rate": 3.4498847467759e-05,
415
+ "loss": 0.6139,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 2.0350877192982457,
420
+ "grad_norm": 0.925588727218562,
421
+ "learning_rate": 3.3950009669249497e-05,
422
+ "loss": 0.5316,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 2.0701754385964914,
427
+ "grad_norm": 2.7861744302281886,
428
+ "learning_rate": 3.339617843144057e-05,
429
+ "loss": 0.6395,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 2.1052631578947367,
434
+ "grad_norm": 2.960320751174846,
435
+ "learning_rate": 3.2837662750944535e-05,
436
+ "loss": 0.5571,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 2.1403508771929824,
441
+ "grad_norm": 0.5858200164045075,
442
+ "learning_rate": 3.227477423794412e-05,
443
+ "loss": 0.5282,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 2.175438596491228,
448
+ "grad_norm": 0.7249551445260521,
449
+ "learning_rate": 3.170782694233712e-05,
450
+ "loss": 0.568,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 2.2105263157894735,
455
+ "grad_norm": 0.8322811685066639,
456
+ "learning_rate": 3.1137137178519985e-05,
457
+ "loss": 0.5588,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 2.245614035087719,
462
+ "grad_norm": 0.4688506121750911,
463
+ "learning_rate": 3.056302334890786e-05,
464
+ "loss": 0.4997,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 2.280701754385965,
469
+ "grad_norm": 0.5395406531134912,
470
+ "learning_rate": 2.9985805766289817e-05,
471
+ "loss": 0.5389,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 2.3157894736842106,
476
+ "grad_norm": 0.5972426732470659,
477
+ "learning_rate": 2.9405806475118048e-05,
478
+ "loss": 0.5154,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 2.3508771929824563,
483
+ "grad_norm": 0.5435761853560287,
484
+ "learning_rate": 2.882334907183115e-05,
485
+ "loss": 0.5696,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 2.3859649122807016,
490
+ "grad_norm": 0.4733058013404621,
491
+ "learning_rate": 2.8238758524311314e-05,
492
+ "loss": 0.5286,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 2.4210526315789473,
497
+ "grad_norm": 0.7320896114370156,
498
+ "learning_rate": 2.7652360990576453e-05,
499
+ "loss": 0.6029,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 2.456140350877193,
504
+ "grad_norm": 0.5143853256014193,
505
+ "learning_rate": 2.7064483636808313e-05,
506
+ "loss": 0.5373,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 2.4912280701754383,
511
+ "grad_norm": 0.47578504969519847,
512
+ "learning_rate": 2.6475454454818073e-05,
513
+ "loss": 0.5372,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 2.526315789473684,
518
+ "grad_norm": 0.47485068019332843,
519
+ "learning_rate": 2.5885602079051353e-05,
520
+ "loss": 0.4714,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 2.56140350877193,
525
+ "grad_norm": 0.5454183913380498,
526
+ "learning_rate": 2.529525560323462e-05,
527
+ "loss": 0.559,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 2.5964912280701755,
532
+ "grad_norm": 0.4805059890683054,
533
+ "learning_rate": 2.470474439676539e-05,
534
+ "loss": 0.5432,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 2.6315789473684212,
539
+ "grad_norm": 0.549573444590586,
540
+ "learning_rate": 2.4114397920948657e-05,
541
+ "loss": 0.544,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 2.6666666666666665,
546
+ "grad_norm": 0.44171024079549115,
547
+ "learning_rate": 2.3524545545181933e-05,
548
+ "loss": 0.5719,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 2.7017543859649122,
553
+ "grad_norm": 0.40375286197219823,
554
+ "learning_rate": 2.2935516363191693e-05,
555
+ "loss": 0.5574,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 2.736842105263158,
560
+ "grad_norm": 0.44079765151450895,
561
+ "learning_rate": 2.2347639009423553e-05,
562
+ "loss": 0.5473,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 2.7719298245614032,
567
+ "grad_norm": 0.3837140844283907,
568
+ "learning_rate": 2.1761241475688695e-05,
569
+ "loss": 0.5,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 2.807017543859649,
574
+ "grad_norm": 0.36498294953041693,
575
+ "learning_rate": 2.117665092816885e-05,
576
+ "loss": 0.4579,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 2.8421052631578947,
581
+ "grad_norm": 0.4176708774075213,
582
+ "learning_rate": 2.059419352488196e-05,
583
+ "loss": 0.5302,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 2.8771929824561404,
588
+ "grad_norm": 0.3801878678793892,
589
+ "learning_rate": 2.0014194233710193e-05,
590
+ "loss": 0.5338,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 2.912280701754386,
595
+ "grad_norm": 0.46768889533074776,
596
+ "learning_rate": 1.9436976651092144e-05,
597
+ "loss": 0.5636,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 2.9473684210526314,
602
+ "grad_norm": 0.41361908756083027,
603
+ "learning_rate": 1.8862862821480025e-05,
604
+ "loss": 0.4871,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 2.982456140350877,
609
+ "grad_norm": 0.35900229029204755,
610
+ "learning_rate": 1.829217305766289e-05,
611
+ "loss": 0.545,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 3.0,
616
+ "grad_norm": 0.35900229029204755,
617
+ "learning_rate": 1.7725225762055887e-05,
618
+ "loss": 0.3114,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 3.0350877192982457,
623
+ "grad_norm": 1.039088884520627,
624
+ "learning_rate": 1.7162337249055477e-05,
625
+ "loss": 0.4039,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 3.0701754385964914,
630
+ "grad_norm": 1.2225625714935646,
631
+ "learning_rate": 1.6603821568559437e-05,
632
+ "loss": 0.4477,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 3.1052631578947367,
637
+ "grad_norm": 0.517211355092857,
638
+ "learning_rate": 1.604999033075051e-05,
639
+ "loss": 0.4303,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 3.1403508771929824,
644
+ "grad_norm": 1.2522323591078175,
645
+ "learning_rate": 1.5501152532241005e-05,
646
+ "loss": 0.3948,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 3.175438596491228,
651
+ "grad_norm": 1.4369568509391157,
652
+ "learning_rate": 1.495761438367577e-05,
653
+ "loss": 0.3998,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 3.2105263157894735,
658
+ "grad_norm": 1.080289936134096,
659
+ "learning_rate": 1.4419679138889378e-05,
660
+ "loss": 0.4489,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 3.245614035087719,
665
+ "grad_norm": 0.3959735616331335,
666
+ "learning_rate": 1.3887646925713116e-05,
667
+ "loss": 0.3701,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 3.280701754385965,
672
+ "grad_norm": 0.6536961872630214,
673
+ "learning_rate": 1.3361814578525922e-05,
674
+ "loss": 0.3669,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 3.3157894736842106,
679
+ "grad_norm": 0.9236561795720727,
680
+ "learning_rate": 1.2842475472642968e-05,
681
+ "loss": 0.4101,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 3.3508771929824563,
686
+ "grad_norm": 0.624339506754103,
687
+ "learning_rate": 1.2329919360634002e-05,
688
+ "loss": 0.3797,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 3.3859649122807016,
693
+ "grad_norm": 0.4687946351643177,
694
+ "learning_rate": 1.182443221066303e-05,
695
+ "loss": 0.3414,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 3.4210526315789473,
700
+ "grad_norm": 0.47331039977421663,
701
+ "learning_rate": 1.1326296046939333e-05,
702
+ "loss": 0.3378,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 3.456140350877193,
707
+ "grad_norm": 0.4780339258304509,
708
+ "learning_rate": 1.083578879236895e-05,
709
+ "loss": 0.3148,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 3.4912280701754383,
714
+ "grad_norm": 0.472991860964808,
715
+ "learning_rate": 1.0353184113494386e-05,
716
+ "loss": 0.362,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 3.526315789473684,
721
+ "grad_norm": 0.5473896318173218,
722
+ "learning_rate": 9.878751267809069e-06,
723
+ "loss": 0.366,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 3.56140350877193,
728
+ "grad_norm": 0.49421552981457206,
729
+ "learning_rate": 9.412754953531663e-06,
730
+ "loss": 0.3753,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 3.5964912280701755,
735
+ "grad_norm": 0.41594310192216705,
736
+ "learning_rate": 8.955455161924217e-06,
737
+ "loss": 0.3392,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 3.6315789473684212,
742
+ "grad_norm": 0.3728949229584135,
743
+ "learning_rate": 8.507107032236322e-06,
744
+ "loss": 0.3265,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 3.6666666666666665,
749
+ "grad_norm": 0.4105187771371921,
750
+ "learning_rate": 8.067960709356478e-06,
751
+ "loss": 0.3411,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 3.7017543859649122,
756
+ "grad_norm": 0.4016073311581445,
757
+ "learning_rate": 7.638261204249784e-06,
758
+ "loss": 0.3637,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 3.736842105263158,
763
+ "grad_norm": 0.5286770481220647,
764
+ "learning_rate": 7.218248257260127e-06,
765
+ "loss": 0.4157,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 3.7719298245614032,
770
+ "grad_norm": 0.3890055642916449,
771
+ "learning_rate": 6.8081562043528445e-06,
772
+ "loss": 0.4434,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 3.807017543859649,
777
+ "grad_norm": 0.38635140940193147,
778
+ "learning_rate": 6.40821384637276e-06,
779
+ "loss": 0.367,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 3.8421052631578947,
784
+ "grad_norm": 0.37252947829119043,
785
+ "learning_rate": 6.018644321390288e-06,
786
+ "loss": 0.3714,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 3.8771929824561404,
791
+ "grad_norm": 0.3916205714633107,
792
+ "learning_rate": 5.639664980207024e-06,
793
+ "loss": 0.333,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 3.912280701754386,
798
+ "grad_norm": 0.39308963657720947,
799
+ "learning_rate": 5.271487265090163e-06,
800
+ "loss": 0.3425,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 3.9473684210526314,
805
+ "grad_norm": 0.34722098404157115,
806
+ "learning_rate": 4.914316591803475e-06,
807
+ "loss": 0.3638,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 3.982456140350877,
812
+ "grad_norm": 0.33647207931419637,
813
+ "learning_rate": 4.56835223500055e-06,
814
+ "loss": 0.3789,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 4.0,
819
+ "grad_norm": 0.5236255764345163,
820
+ "learning_rate": 4.23378721704443e-06,
821
+ "loss": 0.2909,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 4.035087719298246,
826
+ "grad_norm": 0.8841805541656866,
827
+ "learning_rate": 3.9108082003154325e-06,
828
+ "loss": 0.2855,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 4.0701754385964914,
833
+ "grad_norm": 0.6923099905470135,
834
+ "learning_rate": 3.5995953830675e-06,
835
+ "loss": 0.2633,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 4.105263157894737,
840
+ "grad_norm": 0.6620353497411435,
841
+ "learning_rate": 3.3003223988909234e-06,
842
+ "loss": 0.3226,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 4.140350877192983,
847
+ "grad_norm": 0.650008912023062,
848
+ "learning_rate": 3.013156219837776e-06,
849
+ "loss": 0.2737,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 4.175438596491228,
854
+ "grad_norm": 0.3605625952290065,
855
+ "learning_rate": 2.7382570632638854e-06,
856
+ "loss": 0.2583,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 4.2105263157894735,
861
+ "grad_norm": 0.4135475914214625,
862
+ "learning_rate": 2.475778302439524e-06,
863
+ "loss": 0.2862,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 4.245614035087719,
868
+ "grad_norm": 0.43014886648158956,
869
+ "learning_rate": 2.2258663809784892e-06,
870
+ "loss": 0.2859,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 4.280701754385965,
875
+ "grad_norm": 0.45188021970301084,
876
+ "learning_rate": 1.988660731133499e-06,
877
+ "loss": 0.2567,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 4.315789473684211,
882
+ "grad_norm": 0.49482131490182824,
883
+ "learning_rate": 1.7642936960033578e-06,
884
+ "loss": 0.3123,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 4.350877192982456,
889
+ "grad_norm": 0.506378432005352,
890
+ "learning_rate": 1.552890455695369e-06,
891
+ "loss": 0.2893,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 4.385964912280702,
896
+ "grad_norm": 0.6006692479468094,
897
+ "learning_rate": 1.3545689574841342e-06,
898
+ "loss": 0.2996,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 4.421052631578947,
903
+ "grad_norm": 0.4134648249918282,
904
+ "learning_rate": 1.1694398500057714e-06,
905
+ "loss": 0.2885,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 4.456140350877193,
910
+ "grad_norm": 0.4541281916604005,
911
+ "learning_rate": 9.97606421524186e-07,
912
+ "loss": 0.315,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 4.491228070175438,
917
+ "grad_norm": 0.43627770320061965,
918
+ "learning_rate": 8.391645423039357e-07,
919
+ "loss": 0.3276,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 4.526315789473684,
924
+ "grad_norm": 0.3477912958948792,
925
+ "learning_rate": 6.942026111217359e-07,
926
+ "loss": 0.2757,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 4.56140350877193,
931
+ "grad_norm": 0.39848546143547475,
932
+ "learning_rate": 5.628015059465363e-07,
933
+ "loss": 0.2936,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 4.5964912280701755,
938
+ "grad_norm": 0.3221233461151991,
939
+ "learning_rate": 4.4503453881561407e-07,
940
+ "loss": 0.2509,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 4.631578947368421,
945
+ "grad_norm": 0.340020385629736,
946
+ "learning_rate": 3.4096741493194197e-07,
947
+ "loss": 0.2381,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 4.666666666666667,
952
+ "grad_norm": 0.33265087313567104,
953
+ "learning_rate": 2.506581960055432e-07,
954
+ "loss": 0.279,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 4.701754385964913,
959
+ "grad_norm": 0.31762848250059117,
960
+ "learning_rate": 1.7415726785939834e-07,
961
+ "loss": 0.2569,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 4.7368421052631575,
966
+ "grad_norm": 0.3160736494467554,
967
+ "learning_rate": 1.1150731231791279e-07,
968
+ "loss": 0.2967,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 4.771929824561403,
973
+ "grad_norm": 0.32521146124916683,
974
+ "learning_rate": 6.274328339360703e-08,
975
+ "loss": 0.3195,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 4.807017543859649,
980
+ "grad_norm": 0.34493893878781917,
981
+ "learning_rate": 2.789238778540537e-08,
982
+ "loss": 0.2815,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 4.842105263157895,
987
+ "grad_norm": 0.3235167178806271,
988
+ "learning_rate": 6.974069699314245e-09,
989
+ "loss": 0.2724,
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 sha256:1d5258a2c8f9a5bdae8915825e2fb8920d3e2da89a09b4c5ec16fd2bd74a14f6
3
+ size 8017
vocab.json ADDED
The diff for this file is too large to render. See raw diff