anurag-deo commited on
Commit
7dde336
·
verified ·
1 Parent(s): ba1505e

Upload checkpoint

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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention"
43
+ ],
44
+ "max_position_embeddings": 32768,
45
+ "max_window_layers": 28,
46
+ "model_type": "qwen3",
47
+ "num_attention_heads": 16,
48
+ "num_hidden_layers": 28,
49
+ "num_key_value_heads": 8,
50
+ "pad_token_id": 151643,
51
+ "problem_type": "single_label_classification",
52
+ "rms_norm_eps": 1e-06,
53
+ "rope_scaling": null,
54
+ "rope_theta": 1000000,
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": true,
57
+ "transformers_version": "4.56.2",
58
+ "use_cache": true,
59
+ "use_sliding_window": false,
60
+ "vocab_size": 151669
61
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf8e05b10f187149ff63f8f7e1013d3764d88a66873d68405dc7472b6d17328
3
+ size 1191592464
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108bdbccf11992741ed5c571b03c54280f82834800f0f44d305ad5f34edd3de9
3
+ size 2383380107
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33f644dac6433e61e349ef8669f0adc94c00610dfec6cfb02354c5c90528361
3
+ size 1465
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:def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a
3
+ size 11423705
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
trainer_state.json ADDED
@@ -0,0 +1,793 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 5000,
3
+ "best_metric": 0.9975800357733842,
4
+ "best_model_checkpoint": "/workspace/binary_code_classification/checkpoint-5000",
5
+ "epoch": 0.64,
6
+ "eval_steps": 1000,
7
+ "global_step": 5000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0064,
14
+ "grad_norm": 28.0,
15
+ "learning_rate": 1.9874568027646234e-05,
16
+ "loss": 1.2089,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.0128,
21
+ "grad_norm": 3.515625,
22
+ "learning_rate": 1.9746576219121978e-05,
23
+ "loss": 0.4148,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.0192,
28
+ "grad_norm": 264.0,
29
+ "learning_rate": 1.9618584410597722e-05,
30
+ "loss": 0.308,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.0256,
35
+ "grad_norm": 99.0,
36
+ "learning_rate": 1.949059260207347e-05,
37
+ "loss": 0.33,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.032,
42
+ "grad_norm": 94.0,
43
+ "learning_rate": 1.9362600793549217e-05,
44
+ "loss": 0.2195,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.0384,
49
+ "grad_norm": 7.09375,
50
+ "learning_rate": 1.923460898502496e-05,
51
+ "loss": 0.4419,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.0448,
56
+ "grad_norm": 0.765625,
57
+ "learning_rate": 1.9106617176500705e-05,
58
+ "loss": 0.2258,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.0512,
63
+ "grad_norm": 57.25,
64
+ "learning_rate": 1.8978625367976452e-05,
65
+ "loss": 0.2686,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.0576,
70
+ "grad_norm": 12.5,
71
+ "learning_rate": 1.8850633559452196e-05,
72
+ "loss": 0.3966,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.064,
77
+ "grad_norm": 64.5,
78
+ "learning_rate": 1.872264175092794e-05,
79
+ "loss": 0.2699,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.0704,
84
+ "grad_norm": 0.51171875,
85
+ "learning_rate": 1.8594649942403687e-05,
86
+ "loss": 0.2411,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.0768,
91
+ "grad_norm": 8.6875,
92
+ "learning_rate": 1.8466658133879435e-05,
93
+ "loss": 0.2031,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.0832,
98
+ "grad_norm": 2.8125,
99
+ "learning_rate": 1.833866632535518e-05,
100
+ "loss": 0.3483,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.0896,
105
+ "grad_norm": 0.0150146484375,
106
+ "learning_rate": 1.8210674516830923e-05,
107
+ "loss": 0.1653,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.096,
112
+ "grad_norm": 4.875,
113
+ "learning_rate": 1.808268270830667e-05,
114
+ "loss": 0.2272,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.1024,
119
+ "grad_norm": 0.34765625,
120
+ "learning_rate": 1.7954690899782414e-05,
121
+ "loss": 0.0645,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.1088,
126
+ "grad_norm": 0.1513671875,
127
+ "learning_rate": 1.782669909125816e-05,
128
+ "loss": 0.2417,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.1152,
133
+ "grad_norm": 60.5,
134
+ "learning_rate": 1.7698707282733905e-05,
135
+ "loss": 0.2026,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.1216,
140
+ "grad_norm": 22.5,
141
+ "learning_rate": 1.7570715474209653e-05,
142
+ "loss": 0.2203,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.128,
147
+ "grad_norm": 0.96875,
148
+ "learning_rate": 1.7442723665685397e-05,
149
+ "loss": 0.1783,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.128,
154
+ "eval_accuracy": 0.99566,
155
+ "eval_f1": 0.9958571974035891,
156
+ "eval_loss": 0.024950675666332245,
157
+ "eval_runtime": 913.3142,
158
+ "eval_samples_per_second": 109.491,
159
+ "eval_steps_per_second": 13.686,
160
+ "step": 1000
161
+ },
162
+ {
163
+ "epoch": 0.1344,
164
+ "grad_norm": 5.40625,
165
+ "learning_rate": 1.731473185716114e-05,
166
+ "loss": 0.1486,
167
+ "step": 1050
168
+ },
169
+ {
170
+ "epoch": 0.1408,
171
+ "grad_norm": 0.400390625,
172
+ "learning_rate": 1.7186740048636888e-05,
173
+ "loss": 0.2601,
174
+ "step": 1100
175
+ },
176
+ {
177
+ "epoch": 0.1472,
178
+ "grad_norm": 0.16796875,
179
+ "learning_rate": 1.7058748240112635e-05,
180
+ "loss": 0.2022,
181
+ "step": 1150
182
+ },
183
+ {
184
+ "epoch": 0.1536,
185
+ "grad_norm": 0.2890625,
186
+ "learning_rate": 1.693075643158838e-05,
187
+ "loss": 0.1838,
188
+ "step": 1200
189
+ },
190
+ {
191
+ "epoch": 0.16,
192
+ "grad_norm": 0.11376953125,
193
+ "learning_rate": 1.6802764623064127e-05,
194
+ "loss": 0.1088,
195
+ "step": 1250
196
+ },
197
+ {
198
+ "epoch": 0.1664,
199
+ "grad_norm": 5.53125,
200
+ "learning_rate": 1.667477281453987e-05,
201
+ "loss": 0.2011,
202
+ "step": 1300
203
+ },
204
+ {
205
+ "epoch": 0.1728,
206
+ "grad_norm": 0.0157470703125,
207
+ "learning_rate": 1.6546781006015615e-05,
208
+ "loss": 0.1801,
209
+ "step": 1350
210
+ },
211
+ {
212
+ "epoch": 0.1792,
213
+ "grad_norm": 0.0203857421875,
214
+ "learning_rate": 1.6418789197491362e-05,
215
+ "loss": 0.1805,
216
+ "step": 1400
217
+ },
218
+ {
219
+ "epoch": 0.1856,
220
+ "grad_norm": 0.0703125,
221
+ "learning_rate": 1.629079738896711e-05,
222
+ "loss": 0.2422,
223
+ "step": 1450
224
+ },
225
+ {
226
+ "epoch": 0.192,
227
+ "grad_norm": 1.1875,
228
+ "learning_rate": 1.6162805580442853e-05,
229
+ "loss": 0.1445,
230
+ "step": 1500
231
+ },
232
+ {
233
+ "epoch": 0.1984,
234
+ "grad_norm": 0.0012664794921875,
235
+ "learning_rate": 1.6034813771918597e-05,
236
+ "loss": 0.2215,
237
+ "step": 1550
238
+ },
239
+ {
240
+ "epoch": 0.2048,
241
+ "grad_norm": 0.0174560546875,
242
+ "learning_rate": 1.5906821963394345e-05,
243
+ "loss": 0.1468,
244
+ "step": 1600
245
+ },
246
+ {
247
+ "epoch": 0.2112,
248
+ "grad_norm": 0.302734375,
249
+ "learning_rate": 1.5778830154870092e-05,
250
+ "loss": 0.1715,
251
+ "step": 1650
252
+ },
253
+ {
254
+ "epoch": 0.2176,
255
+ "grad_norm": 0.55078125,
256
+ "learning_rate": 1.5650838346345836e-05,
257
+ "loss": 0.1522,
258
+ "step": 1700
259
+ },
260
+ {
261
+ "epoch": 0.224,
262
+ "grad_norm": 0.00408935546875,
263
+ "learning_rate": 1.552284653782158e-05,
264
+ "loss": 0.1444,
265
+ "step": 1750
266
+ },
267
+ {
268
+ "epoch": 0.2304,
269
+ "grad_norm": 0.02880859375,
270
+ "learning_rate": 1.5394854729297327e-05,
271
+ "loss": 0.2084,
272
+ "step": 1800
273
+ },
274
+ {
275
+ "epoch": 0.2368,
276
+ "grad_norm": 0.01190185546875,
277
+ "learning_rate": 1.526686292077307e-05,
278
+ "loss": 0.1653,
279
+ "step": 1850
280
+ },
281
+ {
282
+ "epoch": 0.2432,
283
+ "grad_norm": 35.75,
284
+ "learning_rate": 1.5138871112248817e-05,
285
+ "loss": 0.2464,
286
+ "step": 1900
287
+ },
288
+ {
289
+ "epoch": 0.2496,
290
+ "grad_norm": 0.043212890625,
291
+ "learning_rate": 1.5010879303724564e-05,
292
+ "loss": 0.16,
293
+ "step": 1950
294
+ },
295
+ {
296
+ "epoch": 0.256,
297
+ "grad_norm": 0.1806640625,
298
+ "learning_rate": 1.4882887495200308e-05,
299
+ "loss": 0.1486,
300
+ "step": 2000
301
+ },
302
+ {
303
+ "epoch": 0.256,
304
+ "eval_accuracy": 0.99674,
305
+ "eval_f1": 0.996885389995032,
306
+ "eval_loss": 0.017144883051514626,
307
+ "eval_runtime": 909.1435,
308
+ "eval_samples_per_second": 109.994,
309
+ "eval_steps_per_second": 13.749,
310
+ "step": 2000
311
+ },
312
+ {
313
+ "epoch": 0.2624,
314
+ "grad_norm": 55.0,
315
+ "learning_rate": 1.4754895686676054e-05,
316
+ "loss": 0.0849,
317
+ "step": 2050
318
+ },
319
+ {
320
+ "epoch": 0.2688,
321
+ "grad_norm": 121.0,
322
+ "learning_rate": 1.46269038781518e-05,
323
+ "loss": 0.2893,
324
+ "step": 2100
325
+ },
326
+ {
327
+ "epoch": 0.2752,
328
+ "grad_norm": 192.0,
329
+ "learning_rate": 1.4498912069627544e-05,
330
+ "loss": 0.1689,
331
+ "step": 2150
332
+ },
333
+ {
334
+ "epoch": 0.2816,
335
+ "grad_norm": 0.0830078125,
336
+ "learning_rate": 1.4370920261103291e-05,
337
+ "loss": 0.1342,
338
+ "step": 2200
339
+ },
340
+ {
341
+ "epoch": 0.288,
342
+ "grad_norm": 0.166015625,
343
+ "learning_rate": 1.4242928452579037e-05,
344
+ "loss": 0.1543,
345
+ "step": 2250
346
+ },
347
+ {
348
+ "epoch": 0.2944,
349
+ "grad_norm": 2.4375,
350
+ "learning_rate": 1.4114936644054782e-05,
351
+ "loss": 0.1923,
352
+ "step": 2300
353
+ },
354
+ {
355
+ "epoch": 0.3008,
356
+ "grad_norm": 3.625,
357
+ "learning_rate": 1.3986944835530526e-05,
358
+ "loss": 0.0801,
359
+ "step": 2350
360
+ },
361
+ {
362
+ "epoch": 0.3072,
363
+ "grad_norm": 2.859375,
364
+ "learning_rate": 1.3858953027006272e-05,
365
+ "loss": 0.0627,
366
+ "step": 2400
367
+ },
368
+ {
369
+ "epoch": 0.3136,
370
+ "grad_norm": 0.0220947265625,
371
+ "learning_rate": 1.3730961218482018e-05,
372
+ "loss": 0.179,
373
+ "step": 2450
374
+ },
375
+ {
376
+ "epoch": 0.32,
377
+ "grad_norm": 0.009765625,
378
+ "learning_rate": 1.3602969409957765e-05,
379
+ "loss": 0.1449,
380
+ "step": 2500
381
+ },
382
+ {
383
+ "epoch": 0.3264,
384
+ "grad_norm": 0.05029296875,
385
+ "learning_rate": 1.3474977601433509e-05,
386
+ "loss": 0.1721,
387
+ "step": 2550
388
+ },
389
+ {
390
+ "epoch": 0.3328,
391
+ "grad_norm": 27.0,
392
+ "learning_rate": 1.3346985792909255e-05,
393
+ "loss": 0.1431,
394
+ "step": 2600
395
+ },
396
+ {
397
+ "epoch": 0.3392,
398
+ "grad_norm": 0.17578125,
399
+ "learning_rate": 1.3218993984385e-05,
400
+ "loss": 0.1559,
401
+ "step": 2650
402
+ },
403
+ {
404
+ "epoch": 0.3456,
405
+ "grad_norm": 65.5,
406
+ "learning_rate": 1.3091002175860746e-05,
407
+ "loss": 0.1233,
408
+ "step": 2700
409
+ },
410
+ {
411
+ "epoch": 0.352,
412
+ "grad_norm": 0.01513671875,
413
+ "learning_rate": 1.296301036733649e-05,
414
+ "loss": 0.1612,
415
+ "step": 2750
416
+ },
417
+ {
418
+ "epoch": 0.3584,
419
+ "grad_norm": 143.0,
420
+ "learning_rate": 1.2835018558812237e-05,
421
+ "loss": 0.1892,
422
+ "step": 2800
423
+ },
424
+ {
425
+ "epoch": 0.3648,
426
+ "grad_norm": 31.25,
427
+ "learning_rate": 1.2707026750287983e-05,
428
+ "loss": 0.1182,
429
+ "step": 2850
430
+ },
431
+ {
432
+ "epoch": 0.3712,
433
+ "grad_norm": 0.029296875,
434
+ "learning_rate": 1.2579034941763729e-05,
435
+ "loss": 0.0563,
436
+ "step": 2900
437
+ },
438
+ {
439
+ "epoch": 0.3776,
440
+ "grad_norm": 18.75,
441
+ "learning_rate": 1.2451043133239473e-05,
442
+ "loss": 0.1102,
443
+ "step": 2950
444
+ },
445
+ {
446
+ "epoch": 0.384,
447
+ "grad_norm": 0.0036773681640625,
448
+ "learning_rate": 1.2323051324715218e-05,
449
+ "loss": 0.1909,
450
+ "step": 3000
451
+ },
452
+ {
453
+ "epoch": 0.384,
454
+ "eval_accuracy": 0.9971,
455
+ "eval_f1": 0.9972248272694214,
456
+ "eval_loss": 0.017062190920114517,
457
+ "eval_runtime": 904.9768,
458
+ "eval_samples_per_second": 110.5,
459
+ "eval_steps_per_second": 13.813,
460
+ "step": 3000
461
+ },
462
+ {
463
+ "epoch": 0.3904,
464
+ "grad_norm": 5.15625,
465
+ "learning_rate": 1.2195059516190966e-05,
466
+ "loss": 0.1288,
467
+ "step": 3050
468
+ },
469
+ {
470
+ "epoch": 0.3968,
471
+ "grad_norm": 16.625,
472
+ "learning_rate": 1.2067067707666711e-05,
473
+ "loss": 0.1788,
474
+ "step": 3100
475
+ },
476
+ {
477
+ "epoch": 0.4032,
478
+ "grad_norm": 0.1396484375,
479
+ "learning_rate": 1.1939075899142455e-05,
480
+ "loss": 0.1393,
481
+ "step": 3150
482
+ },
483
+ {
484
+ "epoch": 0.4096,
485
+ "grad_norm": 0.0078125,
486
+ "learning_rate": 1.1811084090618201e-05,
487
+ "loss": 0.1543,
488
+ "step": 3200
489
+ },
490
+ {
491
+ "epoch": 0.416,
492
+ "grad_norm": 0.248046875,
493
+ "learning_rate": 1.1683092282093947e-05,
494
+ "loss": 0.1036,
495
+ "step": 3250
496
+ },
497
+ {
498
+ "epoch": 0.4224,
499
+ "grad_norm": 0.10205078125,
500
+ "learning_rate": 1.155510047356969e-05,
501
+ "loss": 0.1249,
502
+ "step": 3300
503
+ },
504
+ {
505
+ "epoch": 0.4288,
506
+ "grad_norm": 0.66796875,
507
+ "learning_rate": 1.1427108665045438e-05,
508
+ "loss": 0.1616,
509
+ "step": 3350
510
+ },
511
+ {
512
+ "epoch": 0.4352,
513
+ "grad_norm": 177.0,
514
+ "learning_rate": 1.1299116856521184e-05,
515
+ "loss": 0.1315,
516
+ "step": 3400
517
+ },
518
+ {
519
+ "epoch": 0.4416,
520
+ "grad_norm": 1.4140625,
521
+ "learning_rate": 1.117112504799693e-05,
522
+ "loss": 0.0905,
523
+ "step": 3450
524
+ },
525
+ {
526
+ "epoch": 0.448,
527
+ "grad_norm": 0.0159912109375,
528
+ "learning_rate": 1.1043133239472675e-05,
529
+ "loss": 0.0881,
530
+ "step": 3500
531
+ },
532
+ {
533
+ "epoch": 0.4544,
534
+ "grad_norm": 0.263671875,
535
+ "learning_rate": 1.0915141430948419e-05,
536
+ "loss": 0.0923,
537
+ "step": 3550
538
+ },
539
+ {
540
+ "epoch": 0.4608,
541
+ "grad_norm": 0.322265625,
542
+ "learning_rate": 1.0787149622424166e-05,
543
+ "loss": 0.1584,
544
+ "step": 3600
545
+ },
546
+ {
547
+ "epoch": 0.4672,
548
+ "grad_norm": 0.1435546875,
549
+ "learning_rate": 1.0659157813899912e-05,
550
+ "loss": 0.1988,
551
+ "step": 3650
552
+ },
553
+ {
554
+ "epoch": 0.4736,
555
+ "grad_norm": 120.0,
556
+ "learning_rate": 1.0531166005375658e-05,
557
+ "loss": 0.1292,
558
+ "step": 3700
559
+ },
560
+ {
561
+ "epoch": 0.48,
562
+ "grad_norm": 0.0037841796875,
563
+ "learning_rate": 1.0403174196851402e-05,
564
+ "loss": 0.1181,
565
+ "step": 3750
566
+ },
567
+ {
568
+ "epoch": 0.4864,
569
+ "grad_norm": 0.044677734375,
570
+ "learning_rate": 1.0275182388327147e-05,
571
+ "loss": 0.1447,
572
+ "step": 3800
573
+ },
574
+ {
575
+ "epoch": 0.4928,
576
+ "grad_norm": 0.045654296875,
577
+ "learning_rate": 1.0147190579802893e-05,
578
+ "loss": 0.0817,
579
+ "step": 3850
580
+ },
581
+ {
582
+ "epoch": 0.4992,
583
+ "grad_norm": 35.5,
584
+ "learning_rate": 1.001919877127864e-05,
585
+ "loss": 0.1444,
586
+ "step": 3900
587
+ },
588
+ {
589
+ "epoch": 0.5056,
590
+ "grad_norm": 0.037841796875,
591
+ "learning_rate": 9.891206962754384e-06,
592
+ "loss": 0.0917,
593
+ "step": 3950
594
+ },
595
+ {
596
+ "epoch": 0.512,
597
+ "grad_norm": 27.25,
598
+ "learning_rate": 9.76321515423013e-06,
599
+ "loss": 0.1268,
600
+ "step": 4000
601
+ },
602
+ {
603
+ "epoch": 0.512,
604
+ "eval_accuracy": 0.99744,
605
+ "eval_f1": 0.997552862004359,
606
+ "eval_loss": 0.013922800309956074,
607
+ "eval_runtime": 898.5674,
608
+ "eval_samples_per_second": 111.288,
609
+ "eval_steps_per_second": 13.911,
610
+ "step": 4000
611
+ },
612
+ {
613
+ "epoch": 0.5184,
614
+ "grad_norm": 0.033447265625,
615
+ "learning_rate": 9.635223345705876e-06,
616
+ "loss": 0.07,
617
+ "step": 4050
618
+ },
619
+ {
620
+ "epoch": 0.5248,
621
+ "grad_norm": 190.0,
622
+ "learning_rate": 9.507231537181621e-06,
623
+ "loss": 0.1475,
624
+ "step": 4100
625
+ },
626
+ {
627
+ "epoch": 0.5312,
628
+ "grad_norm": 0.0235595703125,
629
+ "learning_rate": 9.379239728657367e-06,
630
+ "loss": 0.0784,
631
+ "step": 4150
632
+ },
633
+ {
634
+ "epoch": 0.5376,
635
+ "grad_norm": 294.0,
636
+ "learning_rate": 9.251247920133111e-06,
637
+ "loss": 0.1048,
638
+ "step": 4200
639
+ },
640
+ {
641
+ "epoch": 0.544,
642
+ "grad_norm": 0.1796875,
643
+ "learning_rate": 9.123256111608858e-06,
644
+ "loss": 0.0931,
645
+ "step": 4250
646
+ },
647
+ {
648
+ "epoch": 0.5504,
649
+ "grad_norm": 17.875,
650
+ "learning_rate": 8.995264303084602e-06,
651
+ "loss": 0.141,
652
+ "step": 4300
653
+ },
654
+ {
655
+ "epoch": 0.5568,
656
+ "grad_norm": 1.5703125,
657
+ "learning_rate": 8.867272494560348e-06,
658
+ "loss": 0.0873,
659
+ "step": 4350
660
+ },
661
+ {
662
+ "epoch": 0.5632,
663
+ "grad_norm": 0.055908203125,
664
+ "learning_rate": 8.739280686036095e-06,
665
+ "loss": 0.1422,
666
+ "step": 4400
667
+ },
668
+ {
669
+ "epoch": 0.5696,
670
+ "grad_norm": 0.007293701171875,
671
+ "learning_rate": 8.61128887751184e-06,
672
+ "loss": 0.1255,
673
+ "step": 4450
674
+ },
675
+ {
676
+ "epoch": 0.576,
677
+ "grad_norm": 35.75,
678
+ "learning_rate": 8.483297068987587e-06,
679
+ "loss": 0.0567,
680
+ "step": 4500
681
+ },
682
+ {
683
+ "epoch": 0.5824,
684
+ "grad_norm": 0.047607421875,
685
+ "learning_rate": 8.35530526046333e-06,
686
+ "loss": 0.1207,
687
+ "step": 4550
688
+ },
689
+ {
690
+ "epoch": 0.5888,
691
+ "grad_norm": 0.12158203125,
692
+ "learning_rate": 8.227313451939076e-06,
693
+ "loss": 0.148,
694
+ "step": 4600
695
+ },
696
+ {
697
+ "epoch": 0.5952,
698
+ "grad_norm": 0.1318359375,
699
+ "learning_rate": 8.099321643414822e-06,
700
+ "loss": 0.0824,
701
+ "step": 4650
702
+ },
703
+ {
704
+ "epoch": 0.6016,
705
+ "grad_norm": 0.0257568359375,
706
+ "learning_rate": 7.971329834890568e-06,
707
+ "loss": 0.0608,
708
+ "step": 4700
709
+ },
710
+ {
711
+ "epoch": 0.608,
712
+ "grad_norm": 36.5,
713
+ "learning_rate": 7.843338026366313e-06,
714
+ "loss": 0.1218,
715
+ "step": 4750
716
+ },
717
+ {
718
+ "epoch": 0.6144,
719
+ "grad_norm": 0.1455078125,
720
+ "learning_rate": 7.715346217842059e-06,
721
+ "loss": 0.1319,
722
+ "step": 4800
723
+ },
724
+ {
725
+ "epoch": 0.6208,
726
+ "grad_norm": 0.19921875,
727
+ "learning_rate": 7.587354409317804e-06,
728
+ "loss": 0.1269,
729
+ "step": 4850
730
+ },
731
+ {
732
+ "epoch": 0.6272,
733
+ "grad_norm": 0.0172119140625,
734
+ "learning_rate": 7.4593626007935496e-06,
735
+ "loss": 0.1295,
736
+ "step": 4900
737
+ },
738
+ {
739
+ "epoch": 0.6336,
740
+ "grad_norm": 42.0,
741
+ "learning_rate": 7.331370792269295e-06,
742
+ "loss": 0.1743,
743
+ "step": 4950
744
+ },
745
+ {
746
+ "epoch": 0.64,
747
+ "grad_norm": 0.60546875,
748
+ "learning_rate": 7.203378983745041e-06,
749
+ "loss": 0.1283,
750
+ "step": 5000
751
+ },
752
+ {
753
+ "epoch": 0.64,
754
+ "eval_accuracy": 0.99747,
755
+ "eval_f1": 0.9975800357733842,
756
+ "eval_loss": 0.012660462409257889,
757
+ "eval_runtime": 867.1685,
758
+ "eval_samples_per_second": 115.318,
759
+ "eval_steps_per_second": 14.415,
760
+ "step": 5000
761
+ }
762
+ ],
763
+ "logging_steps": 50,
764
+ "max_steps": 7813,
765
+ "num_input_tokens_seen": 0,
766
+ "num_train_epochs": 1,
767
+ "save_steps": 1000,
768
+ "stateful_callbacks": {
769
+ "EarlyStoppingCallback": {
770
+ "args": {
771
+ "early_stopping_patience": 3,
772
+ "early_stopping_threshold": 0.0
773
+ },
774
+ "attributes": {
775
+ "early_stopping_patience_counter": 0
776
+ }
777
+ },
778
+ "TrainerControl": {
779
+ "args": {
780
+ "should_epoch_stop": false,
781
+ "should_evaluate": false,
782
+ "should_log": false,
783
+ "should_save": true,
784
+ "should_training_stop": false
785
+ },
786
+ "attributes": {}
787
+ }
788
+ },
789
+ "total_flos": 5.778779476171162e+17,
790
+ "train_batch_size": 8,
791
+ "trial_name": null,
792
+ "trial_params": null
793
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e2bd87fd42cb6ef063dd8bf3fbf54e2521ddd3d4647c580e6c25c3cddc1357
3
+ size 5713
vocab.json ADDED
The diff for this file is too large to render. See raw diff