pruas commited on
Commit
11aacd0
1 Parent(s): e4c6310

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B",
14
+ "2": "I"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B": "1",
20
+ "I": "2",
21
+ "O": "0"
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.9.0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 30522
35
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a039a6ca9e3e3ca341ce47c0fdfeba3b94130c86c9c7dbf8d88dee6e1025a3e
3
+ size 871267045
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d0f2ef6fe27ef706eeb07c44d4de96f024616b632aff2e3afa442b50a93e8bd
3
+ size 435659249
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c0f694c4239a050e7af53d0a58e445472e80ed35dd129eda6e0199be166a9a0
3
+ size 17563
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b48197c5e88dfe8edd176504687b1c31b637f30c7aec3968699282335a759b1e
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.04133550822734833,
3
+ "best_model_checkpoint": "data/models/chemical/final/checkpoint-20571",
4
+ "epoch": 1.0,
5
+ "global_step": 20571,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 9.922807350153128e-05,
13
+ "loss": 0.094,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.05,
18
+ "learning_rate": 9.675614700306256e-05,
19
+ "loss": 0.0704,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.07,
24
+ "learning_rate": 9.428422050459385e-05,
25
+ "loss": 0.0626,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.1,
30
+ "learning_rate": 9.181229400612513e-05,
31
+ "loss": 0.0621,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.12,
36
+ "learning_rate": 8.934036750765641e-05,
37
+ "loss": 0.0586,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.15,
42
+ "learning_rate": 8.68684410091877e-05,
43
+ "loss": 0.0535,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.17,
48
+ "learning_rate": 8.439651451071898e-05,
49
+ "loss": 0.0553,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.19,
54
+ "learning_rate": 8.192458801225026e-05,
55
+ "loss": 0.0514,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.22,
60
+ "learning_rate": 7.945266151378155e-05,
61
+ "loss": 0.0513,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.24,
66
+ "learning_rate": 7.698073501531283e-05,
67
+ "loss": 0.0497,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.27,
72
+ "learning_rate": 7.45088085168441e-05,
73
+ "loss": 0.0466,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.29,
78
+ "learning_rate": 7.203688201837538e-05,
79
+ "loss": 0.0481,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.32,
84
+ "learning_rate": 6.956495551990666e-05,
85
+ "loss": 0.0433,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.34,
90
+ "learning_rate": 6.709302902143795e-05,
91
+ "loss": 0.0442,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.36,
96
+ "learning_rate": 6.462110252296923e-05,
97
+ "loss": 0.0471,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.39,
102
+ "learning_rate": 6.214917602450051e-05,
103
+ "loss": 0.0451,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.41,
108
+ "learning_rate": 5.96772495260318e-05,
109
+ "loss": 0.0428,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.44,
114
+ "learning_rate": 5.720532302756308e-05,
115
+ "loss": 0.0406,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.46,
120
+ "learning_rate": 5.473339652909436e-05,
121
+ "loss": 0.0448,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.49,
126
+ "learning_rate": 5.226147003062564e-05,
127
+ "loss": 0.0413,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.51,
132
+ "learning_rate": 4.9789543532156925e-05,
133
+ "loss": 0.0408,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.53,
138
+ "learning_rate": 4.7317617033688203e-05,
139
+ "loss": 0.0386,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.56,
144
+ "learning_rate": 4.484569053521948e-05,
145
+ "loss": 0.0402,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.58,
150
+ "learning_rate": 4.2373764036750766e-05,
151
+ "loss": 0.0365,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.61,
156
+ "learning_rate": 3.990183753828205e-05,
157
+ "loss": 0.038,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.63,
162
+ "learning_rate": 3.742991103981333e-05,
163
+ "loss": 0.0346,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.66,
168
+ "learning_rate": 3.4957984541344614e-05,
169
+ "loss": 0.0356,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.68,
174
+ "learning_rate": 3.248605804287589e-05,
175
+ "loss": 0.0346,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.7,
180
+ "learning_rate": 3.0014131544407173e-05,
181
+ "loss": 0.0304,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.73,
186
+ "learning_rate": 2.754220504593846e-05,
187
+ "loss": 0.0334,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.75,
192
+ "learning_rate": 2.5070278547469743e-05,
193
+ "loss": 0.0312,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.78,
198
+ "learning_rate": 2.259835204900102e-05,
199
+ "loss": 0.0333,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.8,
204
+ "learning_rate": 2.0126425550532302e-05,
205
+ "loss": 0.0321,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.83,
210
+ "learning_rate": 1.7654499052063587e-05,
211
+ "loss": 0.0338,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.85,
216
+ "learning_rate": 1.5182572553594867e-05,
217
+ "loss": 0.0309,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.88,
222
+ "learning_rate": 1.271064605512615e-05,
223
+ "loss": 0.0295,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.9,
228
+ "learning_rate": 1.023871955665743e-05,
229
+ "loss": 0.0281,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.92,
234
+ "learning_rate": 7.766793058188713e-06,
235
+ "loss": 0.0303,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.95,
240
+ "learning_rate": 5.294866559719994e-06,
241
+ "loss": 0.0294,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.97,
246
+ "learning_rate": 2.822940061251276e-06,
247
+ "loss": 0.0274,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 1.0,
252
+ "learning_rate": 3.51013562782558e-07,
253
+ "loss": 0.0283,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 1.0,
258
+ "eval_accuracy": 0.9787234042553191,
259
+ "eval_f1": 0.9333333333333333,
260
+ "eval_loss": 0.04133550822734833,
261
+ "eval_precision": 1.0,
262
+ "eval_recall": 0.875,
263
+ "eval_runtime": 5.3542,
264
+ "eval_samples_per_second": 0.747,
265
+ "eval_steps_per_second": 0.187,
266
+ "step": 20571
267
+ }
268
+ ],
269
+ "max_steps": 20571,
270
+ "num_train_epochs": 1,
271
+ "total_flos": 8.6000072575104e+16,
272
+ "trial_name": null,
273
+ "trial_params": null
274
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e01bd86d9b530791b15a8842726fde85055ba184912eae5da179e2bac88cf32
3
+ size 2671
vocab.txt ADDED
The diff for this file is too large to render. See raw diff