Upload 7 files
Browse files- config.json +41 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- trainer_state.json +286 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dmis-lab/biobert-v1.1",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "Neurology",
|
14 |
+
"1": "Orthopedic",
|
15 |
+
"2": "Radiology",
|
16 |
+
"3": "Gastroenterology",
|
17 |
+
"4": "Urology"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"Gastroenterology": 3,
|
23 |
+
"Neurology": 0,
|
24 |
+
"Orthopedic": 1,
|
25 |
+
"Radiology": 2,
|
26 |
+
"Urology": 4
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"max_position_embeddings": 512,
|
30 |
+
"model_type": "bert",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"pad_token_id": 0,
|
34 |
+
"position_embedding_type": "absolute",
|
35 |
+
"problem_type": "multi_label_classification",
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.28.1",
|
38 |
+
"type_vocab_size": 2,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 28996
|
41 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13e2352bd039f3fa4e82ccfcbc3a9fb484361f0c0cfe184e9fb9823934e0ab0b
|
3 |
+
size 433329269
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 512,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,286 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.09056882560253143,
|
3 |
+
"best_model_checkpoint": "Folds/BioBert-Fold-Classification6-Train/checkpoint-360",
|
4 |
+
"epoch": 30.0,
|
5 |
+
"global_step": 360,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.4361413043478261,
|
13 |
+
"eval_loss": 0.48898497223854065,
|
14 |
+
"eval_runtime": 5.8414,
|
15 |
+
"eval_samples_per_second": 125.998,
|
16 |
+
"eval_steps_per_second": 2.054,
|
17 |
+
"step": 12
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.5271739130434783,
|
22 |
+
"eval_loss": 0.44031521677970886,
|
23 |
+
"eval_runtime": 5.8617,
|
24 |
+
"eval_samples_per_second": 125.56,
|
25 |
+
"eval_steps_per_second": 2.047,
|
26 |
+
"step": 24
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.0,
|
30 |
+
"eval_accuracy": 0.6807065217391305,
|
31 |
+
"eval_loss": 0.3873007297515869,
|
32 |
+
"eval_runtime": 5.8619,
|
33 |
+
"eval_samples_per_second": 125.556,
|
34 |
+
"eval_steps_per_second": 2.047,
|
35 |
+
"step": 36
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 4.0,
|
39 |
+
"eval_accuracy": 0.8383152173913043,
|
40 |
+
"eval_loss": 0.309426873922348,
|
41 |
+
"eval_runtime": 5.8788,
|
42 |
+
"eval_samples_per_second": 125.195,
|
43 |
+
"eval_steps_per_second": 2.041,
|
44 |
+
"step": 48
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 5.0,
|
48 |
+
"eval_accuracy": 0.8641304347826086,
|
49 |
+
"eval_loss": 0.25360310077667236,
|
50 |
+
"eval_runtime": 5.8785,
|
51 |
+
"eval_samples_per_second": 125.201,
|
52 |
+
"eval_steps_per_second": 2.041,
|
53 |
+
"step": 60
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 6.0,
|
57 |
+
"eval_accuracy": 0.873641304347826,
|
58 |
+
"eval_loss": 0.21427620947360992,
|
59 |
+
"eval_runtime": 5.8774,
|
60 |
+
"eval_samples_per_second": 125.225,
|
61 |
+
"eval_steps_per_second": 2.042,
|
62 |
+
"step": 72
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 7.0,
|
66 |
+
"eval_accuracy": 0.8845108695652174,
|
67 |
+
"eval_loss": 0.19029724597930908,
|
68 |
+
"eval_runtime": 5.8739,
|
69 |
+
"eval_samples_per_second": 125.301,
|
70 |
+
"eval_steps_per_second": 2.043,
|
71 |
+
"step": 84
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 8.0,
|
75 |
+
"eval_accuracy": 0.8953804347826086,
|
76 |
+
"eval_loss": 0.1719338744878769,
|
77 |
+
"eval_runtime": 5.8689,
|
78 |
+
"eval_samples_per_second": 125.408,
|
79 |
+
"eval_steps_per_second": 2.045,
|
80 |
+
"step": 96
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 9.0,
|
84 |
+
"eval_accuracy": 0.8980978260869565,
|
85 |
+
"eval_loss": 0.15415431559085846,
|
86 |
+
"eval_runtime": 5.8772,
|
87 |
+
"eval_samples_per_second": 125.229,
|
88 |
+
"eval_steps_per_second": 2.042,
|
89 |
+
"step": 108
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 10.0,
|
93 |
+
"eval_accuracy": 0.9089673913043478,
|
94 |
+
"eval_loss": 0.1418008953332901,
|
95 |
+
"eval_runtime": 5.8616,
|
96 |
+
"eval_samples_per_second": 125.563,
|
97 |
+
"eval_steps_per_second": 2.047,
|
98 |
+
"step": 120
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 11.0,
|
102 |
+
"eval_accuracy": 0.904891304347826,
|
103 |
+
"eval_loss": 0.13952060043811798,
|
104 |
+
"eval_runtime": 5.867,
|
105 |
+
"eval_samples_per_second": 125.447,
|
106 |
+
"eval_steps_per_second": 2.045,
|
107 |
+
"step": 132
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 12.0,
|
111 |
+
"eval_accuracy": 0.9116847826086957,
|
112 |
+
"eval_loss": 0.1263004094362259,
|
113 |
+
"eval_runtime": 5.858,
|
114 |
+
"eval_samples_per_second": 125.641,
|
115 |
+
"eval_steps_per_second": 2.048,
|
116 |
+
"step": 144
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 13.0,
|
120 |
+
"eval_accuracy": 0.9089673913043478,
|
121 |
+
"eval_loss": 0.12378562986850739,
|
122 |
+
"eval_runtime": 5.8578,
|
123 |
+
"eval_samples_per_second": 125.645,
|
124 |
+
"eval_steps_per_second": 2.049,
|
125 |
+
"step": 156
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 14.0,
|
129 |
+
"eval_accuracy": 0.9116847826086957,
|
130 |
+
"eval_loss": 0.1142706423997879,
|
131 |
+
"eval_runtime": 5.858,
|
132 |
+
"eval_samples_per_second": 125.64,
|
133 |
+
"eval_steps_per_second": 2.048,
|
134 |
+
"step": 168
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 15.0,
|
138 |
+
"eval_accuracy": 0.9116847826086957,
|
139 |
+
"eval_loss": 0.11186062544584274,
|
140 |
+
"eval_runtime": 5.8631,
|
141 |
+
"eval_samples_per_second": 125.53,
|
142 |
+
"eval_steps_per_second": 2.047,
|
143 |
+
"step": 180
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 16.0,
|
147 |
+
"eval_accuracy": 0.9103260869565217,
|
148 |
+
"eval_loss": 0.11324188113212585,
|
149 |
+
"eval_runtime": 5.8705,
|
150 |
+
"eval_samples_per_second": 125.374,
|
151 |
+
"eval_steps_per_second": 2.044,
|
152 |
+
"step": 192
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 17.0,
|
156 |
+
"eval_accuracy": 0.9116847826086957,
|
157 |
+
"eval_loss": 0.10590582340955734,
|
158 |
+
"eval_runtime": 5.8563,
|
159 |
+
"eval_samples_per_second": 125.677,
|
160 |
+
"eval_steps_per_second": 2.049,
|
161 |
+
"step": 204
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 18.0,
|
165 |
+
"eval_accuracy": 0.9116847826086957,
|
166 |
+
"eval_loss": 0.10363849252462387,
|
167 |
+
"eval_runtime": 5.8618,
|
168 |
+
"eval_samples_per_second": 125.558,
|
169 |
+
"eval_steps_per_second": 2.047,
|
170 |
+
"step": 216
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 19.0,
|
174 |
+
"eval_accuracy": 0.9116847826086957,
|
175 |
+
"eval_loss": 0.10128873586654663,
|
176 |
+
"eval_runtime": 5.855,
|
177 |
+
"eval_samples_per_second": 125.704,
|
178 |
+
"eval_steps_per_second": 2.05,
|
179 |
+
"step": 228
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 20.0,
|
183 |
+
"eval_accuracy": 0.9116847826086957,
|
184 |
+
"eval_loss": 0.09862995892763138,
|
185 |
+
"eval_runtime": 5.8601,
|
186 |
+
"eval_samples_per_second": 125.595,
|
187 |
+
"eval_steps_per_second": 2.048,
|
188 |
+
"step": 240
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 21.0,
|
192 |
+
"eval_accuracy": 0.9116847826086957,
|
193 |
+
"eval_loss": 0.09753677248954773,
|
194 |
+
"eval_runtime": 5.8531,
|
195 |
+
"eval_samples_per_second": 125.746,
|
196 |
+
"eval_steps_per_second": 2.05,
|
197 |
+
"step": 252
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 22.0,
|
201 |
+
"eval_accuracy": 0.9116847826086957,
|
202 |
+
"eval_loss": 0.09706844389438629,
|
203 |
+
"eval_runtime": 5.8557,
|
204 |
+
"eval_samples_per_second": 125.689,
|
205 |
+
"eval_steps_per_second": 2.049,
|
206 |
+
"step": 264
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 23.0,
|
210 |
+
"eval_accuracy": 0.9116847826086957,
|
211 |
+
"eval_loss": 0.09410360455513,
|
212 |
+
"eval_runtime": 5.8538,
|
213 |
+
"eval_samples_per_second": 125.731,
|
214 |
+
"eval_steps_per_second": 2.05,
|
215 |
+
"step": 276
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 24.0,
|
219 |
+
"eval_accuracy": 0.9116847826086957,
|
220 |
+
"eval_loss": 0.09291024506092072,
|
221 |
+
"eval_runtime": 5.8573,
|
222 |
+
"eval_samples_per_second": 125.655,
|
223 |
+
"eval_steps_per_second": 2.049,
|
224 |
+
"step": 288
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 25.0,
|
228 |
+
"eval_accuracy": 0.9116847826086957,
|
229 |
+
"eval_loss": 0.09271886944770813,
|
230 |
+
"eval_runtime": 5.8572,
|
231 |
+
"eval_samples_per_second": 125.657,
|
232 |
+
"eval_steps_per_second": 2.049,
|
233 |
+
"step": 300
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 26.0,
|
237 |
+
"eval_accuracy": 0.9116847826086957,
|
238 |
+
"eval_loss": 0.0921669453382492,
|
239 |
+
"eval_runtime": 5.864,
|
240 |
+
"eval_samples_per_second": 125.511,
|
241 |
+
"eval_steps_per_second": 2.046,
|
242 |
+
"step": 312
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 27.0,
|
246 |
+
"eval_accuracy": 0.9116847826086957,
|
247 |
+
"eval_loss": 0.09119947999715805,
|
248 |
+
"eval_runtime": 5.8562,
|
249 |
+
"eval_samples_per_second": 125.68,
|
250 |
+
"eval_steps_per_second": 2.049,
|
251 |
+
"step": 324
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 28.0,
|
255 |
+
"eval_accuracy": 0.9116847826086957,
|
256 |
+
"eval_loss": 0.09083416312932968,
|
257 |
+
"eval_runtime": 5.8573,
|
258 |
+
"eval_samples_per_second": 125.655,
|
259 |
+
"eval_steps_per_second": 2.049,
|
260 |
+
"step": 336
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 29.0,
|
264 |
+
"eval_accuracy": 0.9116847826086957,
|
265 |
+
"eval_loss": 0.09062910825014114,
|
266 |
+
"eval_runtime": 5.855,
|
267 |
+
"eval_samples_per_second": 125.705,
|
268 |
+
"eval_steps_per_second": 2.05,
|
269 |
+
"step": 348
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 30.0,
|
273 |
+
"eval_accuracy": 0.9116847826086957,
|
274 |
+
"eval_loss": 0.09056882560253143,
|
275 |
+
"eval_runtime": 5.858,
|
276 |
+
"eval_samples_per_second": 125.64,
|
277 |
+
"eval_steps_per_second": 2.048,
|
278 |
+
"step": 360
|
279 |
+
}
|
280 |
+
],
|
281 |
+
"max_steps": 360,
|
282 |
+
"num_train_epochs": 30,
|
283 |
+
"total_flos": 5809648585605120.0,
|
284 |
+
"trial_name": null,
|
285 |
+
"trial_params": null
|
286 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|