Hugging Face's logo

plncmm
/
roberta-clinical-wl-es

Fill-Mask
Transformers
PyTorch
Safetensors
Spanish
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
2
caracena commited on
Commit
14ef454
•
1 Parent(s): 6b1a0ad

initial commit

Browse files
Files changed (12) hide show
  1. README.md +51 -0
  2. all_results.json +8 -0
  3. config.json +28 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +51 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +65 -0
  9. train_results.json +8 -0
  10. trainer_state.json +601 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: bio-bert-base-spanish-wwm-uncased
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # bio-bert-base-spanish-wwm-uncased
14
+
15
+ This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-biomedical-clinical-es](https://huggingface.co/PlanTL-GOB-ES/roberta-base-biomedical-clinical-es) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 5e-05
35
+ - train_batch_size: 16
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 3.0
41
+
42
+ ### Training results
43
+
44
+
45
+
46
+ ### Framework versions
47
+
48
+ - Transformers 4.20.0.dev0
49
+ - Pytorch 1.11.0+cu113
50
+ - Datasets 2.2.1
51
+ - Tokenizers 0.12.1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.511344972582336,
4
+ "train_runtime": 8035.7257,
5
+ "train_samples": 257393,
6
+ "train_samples_per_second": 96.093,
7
+ "train_steps_per_second": 6.006
8
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PlanTL-GOB-ES/roberta-base-biomedical-clinical-es",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.20.0.dev0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 52000
28
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:648786ce7dac1994af1b4948d0b809cbb023d86745548e71078c52ec677b3f6e
3
+ size 504198571
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "max_len": 512,
37
+ "name_or_path": "PlanTL-GOB-ES/roberta-base-biomedical-clinical-es",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": null,
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.511344972582336,
4
+ "train_runtime": 8035.7257,
5
+ "train_samples": 257393,
6
+ "train_samples_per_second": 96.093,
7
+ "train_steps_per_second": 6.006
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,601 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 48264,
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": 4.9740999740999744e-05,
13
+ "loss": 1.3692,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 4.9481999481999486e-05,
19
+ "loss": 1.1369,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 4.922299922299923e-05,
25
+ "loss": 1.0305,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 4.896399896399896e-05,
31
+ "loss": 0.9746,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.08,
36
+ "learning_rate": 4.8704998704998705e-05,
37
+ "loss": 0.9232,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.09,
42
+ "learning_rate": 4.844599844599845e-05,
43
+ "loss": 0.9313,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.11,
48
+ "learning_rate": 4.818699818699819e-05,
49
+ "loss": 0.8694,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.12,
54
+ "learning_rate": 4.792799792799793e-05,
55
+ "loss": 0.8683,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.14,
60
+ "learning_rate": 4.766899766899767e-05,
61
+ "loss": 0.8391,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.31,
66
+ "learning_rate": 4.482015580971324e-05,
67
+ "loss": 0.8134,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.34,
72
+ "learning_rate": 4.4302171390684573e-05,
73
+ "loss": 0.7795,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.37,
78
+ "learning_rate": 4.37841869716559e-05,
79
+ "loss": 0.7527,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.4,
84
+ "learning_rate": 4.3266202552627213e-05,
85
+ "loss": 0.7455,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.44,
90
+ "learning_rate": 4.2748218133598544e-05,
91
+ "loss": 0.7321,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.47,
96
+ "learning_rate": 4.223023371456987e-05,
97
+ "loss": 0.7099,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.5,
102
+ "learning_rate": 4.17122492955412e-05,
103
+ "loss": 0.7011,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.53,
108
+ "learning_rate": 4.1194264876512514e-05,
109
+ "loss": 0.685,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.56,
114
+ "learning_rate": 4.067628045748384e-05,
115
+ "loss": 0.6889,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.59,
120
+ "learning_rate": 4.015829603845517e-05,
121
+ "loss": 0.6752,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.62,
126
+ "learning_rate": 3.964031161942649e-05,
127
+ "loss": 0.6598,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.65,
132
+ "learning_rate": 3.9122327200397814e-05,
133
+ "loss": 0.6626,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.68,
138
+ "learning_rate": 3.860434278136914e-05,
139
+ "loss": 0.6569,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.71,
144
+ "learning_rate": 3.808635836234046e-05,
145
+ "loss": 0.6452,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.75,
150
+ "learning_rate": 3.7568373943311785e-05,
151
+ "loss": 0.6412,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.78,
156
+ "learning_rate": 3.7050389524283115e-05,
157
+ "loss": 0.6349,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.81,
162
+ "learning_rate": 3.653240510525444e-05,
163
+ "loss": 0.6315,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.84,
168
+ "learning_rate": 3.601442068622576e-05,
169
+ "loss": 0.636,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.87,
174
+ "learning_rate": 3.5496436267197085e-05,
175
+ "loss": 0.621,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.9,
180
+ "learning_rate": 3.497845184816841e-05,
181
+ "loss": 0.6226,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.93,
186
+ "learning_rate": 3.446046742913973e-05,
187
+ "loss": 0.6188,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.96,
192
+ "learning_rate": 3.394248301011106e-05,
193
+ "loss": 0.6055,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.99,
198
+ "learning_rate": 3.342449859108238e-05,
199
+ "loss": 0.6105,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 1.03,
204
+ "learning_rate": 3.29065141720537e-05,
205
+ "loss": 0.5962,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 1.06,
210
+ "learning_rate": 3.238852975302503e-05,
211
+ "loss": 0.5865,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 1.09,
216
+ "learning_rate": 3.1870545333996356e-05,
217
+ "loss": 0.5869,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 1.12,
222
+ "learning_rate": 3.135256091496768e-05,
223
+ "loss": 0.5868,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 1.15,
228
+ "learning_rate": 3.0834576495939e-05,
229
+ "loss": 0.5924,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 1.18,
234
+ "learning_rate": 3.0316592076910326e-05,
235
+ "loss": 0.5798,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 1.21,
240
+ "learning_rate": 2.979860765788165e-05,
241
+ "loss": 0.574,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 1.24,
246
+ "learning_rate": 2.928062323885298e-05,
247
+ "loss": 0.5684,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 1.27,
252
+ "learning_rate": 2.87626388198243e-05,
253
+ "loss": 0.5529,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 1.31,
258
+ "learning_rate": 2.824465440079563e-05,
259
+ "loss": 0.5733,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 1.34,
264
+ "learning_rate": 2.772666998176695e-05,
265
+ "loss": 0.5594,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 1.37,
270
+ "learning_rate": 2.7208685562738273e-05,
271
+ "loss": 0.5557,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 1.4,
276
+ "learning_rate": 2.66907011437096e-05,
277
+ "loss": 0.5595,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 1.43,
282
+ "learning_rate": 2.6172716724680923e-05,
283
+ "loss": 0.5519,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 1.46,
288
+ "learning_rate": 2.5654732305652247e-05,
289
+ "loss": 0.5569,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 1.49,
294
+ "learning_rate": 2.5136747886623573e-05,
295
+ "loss": 0.5457,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 1.52,
300
+ "learning_rate": 2.4618763467594897e-05,
301
+ "loss": 0.5511,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 1.55,
306
+ "learning_rate": 2.410077904856622e-05,
307
+ "loss": 0.5547,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 1.59,
312
+ "learning_rate": 2.3582794629537544e-05,
313
+ "loss": 0.5384,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 1.62,
318
+ "learning_rate": 2.306481021050887e-05,
319
+ "loss": 0.5353,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 1.65,
324
+ "learning_rate": 2.2546825791480194e-05,
325
+ "loss": 0.5226,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 1.68,
330
+ "learning_rate": 2.2028841372451517e-05,
331
+ "loss": 0.5346,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 1.71,
336
+ "learning_rate": 2.151085695342284e-05,
337
+ "loss": 0.5323,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 1.74,
342
+ "learning_rate": 2.0992872534394168e-05,
343
+ "loss": 0.5399,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 1.77,
348
+ "learning_rate": 2.047488811536549e-05,
349
+ "loss": 0.5269,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 1.8,
354
+ "learning_rate": 1.9956903696336814e-05,
355
+ "loss": 0.5348,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 1.83,
360
+ "learning_rate": 1.943891927730814e-05,
361
+ "loss": 0.5273,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 1.86,
366
+ "learning_rate": 1.892093485827946e-05,
367
+ "loss": 0.5239,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 1.9,
372
+ "learning_rate": 1.8402950439250788e-05,
373
+ "loss": 0.5219,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 1.93,
378
+ "learning_rate": 1.7884966020222115e-05,
379
+ "loss": 0.5224,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 1.96,
384
+ "learning_rate": 1.7366981601193438e-05,
385
+ "loss": 0.5255,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 1.99,
390
+ "learning_rate": 1.684899718216476e-05,
391
+ "loss": 0.5115,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 2.02,
396
+ "learning_rate": 1.6331012763136085e-05,
397
+ "loss": 0.5238,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 2.05,
402
+ "learning_rate": 1.5813028344107412e-05,
403
+ "loss": 0.5124,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 2.08,
408
+ "learning_rate": 1.5295043925078735e-05,
409
+ "loss": 0.5217,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 2.11,
414
+ "learning_rate": 1.4777059506050059e-05,
415
+ "loss": 0.5122,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 2.14,
420
+ "learning_rate": 1.4259075087021384e-05,
421
+ "loss": 0.504,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 2.18,
426
+ "learning_rate": 1.3741090667992707e-05,
427
+ "loss": 0.5041,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 2.21,
432
+ "learning_rate": 1.3223106248964032e-05,
433
+ "loss": 0.5082,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 2.24,
438
+ "learning_rate": 1.2705121829935357e-05,
439
+ "loss": 0.5005,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 2.27,
444
+ "learning_rate": 1.218713741090668e-05,
445
+ "loss": 0.4966,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 2.3,
450
+ "learning_rate": 1.1669152991878004e-05,
451
+ "loss": 0.5147,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 2.33,
456
+ "learning_rate": 1.115116857284933e-05,
457
+ "loss": 0.5101,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 2.36,
462
+ "learning_rate": 1.0633184153820654e-05,
463
+ "loss": 0.501,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 2.39,
468
+ "learning_rate": 1.0115199734791978e-05,
469
+ "loss": 0.5042,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 2.42,
474
+ "learning_rate": 9.597215315763303e-06,
475
+ "loss": 0.4999,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 2.46,
480
+ "learning_rate": 9.079230896734626e-06,
481
+ "loss": 0.4954,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 2.49,
486
+ "learning_rate": 8.56124647770595e-06,
487
+ "loss": 0.4924,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 2.52,
492
+ "learning_rate": 8.043262058677275e-06,
493
+ "loss": 0.4882,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 2.55,
498
+ "learning_rate": 7.525277639648599e-06,
499
+ "loss": 0.495,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 2.58,
504
+ "learning_rate": 7.007293220619925e-06,
505
+ "loss": 0.5013,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 2.61,
510
+ "learning_rate": 6.489308801591248e-06,
511
+ "loss": 0.4853,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 2.64,
516
+ "learning_rate": 5.971324382562573e-06,
517
+ "loss": 0.5026,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 2.67,
522
+ "learning_rate": 5.453339963533898e-06,
523
+ "loss": 0.4927,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 2.7,
528
+ "learning_rate": 4.935355544505221e-06,
529
+ "loss": 0.49,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 2.73,
534
+ "learning_rate": 4.417371125476545e-06,
535
+ "loss": 0.483,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 2.77,
540
+ "learning_rate": 3.8993867064478705e-06,
541
+ "loss": 0.4942,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 2.8,
546
+ "learning_rate": 3.3814022874191948e-06,
547
+ "loss": 0.4902,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 2.83,
552
+ "learning_rate": 2.863417868390519e-06,
553
+ "loss": 0.486,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 2.86,
558
+ "learning_rate": 2.3454334493618433e-06,
559
+ "loss": 0.4862,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 2.89,
564
+ "learning_rate": 1.8274490303331678e-06,
565
+ "loss": 0.485,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 2.92,
570
+ "learning_rate": 1.309464611304492e-06,
571
+ "loss": 0.4851,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 2.95,
576
+ "learning_rate": 7.914801922758165e-07,
577
+ "loss": 0.4909,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 2.98,
582
+ "learning_rate": 2.7349577324714074e-07,
583
+ "loss": 0.4866,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 3.0,
588
+ "step": 48264,
589
+ "total_flos": 1.9381442927896166e+17,
590
+ "train_loss": 0.511344972582336,
591
+ "train_runtime": 8035.7257,
592
+ "train_samples_per_second": 96.093,
593
+ "train_steps_per_second": 6.006
594
+ }
595
+ ],
596
+ "max_steps": 48264,
597
+ "num_train_epochs": 3,
598
+ "total_flos": 1.9381442927896166e+17,
599
+ "trial_name": null,
600
+ "trial_params": null
601
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d6c6c9455efa7d0da91046eb24b932053c4f2806947597afedd1fd3127d7d8b
3
+ size 3247
vocab.json ADDED
The diff for this file is too large to render. See raw diff