ccasimiro commited on
Commit
488c07f
1 Parent(s): 3d30a21

upload model

Browse files
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.7445234060287476,
4
+ "eval_loss": 2.0729739665985107,
5
+ "eval_runtime": 288.3181,
6
+ "eval_samples": 13786,
7
+ "eval_samples_per_second": 47.815,
8
+ "train_runtime": 75009.1041,
9
+ "train_samples": 110203,
10
+ "train_samples_per_second": 0.459
11
+ }
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bsc/roberta-base-ca-cased",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_10": 10,
40
+ "LABEL_11": 11,
41
+ "LABEL_12": 12,
42
+ "LABEL_13": 13,
43
+ "LABEL_14": 14,
44
+ "LABEL_15": 15,
45
+ "LABEL_16": 16,
46
+ "LABEL_17": 17,
47
+ "LABEL_18": 18,
48
+ "LABEL_2": 2,
49
+ "LABEL_3": 3,
50
+ "LABEL_4": 4,
51
+ "LABEL_5": 5,
52
+ "LABEL_6": 6,
53
+ "LABEL_7": 7,
54
+ "LABEL_8": 8,
55
+ "LABEL_9": 9
56
+ },
57
+ "layer_norm_eps": 1e-05,
58
+ "max_position_embeddings": 514,
59
+ "model_type": "roberta",
60
+ "num_attention_heads": 12,
61
+ "num_hidden_layers": 12,
62
+ "pad_token_id": 1,
63
+ "position_embedding_type": "absolute",
64
+ "problem_type": "single_label_classification",
65
+ "transformers_version": "4.6.1",
66
+ "type_vocab_size": 1,
67
+ "use_cache": true,
68
+ "vocab_size": 52000
69
+ }
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 sha256:1ba4e24198351d2200806517e8888670272493dc496ef924a18611a6832e1615
3
+ size 504059265
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "bsc/roberta-base-ca-cased"}
train_results.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_runtime": 75009.1041,
4
+ "train_samples": 110203,
5
+ "train_samples_per_second": 0.459
6
+ }
trainer_state.json ADDED
@@ -0,0 +1,511 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7445234060287476,
3
+ "best_model_checkpoint": "/home/shared/dt01/temutauro/ccasimiro/berta/src/finetuning/tc/roberta-base-ca-cased-tecla/checkpoint-34440",
4
+ "epoch": 10.0,
5
+ "global_step": 34440,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.15,
12
+ "learning_rate": 4.9274099883855984e-05,
13
+ "loss": 1.3202,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.29,
18
+ "learning_rate": 4.8548199767711965e-05,
19
+ "loss": 0.9902,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.44,
24
+ "learning_rate": 4.782229965156795e-05,
25
+ "loss": 0.9309,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.58,
30
+ "learning_rate": 4.709639953542393e-05,
31
+ "loss": 0.9006,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.73,
36
+ "learning_rate": 4.637049941927991e-05,
37
+ "loss": 0.8717,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.87,
42
+ "learning_rate": 4.564459930313589e-05,
43
+ "loss": 0.8612,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_accuracy": 0.6943275928497314,
49
+ "eval_loss": 0.8295034766197205,
50
+ "eval_runtime": 288.6692,
51
+ "eval_samples_per_second": 47.757,
52
+ "step": 3444
53
+ },
54
+ {
55
+ "epoch": 1.02,
56
+ "learning_rate": 4.491869918699187e-05,
57
+ "loss": 0.8394,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 1.16,
62
+ "learning_rate": 4.4192799070847854e-05,
63
+ "loss": 0.7212,
64
+ "step": 4000
65
+ },
66
+ {
67
+ "epoch": 1.31,
68
+ "learning_rate": 4.3466898954703835e-05,
69
+ "loss": 0.7093,
70
+ "step": 4500
71
+ },
72
+ {
73
+ "epoch": 1.45,
74
+ "learning_rate": 4.2740998838559817e-05,
75
+ "loss": 0.6932,
76
+ "step": 5000
77
+ },
78
+ {
79
+ "epoch": 1.6,
80
+ "learning_rate": 4.20150987224158e-05,
81
+ "loss": 0.7032,
82
+ "step": 5500
83
+ },
84
+ {
85
+ "epoch": 1.74,
86
+ "learning_rate": 4.128919860627178e-05,
87
+ "loss": 0.6976,
88
+ "step": 6000
89
+ },
90
+ {
91
+ "epoch": 1.89,
92
+ "learning_rate": 4.056329849012776e-05,
93
+ "loss": 0.6866,
94
+ "step": 6500
95
+ },
96
+ {
97
+ "epoch": 2.0,
98
+ "eval_accuracy": 0.7147105932235718,
99
+ "eval_loss": 0.7905623912811279,
100
+ "eval_runtime": 288.7903,
101
+ "eval_samples_per_second": 47.737,
102
+ "step": 6888
103
+ },
104
+ {
105
+ "epoch": 2.03,
106
+ "learning_rate": 3.983739837398374e-05,
107
+ "loss": 0.648,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 2.18,
112
+ "learning_rate": 3.9111498257839724e-05,
113
+ "loss": 0.504,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 2.32,
118
+ "learning_rate": 3.8385598141695705e-05,
119
+ "loss": 0.5056,
120
+ "step": 8000
121
+ },
122
+ {
123
+ "epoch": 2.47,
124
+ "learning_rate": 3.7659698025551686e-05,
125
+ "loss": 0.5104,
126
+ "step": 8500
127
+ },
128
+ {
129
+ "epoch": 2.61,
130
+ "learning_rate": 3.693379790940767e-05,
131
+ "loss": 0.5021,
132
+ "step": 9000
133
+ },
134
+ {
135
+ "epoch": 2.76,
136
+ "learning_rate": 3.620789779326365e-05,
137
+ "loss": 0.502,
138
+ "step": 9500
139
+ },
140
+ {
141
+ "epoch": 2.9,
142
+ "learning_rate": 3.548199767711963e-05,
143
+ "loss": 0.501,
144
+ "step": 10000
145
+ },
146
+ {
147
+ "epoch": 3.0,
148
+ "eval_accuracy": 0.7299433946609497,
149
+ "eval_loss": 0.8311841487884521,
150
+ "eval_runtime": 289.0756,
151
+ "eval_samples_per_second": 47.69,
152
+ "step": 10332
153
+ },
154
+ {
155
+ "epoch": 3.05,
156
+ "learning_rate": 3.475609756097561e-05,
157
+ "loss": 0.44,
158
+ "step": 10500
159
+ },
160
+ {
161
+ "epoch": 3.19,
162
+ "learning_rate": 3.4030197444831594e-05,
163
+ "loss": 0.3205,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 3.34,
168
+ "learning_rate": 3.3304297328687575e-05,
169
+ "loss": 0.3217,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 3.48,
174
+ "learning_rate": 3.2578397212543556e-05,
175
+ "loss": 0.3295,
176
+ "step": 12000
177
+ },
178
+ {
179
+ "epoch": 3.63,
180
+ "learning_rate": 3.185249709639954e-05,
181
+ "loss": 0.3314,
182
+ "step": 12500
183
+ },
184
+ {
185
+ "epoch": 3.77,
186
+ "learning_rate": 3.112659698025552e-05,
187
+ "loss": 0.3384,
188
+ "step": 13000
189
+ },
190
+ {
191
+ "epoch": 3.92,
192
+ "learning_rate": 3.04006968641115e-05,
193
+ "loss": 0.3415,
194
+ "step": 13500
195
+ },
196
+ {
197
+ "epoch": 4.0,
198
+ "eval_accuracy": 0.722907304763794,
199
+ "eval_loss": 0.9545897245407104,
200
+ "eval_runtime": 288.9468,
201
+ "eval_samples_per_second": 47.711,
202
+ "step": 13776
203
+ },
204
+ {
205
+ "epoch": 4.07,
206
+ "learning_rate": 2.9674796747967482e-05,
207
+ "loss": 0.2816,
208
+ "step": 14000
209
+ },
210
+ {
211
+ "epoch": 4.21,
212
+ "learning_rate": 2.8948896631823464e-05,
213
+ "loss": 0.1995,
214
+ "step": 14500
215
+ },
216
+ {
217
+ "epoch": 4.36,
218
+ "learning_rate": 2.8222996515679445e-05,
219
+ "loss": 0.2125,
220
+ "step": 15000
221
+ },
222
+ {
223
+ "epoch": 4.5,
224
+ "learning_rate": 2.7497096399535426e-05,
225
+ "loss": 0.2144,
226
+ "step": 15500
227
+ },
228
+ {
229
+ "epoch": 4.65,
230
+ "learning_rate": 2.6771196283391408e-05,
231
+ "loss": 0.2109,
232
+ "step": 16000
233
+ },
234
+ {
235
+ "epoch": 4.79,
236
+ "learning_rate": 2.604529616724739e-05,
237
+ "loss": 0.2238,
238
+ "step": 16500
239
+ },
240
+ {
241
+ "epoch": 4.94,
242
+ "learning_rate": 2.5319396051103367e-05,
243
+ "loss": 0.223,
244
+ "step": 17000
245
+ },
246
+ {
247
+ "epoch": 5.0,
248
+ "eval_accuracy": 0.7305237054824829,
249
+ "eval_loss": 1.0980908870697021,
250
+ "eval_runtime": 288.7866,
251
+ "eval_samples_per_second": 47.738,
252
+ "step": 17220
253
+ },
254
+ {
255
+ "epoch": 5.08,
256
+ "learning_rate": 2.4593495934959352e-05,
257
+ "loss": 0.1694,
258
+ "step": 17500
259
+ },
260
+ {
261
+ "epoch": 5.23,
262
+ "learning_rate": 2.3867595818815333e-05,
263
+ "loss": 0.1347,
264
+ "step": 18000
265
+ },
266
+ {
267
+ "epoch": 5.37,
268
+ "learning_rate": 2.314169570267131e-05,
269
+ "loss": 0.1356,
270
+ "step": 18500
271
+ },
272
+ {
273
+ "epoch": 5.52,
274
+ "learning_rate": 2.2415795586527293e-05,
275
+ "loss": 0.1274,
276
+ "step": 19000
277
+ },
278
+ {
279
+ "epoch": 5.66,
280
+ "learning_rate": 2.1689895470383274e-05,
281
+ "loss": 0.1416,
282
+ "step": 19500
283
+ },
284
+ {
285
+ "epoch": 5.81,
286
+ "learning_rate": 2.096399535423926e-05,
287
+ "loss": 0.1375,
288
+ "step": 20000
289
+ },
290
+ {
291
+ "epoch": 5.95,
292
+ "learning_rate": 2.023809523809524e-05,
293
+ "loss": 0.15,
294
+ "step": 20500
295
+ },
296
+ {
297
+ "epoch": 6.0,
298
+ "eval_accuracy": 0.7300159335136414,
299
+ "eval_loss": 1.323264479637146,
300
+ "eval_runtime": 289.0229,
301
+ "eval_samples_per_second": 47.699,
302
+ "step": 20664
303
+ },
304
+ {
305
+ "epoch": 6.1,
306
+ "learning_rate": 1.9512195121951222e-05,
307
+ "loss": 0.1056,
308
+ "step": 21000
309
+ },
310
+ {
311
+ "epoch": 6.24,
312
+ "learning_rate": 1.8786295005807203e-05,
313
+ "loss": 0.0862,
314
+ "step": 21500
315
+ },
316
+ {
317
+ "epoch": 6.39,
318
+ "learning_rate": 1.806039488966318e-05,
319
+ "loss": 0.0916,
320
+ "step": 22000
321
+ },
322
+ {
323
+ "epoch": 6.53,
324
+ "learning_rate": 1.7334494773519163e-05,
325
+ "loss": 0.0954,
326
+ "step": 22500
327
+ },
328
+ {
329
+ "epoch": 6.68,
330
+ "learning_rate": 1.6608594657375144e-05,
331
+ "loss": 0.0956,
332
+ "step": 23000
333
+ },
334
+ {
335
+ "epoch": 6.82,
336
+ "learning_rate": 1.5882694541231126e-05,
337
+ "loss": 0.0891,
338
+ "step": 23500
339
+ },
340
+ {
341
+ "epoch": 6.97,
342
+ "learning_rate": 1.5156794425087109e-05,
343
+ "loss": 0.0935,
344
+ "step": 24000
345
+ },
346
+ {
347
+ "epoch": 7.0,
348
+ "eval_accuracy": 0.7382127046585083,
349
+ "eval_loss": 1.6066738367080688,
350
+ "eval_runtime": 288.9144,
351
+ "eval_samples_per_second": 47.717,
352
+ "step": 24108
353
+ },
354
+ {
355
+ "epoch": 7.11,
356
+ "learning_rate": 1.443089430894309e-05,
357
+ "loss": 0.0559,
358
+ "step": 24500
359
+ },
360
+ {
361
+ "epoch": 7.26,
362
+ "learning_rate": 1.3704994192799073e-05,
363
+ "loss": 0.0581,
364
+ "step": 25000
365
+ },
366
+ {
367
+ "epoch": 7.4,
368
+ "learning_rate": 1.2979094076655051e-05,
369
+ "loss": 0.06,
370
+ "step": 25500
371
+ },
372
+ {
373
+ "epoch": 7.55,
374
+ "learning_rate": 1.2253193960511034e-05,
375
+ "loss": 0.055,
376
+ "step": 26000
377
+ },
378
+ {
379
+ "epoch": 7.69,
380
+ "learning_rate": 1.1527293844367016e-05,
381
+ "loss": 0.0677,
382
+ "step": 26500
383
+ },
384
+ {
385
+ "epoch": 7.84,
386
+ "learning_rate": 1.0801393728222997e-05,
387
+ "loss": 0.0552,
388
+ "step": 27000
389
+ },
390
+ {
391
+ "epoch": 7.98,
392
+ "learning_rate": 1.0075493612078979e-05,
393
+ "loss": 0.0642,
394
+ "step": 27500
395
+ },
396
+ {
397
+ "epoch": 8.0,
398
+ "eval_accuracy": 0.7361816167831421,
399
+ "eval_loss": 1.801051378250122,
400
+ "eval_runtime": 288.9587,
401
+ "eval_samples_per_second": 47.709,
402
+ "step": 27552
403
+ },
404
+ {
405
+ "epoch": 8.13,
406
+ "learning_rate": 9.34959349593496e-06,
407
+ "loss": 0.0399,
408
+ "step": 28000
409
+ },
410
+ {
411
+ "epoch": 8.28,
412
+ "learning_rate": 8.623693379790942e-06,
413
+ "loss": 0.0324,
414
+ "step": 28500
415
+ },
416
+ {
417
+ "epoch": 8.42,
418
+ "learning_rate": 7.897793263646923e-06,
419
+ "loss": 0.0383,
420
+ "step": 29000
421
+ },
422
+ {
423
+ "epoch": 8.57,
424
+ "learning_rate": 7.1718931475029035e-06,
425
+ "loss": 0.0396,
426
+ "step": 29500
427
+ },
428
+ {
429
+ "epoch": 8.71,
430
+ "learning_rate": 6.445993031358885e-06,
431
+ "loss": 0.038,
432
+ "step": 30000
433
+ },
434
+ {
435
+ "epoch": 8.86,
436
+ "learning_rate": 5.720092915214867e-06,
437
+ "loss": 0.0355,
438
+ "step": 30500
439
+ },
440
+ {
441
+ "epoch": 9.0,
442
+ "eval_accuracy": 0.7436529994010925,
443
+ "eval_loss": 1.9809679985046387,
444
+ "eval_runtime": 288.9869,
445
+ "eval_samples_per_second": 47.705,
446
+ "step": 30996
447
+ },
448
+ {
449
+ "epoch": 9.0,
450
+ "learning_rate": 4.994192799070848e-06,
451
+ "loss": 0.0348,
452
+ "step": 31000
453
+ },
454
+ {
455
+ "epoch": 9.15,
456
+ "learning_rate": 4.26829268292683e-06,
457
+ "loss": 0.0194,
458
+ "step": 31500
459
+ },
460
+ {
461
+ "epoch": 9.29,
462
+ "learning_rate": 3.542392566782811e-06,
463
+ "loss": 0.0181,
464
+ "step": 32000
465
+ },
466
+ {
467
+ "epoch": 9.44,
468
+ "learning_rate": 2.8164924506387924e-06,
469
+ "loss": 0.0158,
470
+ "step": 32500
471
+ },
472
+ {
473
+ "epoch": 9.58,
474
+ "learning_rate": 2.090592334494774e-06,
475
+ "loss": 0.0201,
476
+ "step": 33000
477
+ },
478
+ {
479
+ "epoch": 9.73,
480
+ "learning_rate": 1.364692218350755e-06,
481
+ "loss": 0.0218,
482
+ "step": 33500
483
+ },
484
+ {
485
+ "epoch": 9.87,
486
+ "learning_rate": 6.387921022067365e-07,
487
+ "loss": 0.0203,
488
+ "step": 34000
489
+ },
490
+ {
491
+ "epoch": 10.0,
492
+ "eval_accuracy": 0.7445234060287476,
493
+ "eval_loss": 2.0729739665985107,
494
+ "eval_runtime": 288.9098,
495
+ "eval_samples_per_second": 47.717,
496
+ "step": 34440
497
+ },
498
+ {
499
+ "epoch": 10.0,
500
+ "step": 34440,
501
+ "total_flos": 0,
502
+ "train_runtime": 75009.1041,
503
+ "train_samples_per_second": 0.459
504
+ }
505
+ ],
506
+ "max_steps": 34440,
507
+ "num_train_epochs": 10,
508
+ "total_flos": 0,
509
+ "trial_name": null,
510
+ "trial_params": null
511
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3ab714c61533f8f19db2d699cb8a9738339f662706bb2812ac04f87d906d7c
3
+ size 2479
vocab.json ADDED
The diff for this file is too large to render. See raw diff