schnell commited on
Commit
17dda7a
1 Parent(s): 4fafe61

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 512,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 2048,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 8,
16
+ "num_hidden_layers": 4,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.26.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 512,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 2048,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 8,
16
+ "num_hidden_layers": 4,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.26.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.26.1"
5
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f6378d932e950ab1254ef36b9e6ab99025a224169a2ca3a03a1c49eb436ad7
3
+ size 236470789
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85ed2c77e97f20169419119debbc1bad3c485dc8c178f9384868beb35e2826d
3
+ size 118243218
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f349fb60516eee7d639a446f8b7fb808fe1a817718908bb7e4673dfc7224acb4
3
+ size 15597
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace91fdf9957c2b1d6cc0702dcc423243ac46b57b8426a6c861ff6b63244e5f8
3
+ size 557
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8497765a951f5b927e48aa6982bed76f5d7e8c34565c07318f1b19eb00f331db
3
+ size 627
last-checkpoint/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
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "model_max_length": 128,
5
+ "name_or_path": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/UnidicBpe2",
6
+ "pad_token": "[PAD]",
7
+ "padding_side": "right",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/UnidicBpe2/special_tokens_map.json",
10
+ "tokenizer_class": "PreTrainedTokenizerFast",
11
+ "truncation_side": "right",
12
+ "unk_token": "[UNK]"
13
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,853 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 69473,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 5.140331037318804e-06,
13
+ "loss": 9.66,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 1.0280662074637608e-05,
19
+ "loss": 7.9578,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 1.542099311195641e-05,
25
+ "loss": 6.7356,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.03,
30
+ "learning_rate": 2.0561324149275216e-05,
31
+ "loss": 6.3535,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.04,
36
+ "learning_rate": 2.570165518659402e-05,
37
+ "loss": 6.0716,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.04,
42
+ "learning_rate": 3.084198622391282e-05,
43
+ "loss": 5.7806,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.05,
48
+ "learning_rate": 3.5982317261231625e-05,
49
+ "loss": 5.3296,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.06,
54
+ "learning_rate": 4.112264829855043e-05,
55
+ "loss": 4.8984,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.06,
60
+ "learning_rate": 4.6262979335869235e-05,
61
+ "loss": 4.5987,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.07,
66
+ "learning_rate": 5.140331037318804e-05,
67
+ "loss": 4.3705,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.08,
72
+ "learning_rate": 5.6543641410506844e-05,
73
+ "loss": 4.1875,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.09,
78
+ "learning_rate": 6.168397244782565e-05,
79
+ "loss": 4.0215,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.09,
84
+ "learning_rate": 6.682430348514444e-05,
85
+ "loss": 3.8753,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.1,
90
+ "learning_rate": 7.196463452246325e-05,
91
+ "loss": 3.7559,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.11,
96
+ "learning_rate": 7.710496555978204e-05,
97
+ "loss": 3.6464,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.12,
102
+ "learning_rate": 8.224529659710087e-05,
103
+ "loss": 3.5461,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.12,
108
+ "learning_rate": 8.738562763441966e-05,
109
+ "loss": 3.4592,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.13,
114
+ "learning_rate": 9.252595867173847e-05,
115
+ "loss": 3.3816,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.14,
120
+ "learning_rate": 9.766628970905726e-05,
121
+ "loss": 3.3121,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.14,
126
+ "learning_rate": 9.997164799900302e-05,
127
+ "loss": 3.2467,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.15,
132
+ "learning_rate": 9.991972125725027e-05,
133
+ "loss": 3.1821,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.16,
138
+ "learning_rate": 9.986779451549754e-05,
139
+ "loss": 3.1286,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.17,
144
+ "learning_rate": 9.981586777374481e-05,
145
+ "loss": 3.0801,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.17,
150
+ "learning_rate": 9.976394103199208e-05,
151
+ "loss": 3.0316,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.18,
156
+ "learning_rate": 9.971211814372284e-05,
157
+ "loss": 2.9902,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.19,
162
+ "learning_rate": 9.966019140197011e-05,
163
+ "loss": 2.9502,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.19,
168
+ "learning_rate": 9.960826466021737e-05,
169
+ "loss": 2.9131,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.2,
174
+ "learning_rate": 9.955633791846463e-05,
175
+ "loss": 2.8816,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.21,
180
+ "learning_rate": 9.95045150301954e-05,
181
+ "loss": 2.8481,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.22,
186
+ "learning_rate": 9.945258828844267e-05,
187
+ "loss": 2.8154,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.22,
192
+ "learning_rate": 9.940066154668994e-05,
193
+ "loss": 2.7873,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.23,
198
+ "learning_rate": 9.93487348049372e-05,
199
+ "loss": 2.7658,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.24,
204
+ "learning_rate": 9.929691191666797e-05,
205
+ "loss": 2.7377,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.24,
210
+ "learning_rate": 9.924498517491524e-05,
211
+ "loss": 2.7145,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.25,
216
+ "learning_rate": 9.91930584331625e-05,
217
+ "loss": 2.6943,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.26,
222
+ "learning_rate": 9.914113169140976e-05,
223
+ "loss": 2.6711,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.27,
228
+ "learning_rate": 9.908930880314053e-05,
229
+ "loss": 2.6557,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.27,
234
+ "learning_rate": 9.90373820613878e-05,
235
+ "loss": 2.6369,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.28,
240
+ "learning_rate": 9.898545531963507e-05,
241
+ "loss": 2.6161,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.29,
246
+ "learning_rate": 9.893352857788233e-05,
247
+ "loss": 2.6013,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.3,
252
+ "learning_rate": 9.88817056896131e-05,
253
+ "loss": 2.5856,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.3,
258
+ "learning_rate": 9.882977894786037e-05,
259
+ "loss": 2.5747,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.31,
264
+ "learning_rate": 9.877785220610762e-05,
265
+ "loss": 2.5553,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.32,
270
+ "learning_rate": 9.872592546435489e-05,
271
+ "loss": 2.5415,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.32,
276
+ "learning_rate": 9.867410257608566e-05,
277
+ "loss": 2.5352,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.33,
282
+ "learning_rate": 9.862217583433293e-05,
283
+ "loss": 2.5192,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.34,
288
+ "learning_rate": 9.85702490925802e-05,
289
+ "loss": 2.509,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.35,
294
+ "learning_rate": 9.851832235082745e-05,
295
+ "loss": 2.4963,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 0.35,
300
+ "learning_rate": 9.846649946255823e-05,
301
+ "loss": 2.4866,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 0.36,
306
+ "learning_rate": 9.841457272080548e-05,
307
+ "loss": 2.4738,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 0.37,
312
+ "learning_rate": 9.836264597905277e-05,
313
+ "loss": 2.4613,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 0.37,
318
+ "learning_rate": 9.831071923730002e-05,
319
+ "loss": 2.4566,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 0.38,
324
+ "learning_rate": 9.82588963490308e-05,
325
+ "loss": 2.4492,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 0.39,
330
+ "learning_rate": 9.820696960727805e-05,
331
+ "loss": 2.4387,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 0.4,
336
+ "learning_rate": 9.815504286552532e-05,
337
+ "loss": 2.431,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 0.4,
342
+ "learning_rate": 9.810311612377259e-05,
343
+ "loss": 2.4203,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 0.41,
348
+ "learning_rate": 9.805129323550336e-05,
349
+ "loss": 2.4134,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 0.42,
354
+ "learning_rate": 9.799936649375063e-05,
355
+ "loss": 2.4058,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 0.42,
360
+ "learning_rate": 9.794743975199788e-05,
361
+ "loss": 2.3948,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 0.43,
366
+ "learning_rate": 9.789551301024515e-05,
367
+ "loss": 2.3866,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 0.44,
372
+ "learning_rate": 9.784358626849242e-05,
373
+ "loss": 2.3806,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 0.45,
378
+ "learning_rate": 9.779165952673967e-05,
379
+ "loss": 2.3738,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 0.45,
384
+ "learning_rate": 9.773973278498695e-05,
385
+ "loss": 2.3675,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 0.46,
390
+ "learning_rate": 9.76879098967177e-05,
391
+ "loss": 2.3633,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 0.47,
396
+ "learning_rate": 9.763598315496499e-05,
397
+ "loss": 2.356,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 0.48,
402
+ "learning_rate": 9.758405641321224e-05,
403
+ "loss": 2.3454,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 0.48,
408
+ "learning_rate": 9.753212967145951e-05,
409
+ "loss": 2.3464,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 0.49,
414
+ "learning_rate": 9.748030678319028e-05,
415
+ "loss": 2.3384,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 0.5,
420
+ "learning_rate": 9.742838004143755e-05,
421
+ "loss": 2.3314,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 0.5,
426
+ "learning_rate": 9.737645329968481e-05,
427
+ "loss": 2.3223,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 0.51,
432
+ "learning_rate": 9.732452655793207e-05,
433
+ "loss": 2.3201,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 0.52,
438
+ "learning_rate": 9.727270366966285e-05,
439
+ "loss": 2.3198,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 0.53,
444
+ "learning_rate": 9.72207769279101e-05,
445
+ "loss": 2.3051,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 0.53,
450
+ "learning_rate": 9.716885018615738e-05,
451
+ "loss": 2.3041,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 0.54,
456
+ "learning_rate": 9.711692344440464e-05,
457
+ "loss": 2.3034,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 0.55,
462
+ "learning_rate": 9.70649967026519e-05,
463
+ "loss": 2.2964,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 0.55,
468
+ "learning_rate": 9.701317381438267e-05,
469
+ "loss": 2.2894,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 0.56,
474
+ "learning_rate": 9.696124707262993e-05,
475
+ "loss": 2.2769,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 0.57,
480
+ "learning_rate": 9.690932033087721e-05,
481
+ "loss": 2.2809,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 0.58,
486
+ "learning_rate": 9.685739358912447e-05,
487
+ "loss": 2.2743,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 0.58,
492
+ "learning_rate": 9.680557070085525e-05,
493
+ "loss": 2.2699,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 0.59,
498
+ "learning_rate": 9.67536439591025e-05,
499
+ "loss": 2.2668,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 0.6,
504
+ "learning_rate": 9.670171721734977e-05,
505
+ "loss": 2.2635,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 0.6,
510
+ "learning_rate": 9.664979047559704e-05,
511
+ "loss": 2.2637,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 0.61,
516
+ "learning_rate": 9.65979675873278e-05,
517
+ "loss": 2.2584,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 0.62,
522
+ "learning_rate": 9.654604084557507e-05,
523
+ "loss": 2.2535,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 0.63,
528
+ "learning_rate": 9.649411410382233e-05,
529
+ "loss": 2.2462,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 0.63,
534
+ "learning_rate": 9.64421873620696e-05,
535
+ "loss": 2.2427,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 0.64,
540
+ "learning_rate": 9.639036447380036e-05,
541
+ "loss": 2.242,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 0.65,
546
+ "learning_rate": 9.633843773204764e-05,
547
+ "loss": 2.2341,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 0.65,
552
+ "learning_rate": 9.62865109902949e-05,
553
+ "loss": 2.2321,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 0.66,
558
+ "learning_rate": 9.623458424854217e-05,
559
+ "loss": 2.2311,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 0.67,
564
+ "learning_rate": 9.618265750678943e-05,
565
+ "loss": 2.2242,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 0.68,
570
+ "learning_rate": 9.61308346185202e-05,
571
+ "loss": 2.2206,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 0.68,
576
+ "learning_rate": 9.607890787676747e-05,
577
+ "loss": 2.2164,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 0.69,
582
+ "learning_rate": 9.602698113501472e-05,
583
+ "loss": 2.217,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 0.7,
588
+ "learning_rate": 9.597505439326199e-05,
589
+ "loss": 2.2144,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 0.71,
594
+ "learning_rate": 9.592323150499276e-05,
595
+ "loss": 2.211,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 0.71,
600
+ "learning_rate": 9.587130476324003e-05,
601
+ "loss": 2.2056,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 0.72,
606
+ "learning_rate": 9.58193780214873e-05,
607
+ "loss": 2.2013,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 0.73,
612
+ "learning_rate": 9.576745127973455e-05,
613
+ "loss": 2.2074,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 0.73,
618
+ "learning_rate": 9.571562839146533e-05,
619
+ "loss": 2.1932,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 0.74,
624
+ "learning_rate": 9.566370164971258e-05,
625
+ "loss": 2.1911,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 0.75,
630
+ "learning_rate": 9.561177490795985e-05,
631
+ "loss": 2.1942,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 0.76,
636
+ "learning_rate": 9.555984816620712e-05,
637
+ "loss": 2.1868,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 0.76,
642
+ "learning_rate": 9.550792142445439e-05,
643
+ "loss": 2.1795,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 0.77,
648
+ "learning_rate": 9.545609853618515e-05,
649
+ "loss": 2.187,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 0.78,
654
+ "learning_rate": 9.540417179443242e-05,
655
+ "loss": 2.1752,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 0.78,
660
+ "learning_rate": 9.535224505267969e-05,
661
+ "loss": 2.1789,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 0.79,
666
+ "learning_rate": 9.530031831092695e-05,
667
+ "loss": 2.1755,
668
+ "step": 55000
669
+ },
670
+ {
671
+ "epoch": 0.8,
672
+ "learning_rate": 9.524849542265773e-05,
673
+ "loss": 2.1723,
674
+ "step": 55500
675
+ },
676
+ {
677
+ "epoch": 0.81,
678
+ "learning_rate": 9.519656868090498e-05,
679
+ "loss": 2.1722,
680
+ "step": 56000
681
+ },
682
+ {
683
+ "epoch": 0.81,
684
+ "learning_rate": 9.514464193915225e-05,
685
+ "loss": 2.166,
686
+ "step": 56500
687
+ },
688
+ {
689
+ "epoch": 0.82,
690
+ "learning_rate": 9.509271519739952e-05,
691
+ "loss": 2.1679,
692
+ "step": 57000
693
+ },
694
+ {
695
+ "epoch": 0.83,
696
+ "learning_rate": 9.504089230913028e-05,
697
+ "loss": 2.1619,
698
+ "step": 57500
699
+ },
700
+ {
701
+ "epoch": 0.83,
702
+ "learning_rate": 9.498896556737755e-05,
703
+ "loss": 2.1595,
704
+ "step": 58000
705
+ },
706
+ {
707
+ "epoch": 0.84,
708
+ "learning_rate": 9.493703882562482e-05,
709
+ "loss": 2.1557,
710
+ "step": 58500
711
+ },
712
+ {
713
+ "epoch": 0.85,
714
+ "learning_rate": 9.488511208387207e-05,
715
+ "loss": 2.1567,
716
+ "step": 59000
717
+ },
718
+ {
719
+ "epoch": 0.86,
720
+ "learning_rate": 9.483328919560285e-05,
721
+ "loss": 2.1504,
722
+ "step": 59500
723
+ },
724
+ {
725
+ "epoch": 0.86,
726
+ "learning_rate": 9.478136245385011e-05,
727
+ "loss": 2.1459,
728
+ "step": 60000
729
+ },
730
+ {
731
+ "epoch": 0.87,
732
+ "learning_rate": 9.472943571209738e-05,
733
+ "loss": 2.1499,
734
+ "step": 60500
735
+ },
736
+ {
737
+ "epoch": 0.88,
738
+ "learning_rate": 9.467750897034465e-05,
739
+ "loss": 2.146,
740
+ "step": 61000
741
+ },
742
+ {
743
+ "epoch": 0.89,
744
+ "learning_rate": 9.462568608207541e-05,
745
+ "loss": 2.1437,
746
+ "step": 61500
747
+ },
748
+ {
749
+ "epoch": 0.89,
750
+ "learning_rate": 9.457375934032268e-05,
751
+ "loss": 2.1437,
752
+ "step": 62000
753
+ },
754
+ {
755
+ "epoch": 0.9,
756
+ "learning_rate": 9.452183259856993e-05,
757
+ "loss": 2.1415,
758
+ "step": 62500
759
+ },
760
+ {
761
+ "epoch": 0.91,
762
+ "learning_rate": 9.44699058568172e-05,
763
+ "loss": 2.1406,
764
+ "step": 63000
765
+ },
766
+ {
767
+ "epoch": 0.91,
768
+ "learning_rate": 9.441808296854797e-05,
769
+ "loss": 2.1334,
770
+ "step": 63500
771
+ },
772
+ {
773
+ "epoch": 0.92,
774
+ "learning_rate": 9.436615622679524e-05,
775
+ "loss": 2.1327,
776
+ "step": 64000
777
+ },
778
+ {
779
+ "epoch": 0.93,
780
+ "learning_rate": 9.43142294850425e-05,
781
+ "loss": 2.1297,
782
+ "step": 64500
783
+ },
784
+ {
785
+ "epoch": 0.94,
786
+ "learning_rate": 9.426230274328977e-05,
787
+ "loss": 2.1275,
788
+ "step": 65000
789
+ },
790
+ {
791
+ "epoch": 0.94,
792
+ "learning_rate": 9.421037600153704e-05,
793
+ "loss": 2.1317,
794
+ "step": 65500
795
+ },
796
+ {
797
+ "epoch": 0.95,
798
+ "learning_rate": 9.415855311326781e-05,
799
+ "loss": 2.1305,
800
+ "step": 66000
801
+ },
802
+ {
803
+ "epoch": 0.96,
804
+ "learning_rate": 9.410662637151508e-05,
805
+ "loss": 2.1229,
806
+ "step": 66500
807
+ },
808
+ {
809
+ "epoch": 0.96,
810
+ "learning_rate": 9.405469962976233e-05,
811
+ "loss": 2.1212,
812
+ "step": 67000
813
+ },
814
+ {
815
+ "epoch": 0.97,
816
+ "learning_rate": 9.40027728880096e-05,
817
+ "loss": 2.1172,
818
+ "step": 67500
819
+ },
820
+ {
821
+ "epoch": 0.98,
822
+ "learning_rate": 9.395094999974037e-05,
823
+ "loss": 2.1139,
824
+ "step": 68000
825
+ },
826
+ {
827
+ "epoch": 0.99,
828
+ "learning_rate": 9.389902325798763e-05,
829
+ "loss": 2.1156,
830
+ "step": 68500
831
+ },
832
+ {
833
+ "epoch": 0.99,
834
+ "learning_rate": 9.38470965162349e-05,
835
+ "loss": 2.111,
836
+ "step": 69000
837
+ },
838
+ {
839
+ "epoch": 1.0,
840
+ "eval_accuracy": 0.6055819008431793,
841
+ "eval_loss": 1.98311185836792,
842
+ "eval_runtime": 1276.0691,
843
+ "eval_samples_per_second": 422.342,
844
+ "eval_steps_per_second": 26.397,
845
+ "step": 69473
846
+ }
847
+ ],
848
+ "max_steps": 972622,
849
+ "num_train_epochs": 14,
850
+ "total_flos": 5.2597922942029824e+17,
851
+ "trial_name": null,
852
+ "trial_params": null
853
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9cd80156879db3b48ab7899bac870a586d6f4775c94f4b44809ad7c7c171a4
3
+ size 3579
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85ed2c77e97f20169419119debbc1bad3c485dc8c178f9384868beb35e2826d
3
+ size 118243218
runs/Feb22_09-35-52_ubuntu-2004/1677026198.594139/events.out.tfevents.1677026198.ubuntu-2004.1870487.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4593e5e87a829955e9e8e593f5b3f1f87b019c60971cbabcc1f46f33811678f7
3
+ size 5739
runs/Feb22_09-35-52_ubuntu-2004/events.out.tfevents.1677026198.ubuntu-2004.1870487.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9232beb167562eaf33f47fe2d6b920c358d808cb192d93c201d98b5e7ca7c3c0
3
+ size 26069
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "model_max_length": 128,
5
+ "name_or_path": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/UnidicBpe2",
6
+ "pad_token": "[PAD]",
7
+ "padding_side": "right",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/UnidicBpe2/special_tokens_map.json",
10
+ "tokenizer_class": "PreTrainedTokenizerFast",
11
+ "truncation_side": "right",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9cd80156879db3b48ab7899bac870a586d6f4775c94f4b44809ad7c7c171a4
3
+ size 3579