schnell commited on
Commit
7f3ae11
1 Parent(s): 16f32e2

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": "4.19.2",
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": "4.19.2",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4191882273c5a8746cb916e8baa1936e09792e8f0e84da870e5b514516f4b505
3
+ size 236469913
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87809337f73cbefa3f4256bff6ac6d089e7cd202413cf523cc94eba02f885d92
3
+ size 118242180
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a383bd3c41c7ad946fe831a5bbaff0eba255128e9e93271cf83217e47eb4255
3
+ size 14503
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99df4785c941e8c4e03cbdd4f4f84fd82107cdcd3641b8702d99451603142a8d
3
+ size 14503
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d86f63275fadec97efe771135cfa5d2ead7eb458a3fb6752811165f2b697978
3
+ size 14503
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad6bb54446554495dea04728900fe92967415e4578c0e450cc1f096b8207bd3
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ab24724d369d602d643c2e6bd7db8ff740cde990c1e3084102ee259fdc6825
3
+ size 623
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
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 @@
 
 
1
+ {"model_max_length": 128, "padding_side": "right", "truncation_side": "right", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "special_tokens_map_file": "pretrained_tokenizers/ex3-1_ipadic_bpe/special_tokens_map.json", "name_or_path": "pretrained_tokenizers/ex3-1_ipadic_bpe", "tokenizer_class": "PreTrainedTokenizerFast"}
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": 9.6819,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 1.0280662074637608e-05,
19
+ "loss": 8.0932,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 1.542099311195641e-05,
25
+ "loss": 6.9551,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.03,
30
+ "learning_rate": 2.0561324149275216e-05,
31
+ "loss": 6.6147,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.04,
36
+ "learning_rate": 2.570165518659402e-05,
37
+ "loss": 6.3513,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.04,
42
+ "learning_rate": 3.084198622391282e-05,
43
+ "loss": 6.0637,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.05,
48
+ "learning_rate": 3.5982317261231625e-05,
49
+ "loss": 5.6379,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.06,
54
+ "learning_rate": 4.112264829855043e-05,
55
+ "loss": 5.1989,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.06,
60
+ "learning_rate": 4.6262979335869235e-05,
61
+ "loss": 4.867,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.07,
66
+ "learning_rate": 5.140331037318804e-05,
67
+ "loss": 4.6153,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.08,
72
+ "learning_rate": 5.6543641410506844e-05,
73
+ "loss": 4.4195,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.09,
78
+ "learning_rate": 6.168397244782565e-05,
79
+ "loss": 4.2546,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.09,
84
+ "learning_rate": 6.682430348514444e-05,
85
+ "loss": 4.1156,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.1,
90
+ "learning_rate": 7.196463452246325e-05,
91
+ "loss": 3.9908,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.11,
96
+ "learning_rate": 7.710496555978204e-05,
97
+ "loss": 3.8759,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.12,
102
+ "learning_rate": 8.224529659710087e-05,
103
+ "loss": 3.7715,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.12,
108
+ "learning_rate": 8.738562763441966e-05,
109
+ "loss": 3.6865,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.13,
114
+ "learning_rate": 9.252595867173847e-05,
115
+ "loss": 3.6037,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.14,
120
+ "learning_rate": 9.766628970905726e-05,
121
+ "loss": 3.5251,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.14,
126
+ "learning_rate": 9.997164799900302e-05,
127
+ "loss": 3.4598,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.15,
132
+ "learning_rate": 9.991982511073378e-05,
133
+ "loss": 3.394,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.16,
138
+ "learning_rate": 9.986789836898105e-05,
139
+ "loss": 3.3329,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.17,
144
+ "learning_rate": 9.98159716272283e-05,
145
+ "loss": 3.2819,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.17,
150
+ "learning_rate": 9.976404488547557e-05,
151
+ "loss": 3.2306,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.18,
156
+ "learning_rate": 9.971222199720634e-05,
157
+ "loss": 3.1876,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.19,
162
+ "learning_rate": 9.966029525545361e-05,
163
+ "loss": 3.1435,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.19,
168
+ "learning_rate": 9.960836851370088e-05,
169
+ "loss": 3.1032,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.2,
174
+ "learning_rate": 9.955644177194815e-05,
175
+ "loss": 3.07,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.21,
180
+ "learning_rate": 9.950461888367891e-05,
181
+ "loss": 3.0312,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.22,
186
+ "learning_rate": 9.945269214192618e-05,
187
+ "loss": 2.9979,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.22,
192
+ "learning_rate": 9.940076540017345e-05,
193
+ "loss": 2.9722,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.23,
198
+ "learning_rate": 9.93488386584207e-05,
199
+ "loss": 2.945,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.24,
204
+ "learning_rate": 9.929701577015148e-05,
205
+ "loss": 2.9172,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.24,
210
+ "learning_rate": 9.924519288188225e-05,
211
+ "loss": 2.8928,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.25,
216
+ "learning_rate": 9.919326614012952e-05,
217
+ "loss": 2.8699,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.26,
222
+ "learning_rate": 9.914133939837677e-05,
223
+ "loss": 2.8491,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.27,
228
+ "learning_rate": 9.908941265662404e-05,
229
+ "loss": 2.8275,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.27,
234
+ "learning_rate": 9.903748591487131e-05,
235
+ "loss": 2.8038,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.28,
240
+ "learning_rate": 9.898555917311856e-05,
241
+ "loss": 2.787,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.29,
246
+ "learning_rate": 9.893363243136583e-05,
247
+ "loss": 2.768,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.3,
252
+ "learning_rate": 9.88818095430966e-05,
253
+ "loss": 2.7538,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.3,
258
+ "learning_rate": 9.882988280134387e-05,
259
+ "loss": 2.7372,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.31,
264
+ "learning_rate": 9.877795605959113e-05,
265
+ "loss": 2.7222,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.32,
270
+ "learning_rate": 9.87260293178384e-05,
271
+ "loss": 2.7134,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.32,
276
+ "learning_rate": 9.867410257608566e-05,
277
+ "loss": 2.6956,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.33,
282
+ "learning_rate": 9.862227968781644e-05,
283
+ "loss": 2.6807,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.34,
288
+ "learning_rate": 9.857035294606369e-05,
289
+ "loss": 2.671,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.35,
294
+ "learning_rate": 9.851842620431096e-05,
295
+ "loss": 2.6575,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 0.35,
300
+ "learning_rate": 9.846649946255823e-05,
301
+ "loss": 2.6476,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 0.36,
306
+ "learning_rate": 9.8414676574289e-05,
307
+ "loss": 2.6363,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 0.37,
312
+ "learning_rate": 9.836274983253626e-05,
313
+ "loss": 2.6247,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 0.37,
318
+ "learning_rate": 9.831082309078353e-05,
319
+ "loss": 2.6118,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 0.38,
324
+ "learning_rate": 9.82588963490308e-05,
325
+ "loss": 2.6042,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 0.39,
330
+ "learning_rate": 9.820707346076157e-05,
331
+ "loss": 2.5936,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 0.4,
336
+ "learning_rate": 9.815514671900883e-05,
337
+ "loss": 2.5828,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 0.4,
342
+ "learning_rate": 9.810321997725609e-05,
343
+ "loss": 2.5737,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 0.41,
348
+ "learning_rate": 9.805129323550336e-05,
349
+ "loss": 2.5671,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 0.42,
354
+ "learning_rate": 9.799947034723412e-05,
355
+ "loss": 2.5575,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 0.42,
360
+ "learning_rate": 9.794754360548139e-05,
361
+ "loss": 2.5498,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 0.43,
366
+ "learning_rate": 9.789561686372866e-05,
367
+ "loss": 2.5449,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 0.44,
372
+ "learning_rate": 9.784369012197591e-05,
373
+ "loss": 2.5361,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 0.45,
378
+ "learning_rate": 9.77918672337067e-05,
379
+ "loss": 2.5307,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 0.45,
384
+ "learning_rate": 9.774004434543746e-05,
385
+ "loss": 2.523,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 0.46,
390
+ "learning_rate": 9.768811760368473e-05,
391
+ "loss": 2.5129,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 0.47,
396
+ "learning_rate": 9.763619086193198e-05,
397
+ "loss": 2.509,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 0.48,
402
+ "learning_rate": 9.758426412017925e-05,
403
+ "loss": 2.4989,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 0.48,
408
+ "learning_rate": 9.753233737842652e-05,
409
+ "loss": 2.4968,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 0.49,
414
+ "learning_rate": 9.748051449015729e-05,
415
+ "loss": 2.4901,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 0.5,
420
+ "learning_rate": 9.742858774840455e-05,
421
+ "loss": 2.4799,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 0.5,
426
+ "learning_rate": 9.737666100665181e-05,
427
+ "loss": 2.4764,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 0.51,
432
+ "learning_rate": 9.732473426489909e-05,
433
+ "loss": 2.4707,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 0.52,
438
+ "learning_rate": 9.727280752314635e-05,
439
+ "loss": 2.4663,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 0.53,
444
+ "learning_rate": 9.722098463487713e-05,
445
+ "loss": 2.4592,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 0.53,
450
+ "learning_rate": 9.716905789312438e-05,
451
+ "loss": 2.4528,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 0.54,
456
+ "learning_rate": 9.711713115137165e-05,
457
+ "loss": 2.4517,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 0.55,
462
+ "learning_rate": 9.706520440961892e-05,
463
+ "loss": 2.447,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 0.55,
468
+ "learning_rate": 9.701338152134968e-05,
469
+ "loss": 2.4342,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 0.56,
474
+ "learning_rate": 9.696145477959695e-05,
475
+ "loss": 2.4355,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 0.57,
480
+ "learning_rate": 9.69095280378442e-05,
481
+ "loss": 2.4292,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 0.58,
486
+ "learning_rate": 9.685760129609149e-05,
487
+ "loss": 2.426,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 0.58,
492
+ "learning_rate": 9.680567455433874e-05,
493
+ "loss": 2.4177,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 0.59,
498
+ "learning_rate": 9.6753747812586e-05,
499
+ "loss": 2.4136,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 0.6,
504
+ "learning_rate": 9.670192492431678e-05,
505
+ "loss": 2.4099,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 0.6,
510
+ "learning_rate": 9.664999818256403e-05,
511
+ "loss": 2.4072,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 0.61,
516
+ "learning_rate": 9.659807144081131e-05,
517
+ "loss": 2.402,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 0.62,
522
+ "learning_rate": 9.654614469905857e-05,
523
+ "loss": 2.3975,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 0.63,
528
+ "learning_rate": 9.649432181078935e-05,
529
+ "loss": 2.3914,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 0.63,
534
+ "learning_rate": 9.64423950690366e-05,
535
+ "loss": 2.3901,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 0.64,
540
+ "learning_rate": 9.639046832728387e-05,
541
+ "loss": 2.388,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 0.65,
546
+ "learning_rate": 9.633854158553114e-05,
547
+ "loss": 2.3837,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 0.65,
552
+ "learning_rate": 9.62867186972619e-05,
553
+ "loss": 2.3821,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 0.66,
558
+ "learning_rate": 9.623479195550917e-05,
559
+ "loss": 2.3754,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 0.67,
564
+ "learning_rate": 9.618286521375643e-05,
565
+ "loss": 2.371,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 0.68,
570
+ "learning_rate": 9.613093847200371e-05,
571
+ "loss": 2.3657,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 0.68,
576
+ "learning_rate": 9.607901173025097e-05,
577
+ "loss": 2.3574,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 0.69,
582
+ "learning_rate": 9.602718884198175e-05,
583
+ "loss": 2.3635,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 0.7,
588
+ "learning_rate": 9.5975262100229e-05,
589
+ "loss": 2.356,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 0.71,
594
+ "learning_rate": 9.592333535847627e-05,
595
+ "loss": 2.3499,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 0.71,
600
+ "learning_rate": 9.587140861672354e-05,
601
+ "loss": 2.3485,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 0.72,
606
+ "learning_rate": 9.581948187497079e-05,
607
+ "loss": 2.3504,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 0.73,
612
+ "learning_rate": 9.576755513321806e-05,
613
+ "loss": 2.341,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 0.73,
618
+ "learning_rate": 9.571573224494883e-05,
619
+ "loss": 2.3404,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 0.74,
624
+ "learning_rate": 9.56638055031961e-05,
625
+ "loss": 2.3353,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 0.75,
630
+ "learning_rate": 9.561187876144336e-05,
631
+ "loss": 2.3323,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 0.76,
636
+ "learning_rate": 9.555995201969062e-05,
637
+ "loss": 2.3328,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 0.76,
642
+ "learning_rate": 9.55081291314214e-05,
643
+ "loss": 2.3304,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 0.77,
648
+ "learning_rate": 9.545620238966865e-05,
649
+ "loss": 2.3251,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 0.78,
654
+ "learning_rate": 9.540427564791592e-05,
655
+ "loss": 2.3243,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 0.78,
660
+ "learning_rate": 9.535234890616319e-05,
661
+ "loss": 2.3267,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 0.79,
666
+ "learning_rate": 9.530042216441046e-05,
667
+ "loss": 2.3152,
668
+ "step": 55000
669
+ },
670
+ {
671
+ "epoch": 0.8,
672
+ "learning_rate": 9.524849542265773e-05,
673
+ "loss": 2.3157,
674
+ "step": 55500
675
+ },
676
+ {
677
+ "epoch": 0.81,
678
+ "learning_rate": 9.519656868090498e-05,
679
+ "loss": 2.3077,
680
+ "step": 56000
681
+ },
682
+ {
683
+ "epoch": 0.81,
684
+ "learning_rate": 9.514474579263576e-05,
685
+ "loss": 2.3043,
686
+ "step": 56500
687
+ },
688
+ {
689
+ "epoch": 0.82,
690
+ "learning_rate": 9.509281905088301e-05,
691
+ "loss": 2.3081,
692
+ "step": 57000
693
+ },
694
+ {
695
+ "epoch": 0.83,
696
+ "learning_rate": 9.504089230913028e-05,
697
+ "loss": 2.2992,
698
+ "step": 57500
699
+ },
700
+ {
701
+ "epoch": 0.83,
702
+ "learning_rate": 9.498896556737755e-05,
703
+ "loss": 2.3053,
704
+ "step": 58000
705
+ },
706
+ {
707
+ "epoch": 0.84,
708
+ "learning_rate": 9.493714267910832e-05,
709
+ "loss": 2.2959,
710
+ "step": 58500
711
+ },
712
+ {
713
+ "epoch": 0.85,
714
+ "learning_rate": 9.488521593735559e-05,
715
+ "loss": 2.2958,
716
+ "step": 59000
717
+ },
718
+ {
719
+ "epoch": 0.86,
720
+ "learning_rate": 9.483328919560285e-05,
721
+ "loss": 2.292,
722
+ "step": 59500
723
+ },
724
+ {
725
+ "epoch": 0.86,
726
+ "learning_rate": 9.478136245385011e-05,
727
+ "loss": 2.2902,
728
+ "step": 60000
729
+ },
730
+ {
731
+ "epoch": 0.87,
732
+ "learning_rate": 9.472943571209738e-05,
733
+ "loss": 2.2859,
734
+ "step": 60500
735
+ },
736
+ {
737
+ "epoch": 0.88,
738
+ "learning_rate": 9.467750897034465e-05,
739
+ "loss": 2.2821,
740
+ "step": 61000
741
+ },
742
+ {
743
+ "epoch": 0.89,
744
+ "learning_rate": 9.46255822285919e-05,
745
+ "loss": 2.2826,
746
+ "step": 61500
747
+ },
748
+ {
749
+ "epoch": 0.89,
750
+ "learning_rate": 9.457365548683917e-05,
751
+ "loss": 2.2825,
752
+ "step": 62000
753
+ },
754
+ {
755
+ "epoch": 0.9,
756
+ "learning_rate": 9.452183259856993e-05,
757
+ "loss": 2.2826,
758
+ "step": 62500
759
+ },
760
+ {
761
+ "epoch": 0.91,
762
+ "learning_rate": 9.44699058568172e-05,
763
+ "loss": 2.2723,
764
+ "step": 63000
765
+ },
766
+ {
767
+ "epoch": 0.91,
768
+ "learning_rate": 9.441797911506447e-05,
769
+ "loss": 2.2721,
770
+ "step": 63500
771
+ },
772
+ {
773
+ "epoch": 0.92,
774
+ "learning_rate": 9.436605237331174e-05,
775
+ "loss": 2.2744,
776
+ "step": 64000
777
+ },
778
+ {
779
+ "epoch": 0.93,
780
+ "learning_rate": 9.431412563155901e-05,
781
+ "loss": 2.2722,
782
+ "step": 64500
783
+ },
784
+ {
785
+ "epoch": 0.94,
786
+ "learning_rate": 9.426230274328977e-05,
787
+ "loss": 2.2649,
788
+ "step": 65000
789
+ },
790
+ {
791
+ "epoch": 0.94,
792
+ "learning_rate": 9.421037600153704e-05,
793
+ "loss": 2.2639,
794
+ "step": 65500
795
+ },
796
+ {
797
+ "epoch": 0.95,
798
+ "learning_rate": 9.41584492597843e-05,
799
+ "loss": 2.2653,
800
+ "step": 66000
801
+ },
802
+ {
803
+ "epoch": 0.96,
804
+ "learning_rate": 9.410652251803157e-05,
805
+ "loss": 2.2565,
806
+ "step": 66500
807
+ },
808
+ {
809
+ "epoch": 0.96,
810
+ "learning_rate": 9.405459577627883e-05,
811
+ "loss": 2.2624,
812
+ "step": 67000
813
+ },
814
+ {
815
+ "epoch": 0.97,
816
+ "learning_rate": 9.400266903452609e-05,
817
+ "loss": 2.2556,
818
+ "step": 67500
819
+ },
820
+ {
821
+ "epoch": 0.98,
822
+ "learning_rate": 9.395074229277337e-05,
823
+ "loss": 2.2516,
824
+ "step": 68000
825
+ },
826
+ {
827
+ "epoch": 0.99,
828
+ "learning_rate": 9.389881555102063e-05,
829
+ "loss": 2.249,
830
+ "step": 68500
831
+ },
832
+ {
833
+ "epoch": 0.99,
834
+ "learning_rate": 9.38469926627514e-05,
835
+ "loss": 2.2548,
836
+ "step": 69000
837
+ },
838
+ {
839
+ "epoch": 1.0,
840
+ "eval_accuracy": 0.588244433320517,
841
+ "eval_loss": 2.116262674331665,
842
+ "eval_runtime": 646.5563,
843
+ "eval_samples_per_second": 833.55,
844
+ "eval_steps_per_second": 34.732,
845
+ "step": 69473
846
+ }
847
+ ],
848
+ "max_steps": 972622,
849
+ "num_train_epochs": 14,
850
+ "total_flos": 4.861649092817715e+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 sha256:5883b79fc19dbeacc6f4d380b20de1f85c6a4e0818d4ad41bbf211141fc2852c
3
+ size 3311
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87809337f73cbefa3f4256bff6ac6d089e7cd202413cf523cc94eba02f885d92
3
+ size 118242180
runs/Aug02_00-40-05_user-SYS-5049A-TR/1659368419.1431136/events.out.tfevents.1659368419.user-SYS-5049A-TR.4008140.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a0de85c3d52322900c156be9b5d4b224b3c08eb3e637244beeff205cc714b41
3
+ size 5205
runs/Aug02_00-40-05_user-SYS-5049A-TR/events.out.tfevents.1659368419.user-SYS-5049A-TR.4008140.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b81e4f8544ddb0e18873e3b46cfdf0598b127727164457773f3155a79889585b
3
+ size 25739
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
+ {"model_max_length": 128, "padding_side": "right", "truncation_side": "right", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "special_tokens_map_file": "pretrained_tokenizers/ex3-1_ipadic_bpe/special_tokens_map.json", "name_or_path": "pretrained_tokenizers/ex3-1_ipadic_bpe", "tokenizer_class": "PreTrainedTokenizerFast"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5883b79fc19dbeacc6f4d380b20de1f85c6a4e0818d4ad41bbf211141fc2852c
3
+ size 3311