rttl commited on
Commit
9b4ca9a
1 Parent(s): 4c0d0fd

Upload 10 files

Browse files
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/vera/Desktop/yelp-review/yelp-review-TAPT/checkpoint-857907",
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": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2,
25
+ "LABEL_3": 3,
26
+ "LABEL_4": 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": "single_label_classification",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.22.0.dev0",
38
+ "type_vocab_size": 2,
39
+ "use_cache": true,
40
+ "vocab_size": 30522
41
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743b5d3e9bea36440bdea783ffac203d8845f925e10e56c24ad4f63de2ca9872
3
+ size 876005597
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ea250132c61843624645a372206f9e7f8313b946e205dba9180a2696aa03cd
3
+ size 438015341
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2780c69471eb1e88b5b1c38acfeef49bc3963662859ad1704528b46d95cbc73a
3
+ size 15523
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6eba430d6a54d74e9ca84b71fc82c83bc18194405bb3db5b8642d1654ac91d7
3
+ size 623
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_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "name_or_path": "/home/vera/Desktop/yelp-review/yelp-review-TAPT/checkpoint-857907",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]",
16
+ "use_fast": true
17
+ }
trainer_state.json ADDED
@@ -0,0 +1,1006 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 81250,
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": 5.000000000000001e-07,
13
+ "loss": 1.6109,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 1.0000000000000002e-06,
19
+ "loss": 1.5501,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.04,
24
+ "learning_rate": 1.5e-06,
25
+ "loss": 1.1228,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.05,
30
+ "learning_rate": 2.0000000000000003e-06,
31
+ "loss": 0.8543,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.06,
36
+ "learning_rate": 2.5e-06,
37
+ "loss": 0.8183,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.07,
42
+ "learning_rate": 3e-06,
43
+ "loss": 0.7931,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.09,
48
+ "learning_rate": 3.5e-06,
49
+ "loss": 0.7792,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.1,
54
+ "learning_rate": 4.000000000000001e-06,
55
+ "loss": 0.7713,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.11,
60
+ "learning_rate": 4.5e-06,
61
+ "loss": 0.7678,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.12,
66
+ "learning_rate": 5e-06,
67
+ "loss": 0.7736,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.14,
72
+ "learning_rate": 5.500000000000001e-06,
73
+ "loss": 0.7527,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.15,
78
+ "learning_rate": 6e-06,
79
+ "loss": 0.7499,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.16,
84
+ "learning_rate": 6.5000000000000004e-06,
85
+ "loss": 0.7438,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.17,
90
+ "learning_rate": 7e-06,
91
+ "loss": 0.7462,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.18,
96
+ "learning_rate": 7.500000000000001e-06,
97
+ "loss": 0.7524,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.2,
102
+ "learning_rate": 8.000000000000001e-06,
103
+ "loss": 0.7427,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.21,
108
+ "learning_rate": 8.5e-06,
109
+ "loss": 0.7342,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.22,
114
+ "learning_rate": 9e-06,
115
+ "loss": 0.7347,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.23,
120
+ "learning_rate": 9.5e-06,
121
+ "loss": 0.749,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.25,
126
+ "learning_rate": 1e-05,
127
+ "loss": 0.7288,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.26,
132
+ "learning_rate": 9.993769470404985e-06,
133
+ "loss": 0.7326,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.27,
138
+ "learning_rate": 9.98753894080997e-06,
139
+ "loss": 0.7256,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.28,
144
+ "learning_rate": 9.981308411214954e-06,
145
+ "loss": 0.7386,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.3,
150
+ "learning_rate": 9.97507788161994e-06,
151
+ "loss": 0.7285,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.31,
156
+ "learning_rate": 9.968847352024923e-06,
157
+ "loss": 0.7223,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.32,
162
+ "learning_rate": 9.962616822429907e-06,
163
+ "loss": 0.7327,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.33,
168
+ "learning_rate": 9.956386292834892e-06,
169
+ "loss": 0.7189,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.34,
174
+ "learning_rate": 9.950155763239876e-06,
175
+ "loss": 0.7316,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.36,
180
+ "learning_rate": 9.943925233644862e-06,
181
+ "loss": 0.7129,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.37,
186
+ "learning_rate": 9.937694704049845e-06,
187
+ "loss": 0.7096,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.38,
192
+ "learning_rate": 9.931464174454829e-06,
193
+ "loss": 0.7134,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.39,
198
+ "learning_rate": 9.925233644859815e-06,
199
+ "loss": 0.7201,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.41,
204
+ "learning_rate": 9.919003115264798e-06,
205
+ "loss": 0.7185,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.42,
210
+ "learning_rate": 9.912772585669784e-06,
211
+ "loss": 0.7215,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.43,
216
+ "learning_rate": 9.906542056074768e-06,
217
+ "loss": 0.7142,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.44,
222
+ "learning_rate": 9.900311526479751e-06,
223
+ "loss": 0.7261,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.46,
228
+ "learning_rate": 9.894080996884737e-06,
229
+ "loss": 0.7091,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.47,
234
+ "learning_rate": 9.88785046728972e-06,
235
+ "loss": 0.7138,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.48,
240
+ "learning_rate": 9.881619937694706e-06,
241
+ "loss": 0.7134,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.49,
246
+ "learning_rate": 9.87538940809969e-06,
247
+ "loss": 0.7157,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.5,
252
+ "learning_rate": 9.869158878504674e-06,
253
+ "loss": 0.7136,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.52,
258
+ "learning_rate": 9.862928348909659e-06,
259
+ "loss": 0.7133,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.53,
264
+ "learning_rate": 9.856697819314643e-06,
265
+ "loss": 0.7048,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.54,
270
+ "learning_rate": 9.850467289719627e-06,
271
+ "loss": 0.7004,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.55,
276
+ "learning_rate": 9.844236760124612e-06,
277
+ "loss": 0.69,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.57,
282
+ "learning_rate": 9.838006230529596e-06,
283
+ "loss": 0.7158,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.58,
288
+ "learning_rate": 9.83177570093458e-06,
289
+ "loss": 0.6995,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.59,
294
+ "learning_rate": 9.825545171339565e-06,
295
+ "loss": 0.6893,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 0.6,
300
+ "learning_rate": 9.819314641744549e-06,
301
+ "loss": 0.6978,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 0.62,
306
+ "learning_rate": 9.813084112149533e-06,
307
+ "loss": 0.7025,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 0.63,
312
+ "learning_rate": 9.806853582554518e-06,
313
+ "loss": 0.6952,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 0.64,
318
+ "learning_rate": 9.800623052959502e-06,
319
+ "loss": 0.7102,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 0.65,
324
+ "learning_rate": 9.794392523364486e-06,
325
+ "loss": 0.7042,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 0.66,
330
+ "learning_rate": 9.788161993769471e-06,
331
+ "loss": 0.6953,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 0.68,
336
+ "learning_rate": 9.781931464174455e-06,
337
+ "loss": 0.7247,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 0.69,
342
+ "learning_rate": 9.775700934579439e-06,
343
+ "loss": 0.7081,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 0.7,
348
+ "learning_rate": 9.769470404984424e-06,
349
+ "loss": 0.711,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 0.71,
354
+ "learning_rate": 9.763239875389408e-06,
355
+ "loss": 0.6943,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 0.73,
360
+ "learning_rate": 9.757009345794393e-06,
361
+ "loss": 0.6845,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 0.74,
366
+ "learning_rate": 9.750778816199377e-06,
367
+ "loss": 0.7012,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 0.75,
372
+ "learning_rate": 9.744548286604361e-06,
373
+ "loss": 0.7031,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 0.76,
378
+ "learning_rate": 9.738317757009347e-06,
379
+ "loss": 0.6994,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 0.78,
384
+ "learning_rate": 9.73208722741433e-06,
385
+ "loss": 0.7058,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 0.79,
390
+ "learning_rate": 9.725856697819316e-06,
391
+ "loss": 0.69,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 0.8,
396
+ "learning_rate": 9.7196261682243e-06,
397
+ "loss": 0.6888,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 0.81,
402
+ "learning_rate": 9.713395638629283e-06,
403
+ "loss": 0.7044,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 0.82,
408
+ "learning_rate": 9.707165109034269e-06,
409
+ "loss": 0.6841,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 0.84,
414
+ "learning_rate": 9.700934579439253e-06,
415
+ "loss": 0.6886,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 0.85,
420
+ "learning_rate": 9.694704049844238e-06,
421
+ "loss": 0.6884,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 0.86,
426
+ "learning_rate": 9.688473520249222e-06,
427
+ "loss": 0.699,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 0.87,
432
+ "learning_rate": 9.682242990654206e-06,
433
+ "loss": 0.7042,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 0.89,
438
+ "learning_rate": 9.676012461059191e-06,
439
+ "loss": 0.6993,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 0.9,
444
+ "learning_rate": 9.669781931464175e-06,
445
+ "loss": 0.6983,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 0.91,
450
+ "learning_rate": 9.66355140186916e-06,
451
+ "loss": 0.697,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 0.92,
456
+ "learning_rate": 9.657320872274144e-06,
457
+ "loss": 0.704,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 0.94,
462
+ "learning_rate": 9.651090342679128e-06,
463
+ "loss": 0.6917,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 0.95,
468
+ "learning_rate": 9.644859813084113e-06,
469
+ "loss": 0.6904,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 0.96,
474
+ "learning_rate": 9.638629283489097e-06,
475
+ "loss": 0.6946,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 0.97,
480
+ "learning_rate": 9.632398753894083e-06,
481
+ "loss": 0.6905,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 0.98,
486
+ "learning_rate": 9.626168224299066e-06,
487
+ "loss": 0.7,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 1.0,
492
+ "learning_rate": 9.61993769470405e-06,
493
+ "loss": 0.7068,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 1.0,
498
+ "eval_accuracy": 0.69898,
499
+ "eval_loss": 0.6849758625030518,
500
+ "eval_runtime": 138.1081,
501
+ "eval_samples_per_second": 362.035,
502
+ "eval_steps_per_second": 22.627,
503
+ "step": 40625
504
+ },
505
+ {
506
+ "epoch": 1.01,
507
+ "learning_rate": 9.613707165109036e-06,
508
+ "loss": 0.6541,
509
+ "step": 41000
510
+ },
511
+ {
512
+ "epoch": 1.02,
513
+ "learning_rate": 9.60747663551402e-06,
514
+ "loss": 0.6604,
515
+ "step": 41500
516
+ },
517
+ {
518
+ "epoch": 1.03,
519
+ "learning_rate": 9.601246105919005e-06,
520
+ "loss": 0.6514,
521
+ "step": 42000
522
+ },
523
+ {
524
+ "epoch": 1.05,
525
+ "learning_rate": 9.595015576323989e-06,
526
+ "loss": 0.6295,
527
+ "step": 42500
528
+ },
529
+ {
530
+ "epoch": 1.06,
531
+ "learning_rate": 9.588785046728972e-06,
532
+ "loss": 0.6594,
533
+ "step": 43000
534
+ },
535
+ {
536
+ "epoch": 1.07,
537
+ "learning_rate": 9.582554517133958e-06,
538
+ "loss": 0.6389,
539
+ "step": 43500
540
+ },
541
+ {
542
+ "epoch": 1.08,
543
+ "learning_rate": 9.576323987538942e-06,
544
+ "loss": 0.6329,
545
+ "step": 44000
546
+ },
547
+ {
548
+ "epoch": 1.1,
549
+ "learning_rate": 9.570093457943927e-06,
550
+ "loss": 0.6528,
551
+ "step": 44500
552
+ },
553
+ {
554
+ "epoch": 1.11,
555
+ "learning_rate": 9.563862928348911e-06,
556
+ "loss": 0.6429,
557
+ "step": 45000
558
+ },
559
+ {
560
+ "epoch": 1.12,
561
+ "learning_rate": 9.557632398753895e-06,
562
+ "loss": 0.6358,
563
+ "step": 45500
564
+ },
565
+ {
566
+ "epoch": 1.13,
567
+ "learning_rate": 9.55140186915888e-06,
568
+ "loss": 0.6328,
569
+ "step": 46000
570
+ },
571
+ {
572
+ "epoch": 1.14,
573
+ "learning_rate": 9.545171339563864e-06,
574
+ "loss": 0.6362,
575
+ "step": 46500
576
+ },
577
+ {
578
+ "epoch": 1.16,
579
+ "learning_rate": 9.538940809968848e-06,
580
+ "loss": 0.6299,
581
+ "step": 47000
582
+ },
583
+ {
584
+ "epoch": 1.17,
585
+ "learning_rate": 9.532710280373833e-06,
586
+ "loss": 0.6458,
587
+ "step": 47500
588
+ },
589
+ {
590
+ "epoch": 1.18,
591
+ "learning_rate": 9.526479750778817e-06,
592
+ "loss": 0.6404,
593
+ "step": 48000
594
+ },
595
+ {
596
+ "epoch": 1.19,
597
+ "learning_rate": 9.520249221183802e-06,
598
+ "loss": 0.6451,
599
+ "step": 48500
600
+ },
601
+ {
602
+ "epoch": 1.21,
603
+ "learning_rate": 9.514018691588786e-06,
604
+ "loss": 0.6299,
605
+ "step": 49000
606
+ },
607
+ {
608
+ "epoch": 1.22,
609
+ "learning_rate": 9.50778816199377e-06,
610
+ "loss": 0.6411,
611
+ "step": 49500
612
+ },
613
+ {
614
+ "epoch": 1.23,
615
+ "learning_rate": 9.501557632398755e-06,
616
+ "loss": 0.6398,
617
+ "step": 50000
618
+ },
619
+ {
620
+ "epoch": 1.24,
621
+ "learning_rate": 9.49532710280374e-06,
622
+ "loss": 0.6471,
623
+ "step": 50500
624
+ },
625
+ {
626
+ "epoch": 1.26,
627
+ "learning_rate": 9.489096573208723e-06,
628
+ "loss": 0.6479,
629
+ "step": 51000
630
+ },
631
+ {
632
+ "epoch": 1.27,
633
+ "learning_rate": 9.482866043613708e-06,
634
+ "loss": 0.6239,
635
+ "step": 51500
636
+ },
637
+ {
638
+ "epoch": 1.28,
639
+ "learning_rate": 9.476635514018692e-06,
640
+ "loss": 0.6405,
641
+ "step": 52000
642
+ },
643
+ {
644
+ "epoch": 1.29,
645
+ "learning_rate": 9.470404984423676e-06,
646
+ "loss": 0.6458,
647
+ "step": 52500
648
+ },
649
+ {
650
+ "epoch": 1.3,
651
+ "learning_rate": 9.464174454828661e-06,
652
+ "loss": 0.6269,
653
+ "step": 53000
654
+ },
655
+ {
656
+ "epoch": 1.32,
657
+ "learning_rate": 9.457943925233645e-06,
658
+ "loss": 0.6438,
659
+ "step": 53500
660
+ },
661
+ {
662
+ "epoch": 1.33,
663
+ "learning_rate": 9.451713395638629e-06,
664
+ "loss": 0.65,
665
+ "step": 54000
666
+ },
667
+ {
668
+ "epoch": 1.34,
669
+ "learning_rate": 9.445482866043614e-06,
670
+ "loss": 0.6495,
671
+ "step": 54500
672
+ },
673
+ {
674
+ "epoch": 1.35,
675
+ "learning_rate": 9.439252336448598e-06,
676
+ "loss": 0.6355,
677
+ "step": 55000
678
+ },
679
+ {
680
+ "epoch": 1.37,
681
+ "learning_rate": 9.433021806853582e-06,
682
+ "loss": 0.6452,
683
+ "step": 55500
684
+ },
685
+ {
686
+ "epoch": 1.38,
687
+ "learning_rate": 9.426791277258568e-06,
688
+ "loss": 0.6419,
689
+ "step": 56000
690
+ },
691
+ {
692
+ "epoch": 1.39,
693
+ "learning_rate": 9.420560747663551e-06,
694
+ "loss": 0.6589,
695
+ "step": 56500
696
+ },
697
+ {
698
+ "epoch": 1.4,
699
+ "learning_rate": 9.414330218068537e-06,
700
+ "loss": 0.6426,
701
+ "step": 57000
702
+ },
703
+ {
704
+ "epoch": 1.42,
705
+ "learning_rate": 9.40809968847352e-06,
706
+ "loss": 0.6367,
707
+ "step": 57500
708
+ },
709
+ {
710
+ "epoch": 1.43,
711
+ "learning_rate": 9.401869158878504e-06,
712
+ "loss": 0.6388,
713
+ "step": 58000
714
+ },
715
+ {
716
+ "epoch": 1.44,
717
+ "learning_rate": 9.39563862928349e-06,
718
+ "loss": 0.6507,
719
+ "step": 58500
720
+ },
721
+ {
722
+ "epoch": 1.45,
723
+ "learning_rate": 9.389408099688474e-06,
724
+ "loss": 0.6377,
725
+ "step": 59000
726
+ },
727
+ {
728
+ "epoch": 1.46,
729
+ "learning_rate": 9.383177570093459e-06,
730
+ "loss": 0.6612,
731
+ "step": 59500
732
+ },
733
+ {
734
+ "epoch": 1.48,
735
+ "learning_rate": 9.376947040498443e-06,
736
+ "loss": 0.659,
737
+ "step": 60000
738
+ },
739
+ {
740
+ "epoch": 1.49,
741
+ "learning_rate": 9.370716510903427e-06,
742
+ "loss": 0.6396,
743
+ "step": 60500
744
+ },
745
+ {
746
+ "epoch": 1.5,
747
+ "learning_rate": 9.364485981308412e-06,
748
+ "loss": 0.6541,
749
+ "step": 61000
750
+ },
751
+ {
752
+ "epoch": 1.51,
753
+ "learning_rate": 9.358255451713396e-06,
754
+ "loss": 0.6483,
755
+ "step": 61500
756
+ },
757
+ {
758
+ "epoch": 1.53,
759
+ "learning_rate": 9.352024922118381e-06,
760
+ "loss": 0.6366,
761
+ "step": 62000
762
+ },
763
+ {
764
+ "epoch": 1.54,
765
+ "learning_rate": 9.345794392523365e-06,
766
+ "loss": 0.6476,
767
+ "step": 62500
768
+ },
769
+ {
770
+ "epoch": 1.55,
771
+ "learning_rate": 9.339563862928349e-06,
772
+ "loss": 0.6553,
773
+ "step": 63000
774
+ },
775
+ {
776
+ "epoch": 1.56,
777
+ "learning_rate": 9.333333333333334e-06,
778
+ "loss": 0.6362,
779
+ "step": 63500
780
+ },
781
+ {
782
+ "epoch": 1.58,
783
+ "learning_rate": 9.327102803738318e-06,
784
+ "loss": 0.6442,
785
+ "step": 64000
786
+ },
787
+ {
788
+ "epoch": 1.59,
789
+ "learning_rate": 9.320872274143304e-06,
790
+ "loss": 0.6566,
791
+ "step": 64500
792
+ },
793
+ {
794
+ "epoch": 1.6,
795
+ "learning_rate": 9.314641744548287e-06,
796
+ "loss": 0.6497,
797
+ "step": 65000
798
+ },
799
+ {
800
+ "epoch": 1.61,
801
+ "learning_rate": 9.308411214953271e-06,
802
+ "loss": 0.6461,
803
+ "step": 65500
804
+ },
805
+ {
806
+ "epoch": 1.62,
807
+ "learning_rate": 9.302180685358257e-06,
808
+ "loss": 0.6609,
809
+ "step": 66000
810
+ },
811
+ {
812
+ "epoch": 1.64,
813
+ "learning_rate": 9.29595015576324e-06,
814
+ "loss": 0.6502,
815
+ "step": 66500
816
+ },
817
+ {
818
+ "epoch": 1.65,
819
+ "learning_rate": 9.289719626168226e-06,
820
+ "loss": 0.6531,
821
+ "step": 67000
822
+ },
823
+ {
824
+ "epoch": 1.66,
825
+ "learning_rate": 9.28348909657321e-06,
826
+ "loss": 0.6441,
827
+ "step": 67500
828
+ },
829
+ {
830
+ "epoch": 1.67,
831
+ "learning_rate": 9.277258566978193e-06,
832
+ "loss": 0.6487,
833
+ "step": 68000
834
+ },
835
+ {
836
+ "epoch": 1.69,
837
+ "learning_rate": 9.271028037383179e-06,
838
+ "loss": 0.6436,
839
+ "step": 68500
840
+ },
841
+ {
842
+ "epoch": 1.7,
843
+ "learning_rate": 9.264797507788163e-06,
844
+ "loss": 0.6575,
845
+ "step": 69000
846
+ },
847
+ {
848
+ "epoch": 1.71,
849
+ "learning_rate": 9.258566978193148e-06,
850
+ "loss": 0.6514,
851
+ "step": 69500
852
+ },
853
+ {
854
+ "epoch": 1.72,
855
+ "learning_rate": 9.252336448598132e-06,
856
+ "loss": 0.6424,
857
+ "step": 70000
858
+ },
859
+ {
860
+ "epoch": 1.74,
861
+ "learning_rate": 9.246105919003116e-06,
862
+ "loss": 0.646,
863
+ "step": 70500
864
+ },
865
+ {
866
+ "epoch": 1.75,
867
+ "learning_rate": 9.239875389408101e-06,
868
+ "loss": 0.6445,
869
+ "step": 71000
870
+ },
871
+ {
872
+ "epoch": 1.76,
873
+ "learning_rate": 9.233644859813085e-06,
874
+ "loss": 0.6507,
875
+ "step": 71500
876
+ },
877
+ {
878
+ "epoch": 1.77,
879
+ "learning_rate": 9.22741433021807e-06,
880
+ "loss": 0.6564,
881
+ "step": 72000
882
+ },
883
+ {
884
+ "epoch": 1.78,
885
+ "learning_rate": 9.221183800623054e-06,
886
+ "loss": 0.6422,
887
+ "step": 72500
888
+ },
889
+ {
890
+ "epoch": 1.8,
891
+ "learning_rate": 9.214953271028038e-06,
892
+ "loss": 0.6408,
893
+ "step": 73000
894
+ },
895
+ {
896
+ "epoch": 1.81,
897
+ "learning_rate": 9.208722741433023e-06,
898
+ "loss": 0.6394,
899
+ "step": 73500
900
+ },
901
+ {
902
+ "epoch": 1.82,
903
+ "learning_rate": 9.202492211838007e-06,
904
+ "loss": 0.6421,
905
+ "step": 74000
906
+ },
907
+ {
908
+ "epoch": 1.83,
909
+ "learning_rate": 9.196261682242991e-06,
910
+ "loss": 0.6379,
911
+ "step": 74500
912
+ },
913
+ {
914
+ "epoch": 1.85,
915
+ "learning_rate": 9.190031152647976e-06,
916
+ "loss": 0.6421,
917
+ "step": 75000
918
+ },
919
+ {
920
+ "epoch": 1.86,
921
+ "learning_rate": 9.18380062305296e-06,
922
+ "loss": 0.6277,
923
+ "step": 75500
924
+ },
925
+ {
926
+ "epoch": 1.87,
927
+ "learning_rate": 9.177570093457944e-06,
928
+ "loss": 0.6475,
929
+ "step": 76000
930
+ },
931
+ {
932
+ "epoch": 1.88,
933
+ "learning_rate": 9.17133956386293e-06,
934
+ "loss": 0.65,
935
+ "step": 76500
936
+ },
937
+ {
938
+ "epoch": 1.9,
939
+ "learning_rate": 9.165109034267913e-06,
940
+ "loss": 0.6546,
941
+ "step": 77000
942
+ },
943
+ {
944
+ "epoch": 1.91,
945
+ "learning_rate": 9.158878504672899e-06,
946
+ "loss": 0.6476,
947
+ "step": 77500
948
+ },
949
+ {
950
+ "epoch": 1.92,
951
+ "learning_rate": 9.152647975077882e-06,
952
+ "loss": 0.6362,
953
+ "step": 78000
954
+ },
955
+ {
956
+ "epoch": 1.93,
957
+ "learning_rate": 9.146417445482866e-06,
958
+ "loss": 0.6368,
959
+ "step": 78500
960
+ },
961
+ {
962
+ "epoch": 1.94,
963
+ "learning_rate": 9.140186915887852e-06,
964
+ "loss": 0.6338,
965
+ "step": 79000
966
+ },
967
+ {
968
+ "epoch": 1.96,
969
+ "learning_rate": 9.133956386292835e-06,
970
+ "loss": 0.6456,
971
+ "step": 79500
972
+ },
973
+ {
974
+ "epoch": 1.97,
975
+ "learning_rate": 9.12772585669782e-06,
976
+ "loss": 0.6563,
977
+ "step": 80000
978
+ },
979
+ {
980
+ "epoch": 1.98,
981
+ "learning_rate": 9.121495327102805e-06,
982
+ "loss": 0.6456,
983
+ "step": 80500
984
+ },
985
+ {
986
+ "epoch": 1.99,
987
+ "learning_rate": 9.115264797507789e-06,
988
+ "loss": 0.6518,
989
+ "step": 81000
990
+ },
991
+ {
992
+ "epoch": 2.0,
993
+ "eval_accuracy": 0.70374,
994
+ "eval_loss": 0.679389238357544,
995
+ "eval_runtime": 138.0175,
996
+ "eval_samples_per_second": 362.273,
997
+ "eval_steps_per_second": 22.642,
998
+ "step": 81250
999
+ }
1000
+ ],
1001
+ "max_steps": 812500,
1002
+ "num_train_epochs": 20,
1003
+ "total_flos": 1.710267926016e+17,
1004
+ "trial_name": null,
1005
+ "trial_params": null
1006
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5af338fa3f0963d808b62d76e742880a90bd868542be0b7a7f53ffd8d3cd99
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff