shax commited on
Commit
bbe128e
1 Parent(s): 252a7a2
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.3518991470336914,
4
+ "eval_runtime": 4.6868,
5
+ "eval_samples": 800,
6
+ "eval_samples_per_second": 170.691,
7
+ "eval_steps_per_second": 21.336,
8
+ "perplexity": 3.864758309760122,
9
+ "train_loss": 1.626130136269521,
10
+ "train_runtime": 5849.5407,
11
+ "train_samples": 15300,
12
+ "train_samples_per_second": 13.078,
13
+ "train_steps_per_second": 1.635
14
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
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": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.12.5",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.3518991470336914,
4
+ "eval_runtime": 4.6868,
5
+ "eval_samples": 800,
6
+ "eval_samples_per_second": 170.691,
7
+ "eval_steps_per_second": 21.336,
8
+ "perplexity": 3.864758309760122
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83003076a474ee20562de2189a268818f2b777d4583ba7347bdc0a8c6cbc9e1c
3
+ size 1340869650
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
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-uncased", "tokenizer_class": "BertTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 1.626130136269521,
4
+ "train_runtime": 5849.5407,
5
+ "train_samples": 15300,
6
+ "train_samples_per_second": 13.078,
7
+ "train_steps_per_second": 1.635
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,839 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 9565,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "eval_loss": 2.4315900802612305,
13
+ "eval_runtime": 4.6765,
14
+ "eval_samples_per_second": 171.069,
15
+ "eval_steps_per_second": 21.384,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.1,
20
+ "eval_loss": 2.3032939434051514,
21
+ "eval_runtime": 4.6682,
22
+ "eval_samples_per_second": 171.373,
23
+ "eval_steps_per_second": 21.422,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.16,
28
+ "eval_loss": 2.217759609222412,
29
+ "eval_runtime": 4.6679,
30
+ "eval_samples_per_second": 171.381,
31
+ "eval_steps_per_second": 21.423,
32
+ "step": 300
33
+ },
34
+ {
35
+ "epoch": 0.21,
36
+ "eval_loss": 2.14911150932312,
37
+ "eval_runtime": 4.6757,
38
+ "eval_samples_per_second": 171.099,
39
+ "eval_steps_per_second": 21.387,
40
+ "step": 400
41
+ },
42
+ {
43
+ "epoch": 0.26,
44
+ "eval_loss": 2.155996322631836,
45
+ "eval_runtime": 4.6665,
46
+ "eval_samples_per_second": 171.433,
47
+ "eval_steps_per_second": 21.429,
48
+ "step": 500
49
+ },
50
+ {
51
+ "epoch": 0.31,
52
+ "eval_loss": 2.01924991607666,
53
+ "eval_runtime": 4.6796,
54
+ "eval_samples_per_second": 170.956,
55
+ "eval_steps_per_second": 21.37,
56
+ "step": 600
57
+ },
58
+ {
59
+ "epoch": 0.37,
60
+ "eval_loss": 2.0464463233947754,
61
+ "eval_runtime": 4.6799,
62
+ "eval_samples_per_second": 170.944,
63
+ "eval_steps_per_second": 21.368,
64
+ "step": 700
65
+ },
66
+ {
67
+ "epoch": 0.42,
68
+ "eval_loss": 1.977142333984375,
69
+ "eval_runtime": 4.6707,
70
+ "eval_samples_per_second": 171.279,
71
+ "eval_steps_per_second": 21.41,
72
+ "step": 800
73
+ },
74
+ {
75
+ "epoch": 0.47,
76
+ "eval_loss": 1.967787504196167,
77
+ "eval_runtime": 4.6743,
78
+ "eval_samples_per_second": 171.148,
79
+ "eval_steps_per_second": 21.393,
80
+ "step": 900
81
+ },
82
+ {
83
+ "epoch": 0.52,
84
+ "learning_rate": 8.954521693674857e-06,
85
+ "loss": 2.2574,
86
+ "step": 1000
87
+ },
88
+ {
89
+ "epoch": 0.52,
90
+ "eval_loss": 1.9178065061569214,
91
+ "eval_runtime": 4.721,
92
+ "eval_samples_per_second": 169.457,
93
+ "eval_steps_per_second": 21.182,
94
+ "step": 1000
95
+ },
96
+ {
97
+ "epoch": 0.58,
98
+ "eval_loss": 1.8966461420059204,
99
+ "eval_runtime": 4.6821,
100
+ "eval_samples_per_second": 170.864,
101
+ "eval_steps_per_second": 21.358,
102
+ "step": 1100
103
+ },
104
+ {
105
+ "epoch": 0.63,
106
+ "eval_loss": 1.818562626838684,
107
+ "eval_runtime": 4.6827,
108
+ "eval_samples_per_second": 170.841,
109
+ "eval_steps_per_second": 21.355,
110
+ "step": 1200
111
+ },
112
+ {
113
+ "epoch": 0.68,
114
+ "eval_loss": 1.8336358070373535,
115
+ "eval_runtime": 4.6864,
116
+ "eval_samples_per_second": 170.708,
117
+ "eval_steps_per_second": 21.339,
118
+ "step": 1300
119
+ },
120
+ {
121
+ "epoch": 0.73,
122
+ "eval_loss": 1.8185982704162598,
123
+ "eval_runtime": 4.673,
124
+ "eval_samples_per_second": 171.196,
125
+ "eval_steps_per_second": 21.399,
126
+ "step": 1400
127
+ },
128
+ {
129
+ "epoch": 0.78,
130
+ "eval_loss": 1.8159518241882324,
131
+ "eval_runtime": 4.6851,
132
+ "eval_samples_per_second": 170.755,
133
+ "eval_steps_per_second": 21.344,
134
+ "step": 1500
135
+ },
136
+ {
137
+ "epoch": 0.84,
138
+ "eval_loss": 1.806492567062378,
139
+ "eval_runtime": 4.6846,
140
+ "eval_samples_per_second": 170.771,
141
+ "eval_steps_per_second": 21.346,
142
+ "step": 1600
143
+ },
144
+ {
145
+ "epoch": 0.89,
146
+ "eval_loss": 1.7608861923217773,
147
+ "eval_runtime": 4.6877,
148
+ "eval_samples_per_second": 170.659,
149
+ "eval_steps_per_second": 21.332,
150
+ "step": 1700
151
+ },
152
+ {
153
+ "epoch": 0.94,
154
+ "eval_loss": 1.7618434429168701,
155
+ "eval_runtime": 4.6769,
156
+ "eval_samples_per_second": 171.055,
157
+ "eval_steps_per_second": 21.382,
158
+ "step": 1800
159
+ },
160
+ {
161
+ "epoch": 0.99,
162
+ "eval_loss": 1.7498806715011597,
163
+ "eval_runtime": 4.6908,
164
+ "eval_samples_per_second": 170.546,
165
+ "eval_steps_per_second": 21.318,
166
+ "step": 1900
167
+ },
168
+ {
169
+ "epoch": 1.05,
170
+ "learning_rate": 7.909043387349713e-06,
171
+ "loss": 1.871,
172
+ "step": 2000
173
+ },
174
+ {
175
+ "epoch": 1.05,
176
+ "eval_loss": 1.816186547279358,
177
+ "eval_runtime": 4.7307,
178
+ "eval_samples_per_second": 169.107,
179
+ "eval_steps_per_second": 21.138,
180
+ "step": 2000
181
+ },
182
+ {
183
+ "epoch": 1.1,
184
+ "eval_loss": 1.7303450107574463,
185
+ "eval_runtime": 4.6832,
186
+ "eval_samples_per_second": 170.822,
187
+ "eval_steps_per_second": 21.353,
188
+ "step": 2100
189
+ },
190
+ {
191
+ "epoch": 1.15,
192
+ "eval_loss": 1.6595067977905273,
193
+ "eval_runtime": 4.6808,
194
+ "eval_samples_per_second": 170.912,
195
+ "eval_steps_per_second": 21.364,
196
+ "step": 2200
197
+ },
198
+ {
199
+ "epoch": 1.2,
200
+ "eval_loss": 1.7004770040512085,
201
+ "eval_runtime": 4.6859,
202
+ "eval_samples_per_second": 170.726,
203
+ "eval_steps_per_second": 21.341,
204
+ "step": 2300
205
+ },
206
+ {
207
+ "epoch": 1.25,
208
+ "eval_loss": 1.6547716856002808,
209
+ "eval_runtime": 4.6729,
210
+ "eval_samples_per_second": 171.199,
211
+ "eval_steps_per_second": 21.4,
212
+ "step": 2400
213
+ },
214
+ {
215
+ "epoch": 1.31,
216
+ "eval_loss": 1.6392831802368164,
217
+ "eval_runtime": 4.6758,
218
+ "eval_samples_per_second": 171.094,
219
+ "eval_steps_per_second": 21.387,
220
+ "step": 2500
221
+ },
222
+ {
223
+ "epoch": 1.36,
224
+ "eval_loss": 1.6230372190475464,
225
+ "eval_runtime": 4.6697,
226
+ "eval_samples_per_second": 171.318,
227
+ "eval_steps_per_second": 21.415,
228
+ "step": 2600
229
+ },
230
+ {
231
+ "epoch": 1.41,
232
+ "eval_loss": 1.63216233253479,
233
+ "eval_runtime": 4.6753,
234
+ "eval_samples_per_second": 171.111,
235
+ "eval_steps_per_second": 21.389,
236
+ "step": 2700
237
+ },
238
+ {
239
+ "epoch": 1.46,
240
+ "eval_loss": 1.627321720123291,
241
+ "eval_runtime": 4.6653,
242
+ "eval_samples_per_second": 171.477,
243
+ "eval_steps_per_second": 21.435,
244
+ "step": 2800
245
+ },
246
+ {
247
+ "epoch": 1.52,
248
+ "eval_loss": 1.6078392267227173,
249
+ "eval_runtime": 4.6673,
250
+ "eval_samples_per_second": 171.404,
251
+ "eval_steps_per_second": 21.425,
252
+ "step": 2900
253
+ },
254
+ {
255
+ "epoch": 1.57,
256
+ "learning_rate": 6.863565081024569e-06,
257
+ "loss": 1.7234,
258
+ "step": 3000
259
+ },
260
+ {
261
+ "epoch": 1.57,
262
+ "eval_loss": 1.6030551195144653,
263
+ "eval_runtime": 4.6964,
264
+ "eval_samples_per_second": 170.344,
265
+ "eval_steps_per_second": 21.293,
266
+ "step": 3000
267
+ },
268
+ {
269
+ "epoch": 1.62,
270
+ "eval_loss": 1.553316593170166,
271
+ "eval_runtime": 4.6663,
272
+ "eval_samples_per_second": 171.442,
273
+ "eval_steps_per_second": 21.43,
274
+ "step": 3100
275
+ },
276
+ {
277
+ "epoch": 1.67,
278
+ "eval_loss": 1.6135989427566528,
279
+ "eval_runtime": 4.6687,
280
+ "eval_samples_per_second": 171.355,
281
+ "eval_steps_per_second": 21.419,
282
+ "step": 3200
283
+ },
284
+ {
285
+ "epoch": 1.73,
286
+ "eval_loss": 1.5696121454238892,
287
+ "eval_runtime": 4.6764,
288
+ "eval_samples_per_second": 171.072,
289
+ "eval_steps_per_second": 21.384,
290
+ "step": 3300
291
+ },
292
+ {
293
+ "epoch": 1.78,
294
+ "eval_loss": 1.565152883529663,
295
+ "eval_runtime": 4.6699,
296
+ "eval_samples_per_second": 171.31,
297
+ "eval_steps_per_second": 21.414,
298
+ "step": 3400
299
+ },
300
+ {
301
+ "epoch": 1.83,
302
+ "eval_loss": 1.522884488105774,
303
+ "eval_runtime": 4.6578,
304
+ "eval_samples_per_second": 171.755,
305
+ "eval_steps_per_second": 21.469,
306
+ "step": 3500
307
+ },
308
+ {
309
+ "epoch": 1.88,
310
+ "eval_loss": 1.5707228183746338,
311
+ "eval_runtime": 4.6663,
312
+ "eval_samples_per_second": 171.44,
313
+ "eval_steps_per_second": 21.43,
314
+ "step": 3600
315
+ },
316
+ {
317
+ "epoch": 1.93,
318
+ "eval_loss": 1.587827444076538,
319
+ "eval_runtime": 4.6655,
320
+ "eval_samples_per_second": 171.473,
321
+ "eval_steps_per_second": 21.434,
322
+ "step": 3700
323
+ },
324
+ {
325
+ "epoch": 1.99,
326
+ "eval_loss": 1.5495318174362183,
327
+ "eval_runtime": 4.6751,
328
+ "eval_samples_per_second": 171.121,
329
+ "eval_steps_per_second": 21.39,
330
+ "step": 3800
331
+ },
332
+ {
333
+ "epoch": 2.04,
334
+ "eval_loss": 1.5380765199661255,
335
+ "eval_runtime": 4.6613,
336
+ "eval_samples_per_second": 171.627,
337
+ "eval_steps_per_second": 21.453,
338
+ "step": 3900
339
+ },
340
+ {
341
+ "epoch": 2.09,
342
+ "learning_rate": 5.8180867746994255e-06,
343
+ "loss": 1.611,
344
+ "step": 4000
345
+ },
346
+ {
347
+ "epoch": 2.09,
348
+ "eval_loss": 1.52095627784729,
349
+ "eval_runtime": 4.7023,
350
+ "eval_samples_per_second": 170.13,
351
+ "eval_steps_per_second": 21.266,
352
+ "step": 4000
353
+ },
354
+ {
355
+ "epoch": 2.14,
356
+ "eval_loss": 1.511513113975525,
357
+ "eval_runtime": 4.6667,
358
+ "eval_samples_per_second": 171.428,
359
+ "eval_steps_per_second": 21.428,
360
+ "step": 4100
361
+ },
362
+ {
363
+ "epoch": 2.2,
364
+ "eval_loss": 1.511332392692566,
365
+ "eval_runtime": 4.6592,
366
+ "eval_samples_per_second": 171.703,
367
+ "eval_steps_per_second": 21.463,
368
+ "step": 4200
369
+ },
370
+ {
371
+ "epoch": 2.25,
372
+ "eval_loss": 1.4714492559432983,
373
+ "eval_runtime": 4.6645,
374
+ "eval_samples_per_second": 171.508,
375
+ "eval_steps_per_second": 21.438,
376
+ "step": 4300
377
+ },
378
+ {
379
+ "epoch": 2.3,
380
+ "eval_loss": 1.5099194049835205,
381
+ "eval_runtime": 4.6633,
382
+ "eval_samples_per_second": 171.551,
383
+ "eval_steps_per_second": 21.444,
384
+ "step": 4400
385
+ },
386
+ {
387
+ "epoch": 2.35,
388
+ "eval_loss": 1.4862964153289795,
389
+ "eval_runtime": 4.6767,
390
+ "eval_samples_per_second": 171.061,
391
+ "eval_steps_per_second": 21.383,
392
+ "step": 4500
393
+ },
394
+ {
395
+ "epoch": 2.4,
396
+ "eval_loss": 1.5304350852966309,
397
+ "eval_runtime": 4.6709,
398
+ "eval_samples_per_second": 171.275,
399
+ "eval_steps_per_second": 21.409,
400
+ "step": 4600
401
+ },
402
+ {
403
+ "epoch": 2.46,
404
+ "eval_loss": 1.4990843534469604,
405
+ "eval_runtime": 4.6619,
406
+ "eval_samples_per_second": 171.605,
407
+ "eval_steps_per_second": 21.451,
408
+ "step": 4700
409
+ },
410
+ {
411
+ "epoch": 2.51,
412
+ "eval_loss": 1.5017355680465698,
413
+ "eval_runtime": 4.6598,
414
+ "eval_samples_per_second": 171.682,
415
+ "eval_steps_per_second": 21.46,
416
+ "step": 4800
417
+ },
418
+ {
419
+ "epoch": 2.56,
420
+ "eval_loss": 1.4134238958358765,
421
+ "eval_runtime": 4.6698,
422
+ "eval_samples_per_second": 171.313,
423
+ "eval_steps_per_second": 21.414,
424
+ "step": 4900
425
+ },
426
+ {
427
+ "epoch": 2.61,
428
+ "learning_rate": 4.7726084683742815e-06,
429
+ "loss": 1.5455,
430
+ "step": 5000
431
+ },
432
+ {
433
+ "epoch": 2.61,
434
+ "eval_loss": 1.4892077445983887,
435
+ "eval_runtime": 4.693,
436
+ "eval_samples_per_second": 170.468,
437
+ "eval_steps_per_second": 21.308,
438
+ "step": 5000
439
+ },
440
+ {
441
+ "epoch": 2.67,
442
+ "eval_loss": 1.4631962776184082,
443
+ "eval_runtime": 4.6718,
444
+ "eval_samples_per_second": 171.242,
445
+ "eval_steps_per_second": 21.405,
446
+ "step": 5100
447
+ },
448
+ {
449
+ "epoch": 2.72,
450
+ "eval_loss": 1.4686871767044067,
451
+ "eval_runtime": 4.6795,
452
+ "eval_samples_per_second": 170.959,
453
+ "eval_steps_per_second": 21.37,
454
+ "step": 5200
455
+ },
456
+ {
457
+ "epoch": 2.77,
458
+ "eval_loss": 1.444468379020691,
459
+ "eval_runtime": 4.6722,
460
+ "eval_samples_per_second": 171.227,
461
+ "eval_steps_per_second": 21.403,
462
+ "step": 5300
463
+ },
464
+ {
465
+ "epoch": 2.82,
466
+ "eval_loss": 1.434273362159729,
467
+ "eval_runtime": 4.6709,
468
+ "eval_samples_per_second": 171.273,
469
+ "eval_steps_per_second": 21.409,
470
+ "step": 5400
471
+ },
472
+ {
473
+ "epoch": 2.88,
474
+ "eval_loss": 1.4033972024917603,
475
+ "eval_runtime": 4.674,
476
+ "eval_samples_per_second": 171.159,
477
+ "eval_steps_per_second": 21.395,
478
+ "step": 5500
479
+ },
480
+ {
481
+ "epoch": 2.93,
482
+ "eval_loss": 1.3725674152374268,
483
+ "eval_runtime": 4.658,
484
+ "eval_samples_per_second": 171.746,
485
+ "eval_steps_per_second": 21.468,
486
+ "step": 5600
487
+ },
488
+ {
489
+ "epoch": 2.98,
490
+ "eval_loss": 1.4471670389175415,
491
+ "eval_runtime": 4.6706,
492
+ "eval_samples_per_second": 171.284,
493
+ "eval_steps_per_second": 21.411,
494
+ "step": 5700
495
+ },
496
+ {
497
+ "epoch": 3.03,
498
+ "eval_loss": 1.3971011638641357,
499
+ "eval_runtime": 4.6665,
500
+ "eval_samples_per_second": 171.433,
501
+ "eval_steps_per_second": 21.429,
502
+ "step": 5800
503
+ },
504
+ {
505
+ "epoch": 3.08,
506
+ "eval_loss": 1.4093689918518066,
507
+ "eval_runtime": 4.6837,
508
+ "eval_samples_per_second": 170.804,
509
+ "eval_steps_per_second": 21.351,
510
+ "step": 5900
511
+ },
512
+ {
513
+ "epoch": 3.14,
514
+ "learning_rate": 3.727130162049138e-06,
515
+ "loss": 1.4815,
516
+ "step": 6000
517
+ },
518
+ {
519
+ "epoch": 3.14,
520
+ "eval_loss": 1.434360384941101,
521
+ "eval_runtime": 4.7117,
522
+ "eval_samples_per_second": 169.79,
523
+ "eval_steps_per_second": 21.224,
524
+ "step": 6000
525
+ },
526
+ {
527
+ "epoch": 3.19,
528
+ "eval_loss": 1.412831425666809,
529
+ "eval_runtime": 4.678,
530
+ "eval_samples_per_second": 171.013,
531
+ "eval_steps_per_second": 21.377,
532
+ "step": 6100
533
+ },
534
+ {
535
+ "epoch": 3.24,
536
+ "eval_loss": 1.4168850183486938,
537
+ "eval_runtime": 4.6653,
538
+ "eval_samples_per_second": 171.478,
539
+ "eval_steps_per_second": 21.435,
540
+ "step": 6200
541
+ },
542
+ {
543
+ "epoch": 3.29,
544
+ "eval_loss": 1.399338960647583,
545
+ "eval_runtime": 4.6686,
546
+ "eval_samples_per_second": 171.359,
547
+ "eval_steps_per_second": 21.42,
548
+ "step": 6300
549
+ },
550
+ {
551
+ "epoch": 3.35,
552
+ "eval_loss": 1.4034981727600098,
553
+ "eval_runtime": 4.6638,
554
+ "eval_samples_per_second": 171.535,
555
+ "eval_steps_per_second": 21.442,
556
+ "step": 6400
557
+ },
558
+ {
559
+ "epoch": 3.4,
560
+ "eval_loss": 1.3951754570007324,
561
+ "eval_runtime": 4.6788,
562
+ "eval_samples_per_second": 170.982,
563
+ "eval_steps_per_second": 21.373,
564
+ "step": 6500
565
+ },
566
+ {
567
+ "epoch": 3.45,
568
+ "eval_loss": 1.3877923488616943,
569
+ "eval_runtime": 4.6855,
570
+ "eval_samples_per_second": 170.739,
571
+ "eval_steps_per_second": 21.342,
572
+ "step": 6600
573
+ },
574
+ {
575
+ "epoch": 3.5,
576
+ "eval_loss": 1.3673046827316284,
577
+ "eval_runtime": 4.6699,
578
+ "eval_samples_per_second": 171.31,
579
+ "eval_steps_per_second": 21.414,
580
+ "step": 6700
581
+ },
582
+ {
583
+ "epoch": 3.55,
584
+ "eval_loss": 1.3622443675994873,
585
+ "eval_runtime": 4.671,
586
+ "eval_samples_per_second": 171.271,
587
+ "eval_steps_per_second": 21.409,
588
+ "step": 6800
589
+ },
590
+ {
591
+ "epoch": 3.61,
592
+ "eval_loss": 1.374872088432312,
593
+ "eval_runtime": 4.6712,
594
+ "eval_samples_per_second": 171.263,
595
+ "eval_steps_per_second": 21.408,
596
+ "step": 6900
597
+ },
598
+ {
599
+ "epoch": 3.66,
600
+ "learning_rate": 2.681651855723994e-06,
601
+ "loss": 1.4492,
602
+ "step": 7000
603
+ },
604
+ {
605
+ "epoch": 3.66,
606
+ "eval_loss": 1.4481711387634277,
607
+ "eval_runtime": 4.6991,
608
+ "eval_samples_per_second": 170.247,
609
+ "eval_steps_per_second": 21.281,
610
+ "step": 7000
611
+ },
612
+ {
613
+ "epoch": 3.71,
614
+ "eval_loss": 1.3453810214996338,
615
+ "eval_runtime": 4.6891,
616
+ "eval_samples_per_second": 170.607,
617
+ "eval_steps_per_second": 21.326,
618
+ "step": 7100
619
+ },
620
+ {
621
+ "epoch": 3.76,
622
+ "eval_loss": 1.3628772497177124,
623
+ "eval_runtime": 4.691,
624
+ "eval_samples_per_second": 170.54,
625
+ "eval_steps_per_second": 21.317,
626
+ "step": 7200
627
+ },
628
+ {
629
+ "epoch": 3.82,
630
+ "eval_loss": 1.4115179777145386,
631
+ "eval_runtime": 4.6842,
632
+ "eval_samples_per_second": 170.787,
633
+ "eval_steps_per_second": 21.348,
634
+ "step": 7300
635
+ },
636
+ {
637
+ "epoch": 3.87,
638
+ "eval_loss": 1.3432800769805908,
639
+ "eval_runtime": 4.69,
640
+ "eval_samples_per_second": 170.576,
641
+ "eval_steps_per_second": 21.322,
642
+ "step": 7400
643
+ },
644
+ {
645
+ "epoch": 3.92,
646
+ "eval_loss": 1.368696928024292,
647
+ "eval_runtime": 4.6923,
648
+ "eval_samples_per_second": 170.493,
649
+ "eval_steps_per_second": 21.312,
650
+ "step": 7500
651
+ },
652
+ {
653
+ "epoch": 3.97,
654
+ "eval_loss": 1.4239104986190796,
655
+ "eval_runtime": 4.6873,
656
+ "eval_samples_per_second": 170.674,
657
+ "eval_steps_per_second": 21.334,
658
+ "step": 7600
659
+ },
660
+ {
661
+ "epoch": 4.03,
662
+ "eval_loss": 1.3071486949920654,
663
+ "eval_runtime": 4.6827,
664
+ "eval_samples_per_second": 170.843,
665
+ "eval_steps_per_second": 21.355,
666
+ "step": 7700
667
+ },
668
+ {
669
+ "epoch": 4.08,
670
+ "eval_loss": 1.353852391242981,
671
+ "eval_runtime": 4.6839,
672
+ "eval_samples_per_second": 170.798,
673
+ "eval_steps_per_second": 21.35,
674
+ "step": 7800
675
+ },
676
+ {
677
+ "epoch": 4.13,
678
+ "eval_loss": 1.3432263135910034,
679
+ "eval_runtime": 4.6946,
680
+ "eval_samples_per_second": 170.409,
681
+ "eval_steps_per_second": 21.301,
682
+ "step": 7900
683
+ },
684
+ {
685
+ "epoch": 4.18,
686
+ "learning_rate": 1.63617354939885e-06,
687
+ "loss": 1.4208,
688
+ "step": 8000
689
+ },
690
+ {
691
+ "epoch": 4.18,
692
+ "eval_loss": 1.3502365350723267,
693
+ "eval_runtime": 4.7172,
694
+ "eval_samples_per_second": 169.592,
695
+ "eval_steps_per_second": 21.199,
696
+ "step": 8000
697
+ },
698
+ {
699
+ "epoch": 4.23,
700
+ "eval_loss": 1.363999605178833,
701
+ "eval_runtime": 4.685,
702
+ "eval_samples_per_second": 170.758,
703
+ "eval_steps_per_second": 21.345,
704
+ "step": 8100
705
+ },
706
+ {
707
+ "epoch": 4.29,
708
+ "eval_loss": 1.382441520690918,
709
+ "eval_runtime": 4.6847,
710
+ "eval_samples_per_second": 170.769,
711
+ "eval_steps_per_second": 21.346,
712
+ "step": 8200
713
+ },
714
+ {
715
+ "epoch": 4.34,
716
+ "eval_loss": 1.3818987607955933,
717
+ "eval_runtime": 4.6986,
718
+ "eval_samples_per_second": 170.265,
719
+ "eval_steps_per_second": 21.283,
720
+ "step": 8300
721
+ },
722
+ {
723
+ "epoch": 4.39,
724
+ "eval_loss": 1.340713620185852,
725
+ "eval_runtime": 4.6878,
726
+ "eval_samples_per_second": 170.655,
727
+ "eval_steps_per_second": 21.332,
728
+ "step": 8400
729
+ },
730
+ {
731
+ "epoch": 4.44,
732
+ "eval_loss": 1.3344806432724,
733
+ "eval_runtime": 4.6958,
734
+ "eval_samples_per_second": 170.364,
735
+ "eval_steps_per_second": 21.295,
736
+ "step": 8500
737
+ },
738
+ {
739
+ "epoch": 4.5,
740
+ "eval_loss": 1.3563097715377808,
741
+ "eval_runtime": 4.6877,
742
+ "eval_samples_per_second": 170.66,
743
+ "eval_steps_per_second": 21.333,
744
+ "step": 8600
745
+ },
746
+ {
747
+ "epoch": 4.55,
748
+ "eval_loss": 1.3303130865097046,
749
+ "eval_runtime": 4.6903,
750
+ "eval_samples_per_second": 170.565,
751
+ "eval_steps_per_second": 21.321,
752
+ "step": 8700
753
+ },
754
+ {
755
+ "epoch": 4.6,
756
+ "eval_loss": 1.3454128503799438,
757
+ "eval_runtime": 4.6828,
758
+ "eval_samples_per_second": 170.838,
759
+ "eval_steps_per_second": 21.355,
760
+ "step": 8800
761
+ },
762
+ {
763
+ "epoch": 4.65,
764
+ "eval_loss": 1.3808575868606567,
765
+ "eval_runtime": 4.6966,
766
+ "eval_samples_per_second": 170.335,
767
+ "eval_steps_per_second": 21.292,
768
+ "step": 8900
769
+ },
770
+ {
771
+ "epoch": 4.7,
772
+ "learning_rate": 5.906952430737063e-07,
773
+ "loss": 1.4013,
774
+ "step": 9000
775
+ },
776
+ {
777
+ "epoch": 4.7,
778
+ "eval_loss": 1.3647897243499756,
779
+ "eval_runtime": 4.7177,
780
+ "eval_samples_per_second": 169.575,
781
+ "eval_steps_per_second": 21.197,
782
+ "step": 9000
783
+ },
784
+ {
785
+ "epoch": 4.76,
786
+ "eval_loss": 1.34979248046875,
787
+ "eval_runtime": 4.6998,
788
+ "eval_samples_per_second": 170.221,
789
+ "eval_steps_per_second": 21.278,
790
+ "step": 9100
791
+ },
792
+ {
793
+ "epoch": 4.81,
794
+ "eval_loss": 1.3509832620620728,
795
+ "eval_runtime": 4.685,
796
+ "eval_samples_per_second": 170.758,
797
+ "eval_steps_per_second": 21.345,
798
+ "step": 9200
799
+ },
800
+ {
801
+ "epoch": 4.86,
802
+ "eval_loss": 1.3402700424194336,
803
+ "eval_runtime": 4.6979,
804
+ "eval_samples_per_second": 170.289,
805
+ "eval_steps_per_second": 21.286,
806
+ "step": 9300
807
+ },
808
+ {
809
+ "epoch": 4.91,
810
+ "eval_loss": 1.2718613147735596,
811
+ "eval_runtime": 4.6876,
812
+ "eval_samples_per_second": 170.662,
813
+ "eval_steps_per_second": 21.333,
814
+ "step": 9400
815
+ },
816
+ {
817
+ "epoch": 4.97,
818
+ "eval_loss": 1.3347008228302002,
819
+ "eval_runtime": 4.6849,
820
+ "eval_samples_per_second": 170.762,
821
+ "eval_steps_per_second": 21.345,
822
+ "step": 9500
823
+ },
824
+ {
825
+ "epoch": 5.0,
826
+ "step": 9565,
827
+ "total_flos": 1.1622564417918384e+16,
828
+ "train_loss": 1.626130136269521,
829
+ "train_runtime": 5849.5407,
830
+ "train_samples_per_second": 13.078,
831
+ "train_steps_per_second": 1.635
832
+ }
833
+ ],
834
+ "max_steps": 9565,
835
+ "num_train_epochs": 5,
836
+ "total_flos": 1.1622564417918384e+16,
837
+ "trial_name": null,
838
+ "trial_params": null
839
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5daead9ef2aaf711ba9c0e816c197e8614513538ba8aa593dda51fdc0cb507
3
+ size 2927
vocab.txt ADDED
The diff for this file is too large to render. See raw diff