Davlan commited on
Commit
6d2913a
1 Parent(s): 324c790

Upload 11 files

Browse files
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.7415129030139864,
4
+ "eval_loss": 1.3148167133331299,
5
+ "eval_runtime": 89.1848,
6
+ "eval_samples": 13134,
7
+ "eval_samples_per_second": 147.267,
8
+ "eval_steps_per_second": 4.608,
9
+ "perplexity": 3.7240683506190324,
10
+ "train_loss": 1.5609709015213173,
11
+ "train_runtime": 628686.7825,
12
+ "train_samples": 12549804,
13
+ "train_samples_per_second": 59.886,
14
+ "train_steps_per_second": 0.078
15
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-r-base-script_expand",
3
+ "architectures": [
4
+ "XLMRobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.34.1",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 270002
28
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.7415129030139864,
4
+ "eval_loss": 1.3148167133331299,
5
+ "eval_runtime": 89.1848,
6
+ "eval_samples": 13134,
7
+ "eval_samples_per_second": 147.267,
8
+ "eval_steps_per_second": 4.608,
9
+ "perplexity": 3.7240683506190324
10
+ }
events.out.tfevents.1703577635.strangepork-205-3.3267823.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d292f34948233a6df7787529e38d04cdc3f38537b2ffdb2b1a270c8f966ea53e
3
+ size 4261
events.out.tfevents.1703578032.strangepork-205-3.3271661.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec93f5daa73bf81090c19b39943a8d8c83a8e114e3d888ae09e379351cb8781
3
+ size 4261
events.out.tfevents.1703579137.strangepork-205-3.3273330.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31fc15a7581383905fe053c9e456b631604dc58c7b46ddfb42316e900b21767a
3
+ size 20205
events.out.tfevents.1704207919.strangepork-205-3.3273330.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c6cc1774a11ebf9ff3de286df3470e07dda8c66448f53a174bbde093d5f5ec
3
+ size 417
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "2": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "3": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "250001": {
28
+ "content": "<pad>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "270001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
trainer_state.json ADDED
@@ -0,0 +1,616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 49023,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 5e-05,
14
+ "loss": 4.8278,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 5e-05,
20
+ "loss": 3.5561,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 5e-05,
26
+ "loss": 3.0434,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.12,
31
+ "learning_rate": 5e-05,
32
+ "loss": 2.7336,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.15,
37
+ "learning_rate": 5e-05,
38
+ "loss": 2.5149,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.18,
43
+ "learning_rate": 5e-05,
44
+ "loss": 2.3549,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 5e-05,
50
+ "loss": 2.2287,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.24,
55
+ "learning_rate": 5e-05,
56
+ "loss": 2.1257,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.28,
61
+ "learning_rate": 5e-05,
62
+ "loss": 2.0463,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.31,
67
+ "learning_rate": 5e-05,
68
+ "loss": 1.9848,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.34,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.9228,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.37,
79
+ "learning_rate": 5e-05,
80
+ "loss": 1.8806,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.4,
85
+ "learning_rate": 5e-05,
86
+ "loss": 1.8365,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.43,
91
+ "learning_rate": 5e-05,
92
+ "loss": 1.801,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.46,
97
+ "learning_rate": 5e-05,
98
+ "loss": 1.7703,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.49,
103
+ "learning_rate": 5e-05,
104
+ "loss": 1.7434,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.52,
109
+ "learning_rate": 5e-05,
110
+ "loss": 1.7187,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.55,
115
+ "learning_rate": 5e-05,
116
+ "loss": 1.697,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.58,
121
+ "learning_rate": 5e-05,
122
+ "loss": 1.673,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.61,
127
+ "learning_rate": 5e-05,
128
+ "loss": 1.6555,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.64,
133
+ "learning_rate": 5e-05,
134
+ "loss": 1.6399,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.67,
139
+ "learning_rate": 5e-05,
140
+ "loss": 1.6233,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 0.7,
145
+ "learning_rate": 5e-05,
146
+ "loss": 1.6087,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 0.73,
151
+ "learning_rate": 5e-05,
152
+ "loss": 1.597,
153
+ "step": 12000
154
+ },
155
+ {
156
+ "epoch": 0.76,
157
+ "learning_rate": 5e-05,
158
+ "loss": 1.5816,
159
+ "step": 12500
160
+ },
161
+ {
162
+ "epoch": 0.8,
163
+ "learning_rate": 5e-05,
164
+ "loss": 1.5684,
165
+ "step": 13000
166
+ },
167
+ {
168
+ "epoch": 0.83,
169
+ "learning_rate": 5e-05,
170
+ "loss": 1.5602,
171
+ "step": 13500
172
+ },
173
+ {
174
+ "epoch": 0.86,
175
+ "learning_rate": 5e-05,
176
+ "loss": 1.5453,
177
+ "step": 14000
178
+ },
179
+ {
180
+ "epoch": 0.89,
181
+ "learning_rate": 5e-05,
182
+ "loss": 1.5366,
183
+ "step": 14500
184
+ },
185
+ {
186
+ "epoch": 0.92,
187
+ "learning_rate": 5e-05,
188
+ "loss": 1.5276,
189
+ "step": 15000
190
+ },
191
+ {
192
+ "epoch": 0.95,
193
+ "learning_rate": 5e-05,
194
+ "loss": 1.5156,
195
+ "step": 15500
196
+ },
197
+ {
198
+ "epoch": 0.98,
199
+ "learning_rate": 5e-05,
200
+ "loss": 1.5075,
201
+ "step": 16000
202
+ },
203
+ {
204
+ "epoch": 1.01,
205
+ "learning_rate": 5e-05,
206
+ "loss": 1.4988,
207
+ "step": 16500
208
+ },
209
+ {
210
+ "epoch": 1.04,
211
+ "learning_rate": 5e-05,
212
+ "loss": 1.4935,
213
+ "step": 17000
214
+ },
215
+ {
216
+ "epoch": 1.07,
217
+ "learning_rate": 5e-05,
218
+ "loss": 1.4818,
219
+ "step": 17500
220
+ },
221
+ {
222
+ "epoch": 1.1,
223
+ "learning_rate": 5e-05,
224
+ "loss": 1.4733,
225
+ "step": 18000
226
+ },
227
+ {
228
+ "epoch": 1.13,
229
+ "learning_rate": 5e-05,
230
+ "loss": 1.4661,
231
+ "step": 18500
232
+ },
233
+ {
234
+ "epoch": 1.16,
235
+ "learning_rate": 5e-05,
236
+ "loss": 1.4603,
237
+ "step": 19000
238
+ },
239
+ {
240
+ "epoch": 1.19,
241
+ "learning_rate": 5e-05,
242
+ "loss": 1.4554,
243
+ "step": 19500
244
+ },
245
+ {
246
+ "epoch": 1.22,
247
+ "learning_rate": 5e-05,
248
+ "loss": 1.449,
249
+ "step": 20000
250
+ },
251
+ {
252
+ "epoch": 1.25,
253
+ "learning_rate": 5e-05,
254
+ "loss": 1.4409,
255
+ "step": 20500
256
+ },
257
+ {
258
+ "epoch": 1.29,
259
+ "learning_rate": 5e-05,
260
+ "loss": 1.4382,
261
+ "step": 21000
262
+ },
263
+ {
264
+ "epoch": 1.32,
265
+ "learning_rate": 5e-05,
266
+ "loss": 1.4298,
267
+ "step": 21500
268
+ },
269
+ {
270
+ "epoch": 1.35,
271
+ "learning_rate": 5e-05,
272
+ "loss": 1.4251,
273
+ "step": 22000
274
+ },
275
+ {
276
+ "epoch": 1.38,
277
+ "learning_rate": 5e-05,
278
+ "loss": 1.4225,
279
+ "step": 22500
280
+ },
281
+ {
282
+ "epoch": 1.41,
283
+ "learning_rate": 5e-05,
284
+ "loss": 1.4122,
285
+ "step": 23000
286
+ },
287
+ {
288
+ "epoch": 1.44,
289
+ "learning_rate": 5e-05,
290
+ "loss": 1.4089,
291
+ "step": 23500
292
+ },
293
+ {
294
+ "epoch": 1.47,
295
+ "learning_rate": 5e-05,
296
+ "loss": 1.4041,
297
+ "step": 24000
298
+ },
299
+ {
300
+ "epoch": 1.5,
301
+ "learning_rate": 5e-05,
302
+ "loss": 1.3998,
303
+ "step": 24500
304
+ },
305
+ {
306
+ "epoch": 1.53,
307
+ "learning_rate": 5e-05,
308
+ "loss": 1.3933,
309
+ "step": 25000
310
+ },
311
+ {
312
+ "epoch": 1.56,
313
+ "learning_rate": 5e-05,
314
+ "loss": 1.3897,
315
+ "step": 25500
316
+ },
317
+ {
318
+ "epoch": 1.59,
319
+ "learning_rate": 5e-05,
320
+ "loss": 1.3874,
321
+ "step": 26000
322
+ },
323
+ {
324
+ "epoch": 1.62,
325
+ "learning_rate": 5e-05,
326
+ "loss": 1.3812,
327
+ "step": 26500
328
+ },
329
+ {
330
+ "epoch": 1.65,
331
+ "learning_rate": 5e-05,
332
+ "loss": 1.3745,
333
+ "step": 27000
334
+ },
335
+ {
336
+ "epoch": 1.68,
337
+ "learning_rate": 5e-05,
338
+ "loss": 1.3728,
339
+ "step": 27500
340
+ },
341
+ {
342
+ "epoch": 1.71,
343
+ "learning_rate": 5e-05,
344
+ "loss": 1.3706,
345
+ "step": 28000
346
+ },
347
+ {
348
+ "epoch": 1.74,
349
+ "learning_rate": 5e-05,
350
+ "loss": 1.3673,
351
+ "step": 28500
352
+ },
353
+ {
354
+ "epoch": 1.77,
355
+ "learning_rate": 5e-05,
356
+ "loss": 1.3605,
357
+ "step": 29000
358
+ },
359
+ {
360
+ "epoch": 1.81,
361
+ "learning_rate": 5e-05,
362
+ "loss": 1.3574,
363
+ "step": 29500
364
+ },
365
+ {
366
+ "epoch": 1.84,
367
+ "learning_rate": 5e-05,
368
+ "loss": 1.3514,
369
+ "step": 30000
370
+ },
371
+ {
372
+ "epoch": 1.87,
373
+ "learning_rate": 5e-05,
374
+ "loss": 1.351,
375
+ "step": 30500
376
+ },
377
+ {
378
+ "epoch": 1.9,
379
+ "learning_rate": 5e-05,
380
+ "loss": 1.3457,
381
+ "step": 31000
382
+ },
383
+ {
384
+ "epoch": 1.93,
385
+ "learning_rate": 5e-05,
386
+ "loss": 1.3451,
387
+ "step": 31500
388
+ },
389
+ {
390
+ "epoch": 1.96,
391
+ "learning_rate": 5e-05,
392
+ "loss": 1.3403,
393
+ "step": 32000
394
+ },
395
+ {
396
+ "epoch": 1.99,
397
+ "learning_rate": 5e-05,
398
+ "loss": 1.3389,
399
+ "step": 32500
400
+ },
401
+ {
402
+ "epoch": 2.02,
403
+ "learning_rate": 5e-05,
404
+ "loss": 1.3346,
405
+ "step": 33000
406
+ },
407
+ {
408
+ "epoch": 2.05,
409
+ "learning_rate": 5e-05,
410
+ "loss": 1.3313,
411
+ "step": 33500
412
+ },
413
+ {
414
+ "epoch": 2.08,
415
+ "learning_rate": 5e-05,
416
+ "loss": 1.3278,
417
+ "step": 34000
418
+ },
419
+ {
420
+ "epoch": 2.11,
421
+ "learning_rate": 5e-05,
422
+ "loss": 1.3249,
423
+ "step": 34500
424
+ },
425
+ {
426
+ "epoch": 2.14,
427
+ "learning_rate": 5e-05,
428
+ "loss": 1.3212,
429
+ "step": 35000
430
+ },
431
+ {
432
+ "epoch": 2.17,
433
+ "learning_rate": 5e-05,
434
+ "loss": 1.3191,
435
+ "step": 35500
436
+ },
437
+ {
438
+ "epoch": 2.2,
439
+ "learning_rate": 5e-05,
440
+ "loss": 1.3158,
441
+ "step": 36000
442
+ },
443
+ {
444
+ "epoch": 2.23,
445
+ "learning_rate": 5e-05,
446
+ "loss": 1.3135,
447
+ "step": 36500
448
+ },
449
+ {
450
+ "epoch": 2.26,
451
+ "learning_rate": 5e-05,
452
+ "loss": 1.3086,
453
+ "step": 37000
454
+ },
455
+ {
456
+ "epoch": 2.29,
457
+ "learning_rate": 5e-05,
458
+ "loss": 1.3077,
459
+ "step": 37500
460
+ },
461
+ {
462
+ "epoch": 2.33,
463
+ "learning_rate": 5e-05,
464
+ "loss": 1.3045,
465
+ "step": 38000
466
+ },
467
+ {
468
+ "epoch": 2.36,
469
+ "learning_rate": 5e-05,
470
+ "loss": 1.3013,
471
+ "step": 38500
472
+ },
473
+ {
474
+ "epoch": 2.39,
475
+ "learning_rate": 5e-05,
476
+ "loss": 1.3017,
477
+ "step": 39000
478
+ },
479
+ {
480
+ "epoch": 2.42,
481
+ "learning_rate": 5e-05,
482
+ "loss": 1.2989,
483
+ "step": 39500
484
+ },
485
+ {
486
+ "epoch": 2.45,
487
+ "learning_rate": 5e-05,
488
+ "loss": 1.2963,
489
+ "step": 40000
490
+ },
491
+ {
492
+ "epoch": 2.48,
493
+ "learning_rate": 5e-05,
494
+ "loss": 1.2916,
495
+ "step": 40500
496
+ },
497
+ {
498
+ "epoch": 2.51,
499
+ "learning_rate": 5e-05,
500
+ "loss": 1.2935,
501
+ "step": 41000
502
+ },
503
+ {
504
+ "epoch": 2.54,
505
+ "learning_rate": 5e-05,
506
+ "loss": 1.2922,
507
+ "step": 41500
508
+ },
509
+ {
510
+ "epoch": 2.57,
511
+ "learning_rate": 5e-05,
512
+ "loss": 1.2867,
513
+ "step": 42000
514
+ },
515
+ {
516
+ "epoch": 2.6,
517
+ "learning_rate": 5e-05,
518
+ "loss": 1.2847,
519
+ "step": 42500
520
+ },
521
+ {
522
+ "epoch": 2.63,
523
+ "learning_rate": 5e-05,
524
+ "loss": 1.2831,
525
+ "step": 43000
526
+ },
527
+ {
528
+ "epoch": 2.66,
529
+ "learning_rate": 5e-05,
530
+ "loss": 1.2802,
531
+ "step": 43500
532
+ },
533
+ {
534
+ "epoch": 2.69,
535
+ "learning_rate": 5e-05,
536
+ "loss": 1.2784,
537
+ "step": 44000
538
+ },
539
+ {
540
+ "epoch": 2.72,
541
+ "learning_rate": 5e-05,
542
+ "loss": 1.2748,
543
+ "step": 44500
544
+ },
545
+ {
546
+ "epoch": 2.75,
547
+ "learning_rate": 5e-05,
548
+ "loss": 1.2779,
549
+ "step": 45000
550
+ },
551
+ {
552
+ "epoch": 2.78,
553
+ "learning_rate": 5e-05,
554
+ "loss": 1.2712,
555
+ "step": 45500
556
+ },
557
+ {
558
+ "epoch": 2.82,
559
+ "learning_rate": 5e-05,
560
+ "loss": 1.2695,
561
+ "step": 46000
562
+ },
563
+ {
564
+ "epoch": 2.85,
565
+ "learning_rate": 5e-05,
566
+ "loss": 1.2677,
567
+ "step": 46500
568
+ },
569
+ {
570
+ "epoch": 2.88,
571
+ "learning_rate": 5e-05,
572
+ "loss": 1.2682,
573
+ "step": 47000
574
+ },
575
+ {
576
+ "epoch": 2.91,
577
+ "learning_rate": 5e-05,
578
+ "loss": 1.2651,
579
+ "step": 47500
580
+ },
581
+ {
582
+ "epoch": 2.94,
583
+ "learning_rate": 5e-05,
584
+ "loss": 1.2635,
585
+ "step": 48000
586
+ },
587
+ {
588
+ "epoch": 2.97,
589
+ "learning_rate": 5e-05,
590
+ "loss": 1.2626,
591
+ "step": 48500
592
+ },
593
+ {
594
+ "epoch": 3.0,
595
+ "learning_rate": 5e-05,
596
+ "loss": 1.2583,
597
+ "step": 49000
598
+ },
599
+ {
600
+ "epoch": 3.0,
601
+ "step": 49023,
602
+ "total_flos": 9.937271302396051e+18,
603
+ "train_loss": 1.5609709015213173,
604
+ "train_runtime": 628686.7825,
605
+ "train_samples_per_second": 59.886,
606
+ "train_steps_per_second": 0.078
607
+ }
608
+ ],
609
+ "logging_steps": 500,
610
+ "max_steps": 49023,
611
+ "num_train_epochs": 3,
612
+ "save_steps": 10000,
613
+ "total_flos": 9.937271302396051e+18,
614
+ "trial_name": null,
615
+ "trial_params": null
616
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b297164457bc4c126ab2fa2dd622c44113448fff3b9049f5b117f187319c3e9
3
+ size 6072