danurahul commited on
Commit
4617533
1 Parent(s): d71a7f1

Initial commit

Browse files
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilgpt2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "gradient_checkpointing": false,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 6,
27
+ "n_positions": 1024,
28
+ "resid_pdrop": 0.1,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "task_specific_params": {
35
+ "text-generation": {
36
+ "do_sample": true,
37
+ "max_length": 50
38
+ }
39
+ },
40
+ "transformers_version": "4.5.1",
41
+ "use_cache": true,
42
+ "vocab_size": 50257
43
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:186dc252fe4414ddc2fdcf2aeb4015aec546fbcd40e8d4adfc2105ca69caaae1
3
+ size 655348359
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e50a87396482a6adbb1dffc38f46dfe85a39d39f583a052924f936a16e5d09d
3
+ size 333975623
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62da7b51f6e64a0f055cb2efcaa868bae5f04af58b80a3c13159f7ecd3d815dc
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "distilgpt2"}
trainer_state.json ADDED
@@ -0,0 +1,526 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9716123619074253,
5
+ "global_step": 42500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.03,
12
+ "learning_rate": 4.941733090942992e-05,
13
+ "loss": 3.2035,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.07,
18
+ "learning_rate": 4.8834661818859834e-05,
19
+ "loss": 3.1734,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.1,
24
+ "learning_rate": 4.825199272828975e-05,
25
+ "loss": 3.1439,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.14,
30
+ "learning_rate": 4.766932363771967e-05,
31
+ "loss": 3.1277,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.17,
36
+ "learning_rate": 4.7086654547149584e-05,
37
+ "loss": 3.1302,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.21,
42
+ "learning_rate": 4.65039854565795e-05,
43
+ "loss": 3.1091,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.24,
48
+ "learning_rate": 4.592131636600942e-05,
49
+ "loss": 3.115,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.28,
54
+ "learning_rate": 4.5338647275439334e-05,
55
+ "loss": 3.0718,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.31,
60
+ "learning_rate": 4.4755978184869253e-05,
61
+ "loss": 3.0977,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.35,
66
+ "learning_rate": 4.417330909429917e-05,
67
+ "loss": 3.1092,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.38,
72
+ "learning_rate": 4.3590640003729085e-05,
73
+ "loss": 3.0919,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.42,
78
+ "learning_rate": 4.3007970913159004e-05,
79
+ "loss": 3.0868,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.45,
84
+ "learning_rate": 4.242530182258892e-05,
85
+ "loss": 3.0913,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.49,
90
+ "learning_rate": 4.1842632732018835e-05,
91
+ "loss": 3.0817,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.52,
96
+ "learning_rate": 4.1259963641448754e-05,
97
+ "loss": 3.0835,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.56,
102
+ "learning_rate": 4.0677294550878666e-05,
103
+ "loss": 3.059,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.59,
108
+ "learning_rate": 4.0094625460308585e-05,
109
+ "loss": 3.0757,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.63,
114
+ "learning_rate": 3.95119563697385e-05,
115
+ "loss": 3.0767,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.66,
120
+ "learning_rate": 3.892928727916842e-05,
121
+ "loss": 3.0637,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.7,
126
+ "learning_rate": 3.834661818859833e-05,
127
+ "loss": 3.0504,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.73,
132
+ "learning_rate": 3.776394909802825e-05,
133
+ "loss": 3.0339,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.77,
138
+ "learning_rate": 3.718128000745816e-05,
139
+ "loss": 3.0385,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.8,
144
+ "learning_rate": 3.659861091688808e-05,
145
+ "loss": 3.064,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.84,
150
+ "learning_rate": 3.6015941826318e-05,
151
+ "loss": 3.0685,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.87,
156
+ "learning_rate": 3.543327273574791e-05,
157
+ "loss": 3.0366,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.91,
162
+ "learning_rate": 3.485060364517783e-05,
163
+ "loss": 3.0512,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.94,
168
+ "learning_rate": 3.426793455460775e-05,
169
+ "loss": 3.0179,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.98,
174
+ "learning_rate": 3.368526546403766e-05,
175
+ "loss": 3.0113,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 1.01,
180
+ "learning_rate": 3.310259637346758e-05,
181
+ "loss": 2.9934,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 1.05,
186
+ "learning_rate": 3.25199272828975e-05,
187
+ "loss": 3.0166,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 1.08,
192
+ "learning_rate": 3.193725819232741e-05,
193
+ "loss": 3.0001,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 1.12,
198
+ "learning_rate": 3.135458910175733e-05,
199
+ "loss": 2.9672,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 1.15,
204
+ "learning_rate": 3.077192001118725e-05,
205
+ "loss": 2.9892,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 1.19,
210
+ "learning_rate": 3.018925092061716e-05,
211
+ "loss": 2.9614,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 1.22,
216
+ "learning_rate": 2.960658183004708e-05,
217
+ "loss": 2.9961,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 1.26,
222
+ "learning_rate": 2.9023912739477e-05,
223
+ "loss": 2.9779,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 1.29,
228
+ "learning_rate": 2.8441243648906912e-05,
229
+ "loss": 2.9579,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 1.33,
234
+ "learning_rate": 2.785857455833683e-05,
235
+ "loss": 2.973,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 1.36,
240
+ "learning_rate": 2.727590546776675e-05,
241
+ "loss": 2.9722,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 1.4,
246
+ "learning_rate": 2.6693236377196662e-05,
247
+ "loss": 2.9646,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 1.43,
252
+ "learning_rate": 2.611056728662658e-05,
253
+ "loss": 2.9623,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 1.47,
258
+ "learning_rate": 2.55278981960565e-05,
259
+ "loss": 2.9916,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 1.5,
264
+ "learning_rate": 2.4945229105486416e-05,
265
+ "loss": 2.9656,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 1.54,
270
+ "learning_rate": 2.436256001491633e-05,
271
+ "loss": 2.9928,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 1.57,
276
+ "learning_rate": 2.3779890924346247e-05,
277
+ "loss": 2.9385,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 1.61,
282
+ "learning_rate": 2.3197221833776163e-05,
283
+ "loss": 2.957,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 1.64,
288
+ "learning_rate": 2.261455274320608e-05,
289
+ "loss": 2.9654,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 1.68,
294
+ "learning_rate": 2.2031883652635994e-05,
295
+ "loss": 2.97,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 1.71,
300
+ "learning_rate": 2.144921456206591e-05,
301
+ "loss": 2.9741,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 1.75,
306
+ "learning_rate": 2.086654547149583e-05,
307
+ "loss": 2.9547,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 1.78,
312
+ "learning_rate": 2.0283876380925745e-05,
313
+ "loss": 2.9451,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 1.82,
318
+ "learning_rate": 1.970120729035566e-05,
319
+ "loss": 2.9596,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 1.85,
324
+ "learning_rate": 1.911853819978558e-05,
325
+ "loss": 2.9608,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 1.89,
330
+ "learning_rate": 1.8535869109215495e-05,
331
+ "loss": 2.9353,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 1.92,
336
+ "learning_rate": 1.795320001864541e-05,
337
+ "loss": 2.9597,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 1.96,
342
+ "learning_rate": 1.737053092807533e-05,
343
+ "loss": 2.9766,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 1.99,
348
+ "learning_rate": 1.6787861837505245e-05,
349
+ "loss": 2.9663,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 2.03,
354
+ "learning_rate": 1.620519274693516e-05,
355
+ "loss": 2.9407,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 2.06,
360
+ "learning_rate": 1.562252365636508e-05,
361
+ "loss": 2.9297,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 2.1,
366
+ "learning_rate": 1.5039854565794994e-05,
367
+ "loss": 2.8912,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 2.13,
372
+ "learning_rate": 1.445718547522491e-05,
373
+ "loss": 2.9339,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 2.17,
378
+ "learning_rate": 1.3874516384654828e-05,
379
+ "loss": 2.9428,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 2.2,
384
+ "learning_rate": 1.3291847294084744e-05,
385
+ "loss": 2.9401,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 2.24,
390
+ "learning_rate": 1.270917820351466e-05,
391
+ "loss": 2.9332,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 2.27,
396
+ "learning_rate": 1.2126509112944577e-05,
397
+ "loss": 2.9101,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 2.31,
402
+ "learning_rate": 1.1543840022374494e-05,
403
+ "loss": 2.9166,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 2.34,
408
+ "learning_rate": 1.096117093180441e-05,
409
+ "loss": 2.9384,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 2.38,
414
+ "learning_rate": 1.0378501841234327e-05,
415
+ "loss": 2.9133,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 2.41,
420
+ "learning_rate": 9.795832750664243e-06,
421
+ "loss": 2.8853,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 2.45,
426
+ "learning_rate": 9.213163660094159e-06,
427
+ "loss": 2.9052,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 2.48,
432
+ "learning_rate": 8.630494569524076e-06,
433
+ "loss": 2.9147,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 2.52,
438
+ "learning_rate": 8.047825478953992e-06,
439
+ "loss": 2.9421,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 2.55,
444
+ "learning_rate": 7.465156388383909e-06,
445
+ "loss": 2.9287,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 2.59,
450
+ "learning_rate": 6.8824872978138264e-06,
451
+ "loss": 2.9044,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 2.62,
456
+ "learning_rate": 6.299818207243742e-06,
457
+ "loss": 2.9015,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 2.66,
462
+ "learning_rate": 5.7171491166736594e-06,
463
+ "loss": 2.9207,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 2.69,
468
+ "learning_rate": 5.134480026103575e-06,
469
+ "loss": 2.9307,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 2.73,
474
+ "learning_rate": 4.5518109355334916e-06,
475
+ "loss": 2.9315,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 2.76,
480
+ "learning_rate": 3.969141844963409e-06,
481
+ "loss": 2.9047,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 2.8,
486
+ "learning_rate": 3.386472754393325e-06,
487
+ "loss": 2.9263,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 2.83,
492
+ "learning_rate": 2.8038036638232415e-06,
493
+ "loss": 2.9154,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 2.87,
498
+ "learning_rate": 2.2211345732531584e-06,
499
+ "loss": 2.9042,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 2.9,
504
+ "learning_rate": 1.6384654826830745e-06,
505
+ "loss": 2.886,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 2.94,
510
+ "learning_rate": 1.0557963921129912e-06,
511
+ "loss": 2.9167,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 2.97,
516
+ "learning_rate": 4.731273015429078e-07,
517
+ "loss": 2.8958,
518
+ "step": 42500
519
+ }
520
+ ],
521
+ "max_steps": 42906,
522
+ "num_train_epochs": 3,
523
+ "total_flos": 4.277802369024e+16,
524
+ "trial_name": null,
525
+ "trial_params": null
526
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b80cc04d242bd16bb6b8bcc6a87bc41d998f13105373c518667c57faf1624850
3
+ size 2351
vocab.json ADDED
The diff for this file is too large to render. See raw diff