AleBurzio commited on
Commit
84b3093
1 Parent(s): e1ac3d3

distilgpt2-jje

Browse files
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 1024,
22
+ "n_embd": 768,
23
+ "n_head": 12,
24
+ "n_inner": null,
25
+ "n_layer": 6,
26
+ "n_positions": 1024,
27
+ "reorder_and_upcast_attn": false,
28
+ "resid_pdrop": 0.1,
29
+ "scale_attn_by_inverse_layer_idx": false,
30
+ "scale_attn_weights": true,
31
+ "summary_activation": null,
32
+ "summary_first_dropout": 0.1,
33
+ "summary_proj_to_labels": true,
34
+ "summary_type": "cls_index",
35
+ "summary_use_proj": true,
36
+ "task_specific_params": {
37
+ "text-generation": {
38
+ "do_sample": true,
39
+ "max_length": 50
40
+ }
41
+ },
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.25.0.dev0",
44
+ "use_cache": true,
45
+ "vocab_size": 50257
46
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "distilgpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 2.3804299571036704,
4
+ "train_runtime": 13242.0355,
5
+ "train_samples": 177922,
6
+ "train_samples_per_second": 26.872,
7
+ "train_steps_per_second": 2.687
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,451 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 35586,
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": 4.9297476535716295e-05,
13
+ "loss": 2.948,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.06,
18
+ "learning_rate": 4.859495307143259e-05,
19
+ "loss": 2.7396,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.08,
24
+ "learning_rate": 4.789242960714888e-05,
25
+ "loss": 2.6771,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.11,
30
+ "learning_rate": 4.7189906142865175e-05,
31
+ "loss": 2.619,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.14,
36
+ "learning_rate": 4.648738267858147e-05,
37
+ "loss": 2.5869,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.17,
42
+ "learning_rate": 4.578485921429776e-05,
43
+ "loss": 2.5459,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.2,
48
+ "learning_rate": 4.5082335750014054e-05,
49
+ "loss": 2.5282,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.22,
54
+ "learning_rate": 4.437981228573034e-05,
55
+ "loss": 2.5131,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.25,
60
+ "learning_rate": 4.367728882144664e-05,
61
+ "loss": 2.5023,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.28,
66
+ "learning_rate": 4.297476535716293e-05,
67
+ "loss": 2.4828,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.31,
72
+ "learning_rate": 4.227224189287922e-05,
73
+ "loss": 2.4753,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.34,
78
+ "learning_rate": 4.156971842859552e-05,
79
+ "loss": 2.4594,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.37,
84
+ "learning_rate": 4.086719496431181e-05,
85
+ "loss": 2.4583,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.39,
90
+ "learning_rate": 4.01646715000281e-05,
91
+ "loss": 2.4519,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.42,
96
+ "learning_rate": 3.94621480357444e-05,
97
+ "loss": 2.4164,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.45,
102
+ "learning_rate": 3.875962457146069e-05,
103
+ "loss": 2.4297,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.48,
108
+ "learning_rate": 3.805710110717698e-05,
109
+ "loss": 2.4081,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.51,
114
+ "learning_rate": 3.735457764289327e-05,
115
+ "loss": 2.4227,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.53,
120
+ "learning_rate": 3.665205417860957e-05,
121
+ "loss": 2.4102,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.56,
126
+ "learning_rate": 3.594953071432586e-05,
127
+ "loss": 2.4211,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.59,
132
+ "learning_rate": 3.524700725004215e-05,
133
+ "loss": 2.3949,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.62,
138
+ "learning_rate": 3.454448378575845e-05,
139
+ "loss": 2.3758,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.65,
144
+ "learning_rate": 3.384196032147474e-05,
145
+ "loss": 2.3789,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.67,
150
+ "learning_rate": 3.313943685719103e-05,
151
+ "loss": 2.3722,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.7,
156
+ "learning_rate": 3.243691339290733e-05,
157
+ "loss": 2.366,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.73,
162
+ "learning_rate": 3.173438992862362e-05,
163
+ "loss": 2.3766,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.76,
168
+ "learning_rate": 3.103186646433991e-05,
169
+ "loss": 2.3588,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.79,
174
+ "learning_rate": 3.0329343000056204e-05,
175
+ "loss": 2.3629,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.81,
180
+ "learning_rate": 2.9626819535772498e-05,
181
+ "loss": 2.3556,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.84,
186
+ "learning_rate": 2.8924296071488787e-05,
187
+ "loss": 2.3642,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.87,
192
+ "learning_rate": 2.8221772607205084e-05,
193
+ "loss": 2.3566,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.9,
198
+ "learning_rate": 2.7519249142921377e-05,
199
+ "loss": 2.3593,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.93,
204
+ "learning_rate": 2.6816725678637666e-05,
205
+ "loss": 2.3513,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.96,
210
+ "learning_rate": 2.6114202214353963e-05,
211
+ "loss": 2.3473,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.98,
216
+ "learning_rate": 2.5411678750070256e-05,
217
+ "loss": 2.3507,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 1.01,
222
+ "learning_rate": 2.470915528578655e-05,
223
+ "loss": 2.3396,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 1.04,
228
+ "learning_rate": 2.400663182150284e-05,
229
+ "loss": 2.3263,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 1.07,
234
+ "learning_rate": 2.330410835721913e-05,
235
+ "loss": 2.3359,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 1.1,
240
+ "learning_rate": 2.2601584892935425e-05,
241
+ "loss": 2.3396,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 1.12,
246
+ "learning_rate": 2.1899061428651718e-05,
247
+ "loss": 2.3202,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 1.15,
252
+ "learning_rate": 2.119653796436801e-05,
253
+ "loss": 2.3456,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 1.18,
258
+ "learning_rate": 2.0494014500084304e-05,
259
+ "loss": 2.316,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 1.21,
264
+ "learning_rate": 1.9791491035800597e-05,
265
+ "loss": 2.3161,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 1.24,
270
+ "learning_rate": 1.908896757151689e-05,
271
+ "loss": 2.3293,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 1.26,
276
+ "learning_rate": 1.8386444107233183e-05,
277
+ "loss": 2.3165,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 1.29,
282
+ "learning_rate": 1.7683920642949476e-05,
283
+ "loss": 2.3146,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 1.32,
288
+ "learning_rate": 1.6981397178665766e-05,
289
+ "loss": 2.298,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 1.35,
294
+ "learning_rate": 1.6278873714382062e-05,
295
+ "loss": 2.3104,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 1.38,
300
+ "learning_rate": 1.5576350250098355e-05,
301
+ "loss": 2.3063,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 1.41,
306
+ "learning_rate": 1.4873826785814647e-05,
307
+ "loss": 2.3095,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 1.43,
312
+ "learning_rate": 1.4171303321530941e-05,
313
+ "loss": 2.3047,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 1.46,
318
+ "learning_rate": 1.3468779857247233e-05,
319
+ "loss": 2.2978,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 1.49,
324
+ "learning_rate": 1.2766256392963524e-05,
325
+ "loss": 2.3043,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 1.52,
330
+ "learning_rate": 1.2063732928679819e-05,
331
+ "loss": 2.2825,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 1.55,
336
+ "learning_rate": 1.136120946439611e-05,
337
+ "loss": 2.3048,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 1.57,
342
+ "learning_rate": 1.0658686000112405e-05,
343
+ "loss": 2.3073,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 1.6,
348
+ "learning_rate": 9.956162535828698e-06,
349
+ "loss": 2.3025,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 1.63,
354
+ "learning_rate": 9.25363907154499e-06,
355
+ "loss": 2.2957,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 1.66,
360
+ "learning_rate": 8.551115607261282e-06,
361
+ "loss": 2.3087,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 1.69,
366
+ "learning_rate": 7.848592142977575e-06,
367
+ "loss": 2.3039,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 1.71,
372
+ "learning_rate": 7.146068678693869e-06,
373
+ "loss": 2.2855,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 1.74,
378
+ "learning_rate": 6.4435452144101614e-06,
379
+ "loss": 2.2819,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 1.77,
384
+ "learning_rate": 5.7410217501264545e-06,
385
+ "loss": 2.3046,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 1.8,
390
+ "learning_rate": 5.0384982858427475e-06,
391
+ "loss": 2.2897,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 1.83,
396
+ "learning_rate": 4.335974821559041e-06,
397
+ "loss": 2.2965,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 1.85,
402
+ "learning_rate": 3.6334513572753332e-06,
403
+ "loss": 2.3033,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 1.88,
408
+ "learning_rate": 2.9309278929916263e-06,
409
+ "loss": 2.2887,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 1.91,
414
+ "learning_rate": 2.228404428707919e-06,
415
+ "loss": 2.2937,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 1.94,
420
+ "learning_rate": 1.525880964424212e-06,
421
+ "loss": 2.2957,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 1.97,
426
+ "learning_rate": 8.233575001405047e-07,
427
+ "loss": 2.2956,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 2.0,
432
+ "learning_rate": 1.2083403585679763e-07,
433
+ "loss": 2.2898,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 2.0,
438
+ "step": 35586,
439
+ "total_flos": 9.298088091765965e+16,
440
+ "train_loss": 2.3804299571036704,
441
+ "train_runtime": 13242.0355,
442
+ "train_samples_per_second": 26.872,
443
+ "train_steps_per_second": 2.687
444
+ }
445
+ ],
446
+ "max_steps": 35586,
447
+ "num_train_epochs": 2,
448
+ "total_flos": 9.298088091765965e+16,
449
+ "trial_name": null,
450
+ "trial_params": null
451
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caa8718baa7cde33929d440391be0403e5ec624a4a5ff7d957eb032b5f1c6c16
3
+ size 3387
vocab.json ADDED
The diff for this file is too large to render. See raw diff