LAYEK-143 commited on
Commit
e74b6a4
·
verified ·
1 Parent(s): 9190f77

Initial model upload

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
checkpoint-14000/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.44.2",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
checkpoint-14000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.44.2"
6
+ }
checkpoint-14000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f9d34122006d821cd7b01c4670f681777354b77450841a0e815b3b49099e966
3
+ size 497777280
checkpoint-14000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519d48576b6a199b9cb88ab1a6b032302f699b7aab7a5da7197a2aa1d3a0b425
3
+ size 995648442
checkpoint-14000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84509ef6c8bbcaf6b836f69cb07cbda699e21f9d997b5af089aa00fa31ac857f
3
+ size 14244
checkpoint-14000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6beb4526469c4e96e5cfe4671c37d14f020bb50a22c02403c839b6422b609fd6
3
+ size 1064
checkpoint-14000/trainer_state.json ADDED
@@ -0,0 +1,523 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.976823304273868,
5
+ "eval_steps": 500,
6
+ "global_step": 14000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0425260472039124,
13
+ "grad_norm": 4.5295610427856445,
14
+ "learning_rate": 4.929123254660146e-05,
15
+ "loss": 3.196,
16
+ "step": 200
17
+ },
18
+ {
19
+ "epoch": 0.0850520944078248,
20
+ "grad_norm": 3.153637170791626,
21
+ "learning_rate": 4.858246509320292e-05,
22
+ "loss": 2.0357,
23
+ "step": 400
24
+ },
25
+ {
26
+ "epoch": 0.1275781416117372,
27
+ "grad_norm": 2.833491802215576,
28
+ "learning_rate": 4.7873697639804386e-05,
29
+ "loss": 1.9407,
30
+ "step": 600
31
+ },
32
+ {
33
+ "epoch": 0.1701041888156496,
34
+ "grad_norm": 3.3437952995300293,
35
+ "learning_rate": 4.7164930186405845e-05,
36
+ "loss": 1.8486,
37
+ "step": 800
38
+ },
39
+ {
40
+ "epoch": 0.212630236019562,
41
+ "grad_norm": 2.2692761421203613,
42
+ "learning_rate": 4.64561627330073e-05,
43
+ "loss": 1.8338,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 0.2551562832234744,
48
+ "grad_norm": 9.267280578613281,
49
+ "learning_rate": 4.574739527960876e-05,
50
+ "loss": 1.8259,
51
+ "step": 1200
52
+ },
53
+ {
54
+ "epoch": 0.2976823304273868,
55
+ "grad_norm": 2.5437700748443604,
56
+ "learning_rate": 4.503862782621022e-05,
57
+ "loss": 1.7474,
58
+ "step": 1400
59
+ },
60
+ {
61
+ "epoch": 0.3402083776312992,
62
+ "grad_norm": 3.454941511154175,
63
+ "learning_rate": 4.432986037281168e-05,
64
+ "loss": 1.7185,
65
+ "step": 1600
66
+ },
67
+ {
68
+ "epoch": 0.3827344248352116,
69
+ "grad_norm": 2.709567070007324,
70
+ "learning_rate": 4.3621092919413145e-05,
71
+ "loss": 1.7468,
72
+ "step": 1800
73
+ },
74
+ {
75
+ "epoch": 0.425260472039124,
76
+ "grad_norm": 2.4916956424713135,
77
+ "learning_rate": 4.2912325466014604e-05,
78
+ "loss": 1.7277,
79
+ "step": 2000
80
+ },
81
+ {
82
+ "epoch": 0.4677865192430364,
83
+ "grad_norm": 2.3599932193756104,
84
+ "learning_rate": 4.220355801261606e-05,
85
+ "loss": 1.6742,
86
+ "step": 2200
87
+ },
88
+ {
89
+ "epoch": 0.5103125664469488,
90
+ "grad_norm": 2.518554449081421,
91
+ "learning_rate": 4.149479055921752e-05,
92
+ "loss": 1.6232,
93
+ "step": 2400
94
+ },
95
+ {
96
+ "epoch": 0.5528386136508612,
97
+ "grad_norm": 2.202854633331299,
98
+ "learning_rate": 4.078602310581898e-05,
99
+ "loss": 1.6431,
100
+ "step": 2600
101
+ },
102
+ {
103
+ "epoch": 0.5953646608547736,
104
+ "grad_norm": 2.0834789276123047,
105
+ "learning_rate": 4.007725565242044e-05,
106
+ "loss": 1.6275,
107
+ "step": 2800
108
+ },
109
+ {
110
+ "epoch": 0.637890708058686,
111
+ "grad_norm": 1.998606562614441,
112
+ "learning_rate": 3.9368488199021905e-05,
113
+ "loss": 1.6399,
114
+ "step": 3000
115
+ },
116
+ {
117
+ "epoch": 0.6804167552625984,
118
+ "grad_norm": 2.2863314151763916,
119
+ "learning_rate": 3.8659720745623364e-05,
120
+ "loss": 1.631,
121
+ "step": 3200
122
+ },
123
+ {
124
+ "epoch": 0.7229428024665108,
125
+ "grad_norm": 2.4040656089782715,
126
+ "learning_rate": 3.795095329222482e-05,
127
+ "loss": 1.5873,
128
+ "step": 3400
129
+ },
130
+ {
131
+ "epoch": 0.7654688496704232,
132
+ "grad_norm": 2.490069627761841,
133
+ "learning_rate": 3.724218583882628e-05,
134
+ "loss": 1.6236,
135
+ "step": 3600
136
+ },
137
+ {
138
+ "epoch": 0.8079948968743356,
139
+ "grad_norm": 2.4205753803253174,
140
+ "learning_rate": 3.653341838542774e-05,
141
+ "loss": 1.57,
142
+ "step": 3800
143
+ },
144
+ {
145
+ "epoch": 0.850520944078248,
146
+ "grad_norm": 3.0913541316986084,
147
+ "learning_rate": 3.58246509320292e-05,
148
+ "loss": 1.5535,
149
+ "step": 4000
150
+ },
151
+ {
152
+ "epoch": 0.8930469912821604,
153
+ "grad_norm": 2.7764530181884766,
154
+ "learning_rate": 3.5115883478630665e-05,
155
+ "loss": 1.6216,
156
+ "step": 4200
157
+ },
158
+ {
159
+ "epoch": 0.9355730384860728,
160
+ "grad_norm": 2.6188108921051025,
161
+ "learning_rate": 3.4407116025232124e-05,
162
+ "loss": 1.5819,
163
+ "step": 4400
164
+ },
165
+ {
166
+ "epoch": 0.9780990856899852,
167
+ "grad_norm": 2.5243659019470215,
168
+ "learning_rate": 3.369834857183358e-05,
169
+ "loss": 1.5277,
170
+ "step": 4600
171
+ },
172
+ {
173
+ "epoch": 1.0206251328938976,
174
+ "grad_norm": 2.1120309829711914,
175
+ "learning_rate": 3.298958111843504e-05,
176
+ "loss": 1.5052,
177
+ "step": 4800
178
+ },
179
+ {
180
+ "epoch": 1.06315118009781,
181
+ "grad_norm": 2.532235622406006,
182
+ "learning_rate": 3.22808136650365e-05,
183
+ "loss": 1.4648,
184
+ "step": 5000
185
+ },
186
+ {
187
+ "epoch": 1.1056772273017224,
188
+ "grad_norm": 2.924020767211914,
189
+ "learning_rate": 3.157204621163796e-05,
190
+ "loss": 1.4526,
191
+ "step": 5200
192
+ },
193
+ {
194
+ "epoch": 1.1482032745056348,
195
+ "grad_norm": 3.1454060077667236,
196
+ "learning_rate": 3.0863278758239425e-05,
197
+ "loss": 1.4659,
198
+ "step": 5400
199
+ },
200
+ {
201
+ "epoch": 1.1907293217095472,
202
+ "grad_norm": 2.3973867893218994,
203
+ "learning_rate": 3.0154511304840884e-05,
204
+ "loss": 1.4622,
205
+ "step": 5600
206
+ },
207
+ {
208
+ "epoch": 1.2332553689134595,
209
+ "grad_norm": 2.5608162879943848,
210
+ "learning_rate": 2.9445743851442343e-05,
211
+ "loss": 1.4919,
212
+ "step": 5800
213
+ },
214
+ {
215
+ "epoch": 1.275781416117372,
216
+ "grad_norm": 1.8345551490783691,
217
+ "learning_rate": 2.87369763980438e-05,
218
+ "loss": 1.4644,
219
+ "step": 6000
220
+ },
221
+ {
222
+ "epoch": 1.3183074633212843,
223
+ "grad_norm": 2.1043267250061035,
224
+ "learning_rate": 2.8028208944645264e-05,
225
+ "loss": 1.4662,
226
+ "step": 6200
227
+ },
228
+ {
229
+ "epoch": 1.3608335105251967,
230
+ "grad_norm": 1.9993553161621094,
231
+ "learning_rate": 2.7319441491246722e-05,
232
+ "loss": 1.4558,
233
+ "step": 6400
234
+ },
235
+ {
236
+ "epoch": 1.4033595577291091,
237
+ "grad_norm": 2.4795050621032715,
238
+ "learning_rate": 2.661067403784818e-05,
239
+ "loss": 1.4381,
240
+ "step": 6600
241
+ },
242
+ {
243
+ "epoch": 1.4458856049330215,
244
+ "grad_norm": 2.0630886554718018,
245
+ "learning_rate": 2.5901906584449644e-05,
246
+ "loss": 1.4244,
247
+ "step": 6800
248
+ },
249
+ {
250
+ "epoch": 1.488411652136934,
251
+ "grad_norm": 2.489701509475708,
252
+ "learning_rate": 2.5193139131051102e-05,
253
+ "loss": 1.4263,
254
+ "step": 7000
255
+ },
256
+ {
257
+ "epoch": 1.5309376993408463,
258
+ "grad_norm": 2.2150392532348633,
259
+ "learning_rate": 2.448437167765256e-05,
260
+ "loss": 1.4437,
261
+ "step": 7200
262
+ },
263
+ {
264
+ "epoch": 1.5734637465447587,
265
+ "grad_norm": 2.3309507369995117,
266
+ "learning_rate": 2.3775604224254023e-05,
267
+ "loss": 1.437,
268
+ "step": 7400
269
+ },
270
+ {
271
+ "epoch": 1.6159897937486711,
272
+ "grad_norm": 2.4965591430664062,
273
+ "learning_rate": 2.3066836770855482e-05,
274
+ "loss": 1.4509,
275
+ "step": 7600
276
+ },
277
+ {
278
+ "epoch": 1.6585158409525835,
279
+ "grad_norm": 2.379479169845581,
280
+ "learning_rate": 2.235806931745694e-05,
281
+ "loss": 1.3942,
282
+ "step": 7800
283
+ },
284
+ {
285
+ "epoch": 1.701041888156496,
286
+ "grad_norm": 2.083732843399048,
287
+ "learning_rate": 2.1649301864058403e-05,
288
+ "loss": 1.3781,
289
+ "step": 8000
290
+ },
291
+ {
292
+ "epoch": 1.7435679353604083,
293
+ "grad_norm": 2.258941411972046,
294
+ "learning_rate": 2.0940534410659862e-05,
295
+ "loss": 1.3947,
296
+ "step": 8200
297
+ },
298
+ {
299
+ "epoch": 1.7860939825643207,
300
+ "grad_norm": 2.069312334060669,
301
+ "learning_rate": 2.023176695726132e-05,
302
+ "loss": 1.448,
303
+ "step": 8400
304
+ },
305
+ {
306
+ "epoch": 1.8286200297682331,
307
+ "grad_norm": 2.0143864154815674,
308
+ "learning_rate": 1.9522999503862783e-05,
309
+ "loss": 1.387,
310
+ "step": 8600
311
+ },
312
+ {
313
+ "epoch": 1.8711460769721455,
314
+ "grad_norm": 2.7671608924865723,
315
+ "learning_rate": 1.8814232050464242e-05,
316
+ "loss": 1.4122,
317
+ "step": 8800
318
+ },
319
+ {
320
+ "epoch": 1.913672124176058,
321
+ "grad_norm": 2.4909543991088867,
322
+ "learning_rate": 1.8105464597065704e-05,
323
+ "loss": 1.4364,
324
+ "step": 9000
325
+ },
326
+ {
327
+ "epoch": 1.9561981713799703,
328
+ "grad_norm": 2.471282720565796,
329
+ "learning_rate": 1.7396697143667166e-05,
330
+ "loss": 1.4177,
331
+ "step": 9200
332
+ },
333
+ {
334
+ "epoch": 1.9987242185838827,
335
+ "grad_norm": 3.3425190448760986,
336
+ "learning_rate": 1.6687929690268625e-05,
337
+ "loss": 1.4231,
338
+ "step": 9400
339
+ },
340
+ {
341
+ "epoch": 2.041250265787795,
342
+ "grad_norm": 2.7562530040740967,
343
+ "learning_rate": 1.5979162236870084e-05,
344
+ "loss": 1.3759,
345
+ "step": 9600
346
+ },
347
+ {
348
+ "epoch": 2.0837763129917075,
349
+ "grad_norm": 2.857525587081909,
350
+ "learning_rate": 1.5270394783471546e-05,
351
+ "loss": 1.3467,
352
+ "step": 9800
353
+ },
354
+ {
355
+ "epoch": 2.12630236019562,
356
+ "grad_norm": 2.1692278385162354,
357
+ "learning_rate": 1.4561627330073005e-05,
358
+ "loss": 1.3397,
359
+ "step": 10000
360
+ },
361
+ {
362
+ "epoch": 2.1688284073995323,
363
+ "grad_norm": 2.8106327056884766,
364
+ "learning_rate": 1.3852859876674466e-05,
365
+ "loss": 1.3203,
366
+ "step": 10200
367
+ },
368
+ {
369
+ "epoch": 2.2113544546034447,
370
+ "grad_norm": 2.509658098220825,
371
+ "learning_rate": 1.3144092423275925e-05,
372
+ "loss": 1.3108,
373
+ "step": 10400
374
+ },
375
+ {
376
+ "epoch": 2.253880501807357,
377
+ "grad_norm": 2.2616686820983887,
378
+ "learning_rate": 1.2435324969877383e-05,
379
+ "loss": 1.3394,
380
+ "step": 10600
381
+ },
382
+ {
383
+ "epoch": 2.2964065490112695,
384
+ "grad_norm": 2.6901018619537354,
385
+ "learning_rate": 1.1726557516478844e-05,
386
+ "loss": 1.3267,
387
+ "step": 10800
388
+ },
389
+ {
390
+ "epoch": 2.338932596215182,
391
+ "grad_norm": 3.918454647064209,
392
+ "learning_rate": 1.1017790063080303e-05,
393
+ "loss": 1.3223,
394
+ "step": 11000
395
+ },
396
+ {
397
+ "epoch": 2.3814586434190943,
398
+ "grad_norm": 2.4760806560516357,
399
+ "learning_rate": 1.0309022609681763e-05,
400
+ "loss": 1.3549,
401
+ "step": 11200
402
+ },
403
+ {
404
+ "epoch": 2.4239846906230067,
405
+ "grad_norm": 2.3667821884155273,
406
+ "learning_rate": 9.600255156283224e-06,
407
+ "loss": 1.3398,
408
+ "step": 11400
409
+ },
410
+ {
411
+ "epoch": 2.466510737826919,
412
+ "grad_norm": 2.600486993789673,
413
+ "learning_rate": 8.891487702884683e-06,
414
+ "loss": 1.3195,
415
+ "step": 11600
416
+ },
417
+ {
418
+ "epoch": 2.5090367850308315,
419
+ "grad_norm": 2.0121264457702637,
420
+ "learning_rate": 8.182720249486143e-06,
421
+ "loss": 1.3308,
422
+ "step": 11800
423
+ },
424
+ {
425
+ "epoch": 2.551562832234744,
426
+ "grad_norm": 2.0753839015960693,
427
+ "learning_rate": 7.473952796087604e-06,
428
+ "loss": 1.3607,
429
+ "step": 12000
430
+ },
431
+ {
432
+ "epoch": 2.5940888794386563,
433
+ "grad_norm": 2.37463641166687,
434
+ "learning_rate": 6.7651853426890634e-06,
435
+ "loss": 1.3247,
436
+ "step": 12200
437
+ },
438
+ {
439
+ "epoch": 2.6366149266425687,
440
+ "grad_norm": 2.016892910003662,
441
+ "learning_rate": 6.056417889290524e-06,
442
+ "loss": 1.2809,
443
+ "step": 12400
444
+ },
445
+ {
446
+ "epoch": 2.679140973846481,
447
+ "grad_norm": 2.9185993671417236,
448
+ "learning_rate": 5.3476504358919845e-06,
449
+ "loss": 1.3227,
450
+ "step": 12600
451
+ },
452
+ {
453
+ "epoch": 2.7216670210503935,
454
+ "grad_norm": 3.1016061305999756,
455
+ "learning_rate": 4.638882982493444e-06,
456
+ "loss": 1.3224,
457
+ "step": 12800
458
+ },
459
+ {
460
+ "epoch": 2.764193068254306,
461
+ "grad_norm": 1.890191912651062,
462
+ "learning_rate": 3.930115529094904e-06,
463
+ "loss": 1.3527,
464
+ "step": 13000
465
+ },
466
+ {
467
+ "epoch": 2.8067191154582183,
468
+ "grad_norm": 2.897411346435547,
469
+ "learning_rate": 3.221348075696364e-06,
470
+ "loss": 1.3423,
471
+ "step": 13200
472
+ },
473
+ {
474
+ "epoch": 2.8492451626621307,
475
+ "grad_norm": 2.7592458724975586,
476
+ "learning_rate": 2.512580622297824e-06,
477
+ "loss": 1.3389,
478
+ "step": 13400
479
+ },
480
+ {
481
+ "epoch": 2.891771209866043,
482
+ "grad_norm": 2.054417610168457,
483
+ "learning_rate": 1.8038131688992842e-06,
484
+ "loss": 1.3143,
485
+ "step": 13600
486
+ },
487
+ {
488
+ "epoch": 2.9342972570699555,
489
+ "grad_norm": 2.7590255737304688,
490
+ "learning_rate": 1.0950457155007443e-06,
491
+ "loss": 1.3156,
492
+ "step": 13800
493
+ },
494
+ {
495
+ "epoch": 2.976823304273868,
496
+ "grad_norm": 2.5642201900482178,
497
+ "learning_rate": 3.862782621022043e-07,
498
+ "loss": 1.3214,
499
+ "step": 14000
500
+ }
501
+ ],
502
+ "logging_steps": 200,
503
+ "max_steps": 14109,
504
+ "num_input_tokens_seen": 0,
505
+ "num_train_epochs": 3,
506
+ "save_steps": 500,
507
+ "stateful_callbacks": {
508
+ "TrainerControl": {
509
+ "args": {
510
+ "should_epoch_stop": false,
511
+ "should_evaluate": false,
512
+ "should_log": false,
513
+ "should_save": true,
514
+ "should_training_stop": false
515
+ },
516
+ "attributes": {}
517
+ }
518
+ },
519
+ "total_flos": 3657696509952000.0,
520
+ "train_batch_size": 4,
521
+ "trial_name": null,
522
+ "trial_params": null
523
+ }
checkpoint-14000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0d79f487bca473c020125e524f41452615f14ef4571460fd48afa939e7b0cd
3
+ size 5112
checkpoint-14109/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.44.2",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
checkpoint-14109/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.44.2"
6
+ }
checkpoint-14109/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63aed51723e204f7a61796503e164bb8e03101095014bcf1dc2a67a847ba1b7a
3
+ size 497777280
checkpoint-14109/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b40f1d8f85d2df75f4561faf7c82c50716e249c2900f3ca0c863bed9de0bcf3b
3
+ size 995648442
checkpoint-14109/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40f7a334049217b46c4168887f6dcd7b9b455a6e5c17fb225085ac06ede7fcf6
3
+ size 14244
checkpoint-14109/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0adfd8bab779f36ac0b2b689445faac85a4eebceac1a602fb450e4d6b995067c
3
+ size 1064
checkpoint-14109/trainer_state.json ADDED
@@ -0,0 +1,523 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14109,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0425260472039124,
13
+ "grad_norm": 4.5295610427856445,
14
+ "learning_rate": 4.929123254660146e-05,
15
+ "loss": 3.196,
16
+ "step": 200
17
+ },
18
+ {
19
+ "epoch": 0.0850520944078248,
20
+ "grad_norm": 3.153637170791626,
21
+ "learning_rate": 4.858246509320292e-05,
22
+ "loss": 2.0357,
23
+ "step": 400
24
+ },
25
+ {
26
+ "epoch": 0.1275781416117372,
27
+ "grad_norm": 2.833491802215576,
28
+ "learning_rate": 4.7873697639804386e-05,
29
+ "loss": 1.9407,
30
+ "step": 600
31
+ },
32
+ {
33
+ "epoch": 0.1701041888156496,
34
+ "grad_norm": 3.3437952995300293,
35
+ "learning_rate": 4.7164930186405845e-05,
36
+ "loss": 1.8486,
37
+ "step": 800
38
+ },
39
+ {
40
+ "epoch": 0.212630236019562,
41
+ "grad_norm": 2.2692761421203613,
42
+ "learning_rate": 4.64561627330073e-05,
43
+ "loss": 1.8338,
44
+ "step": 1000
45
+ },
46
+ {
47
+ "epoch": 0.2551562832234744,
48
+ "grad_norm": 9.267280578613281,
49
+ "learning_rate": 4.574739527960876e-05,
50
+ "loss": 1.8259,
51
+ "step": 1200
52
+ },
53
+ {
54
+ "epoch": 0.2976823304273868,
55
+ "grad_norm": 2.5437700748443604,
56
+ "learning_rate": 4.503862782621022e-05,
57
+ "loss": 1.7474,
58
+ "step": 1400
59
+ },
60
+ {
61
+ "epoch": 0.3402083776312992,
62
+ "grad_norm": 3.454941511154175,
63
+ "learning_rate": 4.432986037281168e-05,
64
+ "loss": 1.7185,
65
+ "step": 1600
66
+ },
67
+ {
68
+ "epoch": 0.3827344248352116,
69
+ "grad_norm": 2.709567070007324,
70
+ "learning_rate": 4.3621092919413145e-05,
71
+ "loss": 1.7468,
72
+ "step": 1800
73
+ },
74
+ {
75
+ "epoch": 0.425260472039124,
76
+ "grad_norm": 2.4916956424713135,
77
+ "learning_rate": 4.2912325466014604e-05,
78
+ "loss": 1.7277,
79
+ "step": 2000
80
+ },
81
+ {
82
+ "epoch": 0.4677865192430364,
83
+ "grad_norm": 2.3599932193756104,
84
+ "learning_rate": 4.220355801261606e-05,
85
+ "loss": 1.6742,
86
+ "step": 2200
87
+ },
88
+ {
89
+ "epoch": 0.5103125664469488,
90
+ "grad_norm": 2.518554449081421,
91
+ "learning_rate": 4.149479055921752e-05,
92
+ "loss": 1.6232,
93
+ "step": 2400
94
+ },
95
+ {
96
+ "epoch": 0.5528386136508612,
97
+ "grad_norm": 2.202854633331299,
98
+ "learning_rate": 4.078602310581898e-05,
99
+ "loss": 1.6431,
100
+ "step": 2600
101
+ },
102
+ {
103
+ "epoch": 0.5953646608547736,
104
+ "grad_norm": 2.0834789276123047,
105
+ "learning_rate": 4.007725565242044e-05,
106
+ "loss": 1.6275,
107
+ "step": 2800
108
+ },
109
+ {
110
+ "epoch": 0.637890708058686,
111
+ "grad_norm": 1.998606562614441,
112
+ "learning_rate": 3.9368488199021905e-05,
113
+ "loss": 1.6399,
114
+ "step": 3000
115
+ },
116
+ {
117
+ "epoch": 0.6804167552625984,
118
+ "grad_norm": 2.2863314151763916,
119
+ "learning_rate": 3.8659720745623364e-05,
120
+ "loss": 1.631,
121
+ "step": 3200
122
+ },
123
+ {
124
+ "epoch": 0.7229428024665108,
125
+ "grad_norm": 2.4040656089782715,
126
+ "learning_rate": 3.795095329222482e-05,
127
+ "loss": 1.5873,
128
+ "step": 3400
129
+ },
130
+ {
131
+ "epoch": 0.7654688496704232,
132
+ "grad_norm": 2.490069627761841,
133
+ "learning_rate": 3.724218583882628e-05,
134
+ "loss": 1.6236,
135
+ "step": 3600
136
+ },
137
+ {
138
+ "epoch": 0.8079948968743356,
139
+ "grad_norm": 2.4205753803253174,
140
+ "learning_rate": 3.653341838542774e-05,
141
+ "loss": 1.57,
142
+ "step": 3800
143
+ },
144
+ {
145
+ "epoch": 0.850520944078248,
146
+ "grad_norm": 3.0913541316986084,
147
+ "learning_rate": 3.58246509320292e-05,
148
+ "loss": 1.5535,
149
+ "step": 4000
150
+ },
151
+ {
152
+ "epoch": 0.8930469912821604,
153
+ "grad_norm": 2.7764530181884766,
154
+ "learning_rate": 3.5115883478630665e-05,
155
+ "loss": 1.6216,
156
+ "step": 4200
157
+ },
158
+ {
159
+ "epoch": 0.9355730384860728,
160
+ "grad_norm": 2.6188108921051025,
161
+ "learning_rate": 3.4407116025232124e-05,
162
+ "loss": 1.5819,
163
+ "step": 4400
164
+ },
165
+ {
166
+ "epoch": 0.9780990856899852,
167
+ "grad_norm": 2.5243659019470215,
168
+ "learning_rate": 3.369834857183358e-05,
169
+ "loss": 1.5277,
170
+ "step": 4600
171
+ },
172
+ {
173
+ "epoch": 1.0206251328938976,
174
+ "grad_norm": 2.1120309829711914,
175
+ "learning_rate": 3.298958111843504e-05,
176
+ "loss": 1.5052,
177
+ "step": 4800
178
+ },
179
+ {
180
+ "epoch": 1.06315118009781,
181
+ "grad_norm": 2.532235622406006,
182
+ "learning_rate": 3.22808136650365e-05,
183
+ "loss": 1.4648,
184
+ "step": 5000
185
+ },
186
+ {
187
+ "epoch": 1.1056772273017224,
188
+ "grad_norm": 2.924020767211914,
189
+ "learning_rate": 3.157204621163796e-05,
190
+ "loss": 1.4526,
191
+ "step": 5200
192
+ },
193
+ {
194
+ "epoch": 1.1482032745056348,
195
+ "grad_norm": 3.1454060077667236,
196
+ "learning_rate": 3.0863278758239425e-05,
197
+ "loss": 1.4659,
198
+ "step": 5400
199
+ },
200
+ {
201
+ "epoch": 1.1907293217095472,
202
+ "grad_norm": 2.3973867893218994,
203
+ "learning_rate": 3.0154511304840884e-05,
204
+ "loss": 1.4622,
205
+ "step": 5600
206
+ },
207
+ {
208
+ "epoch": 1.2332553689134595,
209
+ "grad_norm": 2.5608162879943848,
210
+ "learning_rate": 2.9445743851442343e-05,
211
+ "loss": 1.4919,
212
+ "step": 5800
213
+ },
214
+ {
215
+ "epoch": 1.275781416117372,
216
+ "grad_norm": 1.8345551490783691,
217
+ "learning_rate": 2.87369763980438e-05,
218
+ "loss": 1.4644,
219
+ "step": 6000
220
+ },
221
+ {
222
+ "epoch": 1.3183074633212843,
223
+ "grad_norm": 2.1043267250061035,
224
+ "learning_rate": 2.8028208944645264e-05,
225
+ "loss": 1.4662,
226
+ "step": 6200
227
+ },
228
+ {
229
+ "epoch": 1.3608335105251967,
230
+ "grad_norm": 1.9993553161621094,
231
+ "learning_rate": 2.7319441491246722e-05,
232
+ "loss": 1.4558,
233
+ "step": 6400
234
+ },
235
+ {
236
+ "epoch": 1.4033595577291091,
237
+ "grad_norm": 2.4795050621032715,
238
+ "learning_rate": 2.661067403784818e-05,
239
+ "loss": 1.4381,
240
+ "step": 6600
241
+ },
242
+ {
243
+ "epoch": 1.4458856049330215,
244
+ "grad_norm": 2.0630886554718018,
245
+ "learning_rate": 2.5901906584449644e-05,
246
+ "loss": 1.4244,
247
+ "step": 6800
248
+ },
249
+ {
250
+ "epoch": 1.488411652136934,
251
+ "grad_norm": 2.489701509475708,
252
+ "learning_rate": 2.5193139131051102e-05,
253
+ "loss": 1.4263,
254
+ "step": 7000
255
+ },
256
+ {
257
+ "epoch": 1.5309376993408463,
258
+ "grad_norm": 2.2150392532348633,
259
+ "learning_rate": 2.448437167765256e-05,
260
+ "loss": 1.4437,
261
+ "step": 7200
262
+ },
263
+ {
264
+ "epoch": 1.5734637465447587,
265
+ "grad_norm": 2.3309507369995117,
266
+ "learning_rate": 2.3775604224254023e-05,
267
+ "loss": 1.437,
268
+ "step": 7400
269
+ },
270
+ {
271
+ "epoch": 1.6159897937486711,
272
+ "grad_norm": 2.4965591430664062,
273
+ "learning_rate": 2.3066836770855482e-05,
274
+ "loss": 1.4509,
275
+ "step": 7600
276
+ },
277
+ {
278
+ "epoch": 1.6585158409525835,
279
+ "grad_norm": 2.379479169845581,
280
+ "learning_rate": 2.235806931745694e-05,
281
+ "loss": 1.3942,
282
+ "step": 7800
283
+ },
284
+ {
285
+ "epoch": 1.701041888156496,
286
+ "grad_norm": 2.083732843399048,
287
+ "learning_rate": 2.1649301864058403e-05,
288
+ "loss": 1.3781,
289
+ "step": 8000
290
+ },
291
+ {
292
+ "epoch": 1.7435679353604083,
293
+ "grad_norm": 2.258941411972046,
294
+ "learning_rate": 2.0940534410659862e-05,
295
+ "loss": 1.3947,
296
+ "step": 8200
297
+ },
298
+ {
299
+ "epoch": 1.7860939825643207,
300
+ "grad_norm": 2.069312334060669,
301
+ "learning_rate": 2.023176695726132e-05,
302
+ "loss": 1.448,
303
+ "step": 8400
304
+ },
305
+ {
306
+ "epoch": 1.8286200297682331,
307
+ "grad_norm": 2.0143864154815674,
308
+ "learning_rate": 1.9522999503862783e-05,
309
+ "loss": 1.387,
310
+ "step": 8600
311
+ },
312
+ {
313
+ "epoch": 1.8711460769721455,
314
+ "grad_norm": 2.7671608924865723,
315
+ "learning_rate": 1.8814232050464242e-05,
316
+ "loss": 1.4122,
317
+ "step": 8800
318
+ },
319
+ {
320
+ "epoch": 1.913672124176058,
321
+ "grad_norm": 2.4909543991088867,
322
+ "learning_rate": 1.8105464597065704e-05,
323
+ "loss": 1.4364,
324
+ "step": 9000
325
+ },
326
+ {
327
+ "epoch": 1.9561981713799703,
328
+ "grad_norm": 2.471282720565796,
329
+ "learning_rate": 1.7396697143667166e-05,
330
+ "loss": 1.4177,
331
+ "step": 9200
332
+ },
333
+ {
334
+ "epoch": 1.9987242185838827,
335
+ "grad_norm": 3.3425190448760986,
336
+ "learning_rate": 1.6687929690268625e-05,
337
+ "loss": 1.4231,
338
+ "step": 9400
339
+ },
340
+ {
341
+ "epoch": 2.041250265787795,
342
+ "grad_norm": 2.7562530040740967,
343
+ "learning_rate": 1.5979162236870084e-05,
344
+ "loss": 1.3759,
345
+ "step": 9600
346
+ },
347
+ {
348
+ "epoch": 2.0837763129917075,
349
+ "grad_norm": 2.857525587081909,
350
+ "learning_rate": 1.5270394783471546e-05,
351
+ "loss": 1.3467,
352
+ "step": 9800
353
+ },
354
+ {
355
+ "epoch": 2.12630236019562,
356
+ "grad_norm": 2.1692278385162354,
357
+ "learning_rate": 1.4561627330073005e-05,
358
+ "loss": 1.3397,
359
+ "step": 10000
360
+ },
361
+ {
362
+ "epoch": 2.1688284073995323,
363
+ "grad_norm": 2.8106327056884766,
364
+ "learning_rate": 1.3852859876674466e-05,
365
+ "loss": 1.3203,
366
+ "step": 10200
367
+ },
368
+ {
369
+ "epoch": 2.2113544546034447,
370
+ "grad_norm": 2.509658098220825,
371
+ "learning_rate": 1.3144092423275925e-05,
372
+ "loss": 1.3108,
373
+ "step": 10400
374
+ },
375
+ {
376
+ "epoch": 2.253880501807357,
377
+ "grad_norm": 2.2616686820983887,
378
+ "learning_rate": 1.2435324969877383e-05,
379
+ "loss": 1.3394,
380
+ "step": 10600
381
+ },
382
+ {
383
+ "epoch": 2.2964065490112695,
384
+ "grad_norm": 2.6901018619537354,
385
+ "learning_rate": 1.1726557516478844e-05,
386
+ "loss": 1.3267,
387
+ "step": 10800
388
+ },
389
+ {
390
+ "epoch": 2.338932596215182,
391
+ "grad_norm": 3.918454647064209,
392
+ "learning_rate": 1.1017790063080303e-05,
393
+ "loss": 1.3223,
394
+ "step": 11000
395
+ },
396
+ {
397
+ "epoch": 2.3814586434190943,
398
+ "grad_norm": 2.4760806560516357,
399
+ "learning_rate": 1.0309022609681763e-05,
400
+ "loss": 1.3549,
401
+ "step": 11200
402
+ },
403
+ {
404
+ "epoch": 2.4239846906230067,
405
+ "grad_norm": 2.3667821884155273,
406
+ "learning_rate": 9.600255156283224e-06,
407
+ "loss": 1.3398,
408
+ "step": 11400
409
+ },
410
+ {
411
+ "epoch": 2.466510737826919,
412
+ "grad_norm": 2.600486993789673,
413
+ "learning_rate": 8.891487702884683e-06,
414
+ "loss": 1.3195,
415
+ "step": 11600
416
+ },
417
+ {
418
+ "epoch": 2.5090367850308315,
419
+ "grad_norm": 2.0121264457702637,
420
+ "learning_rate": 8.182720249486143e-06,
421
+ "loss": 1.3308,
422
+ "step": 11800
423
+ },
424
+ {
425
+ "epoch": 2.551562832234744,
426
+ "grad_norm": 2.0753839015960693,
427
+ "learning_rate": 7.473952796087604e-06,
428
+ "loss": 1.3607,
429
+ "step": 12000
430
+ },
431
+ {
432
+ "epoch": 2.5940888794386563,
433
+ "grad_norm": 2.37463641166687,
434
+ "learning_rate": 6.7651853426890634e-06,
435
+ "loss": 1.3247,
436
+ "step": 12200
437
+ },
438
+ {
439
+ "epoch": 2.6366149266425687,
440
+ "grad_norm": 2.016892910003662,
441
+ "learning_rate": 6.056417889290524e-06,
442
+ "loss": 1.2809,
443
+ "step": 12400
444
+ },
445
+ {
446
+ "epoch": 2.679140973846481,
447
+ "grad_norm": 2.9185993671417236,
448
+ "learning_rate": 5.3476504358919845e-06,
449
+ "loss": 1.3227,
450
+ "step": 12600
451
+ },
452
+ {
453
+ "epoch": 2.7216670210503935,
454
+ "grad_norm": 3.1016061305999756,
455
+ "learning_rate": 4.638882982493444e-06,
456
+ "loss": 1.3224,
457
+ "step": 12800
458
+ },
459
+ {
460
+ "epoch": 2.764193068254306,
461
+ "grad_norm": 1.890191912651062,
462
+ "learning_rate": 3.930115529094904e-06,
463
+ "loss": 1.3527,
464
+ "step": 13000
465
+ },
466
+ {
467
+ "epoch": 2.8067191154582183,
468
+ "grad_norm": 2.897411346435547,
469
+ "learning_rate": 3.221348075696364e-06,
470
+ "loss": 1.3423,
471
+ "step": 13200
472
+ },
473
+ {
474
+ "epoch": 2.8492451626621307,
475
+ "grad_norm": 2.7592458724975586,
476
+ "learning_rate": 2.512580622297824e-06,
477
+ "loss": 1.3389,
478
+ "step": 13400
479
+ },
480
+ {
481
+ "epoch": 2.891771209866043,
482
+ "grad_norm": 2.054417610168457,
483
+ "learning_rate": 1.8038131688992842e-06,
484
+ "loss": 1.3143,
485
+ "step": 13600
486
+ },
487
+ {
488
+ "epoch": 2.9342972570699555,
489
+ "grad_norm": 2.7590255737304688,
490
+ "learning_rate": 1.0950457155007443e-06,
491
+ "loss": 1.3156,
492
+ "step": 13800
493
+ },
494
+ {
495
+ "epoch": 2.976823304273868,
496
+ "grad_norm": 2.5642201900482178,
497
+ "learning_rate": 3.862782621022043e-07,
498
+ "loss": 1.3214,
499
+ "step": 14000
500
+ }
501
+ ],
502
+ "logging_steps": 200,
503
+ "max_steps": 14109,
504
+ "num_input_tokens_seen": 0,
505
+ "num_train_epochs": 3,
506
+ "save_steps": 500,
507
+ "stateful_callbacks": {
508
+ "TrainerControl": {
509
+ "args": {
510
+ "should_epoch_stop": false,
511
+ "should_evaluate": false,
512
+ "should_log": false,
513
+ "should_save": true,
514
+ "should_training_stop": true
515
+ },
516
+ "attributes": {}
517
+ }
518
+ },
519
+ "total_flos": 3685981372416000.0,
520
+ "train_batch_size": 4,
521
+ "trial_name": null,
522
+ "trial_params": null
523
+ }
checkpoint-14109/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0d79f487bca473c020125e524f41452615f14ef4571460fd48afa939e7b0cd
3
+ size 5112
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.44.2",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.44.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63aed51723e204f7a61796503e164bb8e03101095014bcf1dc2a67a847ba1b7a
3
+ size 497777280
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "unk_token": "<|endoftext|>"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "[PAD]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|endoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "eos_token": "<|endoftext|>",
24
+ "model_max_length": 1024,
25
+ "pad_token": "[PAD]",
26
+ "tokenizer_class": "GPT2Tokenizer",
27
+ "unk_token": "<|endoftext|>"
28
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0d79f487bca473c020125e524f41452615f14ef4571460fd48afa939e7b0cd
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff