zaas12 commited on
Commit
7842bb2
·
verified ·
1 Parent(s): f7b735e

Upload folder using huggingface_hub

Browse files
checkpoint-3032/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-1.4b",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "partial_rotary_factor": 0.25,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "rotary_emb_base": 10000,
25
+ "rotary_pct": 0.25,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.45.0",
29
+ "use_cache": false,
30
+ "use_parallel_residual": true,
31
+ "vocab_size": 50304
32
+ }
checkpoint-3032/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.45.0",
6
+ "use_cache": false
7
+ }
checkpoint-3032/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a40c2a58d50905ec41304935ed26c969897b42342c83010e1be3e811cfe22ff2
3
+ size 2829330208
checkpoint-3032/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ad6eee21c33141bd21e7c5e7c08c430c8c7df3b4b4f30f72a306aeb792d898
3
+ size 11317362842
checkpoint-3032/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
checkpoint-3032/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eaacf3027bc66ee0e0bbedcef10d2aba06184b2f7cc8831e512987b6172c3d7
3
+ size 1064
checkpoint-3032/trainer_state.json ADDED
@@ -0,0 +1,461 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.9353829622268677,
3
+ "best_model_checkpoint": "./checkpoints/ultrafeedback_binarized/pythia-1.4b-ultrafeedback_binarized-lambda0.25-ORPO-28-11-41/checkpoint-3032",
4
+ "epoch": 0.9998351195383347,
5
+ "eval_steps": 500,
6
+ "global_step": 3032,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016488046166529265,
13
+ "grad_norm": 10.5625,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 3.8611,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.03297609233305853,
20
+ "grad_norm": 12.25,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 3.7579,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.0494641384995878,
27
+ "grad_norm": 16.375,
28
+ "learning_rate": 3e-06,
29
+ "loss": 3.5732,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.06595218466611706,
34
+ "grad_norm": 7.21875,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 3.332,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.08244023083264633,
41
+ "grad_norm": 11.25,
42
+ "learning_rate": 5e-06,
43
+ "loss": 3.1433,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.0989282769991756,
48
+ "grad_norm": 5.1875,
49
+ "learning_rate": 6e-06,
50
+ "loss": 2.9956,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.11541632316570487,
55
+ "grad_norm": 8.875,
56
+ "learning_rate": 7e-06,
57
+ "loss": 2.9612,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.13190436933223412,
62
+ "grad_norm": 8.5625,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 2.8493,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.1483924154987634,
69
+ "grad_norm": 6.65625,
70
+ "learning_rate": 9e-06,
71
+ "loss": 2.7876,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.16488046166529266,
76
+ "grad_norm": 9.3125,
77
+ "learning_rate": 1e-05,
78
+ "loss": 2.7949,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.18136850783182193,
83
+ "grad_norm": 7.6875,
84
+ "learning_rate": 1.1000000000000001e-05,
85
+ "loss": 2.724,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.1978565539983512,
90
+ "grad_norm": 4.3125,
91
+ "learning_rate": 1.2e-05,
92
+ "loss": 2.6878,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.21434460016488047,
97
+ "grad_norm": 14.5,
98
+ "learning_rate": 1.3000000000000001e-05,
99
+ "loss": 2.6642,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.23083264633140974,
104
+ "grad_norm": 4.65625,
105
+ "learning_rate": 1.4e-05,
106
+ "loss": 2.6199,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.247320692497939,
111
+ "grad_norm": 8.0625,
112
+ "learning_rate": 1.5000000000000002e-05,
113
+ "loss": 2.5978,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.26380873866446825,
118
+ "grad_norm": 6.03125,
119
+ "learning_rate": 1.6000000000000003e-05,
120
+ "loss": 2.5495,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.2802967848309975,
125
+ "grad_norm": 5.40625,
126
+ "learning_rate": 1.7e-05,
127
+ "loss": 2.5325,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.2967848309975268,
132
+ "grad_norm": 5.53125,
133
+ "learning_rate": 1.8e-05,
134
+ "loss": 2.502,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.31327287716405605,
139
+ "grad_norm": 4.65625,
140
+ "learning_rate": 1.9e-05,
141
+ "loss": 2.4639,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.3297609233305853,
146
+ "grad_norm": 4.40625,
147
+ "learning_rate": 2e-05,
148
+ "loss": 2.4813,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.3462489694971146,
153
+ "grad_norm": 4.4375,
154
+ "learning_rate": 1.999020122924231e-05,
155
+ "loss": 2.4175,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.36273701566364386,
160
+ "grad_norm": 9.3125,
161
+ "learning_rate": 1.9960824120150918e-05,
162
+ "loss": 2.3888,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.3792250618301731,
167
+ "grad_norm": 4.875,
168
+ "learning_rate": 1.9911926244637318e-05,
169
+ "loss": 2.3924,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.3957131079967024,
174
+ "grad_norm": 4.5625,
175
+ "learning_rate": 1.9843603430516055e-05,
176
+ "loss": 2.2982,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.41220115416323166,
181
+ "grad_norm": 8.75,
182
+ "learning_rate": 1.9755989573705744e-05,
183
+ "loss": 2.3696,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.42868920032976093,
188
+ "grad_norm": 7.65625,
189
+ "learning_rate": 1.9649256375826003e-05,
190
+ "loss": 2.3295,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.4451772464962902,
195
+ "grad_norm": 6.03125,
196
+ "learning_rate": 1.9523613007704486e-05,
197
+ "loss": 2.3079,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.46166529266281947,
202
+ "grad_norm": 11.5,
203
+ "learning_rate": 1.9379305699453478e-05,
204
+ "loss": 2.2917,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.47815333882934874,
209
+ "grad_norm": 7.46875,
210
+ "learning_rate": 1.9216617257919427e-05,
211
+ "loss": 2.275,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.494641384995878,
216
+ "grad_norm": 7.71875,
217
+ "learning_rate": 1.9035866512451032e-05,
218
+ "loss": 2.2563,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.5111294311624073,
223
+ "grad_norm": 6.59375,
224
+ "learning_rate": 1.8837407690072117e-05,
225
+ "loss": 2.2598,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.5276174773289365,
230
+ "grad_norm": 8.75,
231
+ "learning_rate": 1.8621629721283748e-05,
232
+ "loss": 2.2132,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.5441055234954658,
237
+ "grad_norm": 6.0625,
238
+ "learning_rate": 1.8388955477856077e-05,
239
+ "loss": 2.2152,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.560593569661995,
244
+ "grad_norm": 6.0625,
245
+ "learning_rate": 1.813984094410361e-05,
246
+ "loss": 2.2046,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.5770816158285244,
251
+ "grad_norm": 9.1875,
252
+ "learning_rate": 1.7874774323268077e-05,
253
+ "loss": 2.1833,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.5935696619950536,
258
+ "grad_norm": 3.953125,
259
+ "learning_rate": 1.75942750807601e-05,
260
+ "loss": 2.1776,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.6100577081615829,
265
+ "grad_norm": 4.875,
266
+ "learning_rate": 1.7298892926134677e-05,
267
+ "loss": 2.1863,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 0.6265457543281121,
272
+ "grad_norm": 8.6875,
273
+ "learning_rate": 1.6989206735795634e-05,
274
+ "loss": 2.1821,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 0.6430338004946414,
279
+ "grad_norm": 3.6875,
280
+ "learning_rate": 1.666582341854016e-05,
281
+ "loss": 2.1375,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 0.6595218466611706,
286
+ "grad_norm": 8.0625,
287
+ "learning_rate": 1.632937672616678e-05,
288
+ "loss": 2.1396,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.6760098928277,
293
+ "grad_norm": 7.34375,
294
+ "learning_rate": 1.5980526011477654e-05,
295
+ "loss": 2.1137,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.6924979389942292,
300
+ "grad_norm": 3.1875,
301
+ "learning_rate": 1.5619954936109148e-05,
302
+ "loss": 2.1607,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 0.7089859851607585,
307
+ "grad_norm": 5.8125,
308
+ "learning_rate": 1.5248370130723151e-05,
309
+ "loss": 2.086,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 0.7254740313272877,
314
+ "grad_norm": 4.78125,
315
+ "learning_rate": 1.4866499810184662e-05,
316
+ "loss": 2.0821,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 0.7419620774938169,
321
+ "grad_norm": 6.4375,
322
+ "learning_rate": 1.4475092346439704e-05,
323
+ "loss": 2.0415,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 0.7584501236603463,
328
+ "grad_norm": 4.6875,
329
+ "learning_rate": 1.4074914801890294e-05,
330
+ "loss": 2.0471,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 0.7749381698268755,
335
+ "grad_norm": 7.9375,
336
+ "learning_rate": 1.366675142614072e-05,
337
+ "loss": 2.0638,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 0.7914262159934048,
342
+ "grad_norm": 4.03125,
343
+ "learning_rate": 1.3251402119061105e-05,
344
+ "loss": 2.0433,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 0.807914262159934,
349
+ "grad_norm": 3.625,
350
+ "learning_rate": 1.2829680863180345e-05,
351
+ "loss": 2.066,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 0.8244023083264633,
356
+ "grad_norm": 4.90625,
357
+ "learning_rate": 1.240241412848044e-05,
358
+ "loss": 2.0081,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 0.8408903544929925,
363
+ "grad_norm": 3.875,
364
+ "learning_rate": 1.1970439252718532e-05,
365
+ "loss": 2.0367,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 0.8573784006595219,
370
+ "grad_norm": 3.265625,
371
+ "learning_rate": 1.1534602800450757e-05,
372
+ "loss": 2.0784,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 0.8738664468260511,
377
+ "grad_norm": 6.84375,
378
+ "learning_rate": 1.1095758903973832e-05,
379
+ "loss": 1.9913,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 0.8903544929925804,
384
+ "grad_norm": 5.15625,
385
+ "learning_rate": 1.0654767589435762e-05,
386
+ "loss": 1.9759,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 0.9068425391591096,
391
+ "grad_norm": 5.71875,
392
+ "learning_rate": 1.0212493091396004e-05,
393
+ "loss": 2.0223,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 0.9233305853256389,
398
+ "grad_norm": 5.0625,
399
+ "learning_rate": 9.769802159138207e-06,
400
+ "loss": 2.0058,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 0.9398186314921682,
405
+ "grad_norm": 5.40625,
406
+ "learning_rate": 9.32756235805472e-06,
407
+ "loss": 1.9625,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 0.9563066776586975,
412
+ "grad_norm": 5.875,
413
+ "learning_rate": 8.88664036943168e-06,
414
+ "loss": 1.9904,
415
+ "step": 2900
416
+ },
417
+ {
418
+ "epoch": 0.9727947238252267,
419
+ "grad_norm": 5.3125,
420
+ "learning_rate": 8.447900291966801e-06,
421
+ "loss": 1.9552,
422
+ "step": 2950
423
+ },
424
+ {
425
+ "epoch": 0.989282769991756,
426
+ "grad_norm": 5.5625,
427
+ "learning_rate": 8.012201948348346e-06,
428
+ "loss": 1.9429,
429
+ "step": 3000
430
+ },
431
+ {
432
+ "epoch": 0.9998351195383347,
433
+ "eval_loss": 1.9353829622268677,
434
+ "eval_runtime": 69.7897,
435
+ "eval_samples_per_second": 23.342,
436
+ "eval_steps_per_second": 2.923,
437
+ "step": 3032
438
+ }
439
+ ],
440
+ "logging_steps": 50,
441
+ "max_steps": 4548,
442
+ "num_input_tokens_seen": 0,
443
+ "num_train_epochs": 2,
444
+ "save_steps": 500,
445
+ "stateful_callbacks": {
446
+ "TrainerControl": {
447
+ "args": {
448
+ "should_epoch_stop": false,
449
+ "should_evaluate": false,
450
+ "should_log": false,
451
+ "should_save": true,
452
+ "should_training_stop": false
453
+ },
454
+ "attributes": {}
455
+ }
456
+ },
457
+ "total_flos": 3.909883836204319e+17,
458
+ "train_batch_size": 8,
459
+ "trial_name": null,
460
+ "trial_params": null
461
+ }
checkpoint-3032/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:067fcca4b639e1227036ee31669835301fff03559a3de4a3d1fe926e551bc124
3
+ size 5432
checkpoint-4548/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-1.4b",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "partial_rotary_factor": 0.25,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "rotary_emb_base": 10000,
25
+ "rotary_pct": 0.25,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.45.0",
29
+ "use_cache": false,
30
+ "use_parallel_residual": true,
31
+ "vocab_size": 50304
32
+ }
checkpoint-4548/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.45.0",
6
+ "use_cache": false
7
+ }
checkpoint-4548/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dec95f92814372913b8e98caf8077087bc0c5cfeb373e8267e14ce7739a252d
3
+ size 2829330208
checkpoint-4548/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5949ce67f0f2bc1f797eb64d25a85ed3e730beb947df6f46e44f112959120e1
3
+ size 11317362842
checkpoint-4548/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
3
+ size 14244
checkpoint-4548/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14cc139af714f2a1d58cfb3d0a37b5913ae643d0ba154345fb54899cb5d635d0
3
+ size 1064
checkpoint-4548/trainer_state.json ADDED
@@ -0,0 +1,679 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.843124270439148,
3
+ "best_model_checkpoint": "./checkpoints/ultrafeedback_binarized/pythia-1.4b-ultrafeedback_binarized-lambda0.25-ORPO-28-11-41/checkpoint-4548",
4
+ "epoch": 1.499752679307502,
5
+ "eval_steps": 500,
6
+ "global_step": 4548,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016488046166529265,
13
+ "grad_norm": 10.5625,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 3.8611,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.03297609233305853,
20
+ "grad_norm": 12.25,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 3.7579,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.0494641384995878,
27
+ "grad_norm": 16.375,
28
+ "learning_rate": 3e-06,
29
+ "loss": 3.5732,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.06595218466611706,
34
+ "grad_norm": 7.21875,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 3.332,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.08244023083264633,
41
+ "grad_norm": 11.25,
42
+ "learning_rate": 5e-06,
43
+ "loss": 3.1433,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.0989282769991756,
48
+ "grad_norm": 5.1875,
49
+ "learning_rate": 6e-06,
50
+ "loss": 2.9956,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.11541632316570487,
55
+ "grad_norm": 8.875,
56
+ "learning_rate": 7e-06,
57
+ "loss": 2.9612,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.13190436933223412,
62
+ "grad_norm": 8.5625,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 2.8493,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.1483924154987634,
69
+ "grad_norm": 6.65625,
70
+ "learning_rate": 9e-06,
71
+ "loss": 2.7876,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.16488046166529266,
76
+ "grad_norm": 9.3125,
77
+ "learning_rate": 1e-05,
78
+ "loss": 2.7949,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.18136850783182193,
83
+ "grad_norm": 7.6875,
84
+ "learning_rate": 1.1000000000000001e-05,
85
+ "loss": 2.724,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.1978565539983512,
90
+ "grad_norm": 4.3125,
91
+ "learning_rate": 1.2e-05,
92
+ "loss": 2.6878,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.21434460016488047,
97
+ "grad_norm": 14.5,
98
+ "learning_rate": 1.3000000000000001e-05,
99
+ "loss": 2.6642,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.23083264633140974,
104
+ "grad_norm": 4.65625,
105
+ "learning_rate": 1.4e-05,
106
+ "loss": 2.6199,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.247320692497939,
111
+ "grad_norm": 8.0625,
112
+ "learning_rate": 1.5000000000000002e-05,
113
+ "loss": 2.5978,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.26380873866446825,
118
+ "grad_norm": 6.03125,
119
+ "learning_rate": 1.6000000000000003e-05,
120
+ "loss": 2.5495,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.2802967848309975,
125
+ "grad_norm": 5.40625,
126
+ "learning_rate": 1.7e-05,
127
+ "loss": 2.5325,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.2967848309975268,
132
+ "grad_norm": 5.53125,
133
+ "learning_rate": 1.8e-05,
134
+ "loss": 2.502,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.31327287716405605,
139
+ "grad_norm": 4.65625,
140
+ "learning_rate": 1.9e-05,
141
+ "loss": 2.4639,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.3297609233305853,
146
+ "grad_norm": 4.40625,
147
+ "learning_rate": 2e-05,
148
+ "loss": 2.4813,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.3462489694971146,
153
+ "grad_norm": 4.4375,
154
+ "learning_rate": 1.999020122924231e-05,
155
+ "loss": 2.4175,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.36273701566364386,
160
+ "grad_norm": 9.3125,
161
+ "learning_rate": 1.9960824120150918e-05,
162
+ "loss": 2.3888,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.3792250618301731,
167
+ "grad_norm": 4.875,
168
+ "learning_rate": 1.9911926244637318e-05,
169
+ "loss": 2.3924,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.3957131079967024,
174
+ "grad_norm": 4.5625,
175
+ "learning_rate": 1.9843603430516055e-05,
176
+ "loss": 2.2982,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.41220115416323166,
181
+ "grad_norm": 8.75,
182
+ "learning_rate": 1.9755989573705744e-05,
183
+ "loss": 2.3696,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.42868920032976093,
188
+ "grad_norm": 7.65625,
189
+ "learning_rate": 1.9649256375826003e-05,
190
+ "loss": 2.3295,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.4451772464962902,
195
+ "grad_norm": 6.03125,
196
+ "learning_rate": 1.9523613007704486e-05,
197
+ "loss": 2.3079,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.46166529266281947,
202
+ "grad_norm": 11.5,
203
+ "learning_rate": 1.9379305699453478e-05,
204
+ "loss": 2.2917,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.47815333882934874,
209
+ "grad_norm": 7.46875,
210
+ "learning_rate": 1.9216617257919427e-05,
211
+ "loss": 2.275,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.494641384995878,
216
+ "grad_norm": 7.71875,
217
+ "learning_rate": 1.9035866512451032e-05,
218
+ "loss": 2.2563,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.5111294311624073,
223
+ "grad_norm": 6.59375,
224
+ "learning_rate": 1.8837407690072117e-05,
225
+ "loss": 2.2598,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.5276174773289365,
230
+ "grad_norm": 8.75,
231
+ "learning_rate": 1.8621629721283748e-05,
232
+ "loss": 2.2132,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.5441055234954658,
237
+ "grad_norm": 6.0625,
238
+ "learning_rate": 1.8388955477856077e-05,
239
+ "loss": 2.2152,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.560593569661995,
244
+ "grad_norm": 6.0625,
245
+ "learning_rate": 1.813984094410361e-05,
246
+ "loss": 2.2046,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.5770816158285244,
251
+ "grad_norm": 9.1875,
252
+ "learning_rate": 1.7874774323268077e-05,
253
+ "loss": 2.1833,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.5935696619950536,
258
+ "grad_norm": 3.953125,
259
+ "learning_rate": 1.75942750807601e-05,
260
+ "loss": 2.1776,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.6100577081615829,
265
+ "grad_norm": 4.875,
266
+ "learning_rate": 1.7298892926134677e-05,
267
+ "loss": 2.1863,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 0.6265457543281121,
272
+ "grad_norm": 8.6875,
273
+ "learning_rate": 1.6989206735795634e-05,
274
+ "loss": 2.1821,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 0.6430338004946414,
279
+ "grad_norm": 3.6875,
280
+ "learning_rate": 1.666582341854016e-05,
281
+ "loss": 2.1375,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 0.6595218466611706,
286
+ "grad_norm": 8.0625,
287
+ "learning_rate": 1.632937672616678e-05,
288
+ "loss": 2.1396,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.6760098928277,
293
+ "grad_norm": 7.34375,
294
+ "learning_rate": 1.5980526011477654e-05,
295
+ "loss": 2.1137,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.6924979389942292,
300
+ "grad_norm": 3.1875,
301
+ "learning_rate": 1.5619954936109148e-05,
302
+ "loss": 2.1607,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 0.7089859851607585,
307
+ "grad_norm": 5.8125,
308
+ "learning_rate": 1.5248370130723151e-05,
309
+ "loss": 2.086,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 0.7254740313272877,
314
+ "grad_norm": 4.78125,
315
+ "learning_rate": 1.4866499810184662e-05,
316
+ "loss": 2.0821,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 0.7419620774938169,
321
+ "grad_norm": 6.4375,
322
+ "learning_rate": 1.4475092346439704e-05,
323
+ "loss": 2.0415,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 0.7584501236603463,
328
+ "grad_norm": 4.6875,
329
+ "learning_rate": 1.4074914801890294e-05,
330
+ "loss": 2.0471,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 0.7749381698268755,
335
+ "grad_norm": 7.9375,
336
+ "learning_rate": 1.366675142614072e-05,
337
+ "loss": 2.0638,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 0.7914262159934048,
342
+ "grad_norm": 4.03125,
343
+ "learning_rate": 1.3251402119061105e-05,
344
+ "loss": 2.0433,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 0.807914262159934,
349
+ "grad_norm": 3.625,
350
+ "learning_rate": 1.2829680863180345e-05,
351
+ "loss": 2.066,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 0.8244023083264633,
356
+ "grad_norm": 4.90625,
357
+ "learning_rate": 1.240241412848044e-05,
358
+ "loss": 2.0081,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 0.8408903544929925,
363
+ "grad_norm": 3.875,
364
+ "learning_rate": 1.1970439252718532e-05,
365
+ "loss": 2.0367,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 0.8573784006595219,
370
+ "grad_norm": 3.265625,
371
+ "learning_rate": 1.1534602800450757e-05,
372
+ "loss": 2.0784,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 0.8738664468260511,
377
+ "grad_norm": 6.84375,
378
+ "learning_rate": 1.1095758903973832e-05,
379
+ "loss": 1.9913,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 0.8903544929925804,
384
+ "grad_norm": 5.15625,
385
+ "learning_rate": 1.0654767589435762e-05,
386
+ "loss": 1.9759,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 0.9068425391591096,
391
+ "grad_norm": 5.71875,
392
+ "learning_rate": 1.0212493091396004e-05,
393
+ "loss": 2.0223,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 0.9233305853256389,
398
+ "grad_norm": 5.0625,
399
+ "learning_rate": 9.769802159138207e-06,
400
+ "loss": 2.0058,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 0.9398186314921682,
405
+ "grad_norm": 5.40625,
406
+ "learning_rate": 9.32756235805472e-06,
407
+ "loss": 1.9625,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 0.9563066776586975,
412
+ "grad_norm": 5.875,
413
+ "learning_rate": 8.88664036943168e-06,
414
+ "loss": 1.9904,
415
+ "step": 2900
416
+ },
417
+ {
418
+ "epoch": 0.9727947238252267,
419
+ "grad_norm": 5.3125,
420
+ "learning_rate": 8.447900291966801e-06,
421
+ "loss": 1.9552,
422
+ "step": 2950
423
+ },
424
+ {
425
+ "epoch": 0.989282769991756,
426
+ "grad_norm": 5.5625,
427
+ "learning_rate": 8.012201948348346e-06,
428
+ "loss": 1.9429,
429
+ "step": 3000
430
+ },
431
+ {
432
+ "epoch": 0.9998351195383347,
433
+ "eval_loss": 1.9353829622268677,
434
+ "eval_runtime": 69.7897,
435
+ "eval_samples_per_second": 23.342,
436
+ "eval_steps_per_second": 2.923,
437
+ "step": 3032
438
+ },
439
+ {
440
+ "epoch": 1.0057708161582852,
441
+ "grad_norm": 5.1875,
442
+ "learning_rate": 7.580399200214027e-06,
443
+ "loss": 1.9445,
444
+ "step": 3050
445
+ },
446
+ {
447
+ "epoch": 1.0222588623248146,
448
+ "grad_norm": 4.1875,
449
+ "learning_rate": 7.153338274792157e-06,
450
+ "loss": 1.8634,
451
+ "step": 3100
452
+ },
453
+ {
454
+ "epoch": 1.0387469084913439,
455
+ "grad_norm": 4.40625,
456
+ "learning_rate": 6.731856106504287e-06,
457
+ "loss": 1.8481,
458
+ "step": 3150
459
+ },
460
+ {
461
+ "epoch": 1.055234954657873,
462
+ "grad_norm": 6.9375,
463
+ "learning_rate": 6.316778696779516e-06,
464
+ "loss": 1.8474,
465
+ "step": 3200
466
+ },
467
+ {
468
+ "epoch": 1.0717230008244023,
469
+ "grad_norm": 6.875,
470
+ "learning_rate": 5.9089194952947645e-06,
471
+ "loss": 1.7904,
472
+ "step": 3250
473
+ },
474
+ {
475
+ "epoch": 1.0882110469909316,
476
+ "grad_norm": 3.796875,
477
+ "learning_rate": 5.509077805813386e-06,
478
+ "loss": 1.8357,
479
+ "step": 3300
480
+ },
481
+ {
482
+ "epoch": 1.104699093157461,
483
+ "grad_norm": 7.84375,
484
+ "learning_rate": 5.118037219746299e-06,
485
+ "loss": 1.8168,
486
+ "step": 3350
487
+ },
488
+ {
489
+ "epoch": 1.12118713932399,
490
+ "grad_norm": 5.25,
491
+ "learning_rate": 4.7365640805054684e-06,
492
+ "loss": 1.8304,
493
+ "step": 3400
494
+ },
495
+ {
496
+ "epoch": 1.1376751854905194,
497
+ "grad_norm": 4.75,
498
+ "learning_rate": 4.365405981659219e-06,
499
+ "loss": 1.8063,
500
+ "step": 3450
501
+ },
502
+ {
503
+ "epoch": 1.1541632316570487,
504
+ "grad_norm": 6.71875,
505
+ "learning_rate": 4.005290301832641e-06,
506
+ "loss": 1.8163,
507
+ "step": 3500
508
+ },
509
+ {
510
+ "epoch": 1.1706512778235778,
511
+ "grad_norm": 8.6875,
512
+ "learning_rate": 3.656922779224313e-06,
513
+ "loss": 1.7911,
514
+ "step": 3550
515
+ },
516
+ {
517
+ "epoch": 1.1871393239901071,
518
+ "grad_norm": 8.375,
519
+ "learning_rate": 3.3209861285329228e-06,
520
+ "loss": 1.8226,
521
+ "step": 3600
522
+ },
523
+ {
524
+ "epoch": 1.2036273701566365,
525
+ "grad_norm": 6.15625,
526
+ "learning_rate": 2.998138703004322e-06,
527
+ "loss": 1.7896,
528
+ "step": 3650
529
+ },
530
+ {
531
+ "epoch": 1.2201154163231658,
532
+ "grad_norm": 6.9375,
533
+ "learning_rate": 2.6890132042209973e-06,
534
+ "loss": 1.8121,
535
+ "step": 3700
536
+ },
537
+ {
538
+ "epoch": 1.2366034624896949,
539
+ "grad_norm": 6.84375,
540
+ "learning_rate": 2.394215442162542e-06,
541
+ "loss": 1.8081,
542
+ "step": 3750
543
+ },
544
+ {
545
+ "epoch": 1.2530915086562242,
546
+ "grad_norm": 4.21875,
547
+ "learning_rate": 2.114323147967009e-06,
548
+ "loss": 1.7445,
549
+ "step": 3800
550
+ },
551
+ {
552
+ "epoch": 1.2695795548227535,
553
+ "grad_norm": 5.53125,
554
+ "learning_rate": 1.8498848417199355e-06,
555
+ "loss": 1.7714,
556
+ "step": 3850
557
+ },
558
+ {
559
+ "epoch": 1.2860676009892829,
560
+ "grad_norm": 7.28125,
561
+ "learning_rate": 1.60141875748981e-06,
562
+ "loss": 1.8226,
563
+ "step": 3900
564
+ },
565
+ {
566
+ "epoch": 1.302555647155812,
567
+ "grad_norm": 4.96875,
568
+ "learning_rate": 1.3694118277167245e-06,
569
+ "loss": 1.8172,
570
+ "step": 3950
571
+ },
572
+ {
573
+ "epoch": 1.3190436933223413,
574
+ "grad_norm": 8.0,
575
+ "learning_rate": 1.1543187289444856e-06,
576
+ "loss": 1.807,
577
+ "step": 4000
578
+ },
579
+ {
580
+ "epoch": 1.3355317394888706,
581
+ "grad_norm": 9.5,
582
+ "learning_rate": 9.565609907663764e-07,
583
+ "loss": 1.8083,
584
+ "step": 4050
585
+ },
586
+ {
587
+ "epoch": 1.3520197856553997,
588
+ "grad_norm": 4.625,
589
+ "learning_rate": 7.765261697307935e-07,
590
+ "loss": 1.7861,
591
+ "step": 4100
592
+ },
593
+ {
594
+ "epoch": 1.368507831821929,
595
+ "grad_norm": 5.875,
596
+ "learning_rate": 6.145670898256784e-07,
597
+ "loss": 1.7685,
598
+ "step": 4150
599
+ },
600
+ {
601
+ "epoch": 1.3849958779884584,
602
+ "grad_norm": 8.0625,
603
+ "learning_rate": 4.710011510302592e-07,
604
+ "loss": 1.7573,
605
+ "step": 4200
606
+ },
607
+ {
608
+ "epoch": 1.4014839241549877,
609
+ "grad_norm": 5.3125,
610
+ "learning_rate": 3.461097072891073e-07,
611
+ "loss": 1.7886,
612
+ "step": 4250
613
+ },
614
+ {
615
+ "epoch": 1.417971970321517,
616
+ "grad_norm": 9.1875,
617
+ "learning_rate": 2.401375151275864e-07,
618
+ "loss": 1.7796,
619
+ "step": 4300
620
+ },
621
+ {
622
+ "epoch": 1.434460016488046,
623
+ "grad_norm": 5.65625,
624
+ "learning_rate": 1.5329225398923232e-07,
625
+ "loss": 1.7321,
626
+ "step": 4350
627
+ },
628
+ {
629
+ "epoch": 1.4509480626545754,
630
+ "grad_norm": 7.40625,
631
+ "learning_rate": 8.574411923510384e-08,
632
+ "loss": 1.7338,
633
+ "step": 4400
634
+ },
635
+ {
636
+ "epoch": 1.4674361088211048,
637
+ "grad_norm": 8.1875,
638
+ "learning_rate": 3.7625488602711645e-08,
639
+ "loss": 1.7685,
640
+ "step": 4450
641
+ },
642
+ {
643
+ "epoch": 1.4839241549876339,
644
+ "grad_norm": 7.6875,
645
+ "learning_rate": 9.030662778205523e-09,
646
+ "loss": 1.7568,
647
+ "step": 4500
648
+ },
649
+ {
650
+ "epoch": 1.499752679307502,
651
+ "eval_loss": 1.843124270439148,
652
+ "eval_runtime": 69.2635,
653
+ "eval_samples_per_second": 23.519,
654
+ "eval_steps_per_second": 2.945,
655
+ "step": 4548
656
+ }
657
+ ],
658
+ "logging_steps": 50,
659
+ "max_steps": 4548,
660
+ "num_input_tokens_seen": 0,
661
+ "num_train_epochs": 2,
662
+ "save_steps": 500,
663
+ "stateful_callbacks": {
664
+ "TrainerControl": {
665
+ "args": {
666
+ "should_epoch_stop": false,
667
+ "should_evaluate": false,
668
+ "should_log": false,
669
+ "should_save": true,
670
+ "should_training_stop": true
671
+ },
672
+ "attributes": {}
673
+ }
674
+ },
675
+ "total_flos": 5.863939305520497e+17,
676
+ "train_batch_size": 8,
677
+ "trial_name": null,
678
+ "trial_params": null
679
+ }
checkpoint-4548/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:067fcca4b639e1227036ee31669835301fff03559a3de4a3d1fe926e551bc124
3
+ size 5432
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-1.4b",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "partial_rotary_factor": 0.25,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "rotary_emb_base": 10000,
25
+ "rotary_pct": 0.25,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.45.0",
29
+ "use_cache": false,
30
+ "use_parallel_residual": true,
31
+ "vocab_size": 50304
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.45.0",
6
+ "use_cache": false
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dec95f92814372913b8e98caf8077087bc0c5cfeb373e8267e14ce7739a252d
3
+ size 2829330208
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ }
206
+ },
207
+ "bos_token": "<|endoftext|>",
208
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
209
+ "clean_up_tokenization_spaces": true,
210
+ "eos_token": "<|endoftext|>",
211
+ "model_max_length": 1000000000000000019884624838656,
212
+ "pad_token": "<|endoftext|>",
213
+ "tokenizer_class": "GPTNeoXTokenizer",
214
+ "unk_token": "<|endoftext|>"
215
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:067fcca4b639e1227036ee31669835301fff03559a3de4a3d1fe926e551bc124
3
+ size 5432