TinyPixel commited on
Commit
d39f68d
1 Parent(s): ab8d5d1

Upload folder using huggingface_hub

Browse files
adapter_config.json CHANGED
@@ -19,10 +19,10 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "dense_h_to_4h",
23
  "dense_4h_to_h",
24
- "query_key_value",
25
- "dense"
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "dense_4h_to_h",
23
+ "dense_h_to_4h",
24
+ "dense",
25
+ "query_key_value"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eecf8169c8be3e35abd4e96a249f53f09943c4687bd081b243b2fef88018cbde
3
  size 134235712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4461c4aed665c1b53a42c76c7a6ff93770827a9bfdcea098c7c1c6a9d4654f
3
  size 134235712
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8492d69578283b2fc86e2d03895bd7c0781b214da6715927578401f47e03f371
3
  size 268514874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb92441d99d23b1bebf1edf2c5306c4997e94ea824d3faea4948b66a6a98ef8
3
  size 268514874
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0cfda1a5b08c3e9214d276266e233a8a53d309b6ebd855baaf595daae3aeb47
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca077bd60595fe183ed3eac1c31057bc0e4041f85096470d60a5ead003f3b02c
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31ea39dd85d8fdd7963ae8fca104a21064c32ab31d9951bd542c75f5d686bcc7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824a429c5f95423b97fd2ff7dc1e1dffcd96691286babb37392f00bfcecaeb1b
3
  size 1064
special_tokens_map.json CHANGED
@@ -14,7 +14,7 @@
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "<|endoftext|>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
 
14
  "single_word": false
15
  },
16
  "pad_token": {
17
+ "content": "[PAD]",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
tokenizer.json CHANGED
@@ -232,6 +232,15 @@
232
  "rstrip": false,
233
  "normalized": true,
234
  "special": false
 
 
 
 
 
 
 
 
 
235
  }
236
  ],
237
  "normalizer": {
 
232
  "rstrip": false,
233
  "normalized": true,
234
  "special": false
235
+ },
236
+ {
237
+ "id": 50277,
238
+ "content": "[PAD]",
239
+ "single_word": false,
240
+ "lstrip": false,
241
+ "rstrip": false,
242
+ "normalized": false,
243
+ "special": true
244
  }
245
  ],
246
  "normalizer": {
tokenizer_config.json CHANGED
@@ -200,13 +200,21 @@
200
  "rstrip": false,
201
  "single_word": false,
202
  "special": false
 
 
 
 
 
 
 
 
203
  }
204
  },
205
  "bos_token": "<|endoftext|>",
206
  "clean_up_tokenization_spaces": true,
207
  "eos_token": "<|endoftext|>",
208
  "model_max_length": 1000000000000000019884624838656,
209
- "pad_token": "<|endoftext|>",
210
  "tokenizer_class": "GPTNeoXTokenizer",
211
  "unk_token": "<|endoftext|>"
212
  }
 
200
  "rstrip": false,
201
  "single_word": false,
202
  "special": false
203
+ },
204
+ "50277": {
205
+ "content": "[PAD]",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
  }
212
  },
213
  "bos_token": "<|endoftext|>",
214
  "clean_up_tokenization_spaces": true,
215
  "eos_token": "<|endoftext|>",
216
  "model_max_length": 1000000000000000019884624838656,
217
+ "pad_token": "[PAD]",
218
  "tokenizer_class": "GPTNeoXTokenizer",
219
  "unk_token": "<|endoftext|>"
220
  }
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.9972041006523766,
5
  "eval_steps": 500,
6
- "global_step": 201,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -11,610 +11,208 @@
11
  {
12
  "epoch": 0.03,
13
  "learning_rate": 0.0002,
14
- "loss": 2.2476,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.06,
19
  "learning_rate": 0.0002,
20
- "loss": 2.2095,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.09,
25
  "learning_rate": 0.0002,
26
- "loss": 1.7971,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.12,
31
  "learning_rate": 0.0002,
32
- "loss": 1.7855,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.15,
37
  "learning_rate": 0.0002,
38
- "loss": 1.5748,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.18,
43
  "learning_rate": 0.0002,
44
- "loss": 1.514,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.21,
49
  "learning_rate": 0.0002,
50
- "loss": 2.0154,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.24,
55
  "learning_rate": 0.0002,
56
- "loss": 2.0265,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.27,
61
  "learning_rate": 0.0002,
62
- "loss": 2.2248,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.3,
67
  "learning_rate": 0.0002,
68
- "loss": 1.6516,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.33,
73
  "learning_rate": 0.0002,
74
- "loss": 1.7012,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.36,
79
  "learning_rate": 0.0002,
80
- "loss": 1.7529,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.39,
85
  "learning_rate": 0.0002,
86
- "loss": 1.6224,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.42,
91
  "learning_rate": 0.0002,
92
- "loss": 1.5869,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.45,
97
  "learning_rate": 0.0002,
98
- "loss": 1.7821,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.48,
103
  "learning_rate": 0.0002,
104
- "loss": 1.8414,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.51,
109
  "learning_rate": 0.0002,
110
- "loss": 2.5965,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 0.54,
115
  "learning_rate": 0.0002,
116
- "loss": 1.8098,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 0.57,
121
  "learning_rate": 0.0002,
122
- "loss": 1.6632,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 0.6,
127
  "learning_rate": 0.0002,
128
- "loss": 1.7756,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 0.63,
133
  "learning_rate": 0.0002,
134
- "loss": 1.5594,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 0.66,
139
  "learning_rate": 0.0002,
140
- "loss": 1.6928,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 0.69,
145
  "learning_rate": 0.0002,
146
- "loss": 1.7223,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 0.72,
151
  "learning_rate": 0.0002,
152
- "loss": 1.5006,
153
  "step": 48
154
  },
155
  {
156
  "epoch": 0.75,
157
  "learning_rate": 0.0002,
158
- "loss": 2.3682,
159
  "step": 50
160
  },
161
  {
162
  "epoch": 0.78,
163
  "learning_rate": 0.0002,
164
- "loss": 1.9393,
165
  "step": 52
166
  },
167
  {
168
  "epoch": 0.81,
169
  "learning_rate": 0.0002,
170
- "loss": 1.823,
171
  "step": 54
172
  },
173
  {
174
  "epoch": 0.84,
175
  "learning_rate": 0.0002,
176
- "loss": 1.6966,
177
  "step": 56
178
  },
179
  {
180
  "epoch": 0.86,
181
  "learning_rate": 0.0002,
182
- "loss": 1.5331,
183
  "step": 58
184
  },
185
  {
186
  "epoch": 0.89,
187
  "learning_rate": 0.0002,
188
- "loss": 1.5971,
189
  "step": 60
190
  },
191
  {
192
  "epoch": 0.92,
193
  "learning_rate": 0.0002,
194
- "loss": 1.7346,
195
  "step": 62
196
  },
197
  {
198
  "epoch": 0.95,
199
  "learning_rate": 0.0002,
200
- "loss": 1.6502,
201
  "step": 64
202
  },
203
  {
204
  "epoch": 0.98,
205
  "learning_rate": 0.0002,
206
- "loss": 1.7093,
207
  "step": 66
208
- },
209
- {
210
- "epoch": 1.01,
211
- "learning_rate": 0.0002,
212
- "loss": 1.9674,
213
- "step": 68
214
- },
215
- {
216
- "epoch": 1.04,
217
- "learning_rate": 0.0002,
218
- "loss": 2.1178,
219
- "step": 70
220
- },
221
- {
222
- "epoch": 1.07,
223
- "learning_rate": 0.0002,
224
- "loss": 1.6422,
225
- "step": 72
226
- },
227
- {
228
- "epoch": 1.1,
229
- "learning_rate": 0.0002,
230
- "loss": 1.5777,
231
- "step": 74
232
- },
233
- {
234
- "epoch": 1.13,
235
- "learning_rate": 0.0002,
236
- "loss": 1.6813,
237
- "step": 76
238
- },
239
- {
240
- "epoch": 1.16,
241
- "learning_rate": 0.0002,
242
- "loss": 1.4568,
243
- "step": 78
244
- },
245
- {
246
- "epoch": 1.19,
247
- "learning_rate": 0.0002,
248
- "loss": 1.4511,
249
- "step": 80
250
- },
251
- {
252
- "epoch": 1.22,
253
- "learning_rate": 0.0002,
254
- "loss": 1.6265,
255
- "step": 82
256
- },
257
- {
258
- "epoch": 1.25,
259
- "learning_rate": 0.0002,
260
- "loss": 1.2337,
261
- "step": 84
262
- },
263
- {
264
- "epoch": 1.28,
265
- "learning_rate": 0.0002,
266
- "loss": 2.0693,
267
- "step": 86
268
- },
269
- {
270
- "epoch": 1.31,
271
- "learning_rate": 0.0002,
272
- "loss": 1.6134,
273
- "step": 88
274
- },
275
- {
276
- "epoch": 1.34,
277
- "learning_rate": 0.0002,
278
- "loss": 1.5955,
279
- "step": 90
280
- },
281
- {
282
- "epoch": 1.37,
283
- "learning_rate": 0.0002,
284
- "loss": 1.4866,
285
- "step": 92
286
- },
287
- {
288
- "epoch": 1.4,
289
- "learning_rate": 0.0002,
290
- "loss": 1.4122,
291
- "step": 94
292
- },
293
- {
294
- "epoch": 1.43,
295
- "learning_rate": 0.0002,
296
- "loss": 1.4224,
297
- "step": 96
298
- },
299
- {
300
- "epoch": 1.46,
301
- "learning_rate": 0.0002,
302
- "loss": 1.5695,
303
- "step": 98
304
- },
305
- {
306
- "epoch": 1.49,
307
- "learning_rate": 0.0002,
308
- "loss": 1.7786,
309
- "step": 100
310
- },
311
- {
312
- "epoch": 1.52,
313
- "learning_rate": 0.0002,
314
- "loss": 2.3576,
315
- "step": 102
316
- },
317
- {
318
- "epoch": 1.55,
319
- "learning_rate": 0.0002,
320
- "loss": 1.6475,
321
- "step": 104
322
- },
323
- {
324
- "epoch": 1.58,
325
- "learning_rate": 0.0002,
326
- "loss": 1.7765,
327
- "step": 106
328
- },
329
- {
330
- "epoch": 1.61,
331
- "learning_rate": 0.0002,
332
- "loss": 1.5304,
333
- "step": 108
334
- },
335
- {
336
- "epoch": 1.64,
337
- "learning_rate": 0.0002,
338
- "loss": 1.33,
339
- "step": 110
340
- },
341
- {
342
- "epoch": 1.67,
343
- "learning_rate": 0.0002,
344
- "loss": 1.4141,
345
- "step": 112
346
- },
347
- {
348
- "epoch": 1.7,
349
- "learning_rate": 0.0002,
350
- "loss": 1.5615,
351
- "step": 114
352
- },
353
- {
354
- "epoch": 1.73,
355
- "learning_rate": 0.0002,
356
- "loss": 1.5599,
357
- "step": 116
358
- },
359
- {
360
- "epoch": 1.76,
361
- "learning_rate": 0.0002,
362
- "loss": 2.1615,
363
- "step": 118
364
- },
365
- {
366
- "epoch": 1.79,
367
- "learning_rate": 0.0002,
368
- "loss": 1.6991,
369
- "step": 120
370
- },
371
- {
372
- "epoch": 1.82,
373
- "learning_rate": 0.0002,
374
- "loss": 1.6502,
375
- "step": 122
376
- },
377
- {
378
- "epoch": 1.85,
379
- "learning_rate": 0.0002,
380
- "loss": 1.5974,
381
- "step": 124
382
- },
383
- {
384
- "epoch": 1.88,
385
- "learning_rate": 0.0002,
386
- "loss": 1.2396,
387
- "step": 126
388
- },
389
- {
390
- "epoch": 1.91,
391
- "learning_rate": 0.0002,
392
- "loss": 1.3839,
393
- "step": 128
394
- },
395
- {
396
- "epoch": 1.94,
397
- "learning_rate": 0.0002,
398
- "loss": 1.5737,
399
- "step": 130
400
- },
401
- {
402
- "epoch": 1.97,
403
- "learning_rate": 0.0002,
404
- "loss": 1.5733,
405
- "step": 132
406
- },
407
- {
408
- "epoch": 2.0,
409
- "learning_rate": 0.0002,
410
- "loss": 1.369,
411
- "step": 134
412
- },
413
- {
414
- "epoch": 2.03,
415
- "learning_rate": 0.0002,
416
- "loss": 2.2205,
417
- "step": 136
418
- },
419
- {
420
- "epoch": 2.06,
421
- "learning_rate": 0.0002,
422
- "loss": 2.0597,
423
- "step": 138
424
- },
425
- {
426
- "epoch": 2.09,
427
- "learning_rate": 0.0002,
428
- "loss": 1.5924,
429
- "step": 140
430
- },
431
- {
432
- "epoch": 2.12,
433
- "learning_rate": 0.0002,
434
- "loss": 1.5504,
435
- "step": 142
436
- },
437
- {
438
- "epoch": 2.15,
439
- "learning_rate": 0.0002,
440
- "loss": 1.4464,
441
- "step": 144
442
- },
443
- {
444
- "epoch": 2.18,
445
- "learning_rate": 0.0002,
446
- "loss": 1.3526,
447
- "step": 146
448
- },
449
- {
450
- "epoch": 2.21,
451
- "learning_rate": 0.0002,
452
- "loss": 1.2872,
453
- "step": 148
454
- },
455
- {
456
- "epoch": 2.24,
457
- "learning_rate": 0.0002,
458
- "loss": 1.139,
459
- "step": 150
460
- },
461
- {
462
- "epoch": 2.27,
463
- "learning_rate": 0.0002,
464
- "loss": 2.0427,
465
- "step": 152
466
- },
467
- {
468
- "epoch": 2.3,
469
- "learning_rate": 0.0002,
470
- "loss": 1.7152,
471
- "step": 154
472
- },
473
- {
474
- "epoch": 2.33,
475
- "learning_rate": 0.0002,
476
- "loss": 1.6782,
477
- "step": 156
478
- },
479
- {
480
- "epoch": 2.36,
481
- "learning_rate": 0.0002,
482
- "loss": 1.5993,
483
- "step": 158
484
- },
485
- {
486
- "epoch": 2.39,
487
- "learning_rate": 0.0002,
488
- "loss": 1.5009,
489
- "step": 160
490
- },
491
- {
492
- "epoch": 2.42,
493
- "learning_rate": 0.0002,
494
- "loss": 1.2242,
495
- "step": 162
496
- },
497
- {
498
- "epoch": 2.45,
499
- "learning_rate": 0.0002,
500
- "loss": 1.3298,
501
- "step": 164
502
- },
503
- {
504
- "epoch": 2.48,
505
- "learning_rate": 0.0002,
506
- "loss": 1.159,
507
- "step": 166
508
- },
509
- {
510
- "epoch": 2.51,
511
- "learning_rate": 0.0002,
512
- "loss": 2.0425,
513
- "step": 168
514
- },
515
- {
516
- "epoch": 2.53,
517
- "learning_rate": 0.0002,
518
- "loss": 1.7428,
519
- "step": 170
520
- },
521
- {
522
- "epoch": 2.56,
523
- "learning_rate": 0.0002,
524
- "loss": 1.6052,
525
- "step": 172
526
- },
527
- {
528
- "epoch": 2.59,
529
- "learning_rate": 0.0002,
530
- "loss": 1.5935,
531
- "step": 174
532
- },
533
- {
534
- "epoch": 2.62,
535
- "learning_rate": 0.0002,
536
- "loss": 1.3055,
537
- "step": 176
538
- },
539
- {
540
- "epoch": 2.65,
541
- "learning_rate": 0.0002,
542
- "loss": 1.1967,
543
- "step": 178
544
- },
545
- {
546
- "epoch": 2.68,
547
- "learning_rate": 0.0002,
548
- "loss": 1.3355,
549
- "step": 180
550
- },
551
- {
552
- "epoch": 2.71,
553
- "learning_rate": 0.0002,
554
- "loss": 1.0649,
555
- "step": 182
556
- },
557
- {
558
- "epoch": 2.74,
559
- "learning_rate": 0.0002,
560
- "loss": 2.3474,
561
- "step": 184
562
- },
563
- {
564
- "epoch": 2.77,
565
- "learning_rate": 0.0002,
566
- "loss": 1.6763,
567
- "step": 186
568
- },
569
- {
570
- "epoch": 2.8,
571
- "learning_rate": 0.0002,
572
- "loss": 1.5105,
573
- "step": 188
574
- },
575
- {
576
- "epoch": 2.83,
577
- "learning_rate": 0.0002,
578
- "loss": 1.5544,
579
- "step": 190
580
- },
581
- {
582
- "epoch": 2.86,
583
- "learning_rate": 0.0002,
584
- "loss": 1.1297,
585
- "step": 192
586
- },
587
- {
588
- "epoch": 2.89,
589
- "learning_rate": 0.0002,
590
- "loss": 1.2825,
591
- "step": 194
592
- },
593
- {
594
- "epoch": 2.92,
595
- "learning_rate": 0.0002,
596
- "loss": 1.3587,
597
- "step": 196
598
- },
599
- {
600
- "epoch": 2.95,
601
- "learning_rate": 0.0002,
602
- "loss": 1.2585,
603
- "step": 198
604
- },
605
- {
606
- "epoch": 2.98,
607
- "learning_rate": 0.0002,
608
- "loss": 1.3599,
609
- "step": 200
610
  }
611
  ],
612
  "logging_steps": 2,
613
- "max_steps": 201,
614
  "num_input_tokens_seen": 0,
615
- "num_train_epochs": 3,
616
  "save_steps": 500,
617
- "total_flos": 8906354934939648.0,
618
  "train_batch_size": 1,
619
  "trial_name": null,
620
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9990680335507922,
5
  "eval_steps": 500,
6
+ "global_step": 67,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
11
  {
12
  "epoch": 0.03,
13
  "learning_rate": 0.0002,
14
+ "loss": 2.4703,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.06,
19
  "learning_rate": 0.0002,
20
+ "loss": 2.1197,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.09,
25
  "learning_rate": 0.0002,
26
+ "loss": 1.7723,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.12,
31
  "learning_rate": 0.0002,
32
+ "loss": 1.7626,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.15,
37
  "learning_rate": 0.0002,
38
+ "loss": 1.852,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.18,
43
  "learning_rate": 0.0002,
44
+ "loss": 1.8027,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.21,
49
  "learning_rate": 0.0002,
50
+ "loss": 1.9243,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.24,
55
  "learning_rate": 0.0002,
56
+ "loss": 2.0395,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.27,
61
  "learning_rate": 0.0002,
62
+ "loss": 2.0185,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.3,
67
  "learning_rate": 0.0002,
68
+ "loss": 1.7649,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.33,
73
  "learning_rate": 0.0002,
74
+ "loss": 1.884,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.36,
79
  "learning_rate": 0.0002,
80
+ "loss": 1.7038,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.39,
85
  "learning_rate": 0.0002,
86
+ "loss": 1.4675,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.42,
91
  "learning_rate": 0.0002,
92
+ "loss": 1.6643,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.45,
97
  "learning_rate": 0.0002,
98
+ "loss": 1.8479,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.48,
103
  "learning_rate": 0.0002,
104
+ "loss": 1.7631,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.51,
109
  "learning_rate": 0.0002,
110
+ "loss": 2.289,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 0.54,
115
  "learning_rate": 0.0002,
116
+ "loss": 1.7244,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 0.57,
121
  "learning_rate": 0.0002,
122
+ "loss": 1.6199,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 0.6,
127
  "learning_rate": 0.0002,
128
+ "loss": 1.8003,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 0.63,
133
  "learning_rate": 0.0002,
134
+ "loss": 1.3866,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 0.66,
139
  "learning_rate": 0.0002,
140
+ "loss": 1.5901,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 0.69,
145
  "learning_rate": 0.0002,
146
+ "loss": 1.7516,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 0.72,
151
  "learning_rate": 0.0002,
152
+ "loss": 1.5123,
153
  "step": 48
154
  },
155
  {
156
  "epoch": 0.75,
157
  "learning_rate": 0.0002,
158
+ "loss": 2.5375,
159
  "step": 50
160
  },
161
  {
162
  "epoch": 0.78,
163
  "learning_rate": 0.0002,
164
+ "loss": 1.8782,
165
  "step": 52
166
  },
167
  {
168
  "epoch": 0.81,
169
  "learning_rate": 0.0002,
170
+ "loss": 1.7455,
171
  "step": 54
172
  },
173
  {
174
  "epoch": 0.84,
175
  "learning_rate": 0.0002,
176
+ "loss": 1.7001,
177
  "step": 56
178
  },
179
  {
180
  "epoch": 0.86,
181
  "learning_rate": 0.0002,
182
+ "loss": 1.345,
183
  "step": 58
184
  },
185
  {
186
  "epoch": 0.89,
187
  "learning_rate": 0.0002,
188
+ "loss": 1.5965,
189
  "step": 60
190
  },
191
  {
192
  "epoch": 0.92,
193
  "learning_rate": 0.0002,
194
+ "loss": 1.7818,
195
  "step": 62
196
  },
197
  {
198
  "epoch": 0.95,
199
  "learning_rate": 0.0002,
200
+ "loss": 1.5499,
201
  "step": 64
202
  },
203
  {
204
  "epoch": 0.98,
205
  "learning_rate": 0.0002,
206
+ "loss": 1.9485,
207
  "step": 66
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
208
  }
209
  ],
210
  "logging_steps": 2,
211
+ "max_steps": 67,
212
  "num_input_tokens_seen": 0,
213
+ "num_train_epochs": 1,
214
  "save_steps": 500,
215
+ "total_flos": 2968886748168192.0,
216
  "train_batch_size": 1,
217
  "trial_name": null,
218
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f041775d0619e837f65da19fcf4653910fa859003661bfbb706e65bc69371e51
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c76c61090f9e71a3620f025aebcf947d167dd8bd4dc37e6f751e6fce36fd3e
3
  size 4728