Namronaldo2004 commited on
Commit
cc14b49
1 Parent(s): 68b3bbd

Update fine-tuned model

Browse files
adapter_config.json CHANGED
@@ -23,12 +23,12 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "down_proj",
27
- "gate_proj",
28
  "k_proj",
 
29
  "q_proj",
30
- "up_proj",
31
  "v_proj",
 
32
  "o_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
26
  "k_proj",
27
+ "gate_proj",
28
  "q_proj",
29
+ "down_proj",
30
  "v_proj",
31
+ "up_proj",
32
  "o_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65a9b6fce1d1506245ada6cd6cc5bfb0ef2cdd9c2c78996f0803adae549838ac
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4da9de7e6a0c855646daa4e8692b61bf593a9e5db24ad71f56b011fd878c8a3
3
  size 159967880
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:531cd8170804b0d605ebdec62107cbfe6d624275f519dd398f6877ebdcd05998
3
  size 852876198
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a93b54fda0e2952d60fd2423d8d212c30612413fbad1598c7e439365d4fa8fc
3
  size 852876198
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:810e51c11eccf7079911fb19c661eb0958cecaa5dc69603ed03fa1e25ccf5bca
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:042eeaadaa77e55313f6c5e71c307c518f1290d990d00304e40386bd32b1d3e0
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
3
  size 1064
trainer_state.json CHANGED
@@ -1,718 +1,298 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.02,
13
- "grad_norm": 0.600925862789154,
14
- "learning_rate": 4e-05,
15
- "loss": 0.4307,
16
  "step": 1
17
  },
18
  {
19
- "epoch": 0.04,
20
- "grad_norm": 0.6059685349464417,
21
- "learning_rate": 8e-05,
22
- "loss": 0.4353,
23
  "step": 2
24
  },
25
  {
26
- "epoch": 0.06,
27
- "grad_norm": 0.5777328014373779,
28
- "learning_rate": 0.00012,
29
- "loss": 0.421,
30
  "step": 3
31
  },
32
  {
33
- "epoch": 0.08,
34
- "grad_norm": 0.548288106918335,
35
- "learning_rate": 0.00016,
36
- "loss": 0.4029,
37
  "step": 4
38
  },
39
  {
40
- "epoch": 0.1,
41
- "grad_norm": 0.4978249967098236,
42
- "learning_rate": 0.0002,
43
- "loss": 0.4102,
44
  "step": 5
45
  },
46
  {
47
- "epoch": 0.12,
48
- "grad_norm": 0.5470420718193054,
49
- "learning_rate": 0.00019994532573409262,
50
- "loss": 0.4123,
51
  "step": 6
52
  },
53
  {
54
- "epoch": 0.14,
55
- "grad_norm": 0.5333985686302185,
56
- "learning_rate": 0.00019978136272187747,
57
- "loss": 0.3966,
58
  "step": 7
59
  },
60
  {
61
- "epoch": 0.16,
62
- "grad_norm": 0.4586232304573059,
63
- "learning_rate": 0.00019950829025450114,
64
- "loss": 0.377,
65
  "step": 8
66
  },
67
  {
68
- "epoch": 0.18,
69
- "grad_norm": 0.49000784754753113,
70
- "learning_rate": 0.00019912640693269752,
71
- "loss": 0.3785,
72
  "step": 9
73
  },
74
  {
75
- "epoch": 0.2,
76
- "grad_norm": 0.45979875326156616,
77
- "learning_rate": 0.00019863613034027224,
78
- "loss": 0.3957,
79
  "step": 10
80
  },
81
  {
82
- "epoch": 0.22,
83
- "grad_norm": 0.4552418887615204,
84
- "learning_rate": 0.00019803799658748094,
85
- "loss": 0.3921,
86
  "step": 11
87
  },
88
  {
89
- "epoch": 0.24,
90
- "grad_norm": 0.4663061201572418,
91
- "learning_rate": 0.0001973326597248006,
92
- "loss": 0.3896,
93
  "step": 12
94
  },
95
  {
96
- "epoch": 0.26,
97
- "grad_norm": 0.4285649359226227,
98
- "learning_rate": 0.00019652089102773488,
99
- "loss": 0.349,
100
  "step": 13
101
  },
102
  {
103
- "epoch": 0.28,
104
- "grad_norm": 0.45254892110824585,
105
- "learning_rate": 0.00019560357815343577,
106
- "loss": 0.3685,
107
  "step": 14
108
  },
109
  {
110
- "epoch": 0.3,
111
- "grad_norm": 0.4699627459049225,
112
- "learning_rate": 0.00019458172417006347,
113
- "loss": 0.3765,
114
  "step": 15
115
  },
116
  {
117
- "epoch": 0.32,
118
- "grad_norm": 0.4629937708377838,
119
- "learning_rate": 0.0001934564464599461,
120
- "loss": 0.3567,
121
  "step": 16
122
  },
123
  {
124
- "epoch": 0.34,
125
- "grad_norm": 0.44340917468070984,
126
- "learning_rate": 0.00019222897549773848,
127
- "loss": 0.3742,
128
  "step": 17
129
  },
130
  {
131
- "epoch": 0.36,
132
- "grad_norm": 0.48120179772377014,
133
- "learning_rate": 0.00019090065350491626,
134
- "loss": 0.3507,
135
  "step": 18
136
  },
137
  {
138
- "epoch": 0.38,
139
- "grad_norm": 0.4626652002334595,
140
- "learning_rate": 0.00018947293298207635,
141
- "loss": 0.3637,
142
  "step": 19
143
  },
144
  {
145
- "epoch": 0.4,
146
- "grad_norm": 0.4551631808280945,
147
- "learning_rate": 0.0001879473751206489,
148
- "loss": 0.3588,
149
  "step": 20
150
  },
151
  {
152
- "epoch": 0.42,
153
- "grad_norm": 0.47978681325912476,
154
- "learning_rate": 0.00018632564809575742,
155
- "loss": 0.3631,
156
  "step": 21
157
  },
158
  {
159
- "epoch": 0.44,
160
- "grad_norm": 0.44357830286026,
161
- "learning_rate": 0.00018460952524209355,
162
- "loss": 0.3634,
163
  "step": 22
164
  },
165
  {
166
- "epoch": 0.46,
167
- "grad_norm": 0.4979308247566223,
168
- "learning_rate": 0.00018280088311480201,
169
- "loss": 0.3497,
170
  "step": 23
171
  },
172
  {
173
- "epoch": 0.48,
174
- "grad_norm": 0.4785916805267334,
175
- "learning_rate": 0.00018090169943749476,
176
- "loss": 0.3506,
177
  "step": 24
178
  },
179
  {
180
- "epoch": 0.5,
181
- "grad_norm": 0.45637139678001404,
182
- "learning_rate": 0.00017891405093963938,
183
- "loss": 0.3621,
184
  "step": 25
185
  },
186
  {
187
- "epoch": 0.52,
188
- "grad_norm": 0.4222208261489868,
189
- "learning_rate": 0.00017684011108568592,
190
- "loss": 0.333,
191
  "step": 26
192
  },
193
  {
194
- "epoch": 0.54,
195
- "grad_norm": 0.4473680555820465,
196
- "learning_rate": 0.0001746821476984154,
197
- "loss": 0.3384,
198
  "step": 27
199
  },
200
  {
201
- "epoch": 0.56,
202
- "grad_norm": 0.45950424671173096,
203
- "learning_rate": 0.00017244252047910892,
204
- "loss": 0.3396,
205
  "step": 28
206
  },
207
  {
208
- "epoch": 0.58,
209
- "grad_norm": 0.4503507614135742,
210
- "learning_rate": 0.00017012367842724887,
211
- "loss": 0.3907,
212
  "step": 29
213
  },
214
  {
215
- "epoch": 0.6,
216
- "grad_norm": 0.4551246166229248,
217
- "learning_rate": 0.00016772815716257412,
218
- "loss": 0.3413,
219
  "step": 30
220
  },
221
  {
222
- "epoch": 0.62,
223
- "grad_norm": 0.42266467213630676,
224
- "learning_rate": 0.00016525857615241687,
225
- "loss": 0.3402,
226
  "step": 31
227
  },
228
  {
229
- "epoch": 0.64,
230
- "grad_norm": 0.473186194896698,
231
- "learning_rate": 0.0001627176358473537,
232
- "loss": 0.3515,
233
  "step": 32
234
  },
235
  {
236
- "epoch": 0.66,
237
- "grad_norm": 0.42668187618255615,
238
- "learning_rate": 0.00016010811472830252,
239
- "loss": 0.3148,
240
  "step": 33
241
  },
242
  {
243
- "epoch": 0.68,
244
- "grad_norm": 0.424800306558609,
245
- "learning_rate": 0.00015743286626829437,
246
- "loss": 0.3224,
247
  "step": 34
248
  },
249
  {
250
- "epoch": 0.7,
251
- "grad_norm": 0.43106356263160706,
252
- "learning_rate": 0.00015469481581224272,
253
- "loss": 0.3143,
254
  "step": 35
255
  },
256
  {
257
- "epoch": 0.72,
258
- "grad_norm": 0.4076085090637207,
259
- "learning_rate": 0.00015189695737812152,
260
- "loss": 0.3329,
261
  "step": 36
262
  },
263
  {
264
- "epoch": 0.74,
265
- "grad_norm": 0.4057788550853729,
266
- "learning_rate": 0.00014904235038305083,
267
- "loss": 0.3389,
268
  "step": 37
269
  },
270
  {
271
- "epoch": 0.76,
272
- "grad_norm": 0.4162575900554657,
273
- "learning_rate": 0.0001461341162978688,
274
- "loss": 0.3268,
275
  "step": 38
276
  },
277
  {
278
- "epoch": 0.78,
279
- "grad_norm": 0.42211902141571045,
280
- "learning_rate": 0.00014317543523384928,
281
- "loss": 0.2971,
282
  "step": 39
283
  },
284
  {
285
- "epoch": 0.8,
286
- "grad_norm": 0.42816001176834106,
287
- "learning_rate": 0.00014016954246529696,
288
- "loss": 0.3303,
289
- "step": 40
290
- },
291
- {
292
- "epoch": 0.82,
293
- "grad_norm": 0.4197749197483063,
294
- "learning_rate": 0.00013711972489182208,
295
- "loss": 0.3443,
296
- "step": 41
297
- },
298
- {
299
- "epoch": 0.84,
300
- "grad_norm": 0.41594424843788147,
301
- "learning_rate": 0.00013402931744416433,
302
- "loss": 0.3417,
303
- "step": 42
304
- },
305
- {
306
- "epoch": 0.86,
307
- "grad_norm": 0.41279336810112,
308
- "learning_rate": 0.00013090169943749476,
309
- "loss": 0.3252,
310
- "step": 43
311
- },
312
- {
313
- "epoch": 0.88,
314
- "grad_norm": 0.42070260643959045,
315
- "learning_rate": 0.00012774029087618446,
316
- "loss": 0.3107,
317
- "step": 44
318
- },
319
- {
320
- "epoch": 0.9,
321
- "grad_norm": 0.4160784184932709,
322
- "learning_rate": 0.00012454854871407994,
323
- "loss": 0.3253,
324
- "step": 45
325
- },
326
- {
327
- "epoch": 0.92,
328
- "grad_norm": 0.4144185483455658,
329
- "learning_rate": 0.0001213299630743747,
330
- "loss": 0.3251,
331
- "step": 46
332
- },
333
- {
334
- "epoch": 0.94,
335
- "grad_norm": 0.3940325081348419,
336
- "learning_rate": 0.000118088053433211,
337
- "loss": 0.3234,
338
- "step": 47
339
- },
340
- {
341
- "epoch": 0.96,
342
- "grad_norm": 0.40852218866348267,
343
- "learning_rate": 0.0001148263647711842,
344
- "loss": 0.3405,
345
- "step": 48
346
- },
347
- {
348
- "epoch": 0.98,
349
- "grad_norm": 0.4145854711532593,
350
- "learning_rate": 0.00011154846369695863,
351
- "loss": 0.3237,
352
- "step": 49
353
- },
354
- {
355
- "epoch": 1.0,
356
- "grad_norm": 0.40923136472702026,
357
- "learning_rate": 0.00010825793454723325,
358
- "loss": 0.3401,
359
- "step": 50
360
- },
361
- {
362
- "epoch": 1.02,
363
- "grad_norm": 0.33250558376312256,
364
- "learning_rate": 0.00010495837546732224,
365
- "loss": 0.2383,
366
- "step": 51
367
- },
368
- {
369
- "epoch": 1.04,
370
- "grad_norm": 0.3187699019908905,
371
- "learning_rate": 0.00010165339447663587,
372
- "loss": 0.2129,
373
- "step": 52
374
- },
375
- {
376
- "epoch": 1.06,
377
- "grad_norm": 0.3277425467967987,
378
- "learning_rate": 9.834660552336415e-05,
379
- "loss": 0.207,
380
- "step": 53
381
- },
382
- {
383
- "epoch": 1.08,
384
- "grad_norm": 0.33040741086006165,
385
- "learning_rate": 9.504162453267777e-05,
386
- "loss": 0.1989,
387
- "step": 54
388
- },
389
- {
390
- "epoch": 1.1,
391
- "grad_norm": 0.33165445923805237,
392
- "learning_rate": 9.174206545276677e-05,
393
- "loss": 0.224,
394
- "step": 55
395
- },
396
- {
397
- "epoch": 1.12,
398
- "grad_norm": 0.3344186842441559,
399
- "learning_rate": 8.845153630304139e-05,
400
- "loss": 0.2011,
401
- "step": 56
402
- },
403
- {
404
- "epoch": 1.1400000000000001,
405
- "grad_norm": 0.3419267535209656,
406
- "learning_rate": 8.517363522881579e-05,
407
- "loss": 0.2195,
408
- "step": 57
409
- },
410
- {
411
- "epoch": 1.16,
412
- "grad_norm": 0.3256666362285614,
413
- "learning_rate": 8.191194656678904e-05,
414
- "loss": 0.1901,
415
- "step": 58
416
- },
417
- {
418
- "epoch": 1.18,
419
- "grad_norm": 0.3259730935096741,
420
- "learning_rate": 7.867003692562534e-05,
421
- "loss": 0.2043,
422
- "step": 59
423
- },
424
- {
425
- "epoch": 1.2,
426
- "grad_norm": 0.3260168433189392,
427
- "learning_rate": 7.54514512859201e-05,
428
- "loss": 0.2002,
429
- "step": 60
430
- },
431
- {
432
- "epoch": 1.22,
433
- "grad_norm": 0.34458276629447937,
434
- "learning_rate": 7.225970912381556e-05,
435
- "loss": 0.2031,
436
- "step": 61
437
- },
438
- {
439
- "epoch": 1.24,
440
- "grad_norm": 0.3367977440357208,
441
- "learning_rate": 6.909830056250527e-05,
442
- "loss": 0.2018,
443
- "step": 62
444
- },
445
- {
446
- "epoch": 1.26,
447
- "grad_norm": 0.36229151487350464,
448
- "learning_rate": 6.59706825558357e-05,
449
- "loss": 0.1987,
450
- "step": 63
451
- },
452
- {
453
- "epoch": 1.28,
454
- "grad_norm": 0.34255215525627136,
455
- "learning_rate": 6.28802751081779e-05,
456
- "loss": 0.1906,
457
- "step": 64
458
- },
459
- {
460
- "epoch": 1.3,
461
- "grad_norm": 0.3520965576171875,
462
- "learning_rate": 5.983045753470308e-05,
463
- "loss": 0.1916,
464
- "step": 65
465
- },
466
- {
467
- "epoch": 1.32,
468
- "grad_norm": 0.3631666600704193,
469
- "learning_rate": 5.6824564766150726e-05,
470
- "loss": 0.2055,
471
- "step": 66
472
- },
473
- {
474
- "epoch": 1.34,
475
- "grad_norm": 0.3751111626625061,
476
- "learning_rate": 5.386588370213124e-05,
477
- "loss": 0.1894,
478
- "step": 67
479
- },
480
- {
481
- "epoch": 1.3599999999999999,
482
- "grad_norm": 0.3539924919605255,
483
- "learning_rate": 5.095764961694922e-05,
484
- "loss": 0.1949,
485
- "step": 68
486
- },
487
- {
488
- "epoch": 1.38,
489
- "grad_norm": 0.35575294494628906,
490
- "learning_rate": 4.810304262187852e-05,
491
- "loss": 0.1947,
492
- "step": 69
493
- },
494
- {
495
- "epoch": 1.4,
496
- "grad_norm": 0.3652094602584839,
497
- "learning_rate": 4.530518418775733e-05,
498
- "loss": 0.1937,
499
- "step": 70
500
- },
501
- {
502
- "epoch": 1.42,
503
- "grad_norm": 0.3642243444919586,
504
- "learning_rate": 4.256713373170564e-05,
505
- "loss": 0.2066,
506
- "step": 71
507
- },
508
- {
509
- "epoch": 1.44,
510
- "grad_norm": 0.37013036012649536,
511
- "learning_rate": 3.9891885271697496e-05,
512
- "loss": 0.2062,
513
- "step": 72
514
- },
515
- {
516
- "epoch": 1.46,
517
- "grad_norm": 0.35074442625045776,
518
- "learning_rate": 3.7282364152646297e-05,
519
- "loss": 0.2015,
520
- "step": 73
521
- },
522
- {
523
- "epoch": 1.48,
524
- "grad_norm": 0.35445520281791687,
525
- "learning_rate": 3.4741423847583134e-05,
526
- "loss": 0.1934,
527
- "step": 74
528
- },
529
- {
530
- "epoch": 1.5,
531
- "grad_norm": 0.3767736852169037,
532
- "learning_rate": 3.227184283742591e-05,
533
- "loss": 0.1955,
534
- "step": 75
535
- },
536
- {
537
- "epoch": 1.52,
538
- "grad_norm": 0.3581729829311371,
539
- "learning_rate": 2.9876321572751144e-05,
540
- "loss": 0.1882,
541
- "step": 76
542
- },
543
- {
544
- "epoch": 1.54,
545
- "grad_norm": 0.362015038728714,
546
- "learning_rate": 2.7557479520891104e-05,
547
- "loss": 0.2056,
548
- "step": 77
549
- },
550
- {
551
- "epoch": 1.56,
552
- "grad_norm": 0.35143327713012695,
553
- "learning_rate": 2.5317852301584643e-05,
554
- "loss": 0.1957,
555
- "step": 78
556
- },
557
- {
558
- "epoch": 1.58,
559
- "grad_norm": 0.3580865263938904,
560
- "learning_rate": 2.315988891431412e-05,
561
- "loss": 0.197,
562
- "step": 79
563
- },
564
- {
565
- "epoch": 1.6,
566
- "grad_norm": 0.3541586399078369,
567
- "learning_rate": 2.1085949060360654e-05,
568
- "loss": 0.2022,
569
- "step": 80
570
- },
571
- {
572
- "epoch": 1.62,
573
- "grad_norm": 0.36059048771858215,
574
- "learning_rate": 1.9098300562505266e-05,
575
- "loss": 0.1855,
576
- "step": 81
577
- },
578
- {
579
- "epoch": 1.6400000000000001,
580
- "grad_norm": 0.3643834888935089,
581
- "learning_rate": 1.7199116885197995e-05,
582
- "loss": 0.1812,
583
- "step": 82
584
- },
585
- {
586
- "epoch": 1.6600000000000001,
587
- "grad_norm": 0.3523213863372803,
588
- "learning_rate": 1.5390474757906446e-05,
589
- "loss": 0.198,
590
- "step": 83
591
- },
592
- {
593
- "epoch": 1.6800000000000002,
594
- "grad_norm": 0.3479655981063843,
595
- "learning_rate": 1.3674351904242611e-05,
596
- "loss": 0.1913,
597
- "step": 84
598
- },
599
- {
600
- "epoch": 1.7,
601
- "grad_norm": 0.3516225218772888,
602
- "learning_rate": 1.2052624879351104e-05,
603
- "loss": 0.1936,
604
- "step": 85
605
- },
606
- {
607
- "epoch": 1.72,
608
- "grad_norm": 0.3603803217411041,
609
- "learning_rate": 1.0527067017923654e-05,
610
- "loss": 0.182,
611
- "step": 86
612
- },
613
- {
614
- "epoch": 1.74,
615
- "grad_norm": 0.3666897416114807,
616
- "learning_rate": 9.09934649508375e-06,
617
- "loss": 0.198,
618
- "step": 87
619
- },
620
- {
621
- "epoch": 1.76,
622
- "grad_norm": 0.347070574760437,
623
- "learning_rate": 7.771024502261526e-06,
624
- "loss": 0.1819,
625
- "step": 88
626
- },
627
- {
628
- "epoch": 1.78,
629
- "grad_norm": 0.366550087928772,
630
- "learning_rate": 6.543553540053926e-06,
631
- "loss": 0.1958,
632
- "step": 89
633
- },
634
- {
635
- "epoch": 1.8,
636
- "grad_norm": 0.3641619384288788,
637
- "learning_rate": 5.418275829936537e-06,
638
- "loss": 0.193,
639
- "step": 90
640
- },
641
- {
642
- "epoch": 1.8199999999999998,
643
- "grad_norm": 0.3448559045791626,
644
- "learning_rate": 4.3964218465642355e-06,
645
- "loss": 0.183,
646
- "step": 91
647
- },
648
- {
649
- "epoch": 1.8399999999999999,
650
- "grad_norm": 0.3684370517730713,
651
- "learning_rate": 3.4791089722651436e-06,
652
- "loss": 0.2036,
653
- "step": 92
654
- },
655
- {
656
- "epoch": 1.8599999999999999,
657
- "grad_norm": 0.3479262590408325,
658
- "learning_rate": 2.667340275199426e-06,
659
- "loss": 0.1871,
660
- "step": 93
661
- },
662
- {
663
- "epoch": 1.88,
664
- "grad_norm": 0.3530682325363159,
665
- "learning_rate": 1.9620034125190644e-06,
666
- "loss": 0.1975,
667
- "step": 94
668
- },
669
- {
670
- "epoch": 1.9,
671
- "grad_norm": 0.3446263074874878,
672
- "learning_rate": 1.3638696597277679e-06,
673
- "loss": 0.1791,
674
- "step": 95
675
- },
676
- {
677
- "epoch": 1.92,
678
- "grad_norm": 0.341688334941864,
679
- "learning_rate": 8.735930673024806e-07,
680
- "loss": 0.1954,
681
- "step": 96
682
- },
683
- {
684
- "epoch": 1.94,
685
- "grad_norm": 0.3435825705528259,
686
- "learning_rate": 4.917097454988584e-07,
687
- "loss": 0.1872,
688
- "step": 97
689
- },
690
- {
691
- "epoch": 1.96,
692
- "grad_norm": 0.35581129789352417,
693
- "learning_rate": 2.1863727812254653e-07,
694
- "loss": 0.1927,
695
- "step": 98
696
- },
697
- {
698
- "epoch": 1.98,
699
- "grad_norm": 0.362829327583313,
700
- "learning_rate": 5.467426590739511e-08,
701
- "loss": 0.1888,
702
- "step": 99
703
- },
704
- {
705
- "epoch": 2.0,
706
- "grad_norm": 0.35802093148231506,
707
  "learning_rate": 0.0,
708
- "loss": 0.1933,
709
- "step": 100
710
  }
711
  ],
712
  "logging_steps": 1,
713
- "max_steps": 100,
714
  "num_input_tokens_seen": 0,
715
- "num_train_epochs": 2,
716
  "save_steps": 500,
717
  "stateful_callbacks": {
718
  "TrainerControl": {
@@ -726,7 +306,7 @@
726
  "attributes": {}
727
  }
728
  },
729
- "total_flos": 1.504376951971676e+17,
730
  "train_batch_size": 1,
731
  "trial_name": null,
732
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 8.016032064128256,
5
  "eval_steps": 500,
6
+ "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.20040080160320642,
13
+ "grad_norm": 3.027674674987793,
14
+ "learning_rate": 0.0001,
15
+ "loss": 1.9225,
16
  "step": 1
17
  },
18
  {
19
+ "epoch": 0.40080160320641284,
20
+ "grad_norm": 3.0814154148101807,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.937,
23
  "step": 2
24
  },
25
  {
26
+ "epoch": 0.6012024048096193,
27
+ "grad_norm": 2.178030252456665,
28
+ "learning_rate": 0.000199658449300667,
29
+ "loss": 1.585,
30
  "step": 3
31
  },
32
  {
33
+ "epoch": 0.8016032064128257,
34
+ "grad_norm": 1.4929898977279663,
35
+ "learning_rate": 0.00019863613034027224,
36
+ "loss": 1.2414,
37
  "step": 4
38
  },
39
  {
40
+ "epoch": 1.002004008016032,
41
+ "grad_norm": 1.2824300527572632,
42
+ "learning_rate": 0.00019694002659393305,
43
+ "loss": 1.109,
44
  "step": 5
45
  },
46
  {
47
+ "epoch": 1.2024048096192386,
48
+ "grad_norm": 0.8394728899002075,
49
+ "learning_rate": 0.00019458172417006347,
50
+ "loss": 0.7618,
51
  "step": 6
52
  },
53
  {
54
+ "epoch": 1.402805611222445,
55
+ "grad_norm": 0.7309438586235046,
56
+ "learning_rate": 0.00019157733266550575,
57
+ "loss": 0.6732,
58
  "step": 7
59
  },
60
  {
61
+ "epoch": 1.6032064128256514,
62
+ "grad_norm": 0.69007807970047,
63
+ "learning_rate": 0.0001879473751206489,
64
+ "loss": 0.646,
65
  "step": 8
66
  },
67
  {
68
+ "epoch": 1.8036072144288577,
69
+ "grad_norm": 0.6368725299835205,
70
+ "learning_rate": 0.00018371664782625287,
71
+ "loss": 0.6147,
72
  "step": 9
73
  },
74
  {
75
+ "epoch": 2.004008016032064,
76
+ "grad_norm": 0.5702280402183533,
77
+ "learning_rate": 0.00017891405093963938,
78
+ "loss": 0.5384,
79
  "step": 10
80
  },
81
  {
82
+ "epoch": 2.2044088176352705,
83
+ "grad_norm": 0.5861708521842957,
84
+ "learning_rate": 0.00017357239106731317,
85
+ "loss": 0.4272,
86
  "step": 11
87
  },
88
  {
89
+ "epoch": 2.404809619238477,
90
+ "grad_norm": 0.537497341632843,
91
+ "learning_rate": 0.00016772815716257412,
92
+ "loss": 0.419,
93
  "step": 12
94
  },
95
  {
96
+ "epoch": 2.6052104208416833,
97
+ "grad_norm": 0.4901179373264313,
98
+ "learning_rate": 0.0001614212712689668,
99
+ "loss": 0.3951,
100
  "step": 13
101
  },
102
  {
103
+ "epoch": 2.80561122244489,
104
+ "grad_norm": 0.44876372814178467,
105
+ "learning_rate": 0.00015469481581224272,
106
+ "loss": 0.3362,
107
  "step": 14
108
  },
109
  {
110
+ "epoch": 3.006012024048096,
111
+ "grad_norm": 0.4591052234172821,
112
+ "learning_rate": 0.00014759473930370736,
113
+ "loss": 0.321,
114
  "step": 15
115
  },
116
  {
117
+ "epoch": 3.2064128256513027,
118
+ "grad_norm": 0.3763630986213684,
119
+ "learning_rate": 0.00014016954246529696,
120
+ "loss": 0.2673,
121
  "step": 16
122
  },
123
  {
124
+ "epoch": 3.406813627254509,
125
+ "grad_norm": 0.37145256996154785,
126
+ "learning_rate": 0.00013246994692046836,
127
+ "loss": 0.2554,
128
  "step": 17
129
  },
130
  {
131
+ "epoch": 3.6072144288577155,
132
+ "grad_norm": 0.3408704102039337,
133
+ "learning_rate": 0.00012454854871407994,
134
+ "loss": 0.229,
135
  "step": 18
136
  },
137
  {
138
+ "epoch": 3.8076152304609217,
139
+ "grad_norm": 0.36588045954704285,
140
+ "learning_rate": 0.00011645945902807341,
141
+ "loss": 0.2371,
142
  "step": 19
143
  },
144
  {
145
+ "epoch": 4.008016032064128,
146
+ "grad_norm": 0.349997341632843,
147
+ "learning_rate": 0.00010825793454723325,
148
+ "loss": 0.2127,
149
  "step": 20
150
  },
151
  {
152
+ "epoch": 4.208416833667335,
153
+ "grad_norm": 0.30794546008110046,
154
+ "learning_rate": 0.0001,
155
+ "loss": 0.1856,
156
  "step": 21
157
  },
158
  {
159
+ "epoch": 4.408817635270541,
160
+ "grad_norm": 0.2869230806827545,
161
+ "learning_rate": 9.174206545276677e-05,
162
+ "loss": 0.152,
163
  "step": 22
164
  },
165
  {
166
+ "epoch": 4.609218436873747,
167
+ "grad_norm": 0.29317694902420044,
168
+ "learning_rate": 8.35405409719266e-05,
169
+ "loss": 0.1581,
170
  "step": 23
171
  },
172
  {
173
+ "epoch": 4.809619238476954,
174
+ "grad_norm": 0.290088951587677,
175
+ "learning_rate": 7.54514512859201e-05,
176
+ "loss": 0.1564,
177
  "step": 24
178
  },
179
  {
180
+ "epoch": 5.01002004008016,
181
+ "grad_norm": 0.30606502294540405,
182
+ "learning_rate": 6.753005307953167e-05,
183
+ "loss": 0.1594,
184
  "step": 25
185
  },
186
  {
187
+ "epoch": 5.210420841683367,
188
+ "grad_norm": 0.2588537335395813,
189
+ "learning_rate": 5.983045753470308e-05,
190
+ "loss": 0.1253,
191
  "step": 26
192
  },
193
  {
194
+ "epoch": 5.410821643286573,
195
+ "grad_norm": 0.2805459201335907,
196
+ "learning_rate": 5.240526069629265e-05,
197
+ "loss": 0.1488,
198
  "step": 27
199
  },
200
  {
201
+ "epoch": 5.61122244488978,
202
+ "grad_norm": 0.24708090722560883,
203
+ "learning_rate": 4.530518418775733e-05,
204
+ "loss": 0.1084,
205
  "step": 28
206
  },
207
  {
208
+ "epoch": 5.811623246492986,
209
+ "grad_norm": 0.2635113298892975,
210
+ "learning_rate": 3.857872873103322e-05,
211
+ "loss": 0.1255,
212
  "step": 29
213
  },
214
  {
215
+ "epoch": 6.012024048096192,
216
+ "grad_norm": 0.24471008777618408,
217
+ "learning_rate": 3.227184283742591e-05,
218
+ "loss": 0.1017,
219
  "step": 30
220
  },
221
  {
222
+ "epoch": 6.212424849699399,
223
+ "grad_norm": 0.23846429586410522,
224
+ "learning_rate": 2.6427608932686843e-05,
225
+ "loss": 0.1089,
226
  "step": 31
227
  },
228
  {
229
+ "epoch": 6.412825651302605,
230
+ "grad_norm": 0.25631099939346313,
231
+ "learning_rate": 2.1085949060360654e-05,
232
+ "loss": 0.1166,
233
  "step": 32
234
  },
235
  {
236
+ "epoch": 6.613226452905812,
237
+ "grad_norm": 0.24143779277801514,
238
+ "learning_rate": 1.6283352173747145e-05,
239
+ "loss": 0.1001,
240
  "step": 33
241
  },
242
  {
243
+ "epoch": 6.813627254509018,
244
+ "grad_norm": 0.22203697264194489,
245
+ "learning_rate": 1.2052624879351104e-05,
246
+ "loss": 0.0966,
247
  "step": 34
248
  },
249
  {
250
+ "epoch": 7.014028056112225,
251
+ "grad_norm": 0.228188157081604,
252
+ "learning_rate": 8.422667334494249e-06,
253
+ "loss": 0.0937,
254
  "step": 35
255
  },
256
  {
257
+ "epoch": 7.214428857715431,
258
+ "grad_norm": 0.22016100585460663,
259
+ "learning_rate": 5.418275829936537e-06,
260
+ "loss": 0.0982,
261
  "step": 36
262
  },
263
  {
264
+ "epoch": 7.414829659318637,
265
+ "grad_norm": 0.21842055022716522,
266
+ "learning_rate": 3.059973406066963e-06,
267
+ "loss": 0.0914,
268
  "step": 37
269
  },
270
  {
271
+ "epoch": 7.615230460921843,
272
+ "grad_norm": 0.22781485319137573,
273
+ "learning_rate": 1.3638696597277679e-06,
274
+ "loss": 0.0948,
275
  "step": 38
276
  },
277
  {
278
+ "epoch": 7.81563126252505,
279
+ "grad_norm": 0.23596827685832977,
280
+ "learning_rate": 3.415506993330153e-07,
281
+ "loss": 0.0959,
282
  "step": 39
283
  },
284
  {
285
+ "epoch": 8.016032064128256,
286
+ "grad_norm": 0.24492216110229492,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
287
  "learning_rate": 0.0,
288
+ "loss": 0.1,
289
+ "step": 40
290
  }
291
  ],
292
  "logging_steps": 1,
293
+ "max_steps": 40,
294
  "num_input_tokens_seen": 0,
295
+ "num_train_epochs": 10,
296
  "save_steps": 500,
297
  "stateful_callbacks": {
298
  "TrainerControl": {
 
306
  "attributes": {}
307
  }
308
  },
309
+ "total_flos": 3.4679807860064256e+16,
310
  "train_batch_size": 1,
311
  "trial_name": null,
312
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5f62da520466ec11857988c4ac579c62bbb48e7524c7062ea3f6f52366b7b1c
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8923db3bbc9d64f25728011e5b67d183e43b0af93caeb0253ce117a78cbdba2
3
  size 5240