SystemAdmin123 commited on
Commit
0a94c30
·
verified ·
1 Parent(s): 2616958

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4dc1cc1cc9b54bfe6d9ce46c6c48d5e71549cfb18e37c573da51b96a6b7c6fc
3
  size 723674912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089ab77c575af96a66c3eebde29eb20b4802b1ca35d7fcd6a82088b5dfc73176
3
  size 723674912
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62c75a7c6cde713dbd13598c54106d019899ffd4c0fae4ead85e640a976d6251
3
- size 735625626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e98a40cf910fd33c1a561f42ff2278b14deead7522e6afa9249393199392ae7
3
+ size 735625370
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0df10be429c2412198f2c4c684866a8c921cbd0d9ee4c865077476da07bda410
3
- size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d497aa3968cd2f05db0d0e8c5e1be496a8a5348df0a825e18ed3fdbaa24257ad
3
+ size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b14d8363b71c1e824421bf14a513f0f951f1c6c9b9494dcedc75b3fa1fecea91
3
- size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dda0d87dad890add5a8f3995389ff6a597895845903171a363aa580fa07ac30
3
+ size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0d27a8e9aed69fdd3b729f8cbf6300af5e0e26e9226d0e2307b0cf80aff9030
3
- size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de656d8e54adb9fa6e0b2ddbe69d4325a775f7e1580ed51c58a759ad9c7520d4
3
+ size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23de9e35ad029c7a59ff383920fe892474d8f295c2e2f82ec3e6f109f3f96960
3
- size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eaa87e4309aa1a00b739cd637a2ec444ea6c757388c653064a1906e4d8dfb2e
3
+ size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40b6b717644e21f80a22ec98694b3a2fd9d62a6467e549d64314725dba905d52
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,619 +1,175 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.23675643681562591,
5
  "eval_steps": 200,
6
- "global_step": 800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.0002959455460195324,
13
- "eval_loss": 3.0371296405792236,
14
- "eval_runtime": 24.5776,
15
- "eval_samples_per_second": 61.112,
16
- "eval_steps_per_second": 15.298,
17
  "step": 1
18
  },
19
  {
20
- "epoch": 0.002959455460195324,
21
- "grad_norm": 2.84375,
22
- "learning_rate": 1.6000000000000003e-05,
23
- "loss": 2.5729,
24
  "step": 10
25
  },
26
  {
27
- "epoch": 0.005918910920390648,
28
- "grad_norm": 4.4375,
29
- "learning_rate": 3.2000000000000005e-05,
30
- "loss": 2.6895,
31
  "step": 20
32
  },
33
  {
34
- "epoch": 0.008878366380585973,
35
- "grad_norm": 5.3125,
36
- "learning_rate": 4.8e-05,
37
- "loss": 2.5333,
38
  "step": 30
39
  },
40
  {
41
- "epoch": 0.011837821840781295,
42
- "grad_norm": 7.9375,
43
- "learning_rate": 6.400000000000001e-05,
44
- "loss": 2.9663,
45
  "step": 40
46
  },
47
  {
48
- "epoch": 0.01479727730097662,
49
- "grad_norm": 25.375,
50
- "learning_rate": 8e-05,
51
- "loss": 3.4106,
52
  "step": 50
53
  },
54
  {
55
- "epoch": 0.017756732761171946,
56
- "grad_norm": 3.125,
57
- "learning_rate": 9.6e-05,
58
- "loss": 2.3132,
59
  "step": 60
60
  },
61
  {
62
- "epoch": 0.020716188221367268,
63
- "grad_norm": 2.9375,
64
- "learning_rate": 0.00011200000000000001,
65
- "loss": 2.3039,
66
  "step": 70
67
  },
68
  {
69
- "epoch": 0.02367564368156259,
70
- "grad_norm": 4.34375,
71
- "learning_rate": 0.00012800000000000002,
72
- "loss": 2.4118,
73
  "step": 80
74
  },
75
  {
76
- "epoch": 0.026635099141757917,
77
- "grad_norm": 5.5,
78
- "learning_rate": 0.000144,
79
- "loss": 2.3272,
80
  "step": 90
81
  },
82
  {
83
- "epoch": 0.02959455460195324,
84
- "grad_norm": 22.0,
85
- "learning_rate": 0.00016,
86
- "loss": 3.3301,
87
  "step": 100
88
  },
89
  {
90
- "epoch": 0.032554010062148565,
91
- "grad_norm": 3.890625,
92
- "learning_rate": 0.00017600000000000002,
93
- "loss": 2.4817,
94
  "step": 110
95
  },
96
  {
97
- "epoch": 0.03551346552234389,
98
- "grad_norm": 2.921875,
99
- "learning_rate": 0.000192,
100
- "loss": 2.2621,
101
  "step": 120
102
  },
103
  {
104
- "epoch": 0.03847292098253921,
105
- "grad_norm": 2.859375,
106
- "learning_rate": 0.0001999978128380225,
107
- "loss": 2.3509,
108
  "step": 130
109
  },
110
  {
111
- "epoch": 0.041432376442734536,
112
- "grad_norm": 7.125,
113
- "learning_rate": 0.0001999803161162393,
114
- "loss": 2.3626,
115
  "step": 140
116
  },
117
  {
118
- "epoch": 0.04439183190292986,
119
- "grad_norm": 32.5,
120
- "learning_rate": 0.00019994532573409262,
121
- "loss": 2.2664,
122
  "step": 150
123
  },
124
  {
125
- "epoch": 0.04735128736312518,
126
- "grad_norm": 5.6875,
127
- "learning_rate": 0.00019989284781388617,
128
- "loss": 2.378,
129
  "step": 160
130
  },
131
  {
132
- "epoch": 0.05031074282332051,
133
- "grad_norm": 2.609375,
134
- "learning_rate": 0.00019982289153773646,
135
- "loss": 2.3008,
136
  "step": 170
137
  },
138
  {
139
- "epoch": 0.053270198283515834,
140
- "grad_norm": 4.40625,
141
- "learning_rate": 0.00019973546914596623,
142
- "loss": 2.4329,
143
  "step": 180
144
  },
145
  {
146
- "epoch": 0.05622965374371116,
147
- "grad_norm": 6.90625,
148
- "learning_rate": 0.00019963059593496268,
149
- "loss": 2.2273,
150
  "step": 190
151
  },
152
  {
153
- "epoch": 0.05918910920390648,
154
- "grad_norm": 26.125,
155
- "learning_rate": 0.00019950829025450114,
156
- "loss": 2.5059,
157
  "step": 200
158
  },
159
  {
160
- "epoch": 0.05918910920390648,
161
- "eval_loss": 2.298793077468872,
162
- "eval_runtime": 23.8828,
163
- "eval_samples_per_second": 62.891,
164
- "eval_steps_per_second": 15.744,
165
  "step": 200
166
- },
167
- {
168
- "epoch": 0.062148564664101805,
169
- "grad_norm": 2.53125,
170
- "learning_rate": 0.0001993685735045343,
171
- "loss": 2.4118,
172
- "step": 210
173
- },
174
- {
175
- "epoch": 0.06510802012429713,
176
- "grad_norm": 2.890625,
177
- "learning_rate": 0.0001992114701314478,
178
- "loss": 2.3572,
179
- "step": 220
180
- },
181
- {
182
- "epoch": 0.06806747558449246,
183
- "grad_norm": 3.046875,
184
- "learning_rate": 0.000199037007623783,
185
- "loss": 2.2494,
186
- "step": 230
187
- },
188
- {
189
- "epoch": 0.07102693104468778,
190
- "grad_norm": 6.65625,
191
- "learning_rate": 0.00019884521650742715,
192
- "loss": 2.2517,
193
- "step": 240
194
- },
195
- {
196
- "epoch": 0.0739863865048831,
197
- "grad_norm": 39.75,
198
- "learning_rate": 0.00019863613034027224,
199
- "loss": 2.7168,
200
- "step": 250
201
- },
202
- {
203
- "epoch": 0.07694584196507842,
204
- "grad_norm": 5.09375,
205
- "learning_rate": 0.0001984097857063434,
206
- "loss": 2.1898,
207
- "step": 260
208
- },
209
- {
210
- "epoch": 0.07990529742527375,
211
- "grad_norm": 2.75,
212
- "learning_rate": 0.0001981662222093976,
213
- "loss": 2.409,
214
- "step": 270
215
- },
216
- {
217
- "epoch": 0.08286475288546907,
218
- "grad_norm": 3.15625,
219
- "learning_rate": 0.00019790548246599447,
220
- "loss": 2.2657,
221
- "step": 280
222
- },
223
- {
224
- "epoch": 0.0858242083456644,
225
- "grad_norm": 5.375,
226
- "learning_rate": 0.00019762761209803927,
227
- "loss": 2.0511,
228
- "step": 290
229
- },
230
- {
231
- "epoch": 0.08878366380585972,
232
- "grad_norm": 15.3125,
233
- "learning_rate": 0.0001973326597248006,
234
- "loss": 2.2033,
235
- "step": 300
236
- },
237
- {
238
- "epoch": 0.09174311926605505,
239
- "grad_norm": 3.234375,
240
- "learning_rate": 0.00019702067695440332,
241
- "loss": 2.4281,
242
- "step": 310
243
- },
244
- {
245
- "epoch": 0.09470257472625036,
246
- "grad_norm": 2.890625,
247
- "learning_rate": 0.00019669171837479873,
248
- "loss": 2.0234,
249
- "step": 320
250
- },
251
- {
252
- "epoch": 0.09766203018644569,
253
- "grad_norm": 3.0,
254
- "learning_rate": 0.00019634584154421317,
255
- "loss": 2.2922,
256
- "step": 330
257
- },
258
- {
259
- "epoch": 0.10062148564664102,
260
- "grad_norm": 5.5,
261
- "learning_rate": 0.00019598310698107702,
262
- "loss": 2.1127,
263
- "step": 340
264
- },
265
- {
266
- "epoch": 0.10358094110683634,
267
- "grad_norm": 23.125,
268
- "learning_rate": 0.00019560357815343577,
269
- "loss": 1.9014,
270
- "step": 350
271
- },
272
- {
273
- "epoch": 0.10654039656703167,
274
- "grad_norm": 2.515625,
275
- "learning_rate": 0.00019520732146784491,
276
- "loss": 2.2815,
277
- "step": 360
278
- },
279
- {
280
- "epoch": 0.109499852027227,
281
- "grad_norm": 3.09375,
282
- "learning_rate": 0.0001947944062577507,
283
- "loss": 2.0484,
284
- "step": 370
285
- },
286
- {
287
- "epoch": 0.11245930748742232,
288
- "grad_norm": 4.125,
289
- "learning_rate": 0.00019436490477135878,
290
- "loss": 2.2128,
291
- "step": 380
292
- },
293
- {
294
- "epoch": 0.11541876294761765,
295
- "grad_norm": 5.5625,
296
- "learning_rate": 0.00019391889215899299,
297
- "loss": 1.9424,
298
- "step": 390
299
- },
300
- {
301
- "epoch": 0.11837821840781296,
302
- "grad_norm": 25.5,
303
- "learning_rate": 0.0001934564464599461,
304
- "loss": 1.8624,
305
- "step": 400
306
- },
307
- {
308
- "epoch": 0.11837821840781296,
309
- "eval_loss": 2.2062976360321045,
310
- "eval_runtime": 23.7998,
311
- "eval_samples_per_second": 63.11,
312
- "eval_steps_per_second": 15.798,
313
- "step": 400
314
- },
315
- {
316
- "epoch": 0.12133767386800828,
317
- "grad_norm": 1.9296875,
318
- "learning_rate": 0.00019297764858882514,
319
- "loss": 2.4526,
320
- "step": 410
321
- },
322
- {
323
- "epoch": 0.12429712932820361,
324
- "grad_norm": 3.765625,
325
- "learning_rate": 0.00019248258232139388,
326
- "loss": 2.2642,
327
- "step": 420
328
- },
329
- {
330
- "epoch": 0.12725658478839894,
331
- "grad_norm": 4.25,
332
- "learning_rate": 0.00019197133427991436,
333
- "loss": 2.1835,
334
- "step": 430
335
- },
336
- {
337
- "epoch": 0.13021604024859426,
338
- "grad_norm": 3.8125,
339
- "learning_rate": 0.00019144399391799043,
340
- "loss": 2.0152,
341
- "step": 440
342
- },
343
- {
344
- "epoch": 0.1331754957087896,
345
- "grad_norm": 26.875,
346
- "learning_rate": 0.00019090065350491626,
347
- "loss": 2.4485,
348
- "step": 450
349
- },
350
- {
351
- "epoch": 0.1361349511689849,
352
- "grad_norm": 2.046875,
353
- "learning_rate": 0.0001903414081095315,
354
- "loss": 2.3844,
355
- "step": 460
356
- },
357
- {
358
- "epoch": 0.13909440662918024,
359
- "grad_norm": 2.265625,
360
- "learning_rate": 0.00018976635558358722,
361
- "loss": 2.1219,
362
- "step": 470
363
- },
364
- {
365
- "epoch": 0.14205386208937557,
366
- "grad_norm": 3.9375,
367
- "learning_rate": 0.00018917559654462474,
368
- "loss": 2.1883,
369
- "step": 480
370
- },
371
- {
372
- "epoch": 0.1450133175495709,
373
- "grad_norm": 5.1875,
374
- "learning_rate": 0.00018856923435837022,
375
- "loss": 2.1962,
376
- "step": 490
377
- },
378
- {
379
- "epoch": 0.1479727730097662,
380
- "grad_norm": 19.625,
381
- "learning_rate": 0.0001879473751206489,
382
- "loss": 1.5941,
383
- "step": 500
384
- },
385
- {
386
- "epoch": 0.15093222846996152,
387
- "grad_norm": 2.125,
388
- "learning_rate": 0.00018731012763882133,
389
- "loss": 2.4096,
390
- "step": 510
391
- },
392
- {
393
- "epoch": 0.15389168393015684,
394
- "grad_norm": 2.828125,
395
- "learning_rate": 0.00018665760341274505,
396
- "loss": 2.1982,
397
- "step": 520
398
- },
399
- {
400
- "epoch": 0.15685113939035217,
401
- "grad_norm": 3.796875,
402
- "learning_rate": 0.00018598991661526572,
403
- "loss": 2.28,
404
- "step": 530
405
- },
406
- {
407
- "epoch": 0.1598105948505475,
408
- "grad_norm": 3.796875,
409
- "learning_rate": 0.00018530718407223974,
410
- "loss": 2.2208,
411
- "step": 540
412
- },
413
- {
414
- "epoch": 0.16277005031074282,
415
- "grad_norm": 19.125,
416
- "learning_rate": 0.00018460952524209355,
417
- "loss": 2.0021,
418
- "step": 550
419
- },
420
- {
421
- "epoch": 0.16572950577093815,
422
- "grad_norm": 2.875,
423
- "learning_rate": 0.00018389706219492147,
424
- "loss": 2.2805,
425
- "step": 560
426
- },
427
- {
428
- "epoch": 0.16868896123113347,
429
- "grad_norm": 2.296875,
430
- "learning_rate": 0.00018316991959112716,
431
- "loss": 2.3686,
432
- "step": 570
433
- },
434
- {
435
- "epoch": 0.1716484166913288,
436
- "grad_norm": 2.78125,
437
- "learning_rate": 0.00018242822465961176,
438
- "loss": 1.8721,
439
- "step": 580
440
- },
441
- {
442
- "epoch": 0.17460787215152412,
443
- "grad_norm": 8.0,
444
- "learning_rate": 0.00018167210717551224,
445
- "loss": 2.078,
446
- "step": 590
447
- },
448
- {
449
- "epoch": 0.17756732761171945,
450
- "grad_norm": 17.625,
451
- "learning_rate": 0.00018090169943749476,
452
- "loss": 1.906,
453
- "step": 600
454
- },
455
- {
456
- "epoch": 0.17756732761171945,
457
- "eval_loss": 2.1775083541870117,
458
- "eval_runtime": 24.018,
459
- "eval_samples_per_second": 62.536,
460
- "eval_steps_per_second": 15.655,
461
- "step": 600
462
- },
463
- {
464
- "epoch": 0.18052678307191478,
465
- "grad_norm": 2.734375,
466
- "learning_rate": 0.00018011713624460608,
467
- "loss": 2.0593,
468
- "step": 610
469
- },
470
- {
471
- "epoch": 0.1834862385321101,
472
- "grad_norm": 2.203125,
473
- "learning_rate": 0.00017931855487268782,
474
- "loss": 2.0449,
475
- "step": 620
476
- },
477
- {
478
- "epoch": 0.18644569399230543,
479
- "grad_norm": 3.0625,
480
- "learning_rate": 0.0001785060950503568,
481
- "loss": 2.4332,
482
- "step": 630
483
- },
484
- {
485
- "epoch": 0.18940514945250073,
486
- "grad_norm": 10.5,
487
- "learning_rate": 0.00017767989893455698,
488
- "loss": 2.2297,
489
- "step": 640
490
- },
491
- {
492
- "epoch": 0.19236460491269605,
493
- "grad_norm": 19.375,
494
- "learning_rate": 0.00017684011108568592,
495
- "loss": 2.2807,
496
- "step": 650
497
- },
498
- {
499
- "epoch": 0.19532406037289138,
500
- "grad_norm": 2.125,
501
- "learning_rate": 0.00017598687844230088,
502
- "loss": 2.4388,
503
- "step": 660
504
- },
505
- {
506
- "epoch": 0.1982835158330867,
507
- "grad_norm": 2.8125,
508
- "learning_rate": 0.00017512035029540885,
509
- "loss": 2.1782,
510
- "step": 670
511
- },
512
- {
513
- "epoch": 0.20124297129328203,
514
- "grad_norm": 5.15625,
515
- "learning_rate": 0.000174240678262345,
516
- "loss": 2.2403,
517
- "step": 680
518
- },
519
- {
520
- "epoch": 0.20420242675347736,
521
- "grad_norm": 6.28125,
522
- "learning_rate": 0.000173348016260244,
523
- "loss": 1.9472,
524
- "step": 690
525
- },
526
- {
527
- "epoch": 0.20716188221367268,
528
- "grad_norm": 26.0,
529
- "learning_rate": 0.00017244252047910892,
530
- "loss": 1.854,
531
- "step": 700
532
- },
533
- {
534
- "epoch": 0.210121337673868,
535
- "grad_norm": 2.140625,
536
- "learning_rate": 0.00017152434935448256,
537
- "loss": 2.215,
538
- "step": 710
539
- },
540
- {
541
- "epoch": 0.21308079313406333,
542
- "grad_norm": 2.484375,
543
- "learning_rate": 0.0001705936635397259,
544
- "loss": 2.3141,
545
- "step": 720
546
- },
547
- {
548
- "epoch": 0.21604024859425866,
549
- "grad_norm": 3.59375,
550
- "learning_rate": 0.00016965062587790823,
551
- "loss": 2.1083,
552
- "step": 730
553
- },
554
- {
555
- "epoch": 0.218999704054454,
556
- "grad_norm": 2.71875,
557
- "learning_rate": 0.00016869540137331445,
558
- "loss": 1.9076,
559
- "step": 740
560
- },
561
- {
562
- "epoch": 0.2219591595146493,
563
- "grad_norm": 9.75,
564
- "learning_rate": 0.00016772815716257412,
565
- "loss": 1.9295,
566
- "step": 750
567
- },
568
- {
569
- "epoch": 0.22491861497484464,
570
- "grad_norm": 1.7890625,
571
- "learning_rate": 0.00016674906248541726,
572
- "loss": 2.3024,
573
- "step": 760
574
- },
575
- {
576
- "epoch": 0.22787807043503996,
577
- "grad_norm": 3.765625,
578
- "learning_rate": 0.00016575828865506245,
579
- "loss": 2.1123,
580
- "step": 770
581
- },
582
- {
583
- "epoch": 0.2308375258952353,
584
- "grad_norm": 4.15625,
585
- "learning_rate": 0.0001647560090282419,
586
- "loss": 2.0384,
587
- "step": 780
588
- },
589
- {
590
- "epoch": 0.2337969813554306,
591
- "grad_norm": 6.5625,
592
- "learning_rate": 0.000163742398974869,
593
- "loss": 1.9151,
594
- "step": 790
595
- },
596
- {
597
- "epoch": 0.23675643681562591,
598
- "grad_norm": 43.0,
599
- "learning_rate": 0.0001627176358473537,
600
- "loss": 2.1016,
601
- "step": 800
602
- },
603
- {
604
- "epoch": 0.23675643681562591,
605
- "eval_loss": 2.1602160930633545,
606
- "eval_runtime": 24.245,
607
- "eval_samples_per_second": 61.951,
608
- "eval_steps_per_second": 15.508,
609
- "step": 800
610
  }
611
  ],
612
  "logging_steps": 10,
613
- "max_steps": 2500,
614
  "num_input_tokens_seen": 0,
615
- "num_train_epochs": 1,
616
- "save_steps": 400,
617
  "stateful_callbacks": {
618
  "TrainerControl": {
619
  "args": {
@@ -621,13 +177,13 @@
621
  "should_evaluate": false,
622
  "should_log": false,
623
  "should_save": true,
624
- "should_training_stop": false
625
  },
626
  "attributes": {}
627
  }
628
  },
629
- "total_flos": 1.24028893790208e+16,
630
- "train_batch_size": 4,
631
  "trial_name": null,
632
  "trial_params": null
633
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 25.0,
5
  "eval_steps": 200,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.125,
13
+ "eval_loss": 2.9946672916412354,
14
+ "eval_runtime": 5.136,
15
+ "eval_samples_per_second": 292.251,
16
+ "eval_steps_per_second": 3.31,
17
  "step": 1
18
  },
19
  {
20
+ "epoch": 1.25,
21
+ "grad_norm": 0.7578125,
22
+ "learning_rate": 0.0002,
23
+ "loss": 2.574,
24
  "step": 10
25
  },
26
  {
27
+ "epoch": 2.5,
28
+ "grad_norm": 0.41015625,
29
+ "learning_rate": 0.00019863613034027224,
30
+ "loss": 2.3858,
31
  "step": 20
32
  },
33
  {
34
+ "epoch": 3.75,
35
+ "grad_norm": 0.22265625,
36
+ "learning_rate": 0.00019458172417006347,
37
+ "loss": 2.2927,
38
  "step": 30
39
  },
40
  {
41
+ "epoch": 5.0,
42
+ "grad_norm": 0.177734375,
43
+ "learning_rate": 0.0001879473751206489,
44
+ "loss": 2.2352,
45
  "step": 40
46
  },
47
  {
48
+ "epoch": 6.25,
49
+ "grad_norm": 0.1513671875,
50
+ "learning_rate": 0.00017891405093963938,
51
+ "loss": 2.2042,
52
  "step": 50
53
  },
54
  {
55
+ "epoch": 7.5,
56
+ "grad_norm": 0.181640625,
57
+ "learning_rate": 0.00016772815716257412,
58
+ "loss": 2.1814,
59
  "step": 60
60
  },
61
  {
62
+ "epoch": 8.75,
63
+ "grad_norm": 0.1240234375,
64
+ "learning_rate": 0.00015469481581224272,
65
+ "loss": 2.1483,
66
  "step": 70
67
  },
68
  {
69
+ "epoch": 10.0,
70
+ "grad_norm": 0.1494140625,
71
+ "learning_rate": 0.00014016954246529696,
72
+ "loss": 2.1455,
73
  "step": 80
74
  },
75
  {
76
+ "epoch": 11.25,
77
+ "grad_norm": 0.125,
78
+ "learning_rate": 0.00012454854871407994,
79
+ "loss": 2.1361,
80
  "step": 90
81
  },
82
  {
83
+ "epoch": 12.5,
84
+ "grad_norm": 0.201171875,
85
+ "learning_rate": 0.00010825793454723325,
86
+ "loss": 2.109,
87
  "step": 100
88
  },
89
  {
90
+ "epoch": 13.75,
91
+ "grad_norm": 0.1259765625,
92
+ "learning_rate": 9.174206545276677e-05,
93
+ "loss": 2.106,
94
  "step": 110
95
  },
96
  {
97
+ "epoch": 15.0,
98
+ "grad_norm": 0.1279296875,
99
+ "learning_rate": 7.54514512859201e-05,
100
+ "loss": 2.0939,
101
  "step": 120
102
  },
103
  {
104
+ "epoch": 16.25,
105
+ "grad_norm": 0.13671875,
106
+ "learning_rate": 5.983045753470308e-05,
107
+ "loss": 2.0901,
108
  "step": 130
109
  },
110
  {
111
+ "epoch": 17.5,
112
+ "grad_norm": 0.1396484375,
113
+ "learning_rate": 4.530518418775733e-05,
114
+ "loss": 2.0959,
115
  "step": 140
116
  },
117
  {
118
+ "epoch": 18.75,
119
+ "grad_norm": 0.138671875,
120
+ "learning_rate": 3.227184283742591e-05,
121
+ "loss": 2.0851,
122
  "step": 150
123
  },
124
  {
125
+ "epoch": 20.0,
126
+ "grad_norm": 0.1259765625,
127
+ "learning_rate": 2.1085949060360654e-05,
128
+ "loss": 2.0874,
129
  "step": 160
130
  },
131
  {
132
+ "epoch": 21.25,
133
+ "grad_norm": 0.1240234375,
134
+ "learning_rate": 1.2052624879351104e-05,
135
+ "loss": 2.0865,
136
  "step": 170
137
  },
138
  {
139
+ "epoch": 22.5,
140
+ "grad_norm": 0.16796875,
141
+ "learning_rate": 5.418275829936537e-06,
142
+ "loss": 2.0931,
143
  "step": 180
144
  },
145
  {
146
+ "epoch": 23.75,
147
+ "grad_norm": 0.1435546875,
148
+ "learning_rate": 1.3638696597277679e-06,
149
+ "loss": 2.0826,
150
  "step": 190
151
  },
152
  {
153
+ "epoch": 25.0,
154
+ "grad_norm": 0.142578125,
155
+ "learning_rate": 0.0,
156
+ "loss": 2.0872,
157
  "step": 200
158
  },
159
  {
160
+ "epoch": 25.0,
161
+ "eval_loss": 2.159134864807129,
162
+ "eval_runtime": 5.0049,
163
+ "eval_samples_per_second": 299.904,
164
+ "eval_steps_per_second": 3.397,
165
  "step": 200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
166
  }
167
  ],
168
  "logging_steps": 10,
169
+ "max_steps": 200,
170
  "num_input_tokens_seen": 0,
171
+ "num_train_epochs": 25,
172
+ "save_steps": 200,
173
  "stateful_callbacks": {
174
  "TrainerControl": {
175
  "args": {
 
177
  "should_evaluate": false,
178
  "should_log": false,
179
  "should_save": true,
180
+ "should_training_stop": true
181
  },
182
  "attributes": {}
183
  }
184
  },
185
+ "total_flos": 7.113876738932736e+16,
186
+ "train_batch_size": 23,
187
  "trial_name": null,
188
  "trial_params": null
189
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c005ee5b7b542fe5c31ab145aa5cb83513af587ae4027e5fb31ac777061c2a2
3
  size 6840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dcec2cd7965a72fb6ad084d768d0c5ed5e5db711cd1f0987f9e8de610b55004
3
  size 6840