emilykang commited on
Commit
a76a569
·
verified ·
1 Parent(s): 513145d

Training in progress, epoch 1

Browse files
adapter_config.json CHANGED
@@ -20,10 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
24
- "q_proj",
25
  "o_proj",
26
- "v_proj"
 
 
 
 
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "o_proj",
24
+ "gate_proj",
25
+ "v_proj",
26
+ "down_proj",
27
+ "up_proj",
28
+ "q_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:562e078b6a35e9889757848bbe9c7f2d25289bbbe309b3459915b84b169b6713
3
- size 14764744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3b74eb05601f3640faca779bdef5346172fe8b2dbb6e8a38a60354b90a63b0
3
+ size 78480072
trainer_state.json ADDED
@@ -0,0 +1,590 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.907120743034056,
5
+ "eval_steps": 500,
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": 0.1238390092879257,
13
+ "grad_norm": 7.5771355628967285,
14
+ "learning_rate": 0.0001999229036240723,
15
+ "loss": 1.3532,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.2476780185758514,
20
+ "grad_norm": 0.3571035861968994,
21
+ "learning_rate": 0.0001996917333733128,
22
+ "loss": 1.0315,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.3715170278637771,
27
+ "grad_norm": 0.3278755843639374,
28
+ "learning_rate": 0.00019930684569549264,
29
+ "loss": 0.9018,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.4953560371517028,
34
+ "grad_norm": 0.4095502495765686,
35
+ "learning_rate": 0.00019876883405951377,
36
+ "loss": 0.807,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.6191950464396285,
41
+ "grad_norm": 0.4147421717643738,
42
+ "learning_rate": 0.00019807852804032305,
43
+ "loss": 0.7204,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.7430340557275542,
48
+ "grad_norm": 0.2525322735309601,
49
+ "learning_rate": 0.00019723699203976766,
50
+ "loss": 0.6548,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.8668730650154799,
55
+ "grad_norm": 0.28104496002197266,
56
+ "learning_rate": 0.00019624552364536473,
57
+ "loss": 0.6687,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.9907120743034056,
62
+ "grad_norm": 0.4467855393886566,
63
+ "learning_rate": 0.00019510565162951537,
64
+ "loss": 0.6317,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.1145510835913313,
69
+ "grad_norm": 0.2571893036365509,
70
+ "learning_rate": 0.00019381913359224842,
71
+ "loss": 0.6319,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.238390092879257,
76
+ "grad_norm": 0.24546292424201965,
77
+ "learning_rate": 0.0001923879532511287,
78
+ "loss": 0.6262,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.3622291021671826,
83
+ "grad_norm": 0.24089373648166656,
84
+ "learning_rate": 0.00019081431738250814,
85
+ "loss": 0.6309,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 1.4860681114551084,
90
+ "grad_norm": 0.24842403829097748,
91
+ "learning_rate": 0.0001891006524188368,
92
+ "loss": 0.6142,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.609907120743034,
97
+ "grad_norm": 0.2339727133512497,
98
+ "learning_rate": 0.00018724960070727972,
99
+ "loss": 0.6131,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 1.7337461300309598,
104
+ "grad_norm": 0.21254688501358032,
105
+ "learning_rate": 0.00018526401643540922,
106
+ "loss": 0.5892,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 1.8575851393188856,
111
+ "grad_norm": 0.34352943301200867,
112
+ "learning_rate": 0.00018314696123025454,
113
+ "loss": 0.6037,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 1.9814241486068112,
118
+ "grad_norm": 0.21427258849143982,
119
+ "learning_rate": 0.00018090169943749476,
120
+ "loss": 0.6051,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 2.1052631578947367,
125
+ "grad_norm": 0.23226872086524963,
126
+ "learning_rate": 0.00017853169308807448,
127
+ "loss": 0.6109,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 2.2291021671826625,
132
+ "grad_norm": 0.254842072725296,
133
+ "learning_rate": 0.0001760405965600031,
134
+ "loss": 0.5912,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 2.3529411764705883,
139
+ "grad_norm": 0.2571081519126892,
140
+ "learning_rate": 0.00017343225094356855,
141
+ "loss": 0.5975,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 2.476780185758514,
146
+ "grad_norm": 0.25343191623687744,
147
+ "learning_rate": 0.00017071067811865476,
148
+ "loss": 0.5786,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 2.6006191950464395,
153
+ "grad_norm": 0.21258015930652618,
154
+ "learning_rate": 0.0001678800745532942,
155
+ "loss": 0.586,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 2.7244582043343653,
160
+ "grad_norm": 0.25848379731178284,
161
+ "learning_rate": 0.00016494480483301836,
162
+ "loss": 0.5714,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 2.848297213622291,
167
+ "grad_norm": 0.26716166734695435,
168
+ "learning_rate": 0.00016190939493098344,
169
+ "loss": 0.5887,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 2.972136222910217,
174
+ "grad_norm": 0.23578402400016785,
175
+ "learning_rate": 0.00015877852522924732,
176
+ "loss": 0.5902,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 3.0959752321981426,
181
+ "grad_norm": 0.23565009236335754,
182
+ "learning_rate": 0.00015555702330196023,
183
+ "loss": 0.5792,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 3.219814241486068,
188
+ "grad_norm": 0.2390134632587433,
189
+ "learning_rate": 0.0001522498564715949,
190
+ "loss": 0.5676,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 3.343653250773994,
195
+ "grad_norm": 0.25006794929504395,
196
+ "learning_rate": 0.00014886212414969553,
197
+ "loss": 0.5788,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 3.4674922600619196,
202
+ "grad_norm": 0.2533760666847229,
203
+ "learning_rate": 0.00014539904997395468,
204
+ "loss": 0.5769,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 3.5913312693498454,
209
+ "grad_norm": 0.2808171510696411,
210
+ "learning_rate": 0.0001418659737537428,
211
+ "loss": 0.5521,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 3.715170278637771,
216
+ "grad_norm": 0.28783777356147766,
217
+ "learning_rate": 0.000138268343236509,
218
+ "loss": 0.5723,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 3.8390092879256965,
223
+ "grad_norm": 0.29237958788871765,
224
+ "learning_rate": 0.0001346117057077493,
225
+ "loss": 0.5668,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 3.9628482972136223,
230
+ "grad_norm": 0.2757062315940857,
231
+ "learning_rate": 0.00013090169943749476,
232
+ "loss": 0.579,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 4.086687306501548,
237
+ "grad_norm": 0.28595200181007385,
238
+ "learning_rate": 0.00012714404498650743,
239
+ "loss": 0.5488,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 4.2105263157894735,
244
+ "grad_norm": 0.2707183063030243,
245
+ "learning_rate": 0.00012334453638559057,
246
+ "loss": 0.5511,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 4.3343653250774,
251
+ "grad_norm": 0.3559975028038025,
252
+ "learning_rate": 0.00011950903220161285,
253
+ "loss": 0.5683,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 4.458204334365325,
258
+ "grad_norm": 0.2762058973312378,
259
+ "learning_rate": 0.0001156434465040231,
260
+ "loss": 0.5499,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 4.58204334365325,
265
+ "grad_norm": 0.2717606723308563,
266
+ "learning_rate": 0.00011175373974578378,
267
+ "loss": 0.5612,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 4.705882352941177,
272
+ "grad_norm": 0.27757707238197327,
273
+ "learning_rate": 0.0001078459095727845,
274
+ "loss": 0.5602,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 4.829721362229102,
279
+ "grad_norm": 0.3977556526660919,
280
+ "learning_rate": 0.00010392598157590688,
281
+ "loss": 0.5459,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 4.953560371517028,
286
+ "grad_norm": 0.26867300271987915,
287
+ "learning_rate": 0.0001,
288
+ "loss": 0.537,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 5.077399380804954,
293
+ "grad_norm": 0.26843276619911194,
294
+ "learning_rate": 9.607401842409317e-05,
295
+ "loss": 0.5601,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 5.201238390092879,
300
+ "grad_norm": 0.30268290638923645,
301
+ "learning_rate": 9.215409042721552e-05,
302
+ "loss": 0.5317,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 5.325077399380805,
307
+ "grad_norm": 0.3163929581642151,
308
+ "learning_rate": 8.824626025421626e-05,
309
+ "loss": 0.5343,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 5.4489164086687305,
314
+ "grad_norm": 0.2883571982383728,
315
+ "learning_rate": 8.435655349597689e-05,
316
+ "loss": 0.5255,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 5.572755417956657,
321
+ "grad_norm": 0.3254496157169342,
322
+ "learning_rate": 8.049096779838719e-05,
323
+ "loss": 0.5281,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 5.696594427244582,
328
+ "grad_norm": 0.2983749508857727,
329
+ "learning_rate": 7.66554636144095e-05,
330
+ "loss": 0.5515,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 5.820433436532507,
335
+ "grad_norm": 0.2880017161369324,
336
+ "learning_rate": 7.285595501349258e-05,
337
+ "loss": 0.5575,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 5.944272445820434,
342
+ "grad_norm": 0.43873119354248047,
343
+ "learning_rate": 6.909830056250527e-05,
344
+ "loss": 0.5367,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 6.068111455108359,
349
+ "grad_norm": 0.33720219135284424,
350
+ "learning_rate": 6.538829429225069e-05,
351
+ "loss": 0.5509,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 6.191950464396285,
356
+ "grad_norm": 0.3185509741306305,
357
+ "learning_rate": 6.173165676349103e-05,
358
+ "loss": 0.5176,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 6.315789473684211,
363
+ "grad_norm": 0.3240034878253937,
364
+ "learning_rate": 5.8134026246257225e-05,
365
+ "loss": 0.5306,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 6.439628482972136,
370
+ "grad_norm": 0.33068713545799255,
371
+ "learning_rate": 5.4600950026045326e-05,
372
+ "loss": 0.517,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 6.563467492260062,
377
+ "grad_norm": 0.33544909954071045,
378
+ "learning_rate": 5.113787585030454e-05,
379
+ "loss": 0.5288,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 6.687306501547988,
384
+ "grad_norm": 0.3468843400478363,
385
+ "learning_rate": 4.7750143528405126e-05,
386
+ "loss": 0.5222,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 6.811145510835914,
391
+ "grad_norm": 0.33482104539871216,
392
+ "learning_rate": 4.444297669803981e-05,
393
+ "loss": 0.5227,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 6.934984520123839,
398
+ "grad_norm": 0.3804668188095093,
399
+ "learning_rate": 4.12214747707527e-05,
400
+ "loss": 0.5251,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 7.0588235294117645,
405
+ "grad_norm": 0.3186335861682892,
406
+ "learning_rate": 3.8090605069016595e-05,
407
+ "loss": 0.5264,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 7.182662538699691,
412
+ "grad_norm": 0.34853196144104004,
413
+ "learning_rate": 3.5055195166981645e-05,
414
+ "loss": 0.5281,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 7.306501547987616,
419
+ "grad_norm": 0.36451995372772217,
420
+ "learning_rate": 3.211992544670582e-05,
421
+ "loss": 0.5074,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 7.430340557275541,
426
+ "grad_norm": 0.3326849639415741,
427
+ "learning_rate": 2.9289321881345254e-05,
428
+ "loss": 0.5249,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 7.554179566563468,
433
+ "grad_norm": 0.3516250550746918,
434
+ "learning_rate": 2.6567749056431467e-05,
435
+ "loss": 0.5112,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 7.678018575851393,
440
+ "grad_norm": 0.3434501588344574,
441
+ "learning_rate": 2.3959403439996907e-05,
442
+ "loss": 0.5176,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 7.801857585139319,
447
+ "grad_norm": 0.3573139011859894,
448
+ "learning_rate": 2.146830691192553e-05,
449
+ "loss": 0.5251,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 7.925696594427245,
454
+ "grad_norm": 0.3552079200744629,
455
+ "learning_rate": 1.9098300562505266e-05,
456
+ "loss": 0.5066,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 8.04953560371517,
461
+ "grad_norm": 0.3211444020271301,
462
+ "learning_rate": 1.6853038769745467e-05,
463
+ "loss": 0.5255,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 8.173374613003096,
468
+ "grad_norm": 0.3437272310256958,
469
+ "learning_rate": 1.4735983564590783e-05,
470
+ "loss": 0.5152,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 8.297213622291022,
475
+ "grad_norm": 0.39420753717422485,
476
+ "learning_rate": 1.2750399292720283e-05,
477
+ "loss": 0.5147,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 8.421052631578947,
482
+ "grad_norm": 0.33711323142051697,
483
+ "learning_rate": 1.0899347581163221e-05,
484
+ "loss": 0.5053,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 8.544891640866872,
489
+ "grad_norm": 0.41042107343673706,
490
+ "learning_rate": 9.185682617491863e-06,
491
+ "loss": 0.4921,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 8.6687306501548,
496
+ "grad_norm": 0.3305673897266388,
497
+ "learning_rate": 7.612046748871327e-06,
498
+ "loss": 0.5182,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 8.792569659442725,
503
+ "grad_norm": 0.42124322056770325,
504
+ "learning_rate": 6.180866407751595e-06,
505
+ "loss": 0.5229,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 8.91640866873065,
510
+ "grad_norm": 0.3476842939853668,
511
+ "learning_rate": 4.8943483704846475e-06,
512
+ "loss": 0.517,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 9.040247678018575,
517
+ "grad_norm": 0.3766673803329468,
518
+ "learning_rate": 3.7544763546352834e-06,
519
+ "loss": 0.4968,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 9.1640866873065,
524
+ "grad_norm": 0.34576883912086487,
525
+ "learning_rate": 2.7630079602323442e-06,
526
+ "loss": 0.5143,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 9.287925696594428,
531
+ "grad_norm": 0.3424369692802429,
532
+ "learning_rate": 1.921471959676957e-06,
533
+ "loss": 0.5028,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 9.411764705882353,
538
+ "grad_norm": 0.3952752947807312,
539
+ "learning_rate": 1.231165940486234e-06,
540
+ "loss": 0.4951,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 9.535603715170279,
545
+ "grad_norm": 0.35501015186309814,
546
+ "learning_rate": 6.931543045073708e-07,
547
+ "loss": 0.5218,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 9.659442724458204,
552
+ "grad_norm": 0.3750287592411041,
553
+ "learning_rate": 3.0826662668720364e-07,
554
+ "loss": 0.5143,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 9.78328173374613,
559
+ "grad_norm": 0.336580365896225,
560
+ "learning_rate": 7.709637592770991e-08,
561
+ "loss": 0.5106,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 9.907120743034056,
566
+ "grad_norm": 0.35525137186050415,
567
+ "learning_rate": 0.0,
568
+ "loss": 0.514,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 9.907120743034056,
573
+ "step": 800,
574
+ "total_flos": 3.90379106992128e+16,
575
+ "train_loss": 0.5782659471035003,
576
+ "train_runtime": 2175.2449,
577
+ "train_samples_per_second": 1.485,
578
+ "train_steps_per_second": 0.368
579
+ }
580
+ ],
581
+ "logging_steps": 10,
582
+ "max_steps": 800,
583
+ "num_input_tokens_seen": 0,
584
+ "num_train_epochs": 10,
585
+ "save_steps": 500,
586
+ "total_flos": 3.90379106992128e+16,
587
+ "train_batch_size": 1,
588
+ "trial_name": null,
589
+ "trial_params": null
590
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6bcabbd06ed3bb6e5375af9e0f56fdfd6c61e840195cfe0cd74d724a76ebccf
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705a2853995e314484503d1a0ae51c3da964356e26fab03b8c300c38563e3519
3
  size 4984