emilykang commited on
Commit
75ffbaa
1 Parent(s): 43fe891

Training in progress, epoch 1

Browse files
adapter_config.json CHANGED
@@ -20,10 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
24
  "v_proj",
 
25
  "q_proj",
26
- "o_proj"
 
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "v_proj",
24
+ "fc1",
25
  "q_proj",
26
+ "k_proj",
27
+ "fc2",
28
+ "dense"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a7316815d035005ad9a4d3f4a9019f951d373f64d3617a6bf026eb6212c9f4b
3
- size 15754264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a42030dbfc1bcc5c6f1d1e64a90bdea47d97fd779dbf1190efdb07f2362f7c38
3
+ size 47236352
trainer_state.json ADDED
@@ -0,0 +1,548 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 740,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.13513513513513514,
13
+ "grad_norm": 10.65625,
14
+ "learning_rate": 0.00019990989662046818,
15
+ "loss": 1.0534,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.2702702702702703,
20
+ "grad_norm": 10.4765625,
21
+ "learning_rate": 0.00019963974885425266,
22
+ "loss": 0.9925,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.40540540540540543,
27
+ "grad_norm": 12.546875,
28
+ "learning_rate": 0.00019919004352588767,
29
+ "loss": 0.9846,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.5405405405405406,
34
+ "grad_norm": 10.9296875,
35
+ "learning_rate": 0.00019856159103477086,
36
+ "loss": 0.9861,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.6756756756756757,
41
+ "grad_norm": 12.125,
42
+ "learning_rate": 0.00019775552389476864,
43
+ "loss": 0.9614,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.8108108108108109,
48
+ "grad_norm": 11.1640625,
49
+ "learning_rate": 0.0001967732946933499,
50
+ "loss": 0.9254,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.9459459459459459,
55
+ "grad_norm": 11.2109375,
56
+ "learning_rate": 0.00019561667347392508,
57
+ "loss": 0.9275,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 1.0810810810810811,
62
+ "grad_norm": 12.0703125,
63
+ "learning_rate": 0.00019428774454610843,
64
+ "loss": 0.9252,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.2162162162162162,
69
+ "grad_norm": 10.671875,
70
+ "learning_rate": 0.00019278890272965096,
71
+ "loss": 0.8997,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.3513513513513513,
76
+ "grad_norm": 10.0234375,
77
+ "learning_rate": 0.0001911228490388136,
78
+ "loss": 0.8997,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.4864864864864864,
83
+ "grad_norm": 9.828125,
84
+ "learning_rate": 0.00018929258581495685,
85
+ "loss": 0.9081,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 1.6216216216216215,
90
+ "grad_norm": 9.78125,
91
+ "learning_rate": 0.00018730141131611882,
92
+ "loss": 0.88,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.7567567567567568,
97
+ "grad_norm": 9.625,
98
+ "learning_rate": 0.00018515291377333112,
99
+ "loss": 0.8677,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 1.8918918918918919,
104
+ "grad_norm": 10.1875,
105
+ "learning_rate": 0.00018285096492438424,
106
+ "loss": 0.8999,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 2.027027027027027,
111
+ "grad_norm": 11.6640625,
112
+ "learning_rate": 0.00018039971303669407,
113
+ "loss": 0.9,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 2.1621621621621623,
118
+ "grad_norm": 12.2109375,
119
+ "learning_rate": 0.00017780357543184397,
120
+ "loss": 0.912,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 2.2972972972972974,
125
+ "grad_norm": 14.1640625,
126
+ "learning_rate": 0.00017506723052527242,
127
+ "loss": 0.8953,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 2.4324324324324325,
132
+ "grad_norm": 15.015625,
133
+ "learning_rate": 0.00017219560939545246,
134
+ "loss": 0.9759,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 2.5675675675675675,
139
+ "grad_norm": 15.5546875,
140
+ "learning_rate": 0.00016919388689775464,
141
+ "loss": 1.0338,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 2.7027027027027026,
146
+ "grad_norm": 16.5,
147
+ "learning_rate": 0.00016606747233900815,
148
+ "loss": 1.0389,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 2.8378378378378377,
153
+ "grad_norm": 16.9375,
154
+ "learning_rate": 0.00016282199972956425,
155
+ "loss": 1.0149,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 2.972972972972973,
160
+ "grad_norm": 14.21875,
161
+ "learning_rate": 0.00015946331763042867,
162
+ "loss": 0.9946,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 3.108108108108108,
167
+ "grad_norm": 11.09375,
168
+ "learning_rate": 0.00015599747861375955,
169
+ "loss": 0.9629,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 3.2432432432432434,
174
+ "grad_norm": 13.4921875,
175
+ "learning_rate": 0.00015243072835572318,
176
+ "loss": 0.9677,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 3.3783783783783785,
181
+ "grad_norm": 13.3046875,
182
+ "learning_rate": 0.00014876949438136347,
183
+ "loss": 0.9327,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 3.5135135135135136,
188
+ "grad_norm": 13.03125,
189
+ "learning_rate": 0.00014502037448176734,
190
+ "loss": 0.9566,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 3.6486486486486487,
195
+ "grad_norm": 11.9921875,
196
+ "learning_rate": 0.0001411901248243993,
197
+ "loss": 0.913,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 3.7837837837837838,
202
+ "grad_norm": 10.953125,
203
+ "learning_rate": 0.00013728564777803088,
204
+ "loss": 0.9266,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 3.918918918918919,
209
+ "grad_norm": 12.15625,
210
+ "learning_rate": 0.00013331397947420576,
211
+ "loss": 0.8859,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 4.054054054054054,
216
+ "grad_norm": 13.1171875,
217
+ "learning_rate": 0.00012928227712765504,
218
+ "loss": 0.8896,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 4.1891891891891895,
223
+ "grad_norm": 11.8203125,
224
+ "learning_rate": 0.00012519780613851254,
225
+ "loss": 0.8317,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 4.324324324324325,
230
+ "grad_norm": 12.53125,
231
+ "learning_rate": 0.00012106792699957263,
232
+ "loss": 0.8712,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 4.45945945945946,
237
+ "grad_norm": 12.671875,
238
+ "learning_rate": 0.00011690008203218493,
239
+ "loss": 0.8436,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 4.594594594594595,
244
+ "grad_norm": 15.8515625,
245
+ "learning_rate": 0.00011270178197468789,
246
+ "loss": 0.8538,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 4.72972972972973,
251
+ "grad_norm": 12.46875,
252
+ "learning_rate": 0.00010848059244755093,
253
+ "loss": 0.8787,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 4.864864864864865,
258
+ "grad_norm": 11.921875,
259
+ "learning_rate": 0.00010424412031961484,
260
+ "loss": 0.8823,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 5.0,
265
+ "grad_norm": 11.8203125,
266
+ "learning_rate": 0.0001,
267
+ "loss": 0.8839,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 5.135135135135135,
272
+ "grad_norm": 11.515625,
273
+ "learning_rate": 9.57558796803852e-05,
274
+ "loss": 0.8362,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 5.27027027027027,
279
+ "grad_norm": 12.15625,
280
+ "learning_rate": 9.151940755244912e-05,
281
+ "loss": 0.8678,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 5.405405405405405,
286
+ "grad_norm": 13.109375,
287
+ "learning_rate": 8.729821802531212e-05,
288
+ "loss": 0.8372,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 5.54054054054054,
293
+ "grad_norm": 12.96875,
294
+ "learning_rate": 8.309991796781511e-05,
295
+ "loss": 0.8662,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 5.675675675675675,
300
+ "grad_norm": 15.203125,
301
+ "learning_rate": 7.89320730004274e-05,
302
+ "loss": 0.9021,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 5.8108108108108105,
307
+ "grad_norm": 12.4765625,
308
+ "learning_rate": 7.48021938614875e-05,
309
+ "loss": 0.8902,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 5.945945945945946,
314
+ "grad_norm": 12.953125,
315
+ "learning_rate": 7.071772287234497e-05,
316
+ "loss": 0.852,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 6.081081081081081,
321
+ "grad_norm": 14.9609375,
322
+ "learning_rate": 6.668602052579424e-05,
323
+ "loss": 0.8743,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 6.216216216216216,
328
+ "grad_norm": 12.8828125,
329
+ "learning_rate": 6.271435222196916e-05,
330
+ "loss": 0.8844,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 6.351351351351352,
335
+ "grad_norm": 13.3984375,
336
+ "learning_rate": 5.880987517560075e-05,
337
+ "loss": 0.8924,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 6.486486486486487,
342
+ "grad_norm": 14.3046875,
343
+ "learning_rate": 5.497962551823266e-05,
344
+ "loss": 0.9041,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 6.621621621621622,
349
+ "grad_norm": 15.421875,
350
+ "learning_rate": 5.123050561863657e-05,
351
+ "loss": 0.871,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 6.756756756756757,
356
+ "grad_norm": 12.7109375,
357
+ "learning_rate": 4.756927164427685e-05,
358
+ "loss": 0.8924,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 6.891891891891892,
363
+ "grad_norm": 13.765625,
364
+ "learning_rate": 4.4002521386240466e-05,
365
+ "loss": 0.9047,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 7.027027027027027,
370
+ "grad_norm": 13.09375,
371
+ "learning_rate": 4.053668236957134e-05,
372
+ "loss": 0.9083,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 7.162162162162162,
377
+ "grad_norm": 13.875,
378
+ "learning_rate": 3.717800027043576e-05,
379
+ "loss": 0.8721,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 7.297297297297297,
384
+ "grad_norm": 12.09375,
385
+ "learning_rate": 3.393252766099187e-05,
386
+ "loss": 0.916,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 7.4324324324324325,
391
+ "grad_norm": 12.3671875,
392
+ "learning_rate": 3.080611310224539e-05,
393
+ "loss": 0.8714,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 7.5675675675675675,
398
+ "grad_norm": 13.2109375,
399
+ "learning_rate": 2.7804390604547557e-05,
400
+ "loss": 0.8843,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 7.702702702702703,
405
+ "grad_norm": 13.9765625,
406
+ "learning_rate": 2.493276947472756e-05,
407
+ "loss": 0.8934,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 7.837837837837838,
412
+ "grad_norm": 14.28125,
413
+ "learning_rate": 2.2196424568156073e-05,
414
+ "loss": 0.8953,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 7.972972972972973,
419
+ "grad_norm": 14.8828125,
420
+ "learning_rate": 1.9600286963305957e-05,
421
+ "loss": 0.8728,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 8.108108108108109,
426
+ "grad_norm": 13.2890625,
427
+ "learning_rate": 1.7149035075615794e-05,
428
+ "loss": 0.8995,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 8.243243243243244,
433
+ "grad_norm": 14.7578125,
434
+ "learning_rate": 1.4847086226668872e-05,
435
+ "loss": 0.8685,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 8.378378378378379,
440
+ "grad_norm": 12.0703125,
441
+ "learning_rate": 1.2698588683881186e-05,
442
+ "loss": 0.88,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 8.513513513513514,
447
+ "grad_norm": 16.8125,
448
+ "learning_rate": 1.0707414185043163e-05,
449
+ "loss": 0.8936,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 8.64864864864865,
454
+ "grad_norm": 14.0859375,
455
+ "learning_rate": 8.87715096118642e-06,
456
+ "loss": 0.8745,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 8.783783783783784,
461
+ "grad_norm": 13.1796875,
462
+ "learning_rate": 7.211097270349066e-06,
463
+ "loss": 0.8849,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 8.91891891891892,
468
+ "grad_norm": 12.6328125,
469
+ "learning_rate": 5.71225545389158e-06,
470
+ "loss": 0.8775,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 9.054054054054054,
475
+ "grad_norm": 12.15625,
476
+ "learning_rate": 4.383326526074916e-06,
477
+ "loss": 0.8663,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 9.18918918918919,
482
+ "grad_norm": 12.9140625,
483
+ "learning_rate": 3.226705306650113e-06,
484
+ "loss": 0.8975,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 9.324324324324325,
489
+ "grad_norm": 14.265625,
490
+ "learning_rate": 2.2444761052313856e-06,
491
+ "loss": 0.8677,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 9.45945945945946,
496
+ "grad_norm": 14.46875,
497
+ "learning_rate": 1.4384089652291543e-06,
498
+ "loss": 0.8565,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 9.594594594594595,
503
+ "grad_norm": 13.4375,
504
+ "learning_rate": 8.099564741123166e-07,
505
+ "loss": 0.8619,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 9.72972972972973,
510
+ "grad_norm": 13.5859375,
511
+ "learning_rate": 3.6025114574734785e-07,
512
+ "loss": 0.8956,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 9.864864864864865,
517
+ "grad_norm": 14.1796875,
518
+ "learning_rate": 9.010337953185843e-08,
519
+ "loss": 0.8906,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 10.0,
524
+ "grad_norm": 13.2109375,
525
+ "learning_rate": 0.0,
526
+ "loss": 0.8617,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 10.0,
531
+ "step": 740,
532
+ "total_flos": 4.83113130000384e+16,
533
+ "train_loss": 0.9043467921179694,
534
+ "train_runtime": 626.4938,
535
+ "train_samples_per_second": 4.725,
536
+ "train_steps_per_second": 1.181
537
+ }
538
+ ],
539
+ "logging_steps": 10,
540
+ "max_steps": 740,
541
+ "num_input_tokens_seen": 0,
542
+ "num_train_epochs": 10,
543
+ "save_steps": 500,
544
+ "total_flos": 4.83113130000384e+16,
545
+ "train_batch_size": 1,
546
+ "trial_name": null,
547
+ "trial_params": null
548
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdf6491437da642350f409bd59645604aa9185e20e5cc3a96b65425ebf9384a9
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76fb599c21eb9014a713ee33e1f268cdfd0aed67152cbcc483a7e45c3976f1ba
3
  size 4984