irishprancer commited on
Commit
4ee4b67
·
verified ·
1 Parent(s): 5e471b4

Training in progress, step 150, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -22,8 +22,8 @@
22
  "rank_pattern": {},
23
  "revision": null,
24
  "target_modules": [
25
- "k_proj",
26
- "q_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
22
  "rank_pattern": {},
23
  "revision": null,
24
  "target_modules": [
25
+ "q_proj",
26
+ "k_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca2c73898824981f7e0729fc57be3e758b804c6877cb01d8db2421cd68ab9ec7
3
  size 527048968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43183ff9e2c22dbb93053273874eb9b6d646a176f5fb18f0dd31185db05e7377
3
  size 527048968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfa421196ea17ada7bbfeeaa47740f883958c13c1c7bf744610376f3f45e10dc
3
  size 1054135994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce614b24ca436c74852389641c5cfce89558c20d90b29c1d08fdf6301620fda1
3
  size 1054135994
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30b57ec052aeaf035e39cd5057ce6977dfdadd2be87b9e8aaa1d9afd55d2f8e1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afdcd158786234085082ce38b1824c51dd8c72881220443fc2d1c6f4e031a983
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8974fc0327a603be8a90ee235d3ef81c4ee4af2818c873bdeb9bfb38f108e1a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cf3f988e8fed2daa2e801eb1f19b681872781cf57f0fb7b896e859a12cfe2bb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,577 +1,125 @@
1
  {
2
- "best_metric": 0.7164609432220459,
3
- "best_model_checkpoint": "./output/checkpoint-450",
4
- "epoch": 32.608695652173914,
5
  "eval_steps": 150,
6
- "global_step": 750,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.43478260869565216,
13
- "grad_norm": 1.5021647214889526,
14
  "learning_rate": 3e-06,
15
- "loss": 0.9064,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.8695652173913043,
20
- "grad_norm": 1.6793277263641357,
21
  "learning_rate": 6e-06,
22
- "loss": 0.9024,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 1.3043478260869565,
27
- "grad_norm": 1.7296056747436523,
28
  "learning_rate": 9e-06,
29
- "loss": 0.9,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 1.7391304347826086,
34
- "grad_norm": 1.4458602666854858,
35
  "learning_rate": 1.2e-05,
36
- "loss": 0.9086,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 2.1739130434782608,
41
- "grad_norm": 1.3516699075698853,
42
  "learning_rate": 1.5e-05,
43
- "loss": 0.8359,
44
  "step": 50
45
  },
46
  {
47
  "epoch": 2.608695652173913,
48
- "grad_norm": 2.03114914894104,
49
  "learning_rate": 1.8e-05,
50
- "loss": 0.8892,
51
  "step": 60
52
  },
53
  {
54
  "epoch": 3.0434782608695654,
55
- "grad_norm": 1.4920729398727417,
56
  "learning_rate": 2.1e-05,
57
- "loss": 0.8913,
58
  "step": 70
59
  },
60
  {
61
  "epoch": 3.4782608695652173,
62
- "grad_norm": 1.7293280363082886,
63
  "learning_rate": 2.4e-05,
64
- "loss": 0.8234,
65
  "step": 80
66
  },
67
  {
68
  "epoch": 3.9130434782608696,
69
- "grad_norm": 1.4240705966949463,
70
  "learning_rate": 2.7000000000000002e-05,
71
- "loss": 0.8529,
72
  "step": 90
73
  },
74
  {
75
  "epoch": 4.3478260869565215,
76
- "grad_norm": 1.3656291961669922,
77
  "learning_rate": 3e-05,
78
- "loss": 0.8649,
79
  "step": 100
80
  },
81
  {
82
  "epoch": 4.782608695652174,
83
- "grad_norm": 2.198136806488037,
84
  "learning_rate": 2.999999702723963e-05,
85
- "loss": 0.8227,
86
  "step": 110
87
  },
88
  {
89
  "epoch": 5.217391304347826,
90
- "grad_norm": 1.0726988315582275,
91
  "learning_rate": 2.9999988108959687e-05,
92
- "loss": 0.765,
93
  "step": 120
94
  },
95
  {
96
  "epoch": 5.6521739130434785,
97
- "grad_norm": 1.5672078132629395,
98
  "learning_rate": 2.9999973245163716e-05,
99
- "loss": 0.7413,
100
  "step": 130
101
  },
102
  {
103
  "epoch": 6.086956521739131,
104
- "grad_norm": 1.9071016311645508,
105
  "learning_rate": 2.99999524358576e-05,
106
- "loss": 0.7655,
107
  "step": 140
108
  },
109
  {
110
  "epoch": 6.521739130434782,
111
- "grad_norm": 1.1219961643218994,
112
  "learning_rate": 2.9999925681049593e-05,
113
- "loss": 0.7855,
114
  "step": 150
115
  },
116
  {
117
  "epoch": 6.521739130434782,
118
- "eval_loss": 0.7960985898971558,
119
- "eval_runtime": 0.5137,
120
- "eval_samples_per_second": 19.465,
121
- "eval_steps_per_second": 19.465,
122
  "step": 150
123
- },
124
- {
125
- "epoch": 6.956521739130435,
126
- "grad_norm": 1.5404783487319946,
127
- "learning_rate": 2.9999892980750297e-05,
128
- "loss": 0.6588,
129
- "step": 160
130
- },
131
- {
132
- "epoch": 7.391304347826087,
133
- "grad_norm": 1.3464210033416748,
134
- "learning_rate": 2.9999854334972675e-05,
135
- "loss": 0.739,
136
- "step": 170
137
- },
138
- {
139
- "epoch": 7.826086956521739,
140
- "grad_norm": 1.7264870405197144,
141
- "learning_rate": 2.999980974373204e-05,
142
- "loss": 0.7292,
143
- "step": 180
144
- },
145
- {
146
- "epoch": 8.26086956521739,
147
- "grad_norm": 1.5393368005752563,
148
- "learning_rate": 2.9999759207046075e-05,
149
- "loss": 0.6244,
150
- "step": 190
151
- },
152
- {
153
- "epoch": 8.695652173913043,
154
- "grad_norm": 1.7342770099639893,
155
- "learning_rate": 2.9999702724934804e-05,
156
- "loss": 0.6764,
157
- "step": 200
158
- },
159
- {
160
- "epoch": 9.130434782608695,
161
- "grad_norm": 1.0416548252105713,
162
- "learning_rate": 2.999964029742062e-05,
163
- "loss": 0.6521,
164
- "step": 210
165
- },
166
- {
167
- "epoch": 9.565217391304348,
168
- "grad_norm": 1.2193585634231567,
169
- "learning_rate": 2.9999571924528263e-05,
170
- "loss": 0.5592,
171
- "step": 220
172
- },
173
- {
174
- "epoch": 10.0,
175
- "grad_norm": 1.5286610126495361,
176
- "learning_rate": 2.9999497606284837e-05,
177
- "loss": 0.756,
178
- "step": 230
179
- },
180
- {
181
- "epoch": 10.434782608695652,
182
- "grad_norm": 1.427451252937317,
183
- "learning_rate": 2.9999417342719796e-05,
184
- "loss": 0.7118,
185
- "step": 240
186
- },
187
- {
188
- "epoch": 10.869565217391305,
189
- "grad_norm": 0.9794074296951294,
190
- "learning_rate": 2.9999331133864956e-05,
191
- "loss": 0.5897,
192
- "step": 250
193
- },
194
- {
195
- "epoch": 11.304347826086957,
196
- "grad_norm": 1.194082260131836,
197
- "learning_rate": 2.9999238979754485e-05,
198
- "loss": 0.6548,
199
- "step": 260
200
- },
201
- {
202
- "epoch": 11.73913043478261,
203
- "grad_norm": 1.0489437580108643,
204
- "learning_rate": 2.999914088042492e-05,
205
- "loss": 0.6474,
206
- "step": 270
207
- },
208
- {
209
- "epoch": 12.173913043478262,
210
- "grad_norm": 1.3105570077896118,
211
- "learning_rate": 2.9999036835915132e-05,
212
- "loss": 0.5936,
213
- "step": 280
214
- },
215
- {
216
- "epoch": 12.608695652173914,
217
- "grad_norm": 1.0830979347229004,
218
- "learning_rate": 2.9998926846266365e-05,
219
- "loss": 0.6328,
220
- "step": 290
221
- },
222
- {
223
- "epoch": 13.043478260869565,
224
- "grad_norm": 1.3943493366241455,
225
- "learning_rate": 2.9998810911522213e-05,
226
- "loss": 0.5806,
227
- "step": 300
228
- },
229
- {
230
- "epoch": 13.043478260869565,
231
- "eval_loss": 0.7312111854553223,
232
- "eval_runtime": 0.6239,
233
- "eval_samples_per_second": 16.028,
234
- "eval_steps_per_second": 16.028,
235
- "step": 300
236
- },
237
- {
238
- "epoch": 13.478260869565217,
239
- "grad_norm": 1.7821625471115112,
240
- "learning_rate": 2.9998689031728636e-05,
241
- "loss": 0.5143,
242
- "step": 310
243
- },
244
- {
245
- "epoch": 13.91304347826087,
246
- "grad_norm": 1.5245319604873657,
247
- "learning_rate": 2.9998561206933938e-05,
248
- "loss": 0.6494,
249
- "step": 320
250
- },
251
- {
252
- "epoch": 14.347826086956522,
253
- "grad_norm": 1.479852557182312,
254
- "learning_rate": 2.9998427437188786e-05,
255
- "loss": 0.5744,
256
- "step": 330
257
- },
258
- {
259
- "epoch": 14.782608695652174,
260
- "grad_norm": 1.318290114402771,
261
- "learning_rate": 2.99982877225462e-05,
262
- "loss": 0.6014,
263
- "step": 340
264
- },
265
- {
266
- "epoch": 15.217391304347826,
267
- "grad_norm": 0.9775345921516418,
268
- "learning_rate": 2.9998142063061564e-05,
269
- "loss": 0.4988,
270
- "step": 350
271
- },
272
- {
273
- "epoch": 15.652173913043478,
274
- "grad_norm": 1.642491340637207,
275
- "learning_rate": 2.9997990458792603e-05,
276
- "loss": 0.5628,
277
- "step": 360
278
- },
279
- {
280
- "epoch": 16.08695652173913,
281
- "grad_norm": 1.6377389430999756,
282
- "learning_rate": 2.9997832909799417e-05,
283
- "loss": 0.6675,
284
- "step": 370
285
- },
286
- {
287
- "epoch": 16.52173913043478,
288
- "grad_norm": 0.9537637829780579,
289
- "learning_rate": 2.9997669416144452e-05,
290
- "loss": 0.5133,
291
- "step": 380
292
- },
293
- {
294
- "epoch": 16.956521739130434,
295
- "grad_norm": 0.9352350234985352,
296
- "learning_rate": 2.999749997789251e-05,
297
- "loss": 0.5792,
298
- "step": 390
299
- },
300
- {
301
- "epoch": 17.391304347826086,
302
- "grad_norm": 1.112601399421692,
303
- "learning_rate": 2.9997324595110743e-05,
304
- "loss": 0.5175,
305
- "step": 400
306
- },
307
- {
308
- "epoch": 17.82608695652174,
309
- "grad_norm": 1.284747838973999,
310
- "learning_rate": 2.9997143267868683e-05,
311
- "loss": 0.5879,
312
- "step": 410
313
- },
314
- {
315
- "epoch": 18.26086956521739,
316
- "grad_norm": 1.1622997522354126,
317
- "learning_rate": 2.9996955996238192e-05,
318
- "loss": 0.5061,
319
- "step": 420
320
- },
321
- {
322
- "epoch": 18.695652173913043,
323
- "grad_norm": 1.1977813243865967,
324
- "learning_rate": 2.9996762780293503e-05,
325
- "loss": 0.5318,
326
- "step": 430
327
- },
328
- {
329
- "epoch": 19.130434782608695,
330
- "grad_norm": 1.2117533683776855,
331
- "learning_rate": 2.9996563620111197e-05,
332
- "loss": 0.5336,
333
- "step": 440
334
- },
335
- {
336
- "epoch": 19.565217391304348,
337
- "grad_norm": 1.4293084144592285,
338
- "learning_rate": 2.9996358515770218e-05,
339
- "loss": 0.5678,
340
- "step": 450
341
- },
342
- {
343
- "epoch": 19.565217391304348,
344
- "eval_loss": 0.7164609432220459,
345
- "eval_runtime": 0.3868,
346
- "eval_samples_per_second": 25.854,
347
- "eval_steps_per_second": 25.854,
348
- "step": 450
349
- },
350
- {
351
- "epoch": 20.0,
352
- "grad_norm": 2.1205103397369385,
353
- "learning_rate": 2.9996147467351856e-05,
354
- "loss": 0.5147,
355
- "step": 460
356
- },
357
- {
358
- "epoch": 20.434782608695652,
359
- "grad_norm": 1.27629554271698,
360
- "learning_rate": 2.9995930474939773e-05,
361
- "loss": 0.4782,
362
- "step": 470
363
- },
364
- {
365
- "epoch": 20.869565217391305,
366
- "grad_norm": 1.4705679416656494,
367
- "learning_rate": 2.9995707538619975e-05,
368
- "loss": 0.5705,
369
- "step": 480
370
- },
371
- {
372
- "epoch": 21.304347826086957,
373
- "grad_norm": 1.3248465061187744,
374
- "learning_rate": 2.9995478658480822e-05,
375
- "loss": 0.5161,
376
- "step": 490
377
- },
378
- {
379
- "epoch": 21.73913043478261,
380
- "grad_norm": 1.2424507141113281,
381
- "learning_rate": 2.9995243834613043e-05,
382
- "loss": 0.5204,
383
- "step": 500
384
- },
385
- {
386
- "epoch": 22.17391304347826,
387
- "grad_norm": 1.783718228340149,
388
- "learning_rate": 2.9995003067109707e-05,
389
- "loss": 0.4837,
390
- "step": 510
391
- },
392
- {
393
- "epoch": 22.608695652173914,
394
- "grad_norm": 1.539941430091858,
395
- "learning_rate": 2.9994756356066246e-05,
396
- "loss": 0.5617,
397
- "step": 520
398
- },
399
- {
400
- "epoch": 23.043478260869566,
401
- "grad_norm": 1.7417247295379639,
402
- "learning_rate": 2.999450370158046e-05,
403
- "loss": 0.4929,
404
- "step": 530
405
- },
406
- {
407
- "epoch": 23.47826086956522,
408
- "grad_norm": 1.3086825609207153,
409
- "learning_rate": 2.9994245103752478e-05,
410
- "loss": 0.4383,
411
- "step": 540
412
- },
413
- {
414
- "epoch": 23.91304347826087,
415
- "grad_norm": 1.2279788255691528,
416
- "learning_rate": 2.999398056268481e-05,
417
- "loss": 0.5266,
418
- "step": 550
419
- },
420
- {
421
- "epoch": 24.347826086956523,
422
- "grad_norm": 1.40565025806427,
423
- "learning_rate": 2.9993710078482306e-05,
424
- "loss": 0.5207,
425
- "step": 560
426
- },
427
- {
428
- "epoch": 24.782608695652176,
429
- "grad_norm": 0.9529893398284912,
430
- "learning_rate": 2.9993433651252185e-05,
431
- "loss": 0.4429,
432
- "step": 570
433
- },
434
- {
435
- "epoch": 25.217391304347824,
436
- "grad_norm": 1.7137924432754517,
437
- "learning_rate": 2.9993151281104006e-05,
438
- "loss": 0.5325,
439
- "step": 580
440
- },
441
- {
442
- "epoch": 25.652173913043477,
443
- "grad_norm": 1.1403567790985107,
444
- "learning_rate": 2.9992862968149695e-05,
445
- "loss": 0.4734,
446
- "step": 590
447
- },
448
- {
449
- "epoch": 26.08695652173913,
450
- "grad_norm": 1.1702338457107544,
451
- "learning_rate": 2.9992568712503533e-05,
452
- "loss": 0.4609,
453
- "step": 600
454
- },
455
- {
456
- "epoch": 26.08695652173913,
457
- "eval_loss": 0.7209551334381104,
458
- "eval_runtime": 0.4345,
459
- "eval_samples_per_second": 23.015,
460
- "eval_steps_per_second": 23.015,
461
- "step": 600
462
- },
463
- {
464
- "epoch": 26.52173913043478,
465
- "grad_norm": 1.076659917831421,
466
- "learning_rate": 2.9992268514282142e-05,
467
- "loss": 0.5118,
468
- "step": 610
469
- },
470
- {
471
- "epoch": 26.956521739130434,
472
- "grad_norm": 1.320320963859558,
473
- "learning_rate": 2.999196237360452e-05,
474
- "loss": 0.4315,
475
- "step": 620
476
- },
477
- {
478
- "epoch": 27.391304347826086,
479
- "grad_norm": 1.1899269819259644,
480
- "learning_rate": 2.9991650290592016e-05,
481
- "loss": 0.476,
482
- "step": 630
483
- },
484
- {
485
- "epoch": 27.82608695652174,
486
- "grad_norm": 1.3601988554000854,
487
- "learning_rate": 2.999133226536832e-05,
488
- "loss": 0.5014,
489
- "step": 640
490
- },
491
- {
492
- "epoch": 28.26086956521739,
493
- "grad_norm": 1.380045771598816,
494
- "learning_rate": 2.9991008298059493e-05,
495
- "loss": 0.4115,
496
- "step": 650
497
- },
498
- {
499
- "epoch": 28.695652173913043,
500
- "grad_norm": 1.549436092376709,
501
- "learning_rate": 2.9990678388793944e-05,
502
- "loss": 0.5072,
503
- "step": 660
504
- },
505
- {
506
- "epoch": 29.130434782608695,
507
- "grad_norm": 1.2787128686904907,
508
- "learning_rate": 2.999034253770244e-05,
509
- "loss": 0.4353,
510
- "step": 670
511
- },
512
- {
513
- "epoch": 29.565217391304348,
514
- "grad_norm": 1.0582035779953003,
515
- "learning_rate": 2.9990000744918097e-05,
516
- "loss": 0.4715,
517
- "step": 680
518
- },
519
- {
520
- "epoch": 30.0,
521
- "grad_norm": 2.4310319423675537,
522
- "learning_rate": 2.9989653010576392e-05,
523
- "loss": 0.4152,
524
- "step": 690
525
- },
526
- {
527
- "epoch": 30.434782608695652,
528
- "grad_norm": 1.2908227443695068,
529
- "learning_rate": 2.9989299334815158e-05,
530
- "loss": 0.478,
531
- "step": 700
532
- },
533
- {
534
- "epoch": 30.869565217391305,
535
- "grad_norm": 1.5819599628448486,
536
- "learning_rate": 2.9988939717774578e-05,
537
- "loss": 0.4132,
538
- "step": 710
539
- },
540
- {
541
- "epoch": 31.304347826086957,
542
- "grad_norm": 0.8957367539405823,
543
- "learning_rate": 2.9988574159597194e-05,
544
- "loss": 0.4261,
545
- "step": 720
546
- },
547
- {
548
- "epoch": 31.73913043478261,
549
- "grad_norm": 1.5984803438186646,
550
- "learning_rate": 2.9988202660427907e-05,
551
- "loss": 0.4842,
552
- "step": 730
553
- },
554
- {
555
- "epoch": 32.17391304347826,
556
- "grad_norm": 1.1771948337554932,
557
- "learning_rate": 2.9987825220413958e-05,
558
- "loss": 0.4401,
559
- "step": 740
560
- },
561
- {
562
- "epoch": 32.608695652173914,
563
- "grad_norm": 1.7258983850479126,
564
- "learning_rate": 2.998744183970496e-05,
565
- "loss": 0.4753,
566
- "step": 750
567
- },
568
- {
569
- "epoch": 32.608695652173914,
570
- "eval_loss": 0.7315500974655151,
571
- "eval_runtime": 0.4171,
572
- "eval_samples_per_second": 23.973,
573
- "eval_steps_per_second": 23.973,
574
- "step": 750
575
  }
576
  ],
577
  "logging_steps": 10,
@@ -591,7 +139,7 @@
591
  "attributes": {}
592
  }
593
  },
594
- "total_flos": 1.9231766387195904e+16,
595
  "train_batch_size": 4,
596
  "trial_name": null,
597
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7971361875534058,
3
+ "best_model_checkpoint": "./output/checkpoint-150",
4
+ "epoch": 6.521739130434782,
5
  "eval_steps": 150,
6
+ "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.43478260869565216,
13
+ "grad_norm": 1.502166986465454,
14
  "learning_rate": 3e-06,
15
+ "loss": 0.9062,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.8695652173913043,
20
+ "grad_norm": 1.687074065208435,
21
  "learning_rate": 6e-06,
22
+ "loss": 0.9026,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 1.3043478260869565,
27
+ "grad_norm": 1.7296172380447388,
28
  "learning_rate": 9e-06,
29
+ "loss": 0.9002,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 1.7391304347826086,
34
+ "grad_norm": 1.4458578824996948,
35
  "learning_rate": 1.2e-05,
36
+ "loss": 0.9088,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 2.1739130434782608,
41
+ "grad_norm": 1.3517787456512451,
42
  "learning_rate": 1.5e-05,
43
+ "loss": 0.8361,
44
  "step": 50
45
  },
46
  {
47
  "epoch": 2.608695652173913,
48
+ "grad_norm": 2.0466721057891846,
49
  "learning_rate": 1.8e-05,
50
+ "loss": 0.8895,
51
  "step": 60
52
  },
53
  {
54
  "epoch": 3.0434782608695654,
55
+ "grad_norm": 1.4843413829803467,
56
  "learning_rate": 2.1e-05,
57
+ "loss": 0.8915,
58
  "step": 70
59
  },
60
  {
61
  "epoch": 3.4782608695652173,
62
+ "grad_norm": 1.7294325828552246,
63
  "learning_rate": 2.4e-05,
64
+ "loss": 0.8233,
65
  "step": 80
66
  },
67
  {
68
  "epoch": 3.9130434782608696,
69
+ "grad_norm": 1.424039602279663,
70
  "learning_rate": 2.7000000000000002e-05,
71
+ "loss": 0.8528,
72
  "step": 90
73
  },
74
  {
75
  "epoch": 4.3478260869565215,
76
+ "grad_norm": 1.3659141063690186,
77
  "learning_rate": 3e-05,
78
+ "loss": 0.8647,
79
  "step": 100
80
  },
81
  {
82
  "epoch": 4.782608695652174,
83
+ "grad_norm": 2.1984479427337646,
84
  "learning_rate": 2.999999702723963e-05,
85
+ "loss": 0.8224,
86
  "step": 110
87
  },
88
  {
89
  "epoch": 5.217391304347826,
90
+ "grad_norm": 1.0726439952850342,
91
  "learning_rate": 2.9999988108959687e-05,
92
+ "loss": 0.7649,
93
  "step": 120
94
  },
95
  {
96
  "epoch": 5.6521739130434785,
97
+ "grad_norm": 1.5597559213638306,
98
  "learning_rate": 2.9999973245163716e-05,
99
+ "loss": 0.7412,
100
  "step": 130
101
  },
102
  {
103
  "epoch": 6.086956521739131,
104
+ "grad_norm": 1.9070907831192017,
105
  "learning_rate": 2.99999524358576e-05,
106
+ "loss": 0.7652,
107
  "step": 140
108
  },
109
  {
110
  "epoch": 6.521739130434782,
111
+ "grad_norm": 1.1221362352371216,
112
  "learning_rate": 2.9999925681049593e-05,
113
+ "loss": 0.7857,
114
  "step": 150
115
  },
116
  {
117
  "epoch": 6.521739130434782,
118
+ "eval_loss": 0.7971361875534058,
119
+ "eval_runtime": 0.4925,
120
+ "eval_samples_per_second": 20.305,
121
+ "eval_steps_per_second": 20.305,
122
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
123
  }
124
  ],
125
  "logging_steps": 10,
 
139
  "attributes": {}
140
  }
141
  },
142
+ "total_flos": 3894839614291968.0,
143
  "train_batch_size": 4,
144
  "trial_name": null,
145
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c84fd1341bca21f546fb34f0984c2737ed54e8dbbe2ce01666781675b951db1
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6df4c7bb743e4dde6c0012813954641954f96e025235aaf027e7b00df2c6d40
3
  size 5368