azherali commited on
Commit
f96f252
·
verified ·
1 Parent(s): 964aeff

Training in progress, step 8000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:287ec11c7aa9785f19f3325e8990b5f18d5c57ec38761318955258821030fe27
3
  size 3555504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74cf435fb7349e8e54506ebb58af01f10261a616a326d059cbcdb64543d5c394
3
  size 3555504
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c31a150124a7ea427f43bc4ac445d44ad12e21e99ecd6c98da84ba3d565dd351
3
  size 7141515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43cecfb928f24cc675ff75e697b1a84f4a59512dbd7a99046461ca8ee5703f8c
3
  size 7141515
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74d09515db2365d54ed4fb3e4ed5de4469a5250824cf3ae5896f1be16012963a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f4a3b1d656476cd8e63479b6c20bd7983f231b968166731d8e9104d57790327
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a673142a4765448623d7954beb82b8e41b9b2064038630b1fde69d4143bc2a13
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fbc30c3a1fa2f1322da3a27761ccd07ada09d565f84aed41120ff0a6bec6f17
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d62c438edc2d4a191166e0bbea3d27e3a449ada773ef41a1c9aec359a7c4c829
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70ea2ab6fa7c8143ca6087fc4038185a17c76d37cc14c472f1fd0dba3cd729f
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 4000,
3
- "best_metric": 0.9586218246722099,
4
- "best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-4000",
5
- "epoch": 0.128,
6
  "eval_steps": 4000,
7
- "global_step": 4000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -300,6 +300,298 @@
300
  "eval_samples_per_second": 122.594,
301
  "eval_steps_per_second": 7.662,
302
  "step": 4000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
303
  }
304
  ],
305
  "logging_steps": 100,
@@ -328,7 +620,7 @@
328
  "attributes": {}
329
  }
330
  },
331
- "total_flos": 1.6992838343814144e+16,
332
  "train_batch_size": 16,
333
  "trial_name": null,
334
  "trial_params": null
 
1
  {
2
+ "best_global_step": 8000,
3
+ "best_metric": 0.9760920422665103,
4
+ "best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-8000",
5
+ "epoch": 0.256,
6
  "eval_steps": 4000,
7
+ "global_step": 8000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
300
  "eval_samples_per_second": 122.594,
301
  "eval_steps_per_second": 7.662,
302
  "step": 4000
303
+ },
304
+ {
305
+ "epoch": 0.1312,
306
+ "grad_norm": 8.65023422241211,
307
+ "learning_rate": 1.9537849117174962e-05,
308
+ "loss": 0.1026,
309
+ "step": 4100
310
+ },
311
+ {
312
+ "epoch": 0.1344,
313
+ "grad_norm": 8.46996784210205,
314
+ "learning_rate": 1.9525008025682183e-05,
315
+ "loss": 0.1251,
316
+ "step": 4200
317
+ },
318
+ {
319
+ "epoch": 0.1376,
320
+ "grad_norm": 6.439260959625244,
321
+ "learning_rate": 1.9512166934189408e-05,
322
+ "loss": 0.1338,
323
+ "step": 4300
324
+ },
325
+ {
326
+ "epoch": 0.1408,
327
+ "grad_norm": 1.012399435043335,
328
+ "learning_rate": 1.949932584269663e-05,
329
+ "loss": 0.1164,
330
+ "step": 4400
331
+ },
332
+ {
333
+ "epoch": 0.144,
334
+ "grad_norm": 0.33647093176841736,
335
+ "learning_rate": 1.9486484751203855e-05,
336
+ "loss": 0.1156,
337
+ "step": 4500
338
+ },
339
+ {
340
+ "epoch": 0.1472,
341
+ "grad_norm": 7.39678955078125,
342
+ "learning_rate": 1.9473643659711076e-05,
343
+ "loss": 0.1013,
344
+ "step": 4600
345
+ },
346
+ {
347
+ "epoch": 0.1504,
348
+ "grad_norm": 4.556000709533691,
349
+ "learning_rate": 1.94608025682183e-05,
350
+ "loss": 0.1038,
351
+ "step": 4700
352
+ },
353
+ {
354
+ "epoch": 0.1536,
355
+ "grad_norm": 0.5087370276451111,
356
+ "learning_rate": 1.9447961476725522e-05,
357
+ "loss": 0.1319,
358
+ "step": 4800
359
+ },
360
+ {
361
+ "epoch": 0.1568,
362
+ "grad_norm": 4.385759353637695,
363
+ "learning_rate": 1.9435120385232747e-05,
364
+ "loss": 0.1229,
365
+ "step": 4900
366
+ },
367
+ {
368
+ "epoch": 0.16,
369
+ "grad_norm": 5.46568489074707,
370
+ "learning_rate": 1.942227929373997e-05,
371
+ "loss": 0.1234,
372
+ "step": 5000
373
+ },
374
+ {
375
+ "epoch": 0.1632,
376
+ "grad_norm": 3.3565216064453125,
377
+ "learning_rate": 1.9409438202247193e-05,
378
+ "loss": 0.1007,
379
+ "step": 5100
380
+ },
381
+ {
382
+ "epoch": 0.1664,
383
+ "grad_norm": 0.17969129979610443,
384
+ "learning_rate": 1.9396597110754415e-05,
385
+ "loss": 0.108,
386
+ "step": 5200
387
+ },
388
+ {
389
+ "epoch": 0.1696,
390
+ "grad_norm": 8.49416732788086,
391
+ "learning_rate": 1.938375601926164e-05,
392
+ "loss": 0.1105,
393
+ "step": 5300
394
+ },
395
+ {
396
+ "epoch": 0.1728,
397
+ "grad_norm": 6.072606086730957,
398
+ "learning_rate": 1.937091492776886e-05,
399
+ "loss": 0.1082,
400
+ "step": 5400
401
+ },
402
+ {
403
+ "epoch": 0.176,
404
+ "grad_norm": 1.2361280918121338,
405
+ "learning_rate": 1.9358073836276086e-05,
406
+ "loss": 0.0966,
407
+ "step": 5500
408
+ },
409
+ {
410
+ "epoch": 0.1792,
411
+ "grad_norm": 6.232377052307129,
412
+ "learning_rate": 1.9345232744783307e-05,
413
+ "loss": 0.1151,
414
+ "step": 5600
415
+ },
416
+ {
417
+ "epoch": 0.1824,
418
+ "grad_norm": 0.6630802154541016,
419
+ "learning_rate": 1.9332391653290532e-05,
420
+ "loss": 0.104,
421
+ "step": 5700
422
+ },
423
+ {
424
+ "epoch": 0.1856,
425
+ "grad_norm": 0.2744814157485962,
426
+ "learning_rate": 1.9319550561797754e-05,
427
+ "loss": 0.104,
428
+ "step": 5800
429
+ },
430
+ {
431
+ "epoch": 0.1888,
432
+ "grad_norm": 0.37808698415756226,
433
+ "learning_rate": 1.930670947030498e-05,
434
+ "loss": 0.1183,
435
+ "step": 5900
436
+ },
437
+ {
438
+ "epoch": 0.192,
439
+ "grad_norm": 11.47230052947998,
440
+ "learning_rate": 1.9293868378812203e-05,
441
+ "loss": 0.1258,
442
+ "step": 6000
443
+ },
444
+ {
445
+ "epoch": 0.1952,
446
+ "grad_norm": 7.168028354644775,
447
+ "learning_rate": 1.928102728731942e-05,
448
+ "loss": 0.1117,
449
+ "step": 6100
450
+ },
451
+ {
452
+ "epoch": 0.1984,
453
+ "grad_norm": 0.11318526417016983,
454
+ "learning_rate": 1.9268186195826646e-05,
455
+ "loss": 0.1004,
456
+ "step": 6200
457
+ },
458
+ {
459
+ "epoch": 0.2016,
460
+ "grad_norm": 9.405433654785156,
461
+ "learning_rate": 1.9255345104333868e-05,
462
+ "loss": 0.1195,
463
+ "step": 6300
464
+ },
465
+ {
466
+ "epoch": 0.2048,
467
+ "grad_norm": 0.507453978061676,
468
+ "learning_rate": 1.9242504012841092e-05,
469
+ "loss": 0.0987,
470
+ "step": 6400
471
+ },
472
+ {
473
+ "epoch": 0.208,
474
+ "grad_norm": 0.15791097283363342,
475
+ "learning_rate": 1.9229662921348314e-05,
476
+ "loss": 0.1156,
477
+ "step": 6500
478
+ },
479
+ {
480
+ "epoch": 0.2112,
481
+ "grad_norm": 5.216452121734619,
482
+ "learning_rate": 1.921682182985554e-05,
483
+ "loss": 0.1375,
484
+ "step": 6600
485
+ },
486
+ {
487
+ "epoch": 0.2144,
488
+ "grad_norm": 0.6168243885040283,
489
+ "learning_rate": 1.9203980738362764e-05,
490
+ "loss": 0.1086,
491
+ "step": 6700
492
+ },
493
+ {
494
+ "epoch": 0.2176,
495
+ "grad_norm": 2.949383497238159,
496
+ "learning_rate": 1.9191139646869985e-05,
497
+ "loss": 0.0957,
498
+ "step": 6800
499
+ },
500
+ {
501
+ "epoch": 0.2208,
502
+ "grad_norm": 9.519874572753906,
503
+ "learning_rate": 1.917829855537721e-05,
504
+ "loss": 0.0935,
505
+ "step": 6900
506
+ },
507
+ {
508
+ "epoch": 0.224,
509
+ "grad_norm": 7.931914329528809,
510
+ "learning_rate": 1.916545746388443e-05,
511
+ "loss": 0.1335,
512
+ "step": 7000
513
+ },
514
+ {
515
+ "epoch": 0.2272,
516
+ "grad_norm": 8.498374938964844,
517
+ "learning_rate": 1.9152616372391656e-05,
518
+ "loss": 0.1025,
519
+ "step": 7100
520
+ },
521
+ {
522
+ "epoch": 0.2304,
523
+ "grad_norm": 5.054536819458008,
524
+ "learning_rate": 1.9139775280898878e-05,
525
+ "loss": 0.1165,
526
+ "step": 7200
527
+ },
528
+ {
529
+ "epoch": 0.2336,
530
+ "grad_norm": 0.17365020513534546,
531
+ "learning_rate": 1.9126934189406102e-05,
532
+ "loss": 0.0996,
533
+ "step": 7300
534
+ },
535
+ {
536
+ "epoch": 0.2368,
537
+ "grad_norm": 2.247058629989624,
538
+ "learning_rate": 1.9114093097913324e-05,
539
+ "loss": 0.1009,
540
+ "step": 7400
541
+ },
542
+ {
543
+ "epoch": 0.24,
544
+ "grad_norm": 15.367574691772461,
545
+ "learning_rate": 1.910125200642055e-05,
546
+ "loss": 0.1082,
547
+ "step": 7500
548
+ },
549
+ {
550
+ "epoch": 0.2432,
551
+ "grad_norm": 6.72482967376709,
552
+ "learning_rate": 1.908841091492777e-05,
553
+ "loss": 0.1308,
554
+ "step": 7600
555
+ },
556
+ {
557
+ "epoch": 0.2464,
558
+ "grad_norm": 0.051803406327962875,
559
+ "learning_rate": 1.9075569823434995e-05,
560
+ "loss": 0.1031,
561
+ "step": 7700
562
+ },
563
+ {
564
+ "epoch": 0.2496,
565
+ "grad_norm": 9.355685234069824,
566
+ "learning_rate": 1.9062728731942216e-05,
567
+ "loss": 0.1012,
568
+ "step": 7800
569
+ },
570
+ {
571
+ "epoch": 0.2528,
572
+ "grad_norm": 2.047060012817383,
573
+ "learning_rate": 1.904988764044944e-05,
574
+ "loss": 0.1249,
575
+ "step": 7900
576
+ },
577
+ {
578
+ "epoch": 0.256,
579
+ "grad_norm": 4.134668350219727,
580
+ "learning_rate": 1.9037046548956663e-05,
581
+ "loss": 0.0821,
582
+ "step": 8000
583
+ },
584
+ {
585
+ "epoch": 0.256,
586
+ "eval_accuracy": 0.97609,
587
+ "eval_f1": 0.9760920422665103,
588
+ "eval_loss": 0.10814645141363144,
589
+ "eval_precision": 0.9761013685233434,
590
+ "eval_recall": 0.97609,
591
+ "eval_runtime": 817.6077,
592
+ "eval_samples_per_second": 122.308,
593
+ "eval_steps_per_second": 7.644,
594
+ "step": 8000
595
  }
596
  ],
597
  "logging_steps": 100,
 
620
  "attributes": {}
621
  }
622
  },
623
+ "total_flos": 3.397795082747213e+16,
624
  "train_batch_size": 16,
625
  "trial_name": null,
626
  "trial_params": null