mtzig commited on
Commit
aca7c24
·
verified ·
1 Parent(s): 6e50ab1

Training in progress, step 800, checkpoint

Browse files
last-checkpoint/optimizer_0/.metadata CHANGED
Binary files a/last-checkpoint/optimizer_0/.metadata and b/last-checkpoint/optimizer_0/.metadata differ
 
last-checkpoint/optimizer_0/__0_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7dc1d8e3e4567fe89f4044c634b8f92aedf608d5bdd3f24fc45d9218d18c608
3
  size 13934748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:690953a5f1eaa9653131c0bd57c0088778a2758f6f1caff67bc9dc9bd0a61e4e
3
  size 13934748
last-checkpoint/optimizer_0/__1_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fa097179e7a3cbf7bef3aa37244226bfd1640b93c7ba0b5dfaa41fa616ac02a
3
  size 13999412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:961a2146c9b2e620d54c67901bd3fa375b0dd4b3895406d10bf2578c5745f6ec
3
  size 13999412
last-checkpoint/optimizer_0/__2_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ed962c5c5afe2495377b16a9858edd276c71d561e3acc283b688b0a7992d8b8
3
  size 13990904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e7156894345a02a9422f425abf2ddc88061246f26736af17b7bd221ea2b39c
3
  size 13990904
last-checkpoint/optimizer_0/__3_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b4f176ea9f6443c51ec492b348b90b111f939183a5e003fcf58ccce5a48bed8
3
  size 13990904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb3878b0710bfa44676e56faea2bf2e81a1c4bc0b34feb980fc568965e9b5bf
3
  size 13990904
last-checkpoint/pytorch_model_fsdp_0/.metadata CHANGED
Binary files a/last-checkpoint/pytorch_model_fsdp_0/.metadata and b/last-checkpoint/pytorch_model_fsdp_0/.metadata differ
 
last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e1032191a70fdd167493a8a8fad09fb846d227558db21ec9589296a5451c68d
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17c8c706eb940a9d1d5520139b6ffe5a44eb3dd61f2326391f6febfc3a6784f
3
  size 6966784
last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43a2e4e249d34019134215ddaa4cc63e8644939816a9a88ec74d584e3f0992dc
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2101a5cc6a3e4ee7d9bcd0e452c1b7b0e0ae6c681cf45975f0c718f88b871286
3
  size 6966784
last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14dadeb199fe580ea06456c94dcbb2d45ed31e34770c0b224e435256b01449ac
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03595f74c1fc252124eeec1b051b356f6d7bf67292b9806a2f8674da24f88c10
3
  size 6966784
last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd840616de0e70d365cbe915046e9309ff83ea7be6461314be0447bd565a18fc
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14a06466128fc4e8a81dd91b128a90acb8f65c2f692c8d576ff2e0ea82b7812
3
  size 6966784
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f4b633cac6d9b72a3e5d722d9f2722a25aaa75c4863f524e50216508a581110
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037251a482261d469d05ca212322fd7a8b0d86b1e9774acdb0dd0d30ed213fb4
3
  size 14960
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b00b812fe39f4d94693255c049b0abd4bfba391cf4f816905b3d288faf6ee1ba
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971deb5c5f50d793d58f55fcc23e2e2e3d0e3e15819213e61585330da863b511
3
  size 14960
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8934e21fbebe2892e28c801cf4e90276a2f5fc0d5159b41c7d9ebdd5b89cbbbd
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6969e1b0dfca6ead716e7d65a7048792f64786424a159e6ca34b0c6558b3ebd0
3
  size 14960
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c08fecc49906d862bfc6e72f4697782e40b17c8a512b907777ac3c47be4f8aa5
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ac0fcb20e2693146b5db8fdd7935ee7136850497cc891b3eff53fc7c189e4b
3
  size 14960
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:328d400156bec7fe19b325dd69ca88353a35391b51331286aebee3364fe74ad0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff85c01ce8c147a5568f0e98607017d923cd6d903d76df137d87352cddf54da
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.8663366336633663,
5
  "eval_steps": 20,
6
- "global_step": 700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -5339,6 +5339,766 @@
5339
  "eval_samples_per_second": 5.719,
5340
  "eval_steps_per_second": 0.186,
5341
  "step": 700
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5342
  }
5343
  ],
5344
  "logging_steps": 1,
@@ -5358,7 +6118,7 @@
5358
  "attributes": {}
5359
  }
5360
  },
5361
- "total_flos": 2.148551864918999e+17,
5362
  "train_batch_size": 8,
5363
  "trial_name": null,
5364
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9900990099009901,
5
  "eval_steps": 20,
6
+ "global_step": 800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
5339
  "eval_samples_per_second": 5.719,
5340
  "eval_steps_per_second": 0.186,
5341
  "step": 700
5342
+ },
5343
+ {
5344
+ "epoch": 0.8675742574257426,
5345
+ "grad_norm": 4.760046005249023,
5346
+ "learning_rate": 1.0500673022258923e-06,
5347
+ "loss": 0.1807,
5348
+ "step": 701
5349
+ },
5350
+ {
5351
+ "epoch": 0.8688118811881188,
5352
+ "grad_norm": 3.5298335552215576,
5353
+ "learning_rate": 1.030874440453944e-06,
5354
+ "loss": 0.1995,
5355
+ "step": 702
5356
+ },
5357
+ {
5358
+ "epoch": 0.870049504950495,
5359
+ "grad_norm": 5.2245049476623535,
5360
+ "learning_rate": 1.0118490653919855e-06,
5361
+ "loss": 0.2404,
5362
+ "step": 703
5363
+ },
5364
+ {
5365
+ "epoch": 0.8712871287128713,
5366
+ "grad_norm": 3.6648762226104736,
5367
+ "learning_rate": 9.92991532314057e-07,
5368
+ "loss": 0.1154,
5369
+ "step": 704
5370
+ },
5371
+ {
5372
+ "epoch": 0.8725247524752475,
5373
+ "grad_norm": 6.1605424880981445,
5374
+ "learning_rate": 9.743021933599695e-07,
5375
+ "loss": 0.2483,
5376
+ "step": 705
5377
+ },
5378
+ {
5379
+ "epoch": 0.8737623762376238,
5380
+ "grad_norm": 4.078556060791016,
5381
+ "learning_rate": 9.557813975287266e-07,
5382
+ "loss": 0.2285,
5383
+ "step": 706
5384
+ },
5385
+ {
5386
+ "epoch": 0.875,
5387
+ "grad_norm": 4.299773216247559,
5388
+ "learning_rate": 9.374294906720083e-07,
5389
+ "loss": 0.1815,
5390
+ "step": 707
5391
+ },
5392
+ {
5393
+ "epoch": 0.8762376237623762,
5394
+ "grad_norm": 4.190319061279297,
5395
+ "learning_rate": 9.192468154877187e-07,
5396
+ "loss": 0.2049,
5397
+ "step": 708
5398
+ },
5399
+ {
5400
+ "epoch": 0.8774752475247525,
5401
+ "grad_norm": 6.507383823394775,
5402
+ "learning_rate": 9.012337115135772e-07,
5403
+ "loss": 0.2033,
5404
+ "step": 709
5405
+ },
5406
+ {
5407
+ "epoch": 0.8787128712871287,
5408
+ "grad_norm": 4.297817707061768,
5409
+ "learning_rate": 8.833905151207833e-07,
5410
+ "loss": 0.1332,
5411
+ "step": 710
5412
+ },
5413
+ {
5414
+ "epoch": 0.879950495049505,
5415
+ "grad_norm": 4.102233409881592,
5416
+ "learning_rate": 8.657175595077317e-07,
5417
+ "loss": 0.1851,
5418
+ "step": 711
5419
+ },
5420
+ {
5421
+ "epoch": 0.8811881188118812,
5422
+ "grad_norm": 7.134310722351074,
5423
+ "learning_rate": 8.482151746937983e-07,
5424
+ "loss": 0.1696,
5425
+ "step": 712
5426
+ },
5427
+ {
5428
+ "epoch": 0.8824257425742574,
5429
+ "grad_norm": 4.428358554840088,
5430
+ "learning_rate": 8.308836875131665e-07,
5431
+ "loss": 0.2061,
5432
+ "step": 713
5433
+ },
5434
+ {
5435
+ "epoch": 0.8836633663366337,
5436
+ "grad_norm": 3.750676393508911,
5437
+ "learning_rate": 8.137234216087353e-07,
5438
+ "loss": 0.1409,
5439
+ "step": 714
5440
+ },
5441
+ {
5442
+ "epoch": 0.8849009900990099,
5443
+ "grad_norm": 4.440266132354736,
5444
+ "learning_rate": 7.967346974260626e-07,
5445
+ "loss": 0.1741,
5446
+ "step": 715
5447
+ },
5448
+ {
5449
+ "epoch": 0.8861386138613861,
5450
+ "grad_norm": 4.9036736488342285,
5451
+ "learning_rate": 7.799178322073941e-07,
5452
+ "loss": 0.1559,
5453
+ "step": 716
5454
+ },
5455
+ {
5456
+ "epoch": 0.8873762376237624,
5457
+ "grad_norm": 4.0620856285095215,
5458
+ "learning_rate": 7.632731399857329e-07,
5459
+ "loss": 0.1934,
5460
+ "step": 717
5461
+ },
5462
+ {
5463
+ "epoch": 0.8886138613861386,
5464
+ "grad_norm": 4.675508975982666,
5465
+ "learning_rate": 7.468009315789748e-07,
5466
+ "loss": 0.176,
5467
+ "step": 718
5468
+ },
5469
+ {
5470
+ "epoch": 0.8898514851485149,
5471
+ "grad_norm": 4.654139041900635,
5472
+ "learning_rate": 7.305015145841055e-07,
5473
+ "loss": 0.1992,
5474
+ "step": 719
5475
+ },
5476
+ {
5477
+ "epoch": 0.8910891089108911,
5478
+ "grad_norm": 5.478711128234863,
5479
+ "learning_rate": 7.143751933714583e-07,
5480
+ "loss": 0.2218,
5481
+ "step": 720
5482
+ },
5483
+ {
5484
+ "epoch": 0.8910891089108911,
5485
+ "eval_accuracy": 0.8625277161862528,
5486
+ "eval_f1": 0.7181818181818181,
5487
+ "eval_loss": 0.29504844546318054,
5488
+ "eval_precision": 0.8449197860962567,
5489
+ "eval_recall": 0.6245059288537549,
5490
+ "eval_runtime": 48.4336,
5491
+ "eval_samples_per_second": 5.699,
5492
+ "eval_steps_per_second": 0.186,
5493
+ "step": 720
5494
+ },
5495
+ {
5496
+ "epoch": 0.8923267326732673,
5497
+ "grad_norm": 4.685728073120117,
5498
+ "learning_rate": 6.984222690790277e-07,
5499
+ "loss": 0.1942,
5500
+ "step": 721
5501
+ },
5502
+ {
5503
+ "epoch": 0.8935643564356436,
5504
+ "grad_norm": 4.345710754394531,
5505
+ "learning_rate": 6.826430396068451e-07,
5506
+ "loss": 0.1774,
5507
+ "step": 722
5508
+ },
5509
+ {
5510
+ "epoch": 0.8948019801980198,
5511
+ "grad_norm": 4.9782328605651855,
5512
+ "learning_rate": 6.67037799611423e-07,
5513
+ "loss": 0.1819,
5514
+ "step": 723
5515
+ },
5516
+ {
5517
+ "epoch": 0.8960396039603961,
5518
+ "grad_norm": 6.226649284362793,
5519
+ "learning_rate": 6.516068405002441e-07,
5520
+ "loss": 0.1995,
5521
+ "step": 724
5522
+ },
5523
+ {
5524
+ "epoch": 0.8972772277227723,
5525
+ "grad_norm": 3.8088414669036865,
5526
+ "learning_rate": 6.363504504263207e-07,
5527
+ "loss": 0.1909,
5528
+ "step": 725
5529
+ },
5530
+ {
5531
+ "epoch": 0.8985148514851485,
5532
+ "grad_norm": 3.8853421211242676,
5533
+ "learning_rate": 6.212689142828232e-07,
5534
+ "loss": 0.1821,
5535
+ "step": 726
5536
+ },
5537
+ {
5538
+ "epoch": 0.8997524752475248,
5539
+ "grad_norm": 3.680631160736084,
5540
+ "learning_rate": 6.063625136977447e-07,
5541
+ "loss": 0.1419,
5542
+ "step": 727
5543
+ },
5544
+ {
5545
+ "epoch": 0.900990099009901,
5546
+ "grad_norm": 4.0216217041015625,
5547
+ "learning_rate": 5.916315270286588e-07,
5548
+ "loss": 0.1715,
5549
+ "step": 728
5550
+ },
5551
+ {
5552
+ "epoch": 0.9022277227722773,
5553
+ "grad_norm": 5.727372646331787,
5554
+ "learning_rate": 5.770762293575083e-07,
5555
+ "loss": 0.3295,
5556
+ "step": 729
5557
+ },
5558
+ {
5559
+ "epoch": 0.9034653465346535,
5560
+ "grad_norm": 4.530044078826904,
5561
+ "learning_rate": 5.626968924854714e-07,
5562
+ "loss": 0.1704,
5563
+ "step": 730
5564
+ },
5565
+ {
5566
+ "epoch": 0.9047029702970297,
5567
+ "grad_norm": 7.712387561798096,
5568
+ "learning_rate": 5.484937849278937e-07,
5569
+ "loss": 0.205,
5570
+ "step": 731
5571
+ },
5572
+ {
5573
+ "epoch": 0.905940594059406,
5574
+ "grad_norm": 5.130886554718018,
5575
+ "learning_rate": 5.344671719092664e-07,
5576
+ "loss": 0.1432,
5577
+ "step": 732
5578
+ },
5579
+ {
5580
+ "epoch": 0.9071782178217822,
5581
+ "grad_norm": 4.739104270935059,
5582
+ "learning_rate": 5.206173153582705e-07,
5583
+ "loss": 0.2583,
5584
+ "step": 733
5585
+ },
5586
+ {
5587
+ "epoch": 0.9084158415841584,
5588
+ "grad_norm": 3.7045702934265137,
5589
+ "learning_rate": 5.069444739029006e-07,
5590
+ "loss": 0.1193,
5591
+ "step": 734
5592
+ },
5593
+ {
5594
+ "epoch": 0.9096534653465347,
5595
+ "grad_norm": 3.3528637886047363,
5596
+ "learning_rate": 4.934489028656164e-07,
5597
+ "loss": 0.1153,
5598
+ "step": 735
5599
+ },
5600
+ {
5601
+ "epoch": 0.9108910891089109,
5602
+ "grad_norm": 3.305149793624878,
5603
+ "learning_rate": 4.801308542585892e-07,
5604
+ "loss": 0.144,
5605
+ "step": 736
5606
+ },
5607
+ {
5608
+ "epoch": 0.9121287128712872,
5609
+ "grad_norm": 4.803959369659424,
5610
+ "learning_rate": 4.669905767789884e-07,
5611
+ "loss": 0.1267,
5612
+ "step": 737
5613
+ },
5614
+ {
5615
+ "epoch": 0.9133663366336634,
5616
+ "grad_norm": 5.374501705169678,
5617
+ "learning_rate": 4.54028315804339e-07,
5618
+ "loss": 0.1991,
5619
+ "step": 738
5620
+ },
5621
+ {
5622
+ "epoch": 0.9146039603960396,
5623
+ "grad_norm": 5.532665729522705,
5624
+ "learning_rate": 4.4124431338794403e-07,
5625
+ "loss": 0.2528,
5626
+ "step": 739
5627
+ },
5628
+ {
5629
+ "epoch": 0.9158415841584159,
5630
+ "grad_norm": 3.2962238788604736,
5631
+ "learning_rate": 4.2863880825435687e-07,
5632
+ "loss": 0.1608,
5633
+ "step": 740
5634
+ },
5635
+ {
5636
+ "epoch": 0.9158415841584159,
5637
+ "eval_accuracy": 0.8603104212860311,
5638
+ "eval_f1": 0.7096774193548387,
5639
+ "eval_loss": 0.2995334267616272,
5640
+ "eval_precision": 0.850828729281768,
5641
+ "eval_recall": 0.6086956521739131,
5642
+ "eval_runtime": 50.016,
5643
+ "eval_samples_per_second": 5.518,
5644
+ "eval_steps_per_second": 0.18,
5645
+ "step": 740
5646
+ },
5647
+ {
5648
+ "epoch": 0.9170792079207921,
5649
+ "grad_norm": 3.7142422199249268,
5650
+ "learning_rate": 4.162120357949284e-07,
5651
+ "loss": 0.1256,
5652
+ "step": 741
5653
+ },
5654
+ {
5655
+ "epoch": 0.9183168316831684,
5656
+ "grad_norm": 6.413259029388428,
5657
+ "learning_rate": 4.039642280634104e-07,
5658
+ "loss": 0.2582,
5659
+ "step": 742
5660
+ },
5661
+ {
5662
+ "epoch": 0.9195544554455446,
5663
+ "grad_norm": 8.874350547790527,
5664
+ "learning_rate": 3.9189561377162343e-07,
5665
+ "loss": 0.3466,
5666
+ "step": 743
5667
+ },
5668
+ {
5669
+ "epoch": 0.9207920792079208,
5670
+ "grad_norm": 3.888648271560669,
5671
+ "learning_rate": 3.800064182851804e-07,
5672
+ "loss": 0.1399,
5673
+ "step": 744
5674
+ },
5675
+ {
5676
+ "epoch": 0.9220297029702971,
5677
+ "grad_norm": 3.599470615386963,
5678
+ "learning_rate": 3.682968636192863e-07,
5679
+ "loss": 0.1305,
5680
+ "step": 745
5681
+ },
5682
+ {
5683
+ "epoch": 0.9232673267326733,
5684
+ "grad_norm": 5.102394104003906,
5685
+ "learning_rate": 3.567671684345875e-07,
5686
+ "loss": 0.2276,
5687
+ "step": 746
5688
+ },
5689
+ {
5690
+ "epoch": 0.9245049504950495,
5691
+ "grad_norm": 3.962132453918457,
5692
+ "learning_rate": 3.4541754803308567e-07,
5693
+ "loss": 0.1582,
5694
+ "step": 747
5695
+ },
5696
+ {
5697
+ "epoch": 0.9257425742574258,
5698
+ "grad_norm": 3.0672736167907715,
5699
+ "learning_rate": 3.342482143541281e-07,
5700
+ "loss": 0.1273,
5701
+ "step": 748
5702
+ },
5703
+ {
5704
+ "epoch": 0.926980198019802,
5705
+ "grad_norm": 3.4861226081848145,
5706
+ "learning_rate": 3.23259375970435e-07,
5707
+ "loss": 0.1595,
5708
+ "step": 749
5709
+ },
5710
+ {
5711
+ "epoch": 0.9282178217821783,
5712
+ "grad_norm": 4.98872184753418,
5713
+ "learning_rate": 3.124512380842204e-07,
5714
+ "loss": 0.1265,
5715
+ "step": 750
5716
+ },
5717
+ {
5718
+ "epoch": 0.9294554455445545,
5719
+ "grad_norm": 3.516669988632202,
5720
+ "learning_rate": 3.0182400252334656e-07,
5721
+ "loss": 0.1916,
5722
+ "step": 751
5723
+ },
5724
+ {
5725
+ "epoch": 0.9306930693069307,
5726
+ "grad_norm": 3.6074628829956055,
5727
+ "learning_rate": 2.9137786773756114e-07,
5728
+ "loss": 0.1395,
5729
+ "step": 752
5730
+ },
5731
+ {
5732
+ "epoch": 0.931930693069307,
5733
+ "grad_norm": 4.940650463104248,
5734
+ "learning_rate": 2.811130287947972e-07,
5735
+ "loss": 0.2394,
5736
+ "step": 753
5737
+ },
5738
+ {
5739
+ "epoch": 0.9331683168316832,
5740
+ "grad_norm": 6.3607072830200195,
5741
+ "learning_rate": 2.710296773775167e-07,
5742
+ "loss": 0.213,
5743
+ "step": 754
5744
+ },
5745
+ {
5746
+ "epoch": 0.9344059405940595,
5747
+ "grad_norm": 4.352235317230225,
5748
+ "learning_rate": 2.61128001779144e-07,
5749
+ "loss": 0.1511,
5750
+ "step": 755
5751
+ },
5752
+ {
5753
+ "epoch": 0.9356435643564357,
5754
+ "grad_norm": 4.3637495040893555,
5755
+ "learning_rate": 2.514081869005458e-07,
5756
+ "loss": 0.224,
5757
+ "step": 756
5758
+ },
5759
+ {
5760
+ "epoch": 0.9368811881188119,
5761
+ "grad_norm": 3.1667957305908203,
5762
+ "learning_rate": 2.418704142465722e-07,
5763
+ "loss": 0.1993,
5764
+ "step": 757
5765
+ },
5766
+ {
5767
+ "epoch": 0.9381188118811881,
5768
+ "grad_norm": 4.96242094039917,
5769
+ "learning_rate": 2.325148619226758e-07,
5770
+ "loss": 0.1221,
5771
+ "step": 758
5772
+ },
5773
+ {
5774
+ "epoch": 0.9393564356435643,
5775
+ "grad_norm": 5.428174018859863,
5776
+ "learning_rate": 2.2334170463158223e-07,
5777
+ "loss": 0.2239,
5778
+ "step": 759
5779
+ },
5780
+ {
5781
+ "epoch": 0.9405940594059405,
5782
+ "grad_norm": 5.158010005950928,
5783
+ "learning_rate": 2.1435111367002826e-07,
5784
+ "loss": 0.2056,
5785
+ "step": 760
5786
+ },
5787
+ {
5788
+ "epoch": 0.9405940594059405,
5789
+ "eval_accuracy": 0.8592017738359202,
5790
+ "eval_f1": 0.7093821510297483,
5791
+ "eval_loss": 0.296718031167984,
5792
+ "eval_precision": 0.842391304347826,
5793
+ "eval_recall": 0.6126482213438735,
5794
+ "eval_runtime": 50.2838,
5795
+ "eval_samples_per_second": 5.489,
5796
+ "eval_steps_per_second": 0.179,
5797
+ "step": 760
5798
+ },
5799
+ {
5800
+ "epoch": 0.9418316831683168,
5801
+ "grad_norm": 3.6793015003204346,
5802
+ "learning_rate": 2.055432569255622e-07,
5803
+ "loss": 0.1978,
5804
+ "step": 761
5805
+ },
5806
+ {
5807
+ "epoch": 0.943069306930693,
5808
+ "grad_norm": 4.697923183441162,
5809
+ "learning_rate": 1.9691829887340864e-07,
5810
+ "loss": 0.2068,
5811
+ "step": 762
5812
+ },
5813
+ {
5814
+ "epoch": 0.9443069306930693,
5815
+ "grad_norm": 3.3791000843048096,
5816
+ "learning_rate": 1.8847640057339966e-07,
5817
+ "loss": 0.1953,
5818
+ "step": 763
5819
+ },
5820
+ {
5821
+ "epoch": 0.9455445544554455,
5822
+ "grad_norm": 5.8897528648376465,
5823
+ "learning_rate": 1.802177196669619e-07,
5824
+ "loss": 0.2229,
5825
+ "step": 764
5826
+ },
5827
+ {
5828
+ "epoch": 0.9467821782178217,
5829
+ "grad_norm": 5.087184906005859,
5830
+ "learning_rate": 1.7214241037418312e-07,
5831
+ "loss": 0.1672,
5832
+ "step": 765
5833
+ },
5834
+ {
5835
+ "epoch": 0.948019801980198,
5836
+ "grad_norm": 7.06437873840332,
5837
+ "learning_rate": 1.6425062349091914e-07,
5838
+ "loss": 0.2658,
5839
+ "step": 766
5840
+ },
5841
+ {
5842
+ "epoch": 0.9492574257425742,
5843
+ "grad_norm": 6.635834693908691,
5844
+ "learning_rate": 1.5654250638598601e-07,
5845
+ "loss": 0.1855,
5846
+ "step": 767
5847
+ },
5848
+ {
5849
+ "epoch": 0.9504950495049505,
5850
+ "grad_norm": 4.292440414428711,
5851
+ "learning_rate": 1.4901820299840997e-07,
5852
+ "loss": 0.1832,
5853
+ "step": 768
5854
+ },
5855
+ {
5856
+ "epoch": 0.9517326732673267,
5857
+ "grad_norm": 6.999221324920654,
5858
+ "learning_rate": 1.4167785383472855e-07,
5859
+ "loss": 0.2044,
5860
+ "step": 769
5861
+ },
5862
+ {
5863
+ "epoch": 0.9529702970297029,
5864
+ "grad_norm": 3.0472869873046875,
5865
+ "learning_rate": 1.345215959663837e-07,
5866
+ "loss": 0.1321,
5867
+ "step": 770
5868
+ },
5869
+ {
5870
+ "epoch": 0.9542079207920792,
5871
+ "grad_norm": 3.8832876682281494,
5872
+ "learning_rate": 1.2754956302714617e-07,
5873
+ "loss": 0.116,
5874
+ "step": 771
5875
+ },
5876
+ {
5877
+ "epoch": 0.9554455445544554,
5878
+ "grad_norm": 2.6631460189819336,
5879
+ "learning_rate": 1.207618852106285e-07,
5880
+ "loss": 0.1369,
5881
+ "step": 772
5882
+ },
5883
+ {
5884
+ "epoch": 0.9566831683168316,
5885
+ "grad_norm": 5.974620819091797,
5886
+ "learning_rate": 1.1415868926785256e-07,
5887
+ "loss": 0.2214,
5888
+ "step": 773
5889
+ },
5890
+ {
5891
+ "epoch": 0.9579207920792079,
5892
+ "grad_norm": 4.9748616218566895,
5893
+ "learning_rate": 1.0774009850488154e-07,
5894
+ "loss": 0.1924,
5895
+ "step": 774
5896
+ },
5897
+ {
5898
+ "epoch": 0.9591584158415841,
5899
+ "grad_norm": 3.96227765083313,
5900
+ "learning_rate": 1.0150623278051719e-07,
5901
+ "loss": 0.1976,
5902
+ "step": 775
5903
+ },
5904
+ {
5905
+ "epoch": 0.9603960396039604,
5906
+ "grad_norm": 3.1740334033966064,
5907
+ "learning_rate": 9.545720850406504e-08,
5908
+ "loss": 0.1266,
5909
+ "step": 776
5910
+ },
5911
+ {
5912
+ "epoch": 0.9616336633663366,
5913
+ "grad_norm": 7.497445583343506,
5914
+ "learning_rate": 8.959313863315388e-08,
5915
+ "loss": 0.231,
5916
+ "step": 777
5917
+ },
5918
+ {
5919
+ "epoch": 0.9628712871287128,
5920
+ "grad_norm": 4.704877853393555,
5921
+ "learning_rate": 8.391413267163418e-08,
5922
+ "loss": 0.163,
5923
+ "step": 778
5924
+ },
5925
+ {
5926
+ "epoch": 0.9641089108910891,
5927
+ "grad_norm": 4.273810386657715,
5928
+ "learning_rate": 7.842029666752627e-08,
5929
+ "loss": 0.1865,
5930
+ "step": 779
5931
+ },
5932
+ {
5933
+ "epoch": 0.9653465346534653,
5934
+ "grad_norm": 4.104014873504639,
5935
+ "learning_rate": 7.311173321104648e-08,
5936
+ "loss": 0.2127,
5937
+ "step": 780
5938
+ },
5939
+ {
5940
+ "epoch": 0.9653465346534653,
5941
+ "eval_accuracy": 0.8625277161862528,
5942
+ "eval_f1": 0.7194570135746606,
5943
+ "eval_loss": 0.2944088578224182,
5944
+ "eval_precision": 0.8412698412698413,
5945
+ "eval_recall": 0.6284584980237155,
5946
+ "eval_runtime": 50.7955,
5947
+ "eval_samples_per_second": 5.434,
5948
+ "eval_steps_per_second": 0.177,
5949
+ "step": 780
5950
+ },
5951
+ {
5952
+ "epoch": 0.9665841584158416,
5953
+ "grad_norm": 6.6444902420043945,
5954
+ "learning_rate": 6.79885414326864e-08,
5955
+ "loss": 0.251,
5956
+ "step": 781
5957
+ },
5958
+ {
5959
+ "epoch": 0.9678217821782178,
5960
+ "grad_norm": 5.593561172485352,
5961
+ "learning_rate": 6.305081700136328e-08,
5962
+ "loss": 0.2616,
5963
+ "step": 782
5964
+ },
5965
+ {
5966
+ "epoch": 0.969059405940594,
5967
+ "grad_norm": 3.74603009223938,
5968
+ "learning_rate": 5.8298652122634747e-08,
5969
+ "loss": 0.1636,
5970
+ "step": 783
5971
+ },
5972
+ {
5973
+ "epoch": 0.9702970297029703,
5974
+ "grad_norm": 4.336615562438965,
5975
+ "learning_rate": 5.373213553697576e-08,
5976
+ "loss": 0.2196,
5977
+ "step": 784
5978
+ },
5979
+ {
5980
+ "epoch": 0.9715346534653465,
5981
+ "grad_norm": 3.183893918991089,
5982
+ "learning_rate": 4.935135251811995e-08,
5983
+ "loss": 0.141,
5984
+ "step": 785
5985
+ },
5986
+ {
5987
+ "epoch": 0.9727722772277227,
5988
+ "grad_norm": 5.894475936889648,
5989
+ "learning_rate": 4.515638487147311e-08,
5990
+ "loss": 0.2093,
5991
+ "step": 786
5992
+ },
5993
+ {
5994
+ "epoch": 0.974009900990099,
5995
+ "grad_norm": 5.151168346405029,
5996
+ "learning_rate": 4.1147310932578845e-08,
5997
+ "loss": 0.2318,
5998
+ "step": 787
5999
+ },
6000
+ {
6001
+ "epoch": 0.9752475247524752,
6002
+ "grad_norm": 3.7331173419952393,
6003
+ "learning_rate": 3.732420556565752e-08,
6004
+ "loss": 0.1696,
6005
+ "step": 788
6006
+ },
6007
+ {
6008
+ "epoch": 0.9764851485148515,
6009
+ "grad_norm": 5.081837177276611,
6010
+ "learning_rate": 3.368714016221186e-08,
6011
+ "loss": 0.1864,
6012
+ "step": 789
6013
+ },
6014
+ {
6015
+ "epoch": 0.9777227722772277,
6016
+ "grad_norm": 5.835230827331543,
6017
+ "learning_rate": 3.023618263968797e-08,
6018
+ "loss": 0.266,
6019
+ "step": 790
6020
+ },
6021
+ {
6022
+ "epoch": 0.9789603960396039,
6023
+ "grad_norm": 4.534897327423096,
6024
+ "learning_rate": 2.6971397440214154e-08,
6025
+ "loss": 0.1775,
6026
+ "step": 791
6027
+ },
6028
+ {
6029
+ "epoch": 0.9801980198019802,
6030
+ "grad_norm": 4.335183620452881,
6031
+ "learning_rate": 2.3892845529390753e-08,
6032
+ "loss": 0.2054,
6033
+ "step": 792
6034
+ },
6035
+ {
6036
+ "epoch": 0.9814356435643564,
6037
+ "grad_norm": 4.6105451583862305,
6038
+ "learning_rate": 2.100058439515551e-08,
6039
+ "loss": 0.1936,
6040
+ "step": 793
6041
+ },
6042
+ {
6043
+ "epoch": 0.9826732673267327,
6044
+ "grad_norm": 3.7368929386138916,
6045
+ "learning_rate": 1.8294668046708874e-08,
6046
+ "loss": 0.2007,
6047
+ "step": 794
6048
+ },
6049
+ {
6050
+ "epoch": 0.9839108910891089,
6051
+ "grad_norm": 4.431072235107422,
6052
+ "learning_rate": 1.577514701350591e-08,
6053
+ "loss": 0.2273,
6054
+ "step": 795
6055
+ },
6056
+ {
6057
+ "epoch": 0.9851485148514851,
6058
+ "grad_norm": 6.609121322631836,
6059
+ "learning_rate": 1.3442068344312609e-08,
6060
+ "loss": 0.238,
6061
+ "step": 796
6062
+ },
6063
+ {
6064
+ "epoch": 0.9863861386138614,
6065
+ "grad_norm": 4.512663841247559,
6066
+ "learning_rate": 1.129547560632771e-08,
6067
+ "loss": 0.2116,
6068
+ "step": 797
6069
+ },
6070
+ {
6071
+ "epoch": 0.9876237623762376,
6072
+ "grad_norm": 4.200558662414551,
6073
+ "learning_rate": 9.335408884366682e-09,
6074
+ "loss": 0.198,
6075
+ "step": 798
6076
+ },
6077
+ {
6078
+ "epoch": 0.9888613861386139,
6079
+ "grad_norm": 6.579875469207764,
6080
+ "learning_rate": 7.561904780116758e-09,
6081
+ "loss": 0.212,
6082
+ "step": 799
6083
+ },
6084
+ {
6085
+ "epoch": 0.9900990099009901,
6086
+ "grad_norm": 5.1703667640686035,
6087
+ "learning_rate": 5.97499641145416e-09,
6088
+ "loss": 0.2252,
6089
+ "step": 800
6090
+ },
6091
+ {
6092
+ "epoch": 0.9900990099009901,
6093
+ "eval_accuracy": 0.8636363636363636,
6094
+ "eval_f1": 0.7223476297968398,
6095
+ "eval_loss": 0.2939181923866272,
6096
+ "eval_precision": 0.8421052631578947,
6097
+ "eval_recall": 0.6324110671936759,
6098
+ "eval_runtime": 48.1373,
6099
+ "eval_samples_per_second": 5.734,
6100
+ "eval_steps_per_second": 0.187,
6101
+ "step": 800
6102
  }
6103
  ],
6104
  "logging_steps": 1,
 
6118
  "attributes": {}
6119
  }
6120
  },
6121
+ "total_flos": 2.4540790520807424e+17,
6122
  "train_batch_size": 8,
6123
  "trial_name": null,
6124
  "trial_params": null