Hugging Face's logo

Team-PIXEL
/
pixel-small-mono

Transformers
PyTorch
pixel
masked-auto-encoding
Generated from Trainer
Model card Files
xet
 Community
plip commited on
Commit
2e5cae2
·
1 Parent(s): ba21848

Training in progress, step 280000

Browse files
Files changed (13) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/rng_state_4.pth +1 -1
  8. last-checkpoint/rng_state_5.pth +1 -1
  9. last-checkpoint/rng_state_6.pth +1 -1
  10. last-checkpoint/rng_state_7.pth +1 -1
  11. last-checkpoint/scheduler.pt +1 -1
  12. last-checkpoint/trainer_state.json +203 -3
  13. pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2db59304ac09b28bcb3c65afafd5ee1982c926ae9e5b3be0a3041e16925dc09d
3
  size 202194449
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a559b0eb78c919f7317440c34ff9418c01d3807356031c4529bd37c83a4e55b0
3
  size 202194449
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6481ae1099357d8bcf88c484382e1abee67e04204a9282cec0553dec29988327
3
  size 102501541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee323f397e17b15c555d3f760433b7c390cda1ae17a7f66787ce543a9c888720
3
  size 102501541
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
3
  size 14503
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
3
  size 14503
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
3
  size 14503
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
3
  size 14503
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
3
  size 14503
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
3
  size 14503
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
3
  size 14503
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8b23debd59dd70fd2819e8cfb49b59ed6e24536a986d25a514bb064603c02e2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231bfff5d6e31c2ba099341e84048971dcc6fd877303b4d5b509a5fb9426fe40
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cb61348726887e329b19406ea4e3e39ac391edeec6dfd8508b3cb524aa33e28
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80db35d9a6af0da10cd7cebe3bf01f3932293e48fc6a8607555efe3b5591e844
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 6.290920105314663,
5
- "global_step": 270000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -5406,11 +5406,211 @@
5406
  "eval_samples_per_second": 1513.389,
5407
  "eval_steps_per_second": 24.099,
5408
  "step": 270000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5409
  }
5410
  ],
5411
  "max_steps": 500000,
5412
  "num_train_epochs": 12,
5413
- "total_flos": 8.626137764966059e+21,
5414
  "trial_name": null,
5415
  "trial_params": null
5416
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 6.523917146252242,
5
+ "global_step": 280000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
5406
  "eval_samples_per_second": 1513.389,
5407
  "eval_steps_per_second": 24.099,
5408
  "step": 270000
5409
+ },
5410
+ {
5411
+ "epoch": 6.3,
5412
+ "learning_rate": 0.00014733147931802578,
5413
+ "loss": 0.27,
5414
+ "step": 270500
5415
+ },
5416
+ {
5417
+ "epoch": 6.31,
5418
+ "learning_rate": 0.00014685268692538238,
5419
+ "loss": 0.2698,
5420
+ "step": 271000
5421
+ },
5422
+ {
5423
+ "epoch": 6.31,
5424
+ "eval_loss": 0.2508079409599304,
5425
+ "eval_runtime": 1.42,
5426
+ "eval_samples_per_second": 1547.911,
5427
+ "eval_steps_per_second": 24.648,
5428
+ "step": 271000
5429
+ },
5430
+ {
5431
+ "epoch": 6.33,
5432
+ "learning_rate": 0.00014637398363044946,
5433
+ "loss": 0.2699,
5434
+ "step": 271500
5435
+ },
5436
+ {
5437
+ "epoch": 6.34,
5438
+ "learning_rate": 0.00014589537466824955,
5439
+ "loss": 0.2703,
5440
+ "step": 272000
5441
+ },
5442
+ {
5443
+ "epoch": 6.34,
5444
+ "eval_loss": 0.2517754137516022,
5445
+ "eval_runtime": 1.4219,
5446
+ "eval_samples_per_second": 1545.829,
5447
+ "eval_steps_per_second": 24.615,
5448
+ "step": 272000
5449
+ },
5450
+ {
5451
+ "epoch": 6.35,
5452
+ "learning_rate": 0.00014541686527277356,
5453
+ "loss": 0.27,
5454
+ "step": 272500
5455
+ },
5456
+ {
5457
+ "epoch": 6.36,
5458
+ "learning_rate": 0.00014493846067692358,
5459
+ "loss": 0.2693,
5460
+ "step": 273000
5461
+ },
5462
+ {
5463
+ "epoch": 6.36,
5464
+ "eval_loss": 0.25326284766197205,
5465
+ "eval_runtime": 1.4476,
5466
+ "eval_samples_per_second": 1518.396,
5467
+ "eval_steps_per_second": 24.178,
5468
+ "step": 273000
5469
+ },
5470
+ {
5471
+ "epoch": 6.37,
5472
+ "learning_rate": 0.00014446016611245567,
5473
+ "loss": 0.2694,
5474
+ "step": 273500
5475
+ },
5476
+ {
5477
+ "epoch": 6.38,
5478
+ "learning_rate": 0.00014398198680992252,
5479
+ "loss": 0.2698,
5480
+ "step": 274000
5481
+ },
5482
+ {
5483
+ "epoch": 6.38,
5484
+ "eval_loss": 0.25300565361976624,
5485
+ "eval_runtime": 1.4333,
5486
+ "eval_samples_per_second": 1533.534,
5487
+ "eval_steps_per_second": 24.419,
5488
+ "step": 274000
5489
+ },
5490
+ {
5491
+ "epoch": 6.4,
5492
+ "learning_rate": 0.00014350392799861636,
5493
+ "loss": 0.2699,
5494
+ "step": 274500
5495
+ },
5496
+ {
5497
+ "epoch": 6.41,
5498
+ "learning_rate": 0.0001430259949065118,
5499
+ "loss": 0.2697,
5500
+ "step": 275000
5501
+ },
5502
+ {
5503
+ "epoch": 6.41,
5504
+ "eval_loss": 0.2506762742996216,
5505
+ "eval_runtime": 1.4367,
5506
+ "eval_samples_per_second": 1529.926,
5507
+ "eval_steps_per_second": 24.362,
5508
+ "step": 275000
5509
+ },
5510
+ {
5511
+ "epoch": 6.42,
5512
+ "learning_rate": 0.0001425481927602085,
5513
+ "loss": 0.2694,
5514
+ "step": 275500
5515
+ },
5516
+ {
5517
+ "epoch": 6.43,
5518
+ "learning_rate": 0.0001420705267848743,
5519
+ "loss": 0.2691,
5520
+ "step": 276000
5521
+ },
5522
+ {
5523
+ "epoch": 6.43,
5524
+ "eval_loss": 0.25103089213371277,
5525
+ "eval_runtime": 1.4586,
5526
+ "eval_samples_per_second": 1506.907,
5527
+ "eval_steps_per_second": 23.995,
5528
+ "step": 276000
5529
+ },
5530
+ {
5531
+ "epoch": 6.44,
5532
+ "learning_rate": 0.00014159300220418757,
5533
+ "loss": 0.2692,
5534
+ "step": 276500
5535
+ },
5536
+ {
5537
+ "epoch": 6.45,
5538
+ "learning_rate": 0.0001411156242402808,
5539
+ "loss": 0.2691,
5540
+ "step": 277000
5541
+ },
5542
+ {
5543
+ "epoch": 6.45,
5544
+ "eval_loss": 0.2522771656513214,
5545
+ "eval_runtime": 1.4334,
5546
+ "eval_samples_per_second": 1533.4,
5547
+ "eval_steps_per_second": 24.417,
5548
+ "step": 277000
5549
+ },
5550
+ {
5551
+ "epoch": 6.47,
5552
+ "learning_rate": 0.0001406383981136829,
5553
+ "loss": 0.269,
5554
+ "step": 277500
5555
+ },
5556
+ {
5557
+ "epoch": 6.48,
5558
+ "learning_rate": 0.00014016132904326226,
5559
+ "loss": 0.2689,
5560
+ "step": 278000
5561
+ },
5562
+ {
5563
+ "epoch": 6.48,
5564
+ "eval_loss": 0.2521708011627197,
5565
+ "eval_runtime": 1.4301,
5566
+ "eval_samples_per_second": 1536.934,
5567
+ "eval_steps_per_second": 24.473,
5568
+ "step": 278000
5569
+ },
5570
+ {
5571
+ "epoch": 6.49,
5572
+ "learning_rate": 0.00013968442224616989,
5573
+ "loss": 0.269,
5574
+ "step": 278500
5575
+ },
5576
+ {
5577
+ "epoch": 6.5,
5578
+ "learning_rate": 0.00013920768293778195,
5579
+ "loss": 0.2688,
5580
+ "step": 279000
5581
+ },
5582
+ {
5583
+ "epoch": 6.5,
5584
+ "eval_loss": 0.25149086117744446,
5585
+ "eval_runtime": 1.4307,
5586
+ "eval_samples_per_second": 1536.357,
5587
+ "eval_steps_per_second": 24.464,
5588
+ "step": 279000
5589
+ },
5590
+ {
5591
+ "epoch": 6.51,
5592
+ "learning_rate": 0.00013873111633164336,
5593
+ "loss": 0.2686,
5594
+ "step": 279500
5595
+ },
5596
+ {
5597
+ "epoch": 6.52,
5598
+ "learning_rate": 0.00013825472763941,
5599
+ "loss": 0.2686,
5600
+ "step": 280000
5601
+ },
5602
+ {
5603
+ "epoch": 6.52,
5604
+ "eval_loss": 0.25161558389663696,
5605
+ "eval_runtime": 1.4115,
5606
+ "eval_samples_per_second": 1557.23,
5607
+ "eval_steps_per_second": 24.797,
5608
+ "step": 280000
5609
  }
5610
  ],
5611
  "max_steps": 500000,
5612
  "num_train_epochs": 12,
5613
+ "total_flos": 8.945624903740559e+21,
5614
  "trial_name": null,
5615
  "trial_params": null
5616
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6481ae1099357d8bcf88c484382e1abee67e04204a9282cec0553dec29988327
3
  size 102501541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee323f397e17b15c555d3f760433b7c390cda1ae17a7f66787ce543a9c888720
3
  size 102501541