Hugging Face's logo

lyan62
/
pixel-small-norm-input

Transformers
PyTorch
pixel
Model card Files
xet
 Community
lyan62 commited on
Commit
f644d24
·
1 Parent(s): 8809559

Training in progress, step 45000

Browse files
Files changed (9) 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/scheduler.pt +1 -1
  8. last-checkpoint/trainer_state.json +63 -3
  9. 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 sha256:48ef65f375b5e59f1f5749f9b5d92b6593185c721625528eb784cce2ed02d68c
3
  size 202193937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246faa74bee80665f358d5669008a0887cddb7b18e016fafe9dd7ea6316dd50e
3
  size 202193937
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65ddc0e4c8f4296ecd3c8937865a6a205702a67b3f399c44945e74c8eb7117ab
3
  size 102501541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e97a922c2788b9920a24141a5e48a7999f9bc8c2eff341a1e699714ef37106
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 sha256:0e78893dd4244a47b1f0ec82be35592851bdbef7f0a2077ad84f084e71bbb0dc
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46dd8d4a8076e5a459a085df9fe23a5e0b6a3ba2a8db83be1492ad01e7ed9159
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 sha256:0e78893dd4244a47b1f0ec82be35592851bdbef7f0a2077ad84f084e71bbb0dc
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46dd8d4a8076e5a459a085df9fe23a5e0b6a3ba2a8db83be1492ad01e7ed9159
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 sha256:0e78893dd4244a47b1f0ec82be35592851bdbef7f0a2077ad84f084e71bbb0dc
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46dd8d4a8076e5a459a085df9fe23a5e0b6a3ba2a8db83be1492ad01e7ed9159
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 sha256:0e78893dd4244a47b1f0ec82be35592851bdbef7f0a2077ad84f084e71bbb0dc
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46dd8d4a8076e5a459a085df9fe23a5e0b6a3ba2a8db83be1492ad01e7ed9159
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c97de0675cb6398d3c3d756355dca4463427408f54efe4c22a7193c161dbf261
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b42368e9f62da349b2760579f9deddc87fbe7062743f1048a9d6bf6e1d86f64
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": 0.6127685649726169,
5
- "global_step": 40000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -486,11 +486,71 @@
486
  "learning_rate": 1.4975414512725056e-05,
487
  "loss": 0.0519,
488
  "step": 40000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
489
  }
490
  ],
491
  "max_steps": 500000,
492
  "num_train_epochs": 8,
493
- "total_flos": 6.38974277549e+20,
494
  "trial_name": null,
495
  "trial_params": null
496
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.689364635594194,
5
+ "global_step": 45000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
486
  "learning_rate": 1.4975414512725056e-05,
487
  "loss": 0.0519,
488
  "step": 40000
489
+ },
490
+ {
491
+ "epoch": 0.62,
492
+ "learning_rate": 1.4973749622593532e-05,
493
+ "loss": 0.0518,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 0.63,
498
+ "learning_rate": 1.4972030340333e-05,
499
+ "loss": 0.0517,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 0.64,
504
+ "learning_rate": 1.4970256684745257e-05,
505
+ "loss": 0.0516,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 0.64,
510
+ "learning_rate": 1.4968428675226714e-05,
511
+ "loss": 0.0516,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 0.65,
516
+ "learning_rate": 1.4966546331768191e-05,
517
+ "loss": 0.0515,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 0.66,
522
+ "learning_rate": 1.4964609674954694e-05,
523
+ "loss": 0.0514,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 0.67,
528
+ "learning_rate": 1.4962618725965194e-05,
529
+ "loss": 0.0512,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 0.67,
534
+ "learning_rate": 1.496057350657239e-05,
535
+ "loss": 0.051,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 0.68,
540
+ "learning_rate": 1.4958474039142468e-05,
541
+ "loss": 0.0509,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 0.69,
546
+ "learning_rate": 1.4956320346634877e-05,
547
+ "loss": 0.0507,
548
+ "step": 45000
549
  }
550
  ],
551
  "max_steps": 500000,
552
  "num_train_epochs": 8,
553
+ "total_flos": 7.18846062242625e+20,
554
  "trial_name": null,
555
  "trial_params": null
556
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65ddc0e4c8f4296ecd3c8937865a6a205702a67b3f399c44945e74c8eb7117ab
3
  size 102501541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e97a922c2788b9920a24141a5e48a7999f9bc8c2eff341a1e699714ef37106
3
  size 102501541