Hugging Face's logo

lyan62
/
pixel-small-norm-input

Transformers
PyTorch
pixel
Model card Files
xet
Community
lyan62 commited on
Commit
73b3cb1
·
1 Parent(s): f644d24

Training in progress, step 50000

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 sha256:246faa74bee80665f358d5669008a0887cddb7b18e016fafe9dd7ea6316dd50e
3
  size 202193937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa1dc7f5fc9388c2d1f5507b2b480a6971d0e5ad4f083763871e5180a4a5eb78
3
  size 202193937
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84e97a922c2788b9920a24141a5e48a7999f9bc8c2eff341a1e699714ef37106
3
  size 102501541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1eb7e02e3a1a4b3d44722003b11278e712b68cfd276db2f8080fca74e3018e
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 sha256:46dd8d4a8076e5a459a085df9fe23a5e0b6a3ba2a8db83be1492ad01e7ed9159
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301dae409878959b42641c88dc8715ef35fdfd1891caf687bdea0e2d195f085b
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 sha256:46dd8d4a8076e5a459a085df9fe23a5e0b6a3ba2a8db83be1492ad01e7ed9159
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301dae409878959b42641c88dc8715ef35fdfd1891caf687bdea0e2d195f085b
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 sha256:46dd8d4a8076e5a459a085df9fe23a5e0b6a3ba2a8db83be1492ad01e7ed9159
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301dae409878959b42641c88dc8715ef35fdfd1891caf687bdea0e2d195f085b
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 sha256:46dd8d4a8076e5a459a085df9fe23a5e0b6a3ba2a8db83be1492ad01e7ed9159
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301dae409878959b42641c88dc8715ef35fdfd1891caf687bdea0e2d195f085b
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b42368e9f62da349b2760579f9deddc87fbe7062743f1048a9d6bf6e1d86f64
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1523b036192bc6bb0c1cee6ebedfe56a79a760af7f78d821bec0d4544f869d8
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": 0.689364635594194,
5
- "global_step": 45000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -546,11 +546,71 @@
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
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.7659607062157712,
5
+ "global_step": 50000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
546
  "learning_rate": 1.4956320346634877e-05,
547
  "loss": 0.0507,
548
  "step": 45000
549
+ },
550
+ {
551
+ "epoch": 0.7,
552
+ "learning_rate": 1.4954112452602043e-05,
553
+ "loss": 0.0505,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 0.7,
558
+ "learning_rate": 1.4951850381189151e-05,
559
+ "loss": 0.0503,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 0.71,
564
+ "learning_rate": 1.4949534157133844e-05,
565
+ "loss": 0.0502,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 0.72,
570
+ "learning_rate": 1.494716380576598e-05,
571
+ "loss": 0.05,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 0.73,
576
+ "learning_rate": 1.4944739353007343e-05,
577
+ "loss": 0.0498,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 0.74,
582
+ "learning_rate": 1.4942260825371358e-05,
583
+ "loss": 0.0496,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 0.74,
588
+ "learning_rate": 1.4939728249962806e-05,
589
+ "loss": 0.0495,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 0.75,
594
+ "learning_rate": 1.4937141654477529e-05,
595
+ "loss": 0.0493,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 0.76,
600
+ "learning_rate": 1.4934501067202117e-05,
601
+ "loss": 0.0491,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 0.77,
606
+ "learning_rate": 1.4931806517013612e-05,
607
+ "loss": 0.0489,
608
+ "step": 50000
609
  }
610
  ],
611
  "max_steps": 500000,
612
  "num_train_epochs": 8,
613
+ "total_flos": 7.9871784693625e+20,
614
  "trial_name": null,
615
  "trial_params": null
616
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84e97a922c2788b9920a24141a5e48a7999f9bc8c2eff341a1e699714ef37106
3
  size 102501541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1eb7e02e3a1a4b3d44722003b11278e712b68cfd276db2f8080fca74e3018e
3
  size 102501541