Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
c91a910
•
1 Parent(s): 42cde88

Training in progress, step 125000

Browse files
Files changed (10) 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/scaler.pt +1 -1
  8. last-checkpoint/scheduler.pt +1 -1
  9. last-checkpoint/trainer_state.json +62 -2
  10. 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 sha256:542104b06e65c9ace54b8e711bbac9cc621773a58de8d01b41cd5415fe72b366
3
  size 402588883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715e0e8be89d37573d9737a1c24d8bdbc9e9b2798c095b6dd77083ee246e4b5e
3
  size 402588883
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b30fa6c8a84af0d7218464b722bd9fc5359deac800cc03a88336084563eec6c
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8869810778716acdf04a14b7810c7cd05a37e77a3b0b8703e480510c9c151d4d
3
  size 201355195
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:253ec9051983bdc300e9d368605149ab9db6148a7cad5289347f4c3ed6bf0e0b
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:485da7cd55263b63446c157f44f27b87fb32ee7fc8eebf027bb180b9c237d45c
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:d26a68a6639ccae89e06188f10a2fdceb2b6d290e074968df743779292dbaf14
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe2becae96d0bfe0642f180656d8f851e08d5cc276fa73454429b9bf4abe4595
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 sha256:36d17390300a97335e809dda525ee1fa7b3c57afe94917c7ee65e3550c222c6f
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a8f27c19602395c972a777956eabb92faa53f9a3ecfed7453e7be61e2a8cd3
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 sha256:8ab3d619cc75d610e67ba5c5005e0fdf4981eb47efeadbcf338f6a49009fb766
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:300b14754e23979cda63a41ff58b9876ace2d573293baa740b780d3a32e65f37
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87e2d1745c681c91159da5acdbfd8bc474c3ecf40e467f65b9d5603d68c91173
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59be1bec87403b8107dac3a9347a48de1f138640ea41452d9e2ca95898d5ca80
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2278aa08713ed016c36bd4379ecb42317a1cf7d42a036b9f5bd0ffaee3d8558c
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1413c187c59724b9bbc5484849686965cd229f2bb3f2f6ffba36fe094d3739fd
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": 2.0425531914893615,
5
- "global_step": 120000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -1446,6 +1446,66 @@
1446
  "learning_rate": 0.00013104195243276762,
1447
  "loss": 0.3452,
1448
  "step": 120000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1449
  }
1450
  ],
1451
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.127659574468085,
5
+ "global_step": 125000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
1446
  "learning_rate": 0.00013104195243276762,
1447
  "loss": 0.3452,
1448
  "step": 120000
1449
+ },
1450
+ {
1451
+ "epoch": 2.05,
1452
+ "learning_rate": 0.0001308912083746959,
1453
+ "loss": 0.3455,
1454
+ "step": 120500
1455
+ },
1456
+ {
1457
+ "epoch": 2.06,
1458
+ "learning_rate": 0.0001307399620409431,
1459
+ "loss": 0.3449,
1460
+ "step": 121000
1461
+ },
1462
+ {
1463
+ "epoch": 2.07,
1464
+ "learning_rate": 0.00013058821492424954,
1465
+ "loss": 0.3455,
1466
+ "step": 121500
1467
+ },
1468
+ {
1469
+ "epoch": 2.08,
1470
+ "learning_rate": 0.00013043627351239063,
1471
+ "loss": 0.3448,
1472
+ "step": 122000
1473
+ },
1474
+ {
1475
+ "epoch": 2.09,
1476
+ "learning_rate": 0.00013028353032185398,
1477
+ "loss": 0.3448,
1478
+ "step": 122500
1479
+ },
1480
+ {
1481
+ "epoch": 2.09,
1482
+ "learning_rate": 0.00013013029085317334,
1483
+ "loss": 0.345,
1484
+ "step": 123000
1485
+ },
1486
+ {
1487
+ "epoch": 2.1,
1488
+ "learning_rate": 0.00012997655661876038,
1489
+ "loss": 0.3447,
1490
+ "step": 123500
1491
+ },
1492
+ {
1493
+ "epoch": 2.11,
1494
+ "learning_rate": 0.00012982232913590996,
1495
+ "loss": 0.3445,
1496
+ "step": 124000
1497
+ },
1498
+ {
1499
+ "epoch": 2.12,
1500
+ "learning_rate": 0.00012966760992678508,
1501
+ "loss": 0.3445,
1502
+ "step": 124500
1503
+ },
1504
+ {
1505
+ "epoch": 2.13,
1506
+ "learning_rate": 0.0001295124005184018,
1507
+ "loss": 0.3442,
1508
+ "step": 125000
1509
  }
1510
  ],
1511
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b30fa6c8a84af0d7218464b722bd9fc5359deac800cc03a88336084563eec6c
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8869810778716acdf04a14b7810c7cd05a37e77a3b0b8703e480510c9c151d4d
3
  size 201355195