Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
87a0fd2
•
1 Parent(s): d185e5d

Training in progress, step 70000

Browse files
Files changed (10) hide show
  1. last-checkpoint/optimizer.pt +2 -2
  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 sha256:508714af13750110697dcc33ea46fa8c5545e4a94eee6178bdccb17fefcd99b6
3
- size 402587859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42eb530ad78e4c5e9233710625a9a47a85f5f4212477901f2e83f08f24c15c16
3
+ size 402588883
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:110d606f122187e413df09cf2f8a265ed4dfc0d65ceb886e487897d1c6480c2b
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19d8c99b140931256d0c697e94d571b3b2af212d719b7f19ba2a7edf190ae3f
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:d21af36309ee088c26a278e0de0ae0ae2f4972c410ac6786b526d393ded0505e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b2a80d31d8b741b0ecbc55d2a266d6f43fbc20bb3c941fdf0d93551d64da28e
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:e7ea0fe0b29bea5a2d2fabbca1105b6b1aaa8cbad86b1fc422ee361a528b8ce2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af87208b0132272f8ddba1ca01cd85ce79b894ce34a8dc1dbba257269f0d6618
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:c8ddda9abab8cc31fa025268cbb81d6a8c8d8aa990201b862378d198cc478d74
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773c4ec450a74083160dd66ee70c2fb827fbb80e8bfa0b8de62c45e67abf67dc
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 sha256:1d21aba50913ad7356ac8eef62498f347ed0dbc65005eea5be26644550e5a47b
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2435f65d9a219727aaa62d009d9d1a2c757dc3cb22266290adb2b6bd106efabc
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:663047b4a0c5f36263512e8d22703fbf5c49fefd0e151ecb448d12f819828b1d
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b4a2e6e3a6625efd59ce06375fdaacaa33f2797311937ee5554db7f4d88c193
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d13c4a77964966ff3b3d8b42bdcca922b42a79ca9fbc55e99378b908569c6cd
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1962a04d7a92e3fcea855b803bc597fa68459b54eddde96cc268a53f2c80b19e
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": 1.1063829787234043,
5
- "global_step": 65000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -786,6 +786,66 @@
786
  "learning_rate": 0.000144247015261805,
787
  "loss": 0.3586,
788
  "step": 65000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
789
  }
790
  ],
791
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.1914893617021276,
5
+ "global_step": 70000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
786
  "learning_rate": 0.000144247015261805,
787
  "loss": 0.3586,
788
  "step": 65000
789
+ },
790
+ {
791
+ "epoch": 1.11,
792
+ "learning_rate": 0.00014415939141212825,
793
+ "loss": 0.3585,
794
+ "step": 65500
795
+ },
796
+ {
797
+ "epoch": 1.12,
798
+ "learning_rate": 0.00014407113433516052,
799
+ "loss": 0.3583,
800
+ "step": 66000
801
+ },
802
+ {
803
+ "epoch": 1.13,
804
+ "learning_rate": 0.00014398224490196345,
805
+ "loss": 0.3578,
806
+ "step": 66500
807
+ },
808
+ {
809
+ "epoch": 1.14,
810
+ "learning_rate": 0.00014389272398983985,
811
+ "loss": 0.3579,
812
+ "step": 67000
813
+ },
814
+ {
815
+ "epoch": 1.15,
816
+ "learning_rate": 0.000143802572482325,
817
+ "loss": 0.3577,
818
+ "step": 67500
819
+ },
820
+ {
821
+ "epoch": 1.16,
822
+ "learning_rate": 0.00014371179126917793,
823
+ "loss": 0.3579,
824
+ "step": 68000
825
+ },
826
+ {
827
+ "epoch": 1.17,
828
+ "learning_rate": 0.0001436203812463725,
829
+ "loss": 0.3576,
830
+ "step": 68500
831
+ },
832
+ {
833
+ "epoch": 1.17,
834
+ "learning_rate": 0.00014352834331608877,
835
+ "loss": 0.3575,
836
+ "step": 69000
837
+ },
838
+ {
839
+ "epoch": 1.18,
840
+ "learning_rate": 0.00014343567838670393,
841
+ "loss": 0.3573,
842
+ "step": 69500
843
+ },
844
+ {
845
+ "epoch": 1.19,
846
+ "learning_rate": 0.00014334257457903268,
847
+ "loss": 0.3572,
848
+ "step": 70000
849
  }
850
  ],
851
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:110d606f122187e413df09cf2f8a265ed4dfc0d65ceb886e487897d1c6480c2b
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19d8c99b140931256d0c697e94d571b3b2af212d719b7f19ba2a7edf190ae3f
3
  size 201355195