Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
d185e5d
•
1 Parent(s): 6bed37a

Training in progress, step 65000

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:fc4b5c38d548341be3fc6afd8378b62fca364b9a262d5e49b6efc3fc65030ea5
3
  size 402587859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:508714af13750110697dcc33ea46fa8c5545e4a94eee6178bdccb17fefcd99b6
3
  size 402587859
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee27d0a5d8910b44eff2a0ce02526c87e97539b95bf5d100d30d6d417b3f746f
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:110d606f122187e413df09cf2f8a265ed4dfc0d65ceb886e487897d1c6480c2b
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 sha256:5b9e46153a153464357c8d7cc6f8af8240f1f9bd785168adecd2070b9a4aeb7f
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21af36309ee088c26a278e0de0ae0ae2f4972c410ac6786b526d393ded0505e
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 sha256:2debf9f408eebd277828e5d3a2c83beeed24c922197846fbb46de266f4c73c50
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7ea0fe0b29bea5a2d2fabbca1105b6b1aaa8cbad86b1fc422ee361a528b8ce2
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:ce0ffd2b212e3bb97c9d1959bc46c09d8be6d1062b4e9a4863f950b2dc626889
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ddda9abab8cc31fa025268cbb81d6a8c8d8aa990201b862378d198cc478d74
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 sha256:10efae63f5e57622a929379da87dd8d685840f8517ee8618d05f88b888c166c2
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d21aba50913ad7356ac8eef62498f347ed0dbc65005eea5be26644550e5a47b
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c5b2d0eac6380d6179c7b005df331b38821e3646464c4f2ddf0b4dc67ec2f03
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:663047b4a0c5f36263512e8d22703fbf5c49fefd0e151ecb448d12f819828b1d
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4618e81b42373dc5f5648c0a2c9f74dfcdbe40964e20a6736201f60748e5ad2a
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d13c4a77964966ff3b3d8b42bdcca922b42a79ca9fbc55e99378b908569c6cd
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": 1.0212765957446808,
5
- "global_step": 60000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -726,6 +726,66 @@
726
  "learning_rate": 0.0001450875916909765,
727
  "loss": 0.3597,
728
  "step": 60000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
729
  }
730
  ],
731
  "max_steps": 500000,
 
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,
 
726
  "learning_rate": 0.0001450875916909765,
727
  "loss": 0.3597,
728
  "step": 60000
729
+ },
730
+ {
731
+ "epoch": 1.03,
732
+ "learning_rate": 0.00014500650464850112,
733
+ "loss": 0.3599,
734
+ "step": 60500
735
+ },
736
+ {
737
+ "epoch": 1.04,
738
+ "learning_rate": 0.00014492461416110898,
739
+ "loss": 0.3597,
740
+ "step": 61000
741
+ },
742
+ {
743
+ "epoch": 1.05,
744
+ "learning_rate": 0.00014484208289398622,
745
+ "loss": 0.3597,
746
+ "step": 61500
747
+ },
748
+ {
749
+ "epoch": 1.06,
750
+ "learning_rate": 0.0001447589116616831,
751
+ "loss": 0.3595,
752
+ "step": 62000
753
+ },
754
+ {
755
+ "epoch": 1.06,
756
+ "learning_rate": 0.00014467510128506612,
757
+ "loss": 0.3592,
758
+ "step": 62500
759
+ },
760
+ {
761
+ "epoch": 1.07,
762
+ "learning_rate": 0.0001445908221251849,
763
+ "loss": 0.3592,
764
+ "step": 63000
765
+ },
766
+ {
767
+ "epoch": 1.08,
768
+ "learning_rate": 0.0001445057372218952,
769
+ "loss": 0.3589,
770
+ "step": 63500
771
+ },
772
+ {
773
+ "epoch": 1.09,
774
+ "learning_rate": 0.0001444203598262954,
775
+ "loss": 0.359,
776
+ "step": 64000
777
+ },
778
+ {
779
+ "epoch": 1.1,
780
+ "learning_rate": 0.0001443340050193786,
781
+ "loss": 0.3585,
782
+ "step": 64500
783
+ },
784
+ {
785
+ "epoch": 1.11,
786
+ "learning_rate": 0.000144247015261805,
787
+ "loss": 0.3586,
788
+ "step": 65000
789
  }
790
  ],
791
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee27d0a5d8910b44eff2a0ce02526c87e97539b95bf5d100d30d6d417b3f746f
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:110d606f122187e413df09cf2f8a265ed4dfc0d65ceb886e487897d1c6480c2b
3
  size 201355195