Hugging Face's logo

Team-PIXEL
/
pixel-small-bigrams

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
jflotz commited on
Commit
fb6a959
•
1 Parent(s): 2421f20

Training in progress, step 50000

Browse files
Files changed (17) hide show
  1. config.json +1 -0
  2. last-checkpoint/config.json +1 -0
  3. last-checkpoint/optimizer.pt +1 -1
  4. last-checkpoint/pytorch_model.bin +1 -1
  5. last-checkpoint/rng_state_0.pth +1 -1
  6. last-checkpoint/rng_state_1.pth +1 -1
  7. last-checkpoint/rng_state_2.pth +1 -1
  8. last-checkpoint/rng_state_3.pth +1 -1
  9. last-checkpoint/rng_state_4.pth +1 -1
  10. last-checkpoint/rng_state_5.pth +1 -1
  11. last-checkpoint/rng_state_6.pth +1 -1
  12. last-checkpoint/rng_state_7.pth +1 -1
  13. last-checkpoint/scheduler.pt +1 -1
  14. last-checkpoint/trainer_state.json +203 -3
  15. last-checkpoint/training_args.bin +1 -1
  16. pytorch_model.bin +1 -1
  17. training_args.bin +1 -1
config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "PIXELForPreTraining"
4
  ],
 
1
  {
2
+ "_name_or_path": "/scratch/project/dd-23-53/experiments/pixel-small-bigrams/checkpoint-40000",
3
  "architectures": [
4
  "PIXELForPreTraining"
5
  ],
last-checkpoint/config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "PIXELForPreTraining"
4
  ],
 
1
  {
2
+ "_name_or_path": "/scratch/project/dd-23-53/experiments/pixel-small-bigrams/checkpoint-40000",
3
  "architectures": [
4
  "PIXELForPreTraining"
5
  ],
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d70265470022ea1ea19ba2ecc6b2ba2ab39831157147b92926ca5299368d28f1
3
  size 202193937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1b801dea4c20ae9f56153a02de048f5ae98203f41a9a2f643b5429e198a7fdc
3
  size 202193937
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07e2b246bf7aa13a5e2f82d46ff1f82b0865e3cc8d30ecbee7edaf22d95ad268
3
  size 102501541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8da0387c8445a52a92bcde48c6a02b31823dfc1997cb4f757ede3d79441e525
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 sha256:26ce7bafde677dd834b0e717580e9362f8261d8f33ccf9c59c48b6a40577d154
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
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 sha256:26ce7bafde677dd834b0e717580e9362f8261d8f33ccf9c59c48b6a40577d154
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
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 sha256:26ce7bafde677dd834b0e717580e9362f8261d8f33ccf9c59c48b6a40577d154
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
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 sha256:26ce7bafde677dd834b0e717580e9362f8261d8f33ccf9c59c48b6a40577d154
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
3
  size 14503
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26ce7bafde677dd834b0e717580e9362f8261d8f33ccf9c59c48b6a40577d154
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
3
  size 14503
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26ce7bafde677dd834b0e717580e9362f8261d8f33ccf9c59c48b6a40577d154
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
3
  size 14503
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26ce7bafde677dd834b0e717580e9362f8261d8f33ccf9c59c48b6a40577d154
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
3
  size 14503
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26ce7bafde677dd834b0e717580e9362f8261d8f33ccf9c59c48b6a40577d154
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748720a887e8570d858c8fc032794290e01333acb84b2a457c98a6bb54b6cd33
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a74054da3729955ad5eacae83f875e2df84ec7d4ca3ed3437d6f2cf84557171f
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec5c60f6b831a1ad5ababd554115ca1132f641d196d63d42183ef95c8827963
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": 0.8922198429693077,
5
- "global_step": 40000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -806,11 +806,211 @@
806
  "eval_samples_per_second": 1227.432,
807
  "eval_steps_per_second": 19.237,
808
  "step": 40000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
809
  }
810
  ],
811
  "max_steps": 500000,
812
  "num_train_epochs": 12,
813
- "total_flos": 1.277948555098e+21,
814
  "trial_name": null,
815
  "trial_params": null
816
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.1152748037116345,
5
+ "global_step": 50000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
806
  "eval_samples_per_second": 1227.432,
807
  "eval_steps_per_second": 19.237,
808
  "step": 40000
809
+ },
810
+ {
811
+ "epoch": 0.9,
812
+ "learning_rate": 0.00029923873905521244,
813
+ "loss": 0.3579,
814
+ "step": 40500
815
+ },
816
+ {
817
+ "epoch": 0.91,
818
+ "learning_rate": 0.000299188879869657,
819
+ "loss": 0.3568,
820
+ "step": 41000
821
+ },
822
+ {
823
+ "epoch": 0.91,
824
+ "eval_loss": 0.33952972292900085,
825
+ "eval_runtime": 2.0164,
826
+ "eval_samples_per_second": 1139.183,
827
+ "eval_steps_per_second": 17.854,
828
+ "step": 41000
829
+ },
830
+ {
831
+ "epoch": 0.93,
832
+ "learning_rate": 0.00029913744385761244,
833
+ "loss": 0.3554,
834
+ "step": 41500
835
+ },
836
+ {
837
+ "epoch": 0.94,
838
+ "learning_rate": 0.00029908443158157465,
839
+ "loss": 0.3549,
840
+ "step": 42000
841
+ },
842
+ {
843
+ "epoch": 0.94,
844
+ "eval_loss": 0.334180623292923,
845
+ "eval_runtime": 1.9257,
846
+ "eval_samples_per_second": 1192.785,
847
+ "eval_steps_per_second": 18.694,
848
+ "step": 42000
849
+ },
850
+ {
851
+ "epoch": 0.95,
852
+ "learning_rate": 0.0002990298436212775,
853
+ "loss": 0.3538,
854
+ "step": 42500
855
+ },
856
+ {
857
+ "epoch": 0.96,
858
+ "learning_rate": 0.0002989736805736861,
859
+ "loss": 0.3524,
860
+ "step": 43000
861
+ },
862
+ {
863
+ "epoch": 0.96,
864
+ "eval_loss": 0.3344336450099945,
865
+ "eval_runtime": 1.9242,
866
+ "eval_samples_per_second": 1193.754,
867
+ "eval_steps_per_second": 18.709,
868
+ "step": 43000
869
+ },
870
+ {
871
+ "epoch": 0.97,
872
+ "learning_rate": 0.00029891594305299065,
873
+ "loss": 0.3519,
874
+ "step": 43500
875
+ },
876
+ {
877
+ "epoch": 0.98,
878
+ "learning_rate": 0.00029885663169059926,
879
+ "loss": 0.3504,
880
+ "step": 44000
881
+ },
882
+ {
883
+ "epoch": 0.98,
884
+ "eval_loss": 0.3332378566265106,
885
+ "eval_runtime": 1.9034,
886
+ "eval_samples_per_second": 1206.779,
887
+ "eval_steps_per_second": 18.913,
888
+ "step": 44000
889
+ },
890
+ {
891
+ "epoch": 0.99,
892
+ "learning_rate": 0.0002987957471351316,
893
+ "loss": 0.3499,
894
+ "step": 44500
895
+ },
896
+ {
897
+ "epoch": 1.0,
898
+ "learning_rate": 0.00029873329005241137,
899
+ "loss": 0.349,
900
+ "step": 45000
901
+ },
902
+ {
903
+ "epoch": 1.0,
904
+ "eval_loss": 0.3305933475494385,
905
+ "eval_runtime": 2.0165,
906
+ "eval_samples_per_second": 1139.102,
907
+ "eval_steps_per_second": 17.853,
908
+ "step": 45000
909
+ },
910
+ {
911
+ "epoch": 1.01,
912
+ "learning_rate": 0.00029866926112545925,
913
+ "loss": 0.3482,
914
+ "step": 45500
915
+ },
916
+ {
917
+ "epoch": 1.03,
918
+ "learning_rate": 0.00029860366105448534,
919
+ "loss": 0.3473,
920
+ "step": 46000
921
+ },
922
+ {
923
+ "epoch": 1.03,
924
+ "eval_loss": 0.32961174845695496,
925
+ "eval_runtime": 2.0634,
926
+ "eval_samples_per_second": 1113.205,
927
+ "eval_steps_per_second": 17.447,
928
+ "step": 46000
929
+ },
930
+ {
931
+ "epoch": 1.04,
932
+ "learning_rate": 0.00029853649055688143,
933
+ "loss": 0.3464,
934
+ "step": 46500
935
+ },
936
+ {
937
+ "epoch": 1.05,
938
+ "learning_rate": 0.00029846775036721337,
939
+ "loss": 0.3459,
940
+ "step": 47000
941
+ },
942
+ {
943
+ "epoch": 1.05,
944
+ "eval_loss": 0.32834696769714355,
945
+ "eval_runtime": 1.9893,
946
+ "eval_samples_per_second": 1154.665,
947
+ "eval_steps_per_second": 18.097,
948
+ "step": 47000
949
+ },
950
+ {
951
+ "epoch": 1.06,
952
+ "learning_rate": 0.0002983974412372129,
953
+ "loss": 0.3446,
954
+ "step": 47500
955
+ },
956
+ {
957
+ "epoch": 1.07,
958
+ "learning_rate": 0.00029832556393576934,
959
+ "loss": 0.3441,
960
+ "step": 48000
961
+ },
962
+ {
963
+ "epoch": 1.07,
964
+ "eval_loss": 0.3241877555847168,
965
+ "eval_runtime": 2.051,
966
+ "eval_samples_per_second": 1119.916,
967
+ "eval_steps_per_second": 17.552,
968
+ "step": 48000
969
+ },
970
+ {
971
+ "epoch": 1.08,
972
+ "learning_rate": 0.0002982521192489214,
973
+ "loss": 0.3434,
974
+ "step": 48500
975
+ },
976
+ {
977
+ "epoch": 1.09,
978
+ "learning_rate": 0.0002981771079798483,
979
+ "loss": 0.3427,
980
+ "step": 49000
981
+ },
982
+ {
983
+ "epoch": 1.09,
984
+ "eval_loss": 0.3232521414756775,
985
+ "eval_runtime": 1.9619,
986
+ "eval_samples_per_second": 1170.819,
987
+ "eval_steps_per_second": 18.35,
988
+ "step": 49000
989
+ },
990
+ {
991
+ "epoch": 1.1,
992
+ "learning_rate": 0.00029810053094886136,
993
+ "loss": 0.3417,
994
+ "step": 49500
995
+ },
996
+ {
997
+ "epoch": 1.12,
998
+ "learning_rate": 0.00029802238899339473,
999
+ "loss": 0.3411,
1000
+ "step": 50000
1001
+ },
1002
+ {
1003
+ "epoch": 1.12,
1004
+ "eval_loss": 0.322670042514801,
1005
+ "eval_runtime": 2.0139,
1006
+ "eval_samples_per_second": 1140.566,
1007
+ "eval_steps_per_second": 17.876,
1008
+ "step": 50000
1009
  }
1010
  ],
1011
  "max_steps": 500000,
1012
  "num_train_epochs": 12,
1013
+ "total_flos": 1.5974072396110847e+21,
1014
  "trial_name": null,
1015
  "trial_params": null
1016
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:229efc1d49e061de5d19e6e496114be212e29dd2150b027ea46959c2a5a56c0b
3
  size 3311
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c715d802a0f8524bc88a58a9da709a3014ffe9a72d25436949dd9981d1ef0ef1
3
  size 3311
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07e2b246bf7aa13a5e2f82d46ff1f82b0865e3cc8d30ecbee7edaf22d95ad268
3
  size 102501541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8da0387c8445a52a92bcde48c6a02b31823dfc1997cb4f757ede3d79441e525
3
  size 102501541
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:229efc1d49e061de5d19e6e496114be212e29dd2150b027ea46959c2a5a56c0b
3
  size 3311
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c715d802a0f8524bc88a58a9da709a3014ffe9a72d25436949dd9981d1ef0ef1
3
  size 3311