Hugging Face's logo

joelniklaus
/
legal-polish-roberta-base

Fill-Mask
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Model card Files
xet
 Metrics Community
1
joelniklaus HF Staff commited on
Commit
c59dcc7
·
1 Parent(s): 15b76ae

Training in progress, step 150000

Browse files
Files changed (14) 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/rng_state_4.pth +1 -1
  8. last-checkpoint/rng_state_5.pth +1 -1
  9. last-checkpoint/rng_state_6.pth +1 -1
  10. last-checkpoint/rng_state_7.pth +1 -1
  11. last-checkpoint/scheduler.pt +1 -1
  12. last-checkpoint/trainer_state.json +311 -3
  13. pytorch_model.bin +1 -1
  14. runs/Feb09_18-30-25_t1v-n-58269bec-w-0/events.out.tfevents.1675967450.t1v-n-58269bec-w-0.26493.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf4019b10b6ed190efff70c7556165d3997acc7bb7f0f07b2092982731a9fc80
3
  size 885325017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a461779564ba5390753865b7c7e5cdb01559b3d77f5daeb0b88ee8b7f0ee0b6c
3
  size 885325017
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c17201af382ce6251128eb3e64a4a914a91fb56a8224f40251bf4c5f91e3e0a
3
  size 442675755
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d67b0d9b43a50a688c8f053a75d17f4d27724c1bab4a2baee84a81df3ad665
3
  size 442675755
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7def850aafbf12913b32009f896f8403a62ad39db7571b068ef4572c2abbf2ab
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b930a1e8f69335ea9febebb5f89a57eab0a63cf76bf0d2e207317b0797c1fd8
3
  size 13611
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7def850aafbf12913b32009f896f8403a62ad39db7571b068ef4572c2abbf2ab
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b930a1e8f69335ea9febebb5f89a57eab0a63cf76bf0d2e207317b0797c1fd8
3
  size 13611
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7def850aafbf12913b32009f896f8403a62ad39db7571b068ef4572c2abbf2ab
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b930a1e8f69335ea9febebb5f89a57eab0a63cf76bf0d2e207317b0797c1fd8
3
  size 13611
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7def850aafbf12913b32009f896f8403a62ad39db7571b068ef4572c2abbf2ab
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b930a1e8f69335ea9febebb5f89a57eab0a63cf76bf0d2e207317b0797c1fd8
3
  size 13611
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7def850aafbf12913b32009f896f8403a62ad39db7571b068ef4572c2abbf2ab
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b930a1e8f69335ea9febebb5f89a57eab0a63cf76bf0d2e207317b0797c1fd8
3
  size 13611
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7def850aafbf12913b32009f896f8403a62ad39db7571b068ef4572c2abbf2ab
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b930a1e8f69335ea9febebb5f89a57eab0a63cf76bf0d2e207317b0797c1fd8
3
  size 13611
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7def850aafbf12913b32009f896f8403a62ad39db7571b068ef4572c2abbf2ab
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b930a1e8f69335ea9febebb5f89a57eab0a63cf76bf0d2e207317b0797c1fd8
3
  size 13611
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7def850aafbf12913b32009f896f8403a62ad39db7571b068ef4572c2abbf2ab
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b930a1e8f69335ea9febebb5f89a57eab0a63cf76bf0d2e207317b0797c1fd8
3
  size 13611
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4178362c6bd24374be7907f1b74df811389bf304534a9b4cb11df3bada4d661b
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466c6a5b8905e18425c9b34e30a286f9f5cd812d089137c68b3bf75167c114fb
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": 0.5,
5
- "global_step": 100000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -622,11 +622,319 @@
622
  "eval_samples_per_second": 469.306,
623
  "eval_steps_per_second": 3.754,
624
  "step": 100000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
625
  }
626
  ],
627
  "max_steps": 200000,
628
  "num_train_epochs": 9223372036854775807,
629
- "total_flos": 1.6845398605824e+18,
630
  "trial_name": null,
631
  "trial_params": null
632
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.2147999999999999,
5
+ "global_step": 150000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
622
  "eval_samples_per_second": 469.306,
623
  "eval_steps_per_second": 3.754,
624
  "step": 100000
625
+ },
626
+ {
627
+ "epoch": 0.51,
628
+ "learning_rate": 5.330452921628497e-05,
629
+ "loss": 0.7122,
630
+ "step": 101000
631
+ },
632
+ {
633
+ "epoch": 0.51,
634
+ "learning_rate": 5.247918773366112e-05,
635
+ "loss": 0.819,
636
+ "step": 102000
637
+ },
638
+ {
639
+ "epoch": 0.52,
640
+ "learning_rate": 5.165316846586541e-05,
641
+ "loss": 0.8136,
642
+ "step": 103000
643
+ },
644
+ {
645
+ "epoch": 0.52,
646
+ "learning_rate": 5.0826697238317935e-05,
647
+ "loss": 0.7301,
648
+ "step": 104000
649
+ },
650
+ {
651
+ "epoch": 0.53,
652
+ "learning_rate": 5e-05,
653
+ "loss": 0.8168,
654
+ "step": 105000
655
+ },
656
+ {
657
+ "epoch": 0.53,
658
+ "learning_rate": 4.917330276168208e-05,
659
+ "loss": 0.7646,
660
+ "step": 106000
661
+ },
662
+ {
663
+ "epoch": 0.54,
664
+ "learning_rate": 4.834683153413459e-05,
665
+ "loss": 0.7741,
666
+ "step": 107000
667
+ },
668
+ {
669
+ "epoch": 1.0,
670
+ "learning_rate": 4.7520812266338885e-05,
671
+ "loss": 0.7258,
672
+ "step": 108000
673
+ },
674
+ {
675
+ "epoch": 1.01,
676
+ "learning_rate": 4.669547078371504e-05,
677
+ "loss": 0.8073,
678
+ "step": 109000
679
+ },
680
+ {
681
+ "epoch": 1.01,
682
+ "learning_rate": 4.5871032726383386e-05,
683
+ "loss": 0.7516,
684
+ "step": 110000
685
+ },
686
+ {
687
+ "epoch": 1.02,
688
+ "learning_rate": 4.504772348747687e-05,
689
+ "loss": 0.7734,
690
+ "step": 111000
691
+ },
692
+ {
693
+ "epoch": 1.02,
694
+ "learning_rate": 4.4225768151520694e-05,
695
+ "loss": 0.8224,
696
+ "step": 112000
697
+ },
698
+ {
699
+ "epoch": 1.03,
700
+ "learning_rate": 4.3405391432896555e-05,
701
+ "loss": 0.7031,
702
+ "step": 113000
703
+ },
704
+ {
705
+ "epoch": 1.03,
706
+ "learning_rate": 4.2586817614407895e-05,
707
+ "loss": 0.8007,
708
+ "step": 114000
709
+ },
710
+ {
711
+ "epoch": 1.04,
712
+ "learning_rate": 4.17702704859633e-05,
713
+ "loss": 0.8144,
714
+ "step": 115000
715
+ },
716
+ {
717
+ "epoch": 1.04,
718
+ "learning_rate": 4.095597328339452e-05,
719
+ "loss": 0.7135,
720
+ "step": 116000
721
+ },
722
+ {
723
+ "epoch": 1.05,
724
+ "learning_rate": 4.0144148627425993e-05,
725
+ "loss": 0.8049,
726
+ "step": 117000
727
+ },
728
+ {
729
+ "epoch": 1.05,
730
+ "learning_rate": 3.933501846281267e-05,
731
+ "loss": 0.7644,
732
+ "step": 118000
733
+ },
734
+ {
735
+ "epoch": 1.06,
736
+ "learning_rate": 3.852880399766243e-05,
737
+ "loss": 0.7534,
738
+ "step": 119000
739
+ },
740
+ {
741
+ "epoch": 1.06,
742
+ "learning_rate": 3.772572564296005e-05,
743
+ "loss": 0.8139,
744
+ "step": 120000
745
+ },
746
+ {
747
+ "epoch": 1.07,
748
+ "learning_rate": 3.6926002952309016e-05,
749
+ "loss": 0.7067,
750
+ "step": 121000
751
+ },
752
+ {
753
+ "epoch": 1.07,
754
+ "learning_rate": 3.612985456190778e-05,
755
+ "loss": 0.7878,
756
+ "step": 122000
757
+ },
758
+ {
759
+ "epoch": 1.08,
760
+ "learning_rate": 3.533749813077677e-05,
761
+ "loss": 0.8106,
762
+ "step": 123000
763
+ },
764
+ {
765
+ "epoch": 1.08,
766
+ "learning_rate": 3.4549150281252636e-05,
767
+ "loss": 0.6941,
768
+ "step": 124000
769
+ },
770
+ {
771
+ "epoch": 1.09,
772
+ "learning_rate": 3.3765026539765834e-05,
773
+ "loss": 0.7911,
774
+ "step": 125000
775
+ },
776
+ {
777
+ "epoch": 1.09,
778
+ "learning_rate": 3.298534127791785e-05,
779
+ "loss": 0.7836,
780
+ "step": 126000
781
+ },
782
+ {
783
+ "epoch": 1.1,
784
+ "learning_rate": 3.221030765387417e-05,
785
+ "loss": 0.7138,
786
+ "step": 127000
787
+ },
788
+ {
789
+ "epoch": 1.1,
790
+ "learning_rate": 3.144013755408895e-05,
791
+ "loss": 0.7949,
792
+ "step": 128000
793
+ },
794
+ {
795
+ "epoch": 1.11,
796
+ "learning_rate": 3.0675041535377405e-05,
797
+ "loss": 0.7253,
798
+ "step": 129000
799
+ },
800
+ {
801
+ "epoch": 1.11,
802
+ "learning_rate": 2.991522876735154e-05,
803
+ "loss": 0.7642,
804
+ "step": 130000
805
+ },
806
+ {
807
+ "epoch": 1.12,
808
+ "learning_rate": 2.916090697523549e-05,
809
+ "loss": 0.8107,
810
+ "step": 131000
811
+ },
812
+ {
813
+ "epoch": 1.12,
814
+ "learning_rate": 2.8412282383075363e-05,
815
+ "loss": 0.6913,
816
+ "step": 132000
817
+ },
818
+ {
819
+ "epoch": 1.13,
820
+ "learning_rate": 2.766955965735968e-05,
821
+ "loss": 0.7929,
822
+ "step": 133000
823
+ },
824
+ {
825
+ "epoch": 1.13,
826
+ "learning_rate": 2.693294185106562e-05,
827
+ "loss": 0.7944,
828
+ "step": 134000
829
+ },
830
+ {
831
+ "epoch": 1.14,
832
+ "learning_rate": 2.6202630348146324e-05,
833
+ "loss": 0.6936,
834
+ "step": 135000
835
+ },
836
+ {
837
+ "epoch": 1.14,
838
+ "learning_rate": 2.547882480847461e-05,
839
+ "loss": 0.785,
840
+ "step": 136000
841
+ },
842
+ {
843
+ "epoch": 1.15,
844
+ "learning_rate": 2.476172311325783e-05,
845
+ "loss": 0.754,
846
+ "step": 137000
847
+ },
848
+ {
849
+ "epoch": 1.15,
850
+ "learning_rate": 2.405152131093926e-05,
851
+ "loss": 0.7297,
852
+ "step": 138000
853
+ },
854
+ {
855
+ "epoch": 1.16,
856
+ "learning_rate": 2.3348413563600325e-05,
857
+ "loss": 0.7924,
858
+ "step": 139000
859
+ },
860
+ {
861
+ "epoch": 1.16,
862
+ "learning_rate": 2.2652592093878666e-05,
863
+ "loss": 0.7295,
864
+ "step": 140000
865
+ },
866
+ {
867
+ "epoch": 1.17,
868
+ "learning_rate": 2.196424713241637e-05,
869
+ "loss": 1.2371,
870
+ "step": 141000
871
+ },
872
+ {
873
+ "epoch": 1.17,
874
+ "learning_rate": 2.128356686585282e-05,
875
+ "loss": 1.1241,
876
+ "step": 142000
877
+ },
878
+ {
879
+ "epoch": 1.18,
880
+ "learning_rate": 2.061073738537635e-05,
881
+ "loss": 0.7291,
882
+ "step": 143000
883
+ },
884
+ {
885
+ "epoch": 1.18,
886
+ "learning_rate": 1.9945942635848748e-05,
887
+ "loss": 0.7905,
888
+ "step": 144000
889
+ },
890
+ {
891
+ "epoch": 1.19,
892
+ "learning_rate": 1.928936436551661e-05,
893
+ "loss": 0.7757,
894
+ "step": 145000
895
+ },
896
+ {
897
+ "epoch": 1.19,
898
+ "learning_rate": 1.8641182076323148e-05,
899
+ "loss": 0.711,
900
+ "step": 146000
901
+ },
902
+ {
903
+ "epoch": 1.2,
904
+ "learning_rate": 1.800157297483417e-05,
905
+ "loss": 0.7894,
906
+ "step": 147000
907
+ },
908
+ {
909
+ "epoch": 1.2,
910
+ "learning_rate": 1.7370711923791567e-05,
911
+ "loss": 0.7203,
912
+ "step": 148000
913
+ },
914
+ {
915
+ "epoch": 1.21,
916
+ "learning_rate": 1.6748771394307585e-05,
917
+ "loss": 0.7491,
918
+ "step": 149000
919
+ },
920
+ {
921
+ "epoch": 1.21,
922
+ "learning_rate": 1.6135921418712956e-05,
923
+ "loss": 0.7926,
924
+ "step": 150000
925
+ },
926
+ {
927
+ "epoch": 1.21,
928
+ "eval_loss": 0.5243843793869019,
929
+ "eval_runtime": 11.9974,
930
+ "eval_samples_per_second": 416.755,
931
+ "eval_steps_per_second": 3.334,
932
+ "step": 150000
933
  }
934
  ],
935
  "max_steps": 200000,
936
  "num_train_epochs": 9223372036854775807,
937
+ "total_flos": 2.5268224249225544e+18,
938
  "trial_name": null,
939
  "trial_params": null
940
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c17201af382ce6251128eb3e64a4a914a91fb56a8224f40251bf4c5f91e3e0a
3
  size 442675755
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d67b0d9b43a50a688c8f053a75d17f4d27724c1bab4a2baee84a81df3ad665
3
  size 442675755
runs/Feb09_18-30-25_t1v-n-58269bec-w-0/events.out.tfevents.1675967450.t1v-n-58269bec-w-0.26493.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f99b19d7c9cd9ff3b92000d6896007061f221a55320f990e63cfa50c9ec4911
3
- size 20279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cdbcf6c33cbc44735fcbd8696083c4760d7563dcd7b1c5bd92b954c9bd0def0
3
+ size 28555