Hugging Face's logo

nbtpj
/
bart-base-rmqa-fine-tune

Text2Text Generation
Transformers
PyTorch
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
nbtpj commited on
Commit
9b0efe0
•
1 Parent(s): b184666

Training in progress, step 15000

Browse files
Files changed (7) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +153 -3
  6. pytorch_model.bin +1 -1
  7. runs/Jan03_01-47-25_21bb7eba274c/events.out.tfevents.1672710460.21bb7eba274c.23.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57f3c69d772afc58e37ee903b2b7079a268d08467aafd7213c557e89eabc81a1
3
  size 1115513717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0abc3bbcb33f1b104a034878ea65a810881545bc5791a855d5351ca104d35090
3
  size 1115513717
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87db461c28c81d8c1f329067e24f4856e8aa966760e3915178a00b7c12a98ad9
3
  size 557969145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf5eb3b818e6cd78b758f5e03fb1f8f3add5c14dfabe0bcca7c806070d48d8f
3
  size 557969145
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c498e4129e3e140b55c067c9e46781a5ac9ad4114d9a53b3d323278fa7cab1b
3
  size 15523
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d352999c7df11b9e94f1fd8a7375a3e73dafb109da22a6956122e5dc1a4f2bf1
3
  size 15523
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9ff76b4edb8bccd8e7ba583674a071e8b77e61693d6d7c7089e776edb889d9d
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c769e63ec1de81b68aee725d82a5604ab67099a79974f6a735c0ba6a65445c
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": 0.7006726457399103,
5
- "global_step": 12500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -756,11 +756,161 @@
756
  "learning_rate": 1.1048829098156454e-05,
757
  "loss": 0.6894,
758
  "step": 12500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
759
  }
760
  ],
761
  "max_steps": 32112,
762
  "num_train_epochs": 2,
763
- "total_flos": 5.775039312666624e+16,
764
  "trial_name": null,
765
  "trial_params": null
766
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.8408071748878924,
5
+ "global_step": 15000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
756
  "learning_rate": 1.1048829098156454e-05,
757
  "loss": 0.6894,
758
  "step": 12500
759
+ },
760
+ {
761
+ "epoch": 0.71,
762
+ "learning_rate": 1.073741903338316e-05,
763
+ "loss": 0.7713,
764
+ "step": 12600
765
+ },
766
+ {
767
+ "epoch": 0.71,
768
+ "learning_rate": 1.0426008968609865e-05,
769
+ "loss": 0.6758,
770
+ "step": 12700
771
+ },
772
+ {
773
+ "epoch": 0.72,
774
+ "learning_rate": 1.0114598903836572e-05,
775
+ "loss": 0.7704,
776
+ "step": 12800
777
+ },
778
+ {
779
+ "epoch": 0.72,
780
+ "learning_rate": 9.803188839063279e-06,
781
+ "loss": 0.7496,
782
+ "step": 12900
783
+ },
784
+ {
785
+ "epoch": 0.73,
786
+ "learning_rate": 9.491778774289986e-06,
787
+ "loss": 0.7154,
788
+ "step": 13000
789
+ },
790
+ {
791
+ "epoch": 0.73,
792
+ "learning_rate": 9.180368709516691e-06,
793
+ "loss": 0.7938,
794
+ "step": 13100
795
+ },
796
+ {
797
+ "epoch": 0.74,
798
+ "learning_rate": 8.868958644743398e-06,
799
+ "loss": 0.6646,
800
+ "step": 13200
801
+ },
802
+ {
803
+ "epoch": 0.75,
804
+ "learning_rate": 8.557548579970105e-06,
805
+ "loss": 0.6602,
806
+ "step": 13300
807
+ },
808
+ {
809
+ "epoch": 0.75,
810
+ "learning_rate": 8.246138515196812e-06,
811
+ "loss": 0.7505,
812
+ "step": 13400
813
+ },
814
+ {
815
+ "epoch": 0.76,
816
+ "learning_rate": 7.934728450423517e-06,
817
+ "loss": 0.766,
818
+ "step": 13500
819
+ },
820
+ {
821
+ "epoch": 0.76,
822
+ "learning_rate": 7.6233183856502244e-06,
823
+ "loss": 0.7222,
824
+ "step": 13600
825
+ },
826
+ {
827
+ "epoch": 0.77,
828
+ "learning_rate": 7.3119083208769314e-06,
829
+ "loss": 0.7841,
830
+ "step": 13700
831
+ },
832
+ {
833
+ "epoch": 0.77,
834
+ "learning_rate": 7.0004982561036385e-06,
835
+ "loss": 0.7688,
836
+ "step": 13800
837
+ },
838
+ {
839
+ "epoch": 0.78,
840
+ "learning_rate": 6.689088191330344e-06,
841
+ "loss": 0.6692,
842
+ "step": 13900
843
+ },
844
+ {
845
+ "epoch": 0.78,
846
+ "learning_rate": 6.377678126557051e-06,
847
+ "loss": 0.7331,
848
+ "step": 14000
849
+ },
850
+ {
851
+ "epoch": 0.79,
852
+ "learning_rate": 6.066268061783757e-06,
853
+ "loss": 0.792,
854
+ "step": 14100
855
+ },
856
+ {
857
+ "epoch": 0.8,
858
+ "learning_rate": 5.754857997010463e-06,
859
+ "loss": 0.7135,
860
+ "step": 14200
861
+ },
862
+ {
863
+ "epoch": 0.8,
864
+ "learning_rate": 5.44344793223717e-06,
865
+ "loss": 0.7422,
866
+ "step": 14300
867
+ },
868
+ {
869
+ "epoch": 0.81,
870
+ "learning_rate": 5.132037867463876e-06,
871
+ "loss": 0.7497,
872
+ "step": 14400
873
+ },
874
+ {
875
+ "epoch": 0.81,
876
+ "learning_rate": 4.820627802690583e-06,
877
+ "loss": 0.7462,
878
+ "step": 14500
879
+ },
880
+ {
881
+ "epoch": 0.82,
882
+ "learning_rate": 4.5092177379172895e-06,
883
+ "loss": 0.7303,
884
+ "step": 14600
885
+ },
886
+ {
887
+ "epoch": 0.82,
888
+ "learning_rate": 4.1978076731439965e-06,
889
+ "loss": 0.7504,
890
+ "step": 14700
891
+ },
892
+ {
893
+ "epoch": 0.83,
894
+ "learning_rate": 3.886397608370703e-06,
895
+ "loss": 0.7655,
896
+ "step": 14800
897
+ },
898
+ {
899
+ "epoch": 0.84,
900
+ "learning_rate": 3.5749875435974093e-06,
901
+ "loss": 0.7503,
902
+ "step": 14900
903
+ },
904
+ {
905
+ "epoch": 0.84,
906
+ "learning_rate": 3.2635774788241163e-06,
907
+ "loss": 0.625,
908
+ "step": 15000
909
  }
910
  ],
911
  "max_steps": 32112,
912
  "num_train_epochs": 2,
913
+ "total_flos": 6.927185891598336e+16,
914
  "trial_name": null,
915
  "trial_params": null
916
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87db461c28c81d8c1f329067e24f4856e8aa966760e3915178a00b7c12a98ad9
3
  size 557969145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf5eb3b818e6cd78b758f5e03fb1f8f3add5c14dfabe0bcca7c806070d48d8f
3
  size 557969145
runs/Jan03_01-47-25_21bb7eba274c/events.out.tfevents.1672710460.21bb7eba274c.23.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eb77c9add49418cf9c6164ece1dbd00292b09e7083152c9df2cb409c236cba4
3
- size 29264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ece1914909553e95eacd390102f6cf8f09e0b33baa54894afe1eb11854cdb7
3
+ size 33189