mgh6 commited on
Commit
928e516
·
verified ·
1 Parent(s): d898a23

Training in progress, epoch 8, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dce8f8856c2efd7382f9b9e2a4fe12b00b61d44949107efc024e135276f2fdc8
3
  size 2682482800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fa54ae6d93b451b3c85c60bcc56e3f542ab09161361776be1f6d5ed8cb76f52
3
  size 2682482800
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfe16b2a0f33c549a3839a37a89e9b93abb4765a7bb87dd5f882f4dfdeda22d5
3
  size 5365108834
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343f67167732c6fba15c09f7c71b27c158c7e96c4f045eaddb7ce1c27807c442
3
  size 5365108834
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f718e7dd3b9cb87c504ffc48bd13d55cc2f00494fff18a58a23c22fe7ad76678
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec16129fc8d2cf204ebb4162f7c55b6461e2bc960e5ef5956a64a5423153fa08
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b03d3d28e89d9fd412a9ce650e3cd74ba4b669fb777294ec0d1b0d38b84c701
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac438770b97bad43b2cf9510520bf93f55aedbcb9fc1040f7825a22cffd7396
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 7.997999636297509,
5
  "eval_steps": 50,
6
- "global_step": 2744,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -817,6 +817,111 @@
817
  "eval_samples_per_second": 41.411,
818
  "eval_steps_per_second": 20.706,
819
  "step": 2700
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
820
  }
821
  ],
822
  "logging_steps": 50,
@@ -836,7 +941,7 @@
836
  "attributes": {}
837
  }
838
  },
839
- "total_flos": 7.148087838884495e+17,
840
  "train_batch_size": 2,
841
  "trial_name": null,
842
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 8.997999636297509,
5
  "eval_steps": 50,
6
+ "global_step": 3087,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
817
  "eval_samples_per_second": 41.411,
818
  "eval_steps_per_second": 20.706,
819
  "step": 2700
820
+ },
821
+ {
822
+ "epoch": 8.01745771958538,
823
+ "grad_norm": 81.85997009277344,
824
+ "learning_rate": 5.991253644314869e-05,
825
+ "loss": 0.8295,
826
+ "step": 2750
827
+ },
828
+ {
829
+ "epoch": 8.01745771958538,
830
+ "eval_loss": 0.7912312746047974,
831
+ "eval_runtime": 117.8188,
832
+ "eval_samples_per_second": 40.961,
833
+ "eval_steps_per_second": 20.481,
834
+ "step": 2750
835
+ },
836
+ {
837
+ "epoch": 8.162938716130206,
838
+ "grad_norm": 87.41828918457031,
839
+ "learning_rate": 5.918367346938776e-05,
840
+ "loss": 0.8146,
841
+ "step": 2800
842
+ },
843
+ {
844
+ "epoch": 8.162938716130206,
845
+ "eval_loss": 0.7906960248947144,
846
+ "eval_runtime": 116.6653,
847
+ "eval_samples_per_second": 41.366,
848
+ "eval_steps_per_second": 20.683,
849
+ "step": 2800
850
+ },
851
+ {
852
+ "epoch": 8.308419712675033,
853
+ "grad_norm": 50.575706481933594,
854
+ "learning_rate": 5.845481049562682e-05,
855
+ "loss": 0.8104,
856
+ "step": 2850
857
+ },
858
+ {
859
+ "epoch": 8.308419712675033,
860
+ "eval_loss": 0.7849209308624268,
861
+ "eval_runtime": 116.6593,
862
+ "eval_samples_per_second": 41.368,
863
+ "eval_steps_per_second": 20.684,
864
+ "step": 2850
865
+ },
866
+ {
867
+ "epoch": 8.453900709219859,
868
+ "grad_norm": 55.96903991699219,
869
+ "learning_rate": 5.77259475218659e-05,
870
+ "loss": 0.8135,
871
+ "step": 2900
872
+ },
873
+ {
874
+ "epoch": 8.453900709219859,
875
+ "eval_loss": 0.7816675305366516,
876
+ "eval_runtime": 116.6099,
877
+ "eval_samples_per_second": 41.386,
878
+ "eval_steps_per_second": 20.693,
879
+ "step": 2900
880
+ },
881
+ {
882
+ "epoch": 8.599381705764685,
883
+ "grad_norm": 46.01133346557617,
884
+ "learning_rate": 5.6997084548104964e-05,
885
+ "loss": 0.8061,
886
+ "step": 2950
887
+ },
888
+ {
889
+ "epoch": 8.599381705764685,
890
+ "eval_loss": 0.7791692614555359,
891
+ "eval_runtime": 116.4849,
892
+ "eval_samples_per_second": 41.43,
893
+ "eval_steps_per_second": 20.715,
894
+ "step": 2950
895
+ },
896
+ {
897
+ "epoch": 8.744862702309511,
898
+ "grad_norm": 57.846012115478516,
899
+ "learning_rate": 5.626822157434403e-05,
900
+ "loss": 0.8114,
901
+ "step": 3000
902
+ },
903
+ {
904
+ "epoch": 8.744862702309511,
905
+ "eval_loss": 0.77262282371521,
906
+ "eval_runtime": 116.493,
907
+ "eval_samples_per_second": 41.427,
908
+ "eval_steps_per_second": 20.714,
909
+ "step": 3000
910
+ },
911
+ {
912
+ "epoch": 8.890343698854338,
913
+ "grad_norm": 86.41826629638672,
914
+ "learning_rate": 5.553935860058309e-05,
915
+ "loss": 0.8061,
916
+ "step": 3050
917
+ },
918
+ {
919
+ "epoch": 8.890343698854338,
920
+ "eval_loss": 0.7756626605987549,
921
+ "eval_runtime": 116.3032,
922
+ "eval_samples_per_second": 41.495,
923
+ "eval_steps_per_second": 20.747,
924
+ "step": 3050
925
  }
926
  ],
927
  "logging_steps": 50,
 
941
  "attributes": {}
942
  }
943
  },
944
+ "total_flos": 8.041105657220301e+17,
945
  "train_batch_size": 2,
946
  "trial_name": null,
947
  "trial_params": null