aleegis11 commited on
Commit
b7bcbd1
·
verified ·
1 Parent(s): 3f69f9b

Training in progress, step 150, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4042e3460985a3074316cb4df206a116ae72905539038a60e6c7081f1ad1eb5
3
  size 100690184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2bcb9b81aad1cc5d4809e55d9aef7c4477fb7e266c1516f8872a8d13e70ba19
3
  size 100690184
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9262d7f534044d64a2ca897fe0b3373be4b46e12331fc6748fe11b0b99e566c
3
  size 51344890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e6feb1e86468980e76ffea6b17496f4fba7a32176a8fc8727346b1c8d43fc0e
3
  size 51344890
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:732f21cca8d6a0fc9c9923a9be0e148b953b1aa91784505e297eceb18abe5e62
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c6f3402711fe7a88fa41227a9218076efd51c1be70a7f47947f361e9b767b0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.400832861661911,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.095890410958904,
5
  "eval_steps": 50,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -731,6 +731,364 @@
731
  "eval_samples_per_second": 79.357,
732
  "eval_steps_per_second": 20.097,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7830764381011968.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.37483757734298706,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.643835616438356,
5
  "eval_steps": 50,
6
+ "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
731
  "eval_samples_per_second": 79.357,
732
  "eval_steps_per_second": 20.097,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.106849315068493,
737
+ "grad_norm": 28.613204956054688,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.3003,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.1178082191780823,
744
+ "grad_norm": 28.404552459716797,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.3235,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.1287671232876713,
751
+ "grad_norm": 31.971712112426758,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.5493,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.1397260273972603,
758
+ "grad_norm": 31.164323806762695,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.3944,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.1506849315068493,
765
+ "grad_norm": 27.70460319519043,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.2497,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.1616438356164385,
772
+ "grad_norm": 42.503597259521484,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.1932,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.1726027397260275,
779
+ "grad_norm": 27.519493103027344,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.3152,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.1835616438356165,
786
+ "grad_norm": 30.81327247619629,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.7175,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.1945205479452055,
793
+ "grad_norm": 36.185123443603516,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.9324,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.2054794520547945,
800
+ "grad_norm": 30.46416473388672,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.2068,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.2164383561643834,
807
+ "grad_norm": 22.46263885498047,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.1815,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.2273972602739727,
814
+ "grad_norm": 20.89829444885254,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.2924,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.2383561643835617,
821
+ "grad_norm": 43.927669525146484,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.9196,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.2493150684931507,
828
+ "grad_norm": 55.13964080810547,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.5384,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.2602739726027397,
835
+ "grad_norm": 71.3852310180664,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.8759,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.2712328767123289,
842
+ "grad_norm": 20.873424530029297,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.2816,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.2821917808219179,
849
+ "grad_norm": 30.306793212890625,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.3711,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.2931506849315069,
856
+ "grad_norm": 27.79682159423828,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.426,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.3041095890410959,
863
+ "grad_norm": 49.33466339111328,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.464,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.3150684931506849,
870
+ "grad_norm": 35.36948013305664,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.618,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.3260273972602739,
877
+ "grad_norm": 38.644927978515625,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.3514,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.336986301369863,
884
+ "grad_norm": 29.98199462890625,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.3034,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.347945205479452,
891
+ "grad_norm": 39.6750602722168,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.3634,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.358904109589041,
898
+ "grad_norm": 46.256343841552734,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.5002,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.36986301369863,
905
+ "grad_norm": 32.30176544189453,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.4205,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.3808219178082193,
912
+ "grad_norm": 32.818485260009766,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.2477,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.3917808219178083,
919
+ "grad_norm": 45.166534423828125,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.4078,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.4027397260273973,
926
+ "grad_norm": 32.647891998291016,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.2282,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.4136986301369863,
933
+ "grad_norm": 40.9683837890625,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.2926,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.4246575342465753,
940
+ "grad_norm": 51.406612396240234,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.9739,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.4356164383561643,
947
+ "grad_norm": 45.16895294189453,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.6762,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.4465753424657535,
954
+ "grad_norm": 44.308189392089844,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.3818,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.4575342465753425,
961
+ "grad_norm": 35.05088424682617,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.1228,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.4684931506849315,
968
+ "grad_norm": 40.73629379272461,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.2048,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.4794520547945205,
975
+ "grad_norm": 77.88436889648438,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.837,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.4904109589041097,
982
+ "grad_norm": 125.36991882324219,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.7284,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.5013698630136987,
989
+ "grad_norm": 57.473472595214844,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.4545,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.5123287671232877,
996
+ "grad_norm": 48.656131744384766,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.3017,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.5232876712328767,
1003
+ "grad_norm": 45.12188720703125,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.4474,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.5342465753424657,
1010
+ "grad_norm": 69.8457260131836,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.3396,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.5452054794520547,
1017
+ "grad_norm": 53.79582977294922,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.5312,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.5561643835616439,
1024
+ "grad_norm": 151.50416564941406,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.7986,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.5671232876712329,
1031
+ "grad_norm": 49.776119232177734,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.1307,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.5780821917808219,
1038
+ "grad_norm": 46.405677795410156,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.4035,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.589041095890411,
1045
+ "grad_norm": 55.024227142333984,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.2362,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.6,
1052
+ "grad_norm": 54.06251907348633,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.1771,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.610958904109589,
1059
+ "grad_norm": 69.43602752685547,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.627,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.621917808219178,
1066
+ "grad_norm": 47.403690338134766,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.161,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.632876712328767,
1073
+ "grad_norm": 63.99250030517578,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.3082,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.643835616438356,
1080
+ "grad_norm": 64.2621078491211,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.3423,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.643835616438356,
1087
+ "eval_loss": 0.37483757734298706,
1088
+ "eval_runtime": 1.9385,
1089
+ "eval_samples_per_second": 79.444,
1090
+ "eval_steps_per_second": 20.119,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.1686769678352384e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null