lesso commited on
Commit
412afe5
·
verified ·
1 Parent(s): 7233fe0

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:d42845b973e3bc777a0f91e7fe884feb4b5a5edd26cfd76d29e8f3e8422347dc
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1b15eeb9008c5660904719b6cc164554489c49294e9ecfcb63bcecc62e13d58
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:751c945561f05e67d2142d6f02fcd382f083d1f9f2159734c4e79e52c8c23edc
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0acd1b9fa201c5bbba696e9b8359bfbbc319c48843f6befcc058c7a95b162f57
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3797af55a6eed419a4b2aa8d35de323588273066825713c5ac4a73961dca2bd9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e50a795028321794c6ddcc60f95cfd10f06c51e97fdeed5b5513e6731d843390
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c16c2a0a7f4d1c317518a0a40a7c58dbcf9237e9297de7a3c67a0a8ebfbe5ded
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c5525f1d8420ca8a81a7fd2ec397a508131d03210dfd36c7ac5758b0e6313b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.0185234546661377,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.00928203462198914,
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": 21.394,
732
  "eval_steps_per_second": 5.352,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7347907728506880.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.0085387229919434,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.01392305193298371,
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": 21.394,
732
  "eval_steps_per_second": 5.352,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.009374854968209032,
737
+ "grad_norm": 0.4157350957393646,
738
+ "learning_rate": 5.231368421052631e-05,
739
+ "loss": 1.9556,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.009467675314428922,
744
+ "grad_norm": 0.433269739151001,
745
+ "learning_rate": 5.178526315789474e-05,
746
+ "loss": 1.7989,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.009560495660648814,
751
+ "grad_norm": 0.43151503801345825,
752
+ "learning_rate": 5.1256842105263165e-05,
753
+ "loss": 1.8229,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.009653316006868706,
758
+ "grad_norm": 0.44042569398880005,
759
+ "learning_rate": 5.072842105263158e-05,
760
+ "loss": 1.7344,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.009746136353088597,
765
+ "grad_norm": 0.4146162271499634,
766
+ "learning_rate": 5.02e-05,
767
+ "loss": 1.9032,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.009838956699308489,
772
+ "grad_norm": 0.4360559582710266,
773
+ "learning_rate": 4.967157894736842e-05,
774
+ "loss": 2.0677,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.00993177704552838,
779
+ "grad_norm": 0.4013524651527405,
780
+ "learning_rate": 4.914315789473684e-05,
781
+ "loss": 1.9427,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01002459739174827,
786
+ "grad_norm": 0.44252482056617737,
787
+ "learning_rate": 4.861473684210526e-05,
788
+ "loss": 1.9804,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.010117417737968162,
793
+ "grad_norm": 0.41882866621017456,
794
+ "learning_rate": 4.8086315789473686e-05,
795
+ "loss": 1.799,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.010210238084188054,
800
+ "grad_norm": 0.43453121185302734,
801
+ "learning_rate": 4.7557894736842104e-05,
802
+ "loss": 2.0016,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.010303058430407946,
807
+ "grad_norm": 0.49610668420791626,
808
+ "learning_rate": 4.702947368421053e-05,
809
+ "loss": 2.0242,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.010395878776627837,
814
+ "grad_norm": 0.42180904746055603,
815
+ "learning_rate": 4.6501052631578946e-05,
816
+ "loss": 1.8779,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.010488699122847727,
821
+ "grad_norm": 0.4709084928035736,
822
+ "learning_rate": 4.5972631578947364e-05,
823
+ "loss": 1.8693,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.010581519469067619,
828
+ "grad_norm": 0.4451385736465454,
829
+ "learning_rate": 4.544421052631579e-05,
830
+ "loss": 1.8203,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.01067433981528751,
835
+ "grad_norm": 0.4565402865409851,
836
+ "learning_rate": 4.4915789473684213e-05,
837
+ "loss": 1.897,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.010767160161507403,
842
+ "grad_norm": 0.4602057635784149,
843
+ "learning_rate": 4.438736842105263e-05,
844
+ "loss": 1.9684,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.010859980507727294,
849
+ "grad_norm": 0.4286463260650635,
850
+ "learning_rate": 4.3858947368421056e-05,
851
+ "loss": 1.8134,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.010952800853947186,
856
+ "grad_norm": 0.4532035291194916,
857
+ "learning_rate": 4.3330526315789474e-05,
858
+ "loss": 1.9204,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.011045621200167076,
863
+ "grad_norm": 0.49677908420562744,
864
+ "learning_rate": 4.280210526315789e-05,
865
+ "loss": 2.0517,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.011138441546386968,
870
+ "grad_norm": 0.4839816391468048,
871
+ "learning_rate": 4.2273684210526317e-05,
872
+ "loss": 2.0162,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.01123126189260686,
877
+ "grad_norm": 0.4714973568916321,
878
+ "learning_rate": 4.174526315789474e-05,
879
+ "loss": 1.9792,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.011324082238826751,
884
+ "grad_norm": 0.48217833042144775,
885
+ "learning_rate": 4.121684210526316e-05,
886
+ "loss": 2.1381,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.011416902585046643,
891
+ "grad_norm": 0.45825913548469543,
892
+ "learning_rate": 4.068842105263158e-05,
893
+ "loss": 1.9006,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.011509722931266534,
898
+ "grad_norm": 0.5154534578323364,
899
+ "learning_rate": 4.016e-05,
900
+ "loss": 2.0451,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.011602543277486424,
905
+ "grad_norm": 0.49753981828689575,
906
+ "learning_rate": 3.963157894736842e-05,
907
+ "loss": 1.9921,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.011695363623706316,
912
+ "grad_norm": 0.48420360684394836,
913
+ "learning_rate": 3.9103157894736844e-05,
914
+ "loss": 1.8454,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.011788183969926208,
919
+ "grad_norm": 0.5063680410385132,
920
+ "learning_rate": 3.857473684210526e-05,
921
+ "loss": 1.8294,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0118810043161461,
926
+ "grad_norm": 0.4992259740829468,
927
+ "learning_rate": 3.804631578947369e-05,
928
+ "loss": 1.9348,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.011973824662365991,
933
+ "grad_norm": 0.508219301700592,
934
+ "learning_rate": 3.7517894736842105e-05,
935
+ "loss": 2.0251,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.012066645008585883,
940
+ "grad_norm": 0.4896531105041504,
941
+ "learning_rate": 3.698947368421052e-05,
942
+ "loss": 1.7667,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.012159465354805773,
947
+ "grad_norm": 0.5085623264312744,
948
+ "learning_rate": 3.646105263157895e-05,
949
+ "loss": 1.8525,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.012252285701025665,
954
+ "grad_norm": 0.49702784419059753,
955
+ "learning_rate": 3.593263157894737e-05,
956
+ "loss": 1.9041,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.012345106047245556,
961
+ "grad_norm": 0.5175393223762512,
962
+ "learning_rate": 3.540421052631579e-05,
963
+ "loss": 2.1606,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.012437926393465448,
968
+ "grad_norm": 0.5096806287765503,
969
+ "learning_rate": 3.4875789473684215e-05,
970
+ "loss": 1.8375,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.01253074673968534,
975
+ "grad_norm": 0.5583460927009583,
976
+ "learning_rate": 3.434736842105263e-05,
977
+ "loss": 2.2475,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.01262356708590523,
982
+ "grad_norm": 0.5094785690307617,
983
+ "learning_rate": 3.381894736842105e-05,
984
+ "loss": 2.019,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.012716387432125121,
989
+ "grad_norm": 0.554124116897583,
990
+ "learning_rate": 3.329052631578947e-05,
991
+ "loss": 2.0397,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.012809207778345013,
996
+ "grad_norm": 0.5521702170372009,
997
+ "learning_rate": 3.27621052631579e-05,
998
+ "loss": 2.067,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.012902028124564905,
1003
+ "grad_norm": 0.5431244373321533,
1004
+ "learning_rate": 3.223368421052632e-05,
1005
+ "loss": 1.9676,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.012994848470784796,
1010
+ "grad_norm": 0.5575247406959534,
1011
+ "learning_rate": 3.1705263157894736e-05,
1012
+ "loss": 1.7978,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.013087668817004688,
1017
+ "grad_norm": 0.5787823796272278,
1018
+ "learning_rate": 3.117684210526316e-05,
1019
+ "loss": 2.1306,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.013180489163224578,
1024
+ "grad_norm": 0.5557217001914978,
1025
+ "learning_rate": 3.064842105263158e-05,
1026
+ "loss": 2.0982,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.01327330950944447,
1031
+ "grad_norm": 0.5702773928642273,
1032
+ "learning_rate": 3.012e-05,
1033
+ "loss": 1.9572,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.013366129855664361,
1038
+ "grad_norm": 0.5814855098724365,
1039
+ "learning_rate": 2.9591578947368418e-05,
1040
+ "loss": 1.9171,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.013458950201884253,
1045
+ "grad_norm": 0.5961145162582397,
1046
+ "learning_rate": 2.9063157894736842e-05,
1047
+ "loss": 2.06,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.013551770548104145,
1052
+ "grad_norm": 0.5634588599205017,
1053
+ "learning_rate": 2.8534736842105264e-05,
1054
+ "loss": 2.0661,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.013644590894324037,
1059
+ "grad_norm": 0.6884035468101501,
1060
+ "learning_rate": 2.800631578947368e-05,
1061
+ "loss": 1.9846,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.013737411240543927,
1066
+ "grad_norm": 0.592460572719574,
1067
+ "learning_rate": 2.7477894736842106e-05,
1068
+ "loss": 2.0338,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.013830231586763818,
1073
+ "grad_norm": 0.598613440990448,
1074
+ "learning_rate": 2.6949473684210527e-05,
1075
+ "loss": 2.1441,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.01392305193298371,
1080
+ "grad_norm": 0.6344769597053528,
1081
+ "learning_rate": 2.6421052631578945e-05,
1082
+ "loss": 2.3666,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.01392305193298371,
1087
+ "eval_loss": 2.0085387229919434,
1088
+ "eval_runtime": 211.7337,
1089
+ "eval_samples_per_second": 21.428,
1090
+ "eval_steps_per_second": 5.361,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.098784350142464e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null