dimasik2987 commited on
Commit
d18a3d6
·
verified ·
1 Parent(s): f4adb8e

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 sha256:1318a6af4bf5730c00d0851e18e28fcbdfb1462dd1271af87e4c39c6c99ec16c
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aaaaae8220a3280392fc0c0a626fc39efbef173acf183c9e12d71040d67bcf7
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66bb5b55b7876853e30802e4d8d471102516a754541cdf3bb1f3f030d488d908
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:605344cba474dbaeca1b86b7bbec27c59206b3dd5212bda658109e72df02e210
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6785c6f8dd654afac42891492ae5633f608cac76e9423997e5f2c062a95168e1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0631ec79f48e6df806e25edf38ffd27fdc412ba9ec78c9e9570dfd72e0fe2d83
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": 10.351698875427246,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.02767017155506364,
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": 96.014,
732
  "eval_steps_per_second": 24.035,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2816654180352.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.350841522216797,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.04150525733259546,
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": 96.014,
732
  "eval_steps_per_second": 24.035,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.027946873270614278,
737
+ "grad_norm": 0.14280512928962708,
738
+ "learning_rate": 5.231368421052631e-05,
739
+ "loss": 10.3587,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.028223574986164915,
744
+ "grad_norm": 0.11392911523580551,
745
+ "learning_rate": 5.178526315789474e-05,
746
+ "loss": 10.361,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.02850027670171555,
751
+ "grad_norm": 0.11263832449913025,
752
+ "learning_rate": 5.1256842105263165e-05,
753
+ "loss": 10.3613,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.02877697841726619,
758
+ "grad_norm": 0.13879412412643433,
759
+ "learning_rate": 5.072842105263158e-05,
760
+ "loss": 10.3606,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.029053680132816822,
765
+ "grad_norm": 0.12684401869773865,
766
+ "learning_rate": 5.02e-05,
767
+ "loss": 10.3576,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.02933038184836746,
772
+ "grad_norm": 0.11932656913995743,
773
+ "learning_rate": 4.967157894736842e-05,
774
+ "loss": 10.3547,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.029607083563918096,
779
+ "grad_norm": 0.10179711133241653,
780
+ "learning_rate": 4.914315789473684e-05,
781
+ "loss": 10.3571,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.029883785279468732,
786
+ "grad_norm": 0.12076177448034286,
787
+ "learning_rate": 4.861473684210526e-05,
788
+ "loss": 10.357,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03016048699501937,
793
+ "grad_norm": 0.07408250123262405,
794
+ "learning_rate": 4.8086315789473686e-05,
795
+ "loss": 10.3571,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.030437188710570006,
800
+ "grad_norm": 0.12372420728206635,
801
+ "learning_rate": 4.7557894736842104e-05,
802
+ "loss": 10.3543,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.030713890426120643,
807
+ "grad_norm": 0.08638908714056015,
808
+ "learning_rate": 4.702947368421053e-05,
809
+ "loss": 10.3485,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.03099059214167128,
814
+ "grad_norm": 0.12098588794469833,
815
+ "learning_rate": 4.6501052631578946e-05,
816
+ "loss": 10.3535,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.03126729385722191,
821
+ "grad_norm": 0.10554546117782593,
822
+ "learning_rate": 4.5972631578947364e-05,
823
+ "loss": 10.3475,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.03154399557277255,
828
+ "grad_norm": 0.07617288827896118,
829
+ "learning_rate": 4.544421052631579e-05,
830
+ "loss": 10.3547,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03182069728832319,
835
+ "grad_norm": 0.10432225465774536,
836
+ "learning_rate": 4.4915789473684213e-05,
837
+ "loss": 10.3502,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.032097399003873824,
842
+ "grad_norm": 0.09122877568006516,
843
+ "learning_rate": 4.438736842105263e-05,
844
+ "loss": 10.3551,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.03237410071942446,
849
+ "grad_norm": 0.09355830401182175,
850
+ "learning_rate": 4.3858947368421056e-05,
851
+ "loss": 10.3508,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0326508024349751,
856
+ "grad_norm": 0.11909081041812897,
857
+ "learning_rate": 4.3330526315789474e-05,
858
+ "loss": 10.3474,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.032927504150525734,
863
+ "grad_norm": 0.0938921570777893,
864
+ "learning_rate": 4.280210526315789e-05,
865
+ "loss": 10.3453,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.03320420586607637,
870
+ "grad_norm": 0.09045830368995667,
871
+ "learning_rate": 4.2273684210526317e-05,
872
+ "loss": 10.3474,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.03348090758162701,
877
+ "grad_norm": 0.11095123738050461,
878
+ "learning_rate": 4.174526315789474e-05,
879
+ "loss": 10.3544,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.033757609297177645,
884
+ "grad_norm": 0.08681843429803848,
885
+ "learning_rate": 4.121684210526316e-05,
886
+ "loss": 10.3565,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.03403431101272828,
891
+ "grad_norm": 0.06601341813802719,
892
+ "learning_rate": 4.068842105263158e-05,
893
+ "loss": 10.3457,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.03431101272827892,
898
+ "grad_norm": 0.08264271169900894,
899
+ "learning_rate": 4.016e-05,
900
+ "loss": 10.3572,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.034587714443829555,
905
+ "grad_norm": 0.06502602994441986,
906
+ "learning_rate": 3.963157894736842e-05,
907
+ "loss": 10.3484,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.034864416159380185,
912
+ "grad_norm": 0.08391563594341278,
913
+ "learning_rate": 3.9103157894736844e-05,
914
+ "loss": 10.3514,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.03514111787493082,
919
+ "grad_norm": 0.08374013006687164,
920
+ "learning_rate": 3.857473684210526e-05,
921
+ "loss": 10.3485,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.03541781959048146,
926
+ "grad_norm": 0.09567815065383911,
927
+ "learning_rate": 3.804631578947369e-05,
928
+ "loss": 10.3476,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.035694521306032095,
933
+ "grad_norm": 0.09184671938419342,
934
+ "learning_rate": 3.7517894736842105e-05,
935
+ "loss": 10.3477,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.03597122302158273,
940
+ "grad_norm": 0.09309260547161102,
941
+ "learning_rate": 3.698947368421052e-05,
942
+ "loss": 10.3535,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.03624792473713337,
947
+ "grad_norm": 0.11253216862678528,
948
+ "learning_rate": 3.646105263157895e-05,
949
+ "loss": 10.3553,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.036524626452684006,
954
+ "grad_norm": 0.07496535778045654,
955
+ "learning_rate": 3.593263157894737e-05,
956
+ "loss": 10.3417,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.03680132816823464,
961
+ "grad_norm": 0.11139296740293503,
962
+ "learning_rate": 3.540421052631579e-05,
963
+ "loss": 10.3447,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.03707802988378528,
968
+ "grad_norm": 0.10377196967601776,
969
+ "learning_rate": 3.4875789473684215e-05,
970
+ "loss": 10.3484,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.037354731599335916,
975
+ "grad_norm": 0.09641505777835846,
976
+ "learning_rate": 3.434736842105263e-05,
977
+ "loss": 10.3467,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.03763143331488655,
982
+ "grad_norm": 0.1256895661354065,
983
+ "learning_rate": 3.381894736842105e-05,
984
+ "loss": 10.3542,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.03790813503043719,
989
+ "grad_norm": 0.10770992189645767,
990
+ "learning_rate": 3.329052631578947e-05,
991
+ "loss": 10.3487,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.03818483674598783,
996
+ "grad_norm": 0.11906769126653671,
997
+ "learning_rate": 3.27621052631579e-05,
998
+ "loss": 10.3482,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.038461538461538464,
1003
+ "grad_norm": 0.1397065669298172,
1004
+ "learning_rate": 3.223368421052632e-05,
1005
+ "loss": 10.353,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0387382401770891,
1010
+ "grad_norm": 0.10772430896759033,
1011
+ "learning_rate": 3.1705263157894736e-05,
1012
+ "loss": 10.3423,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.03901494189263974,
1017
+ "grad_norm": 0.10745060443878174,
1018
+ "learning_rate": 3.117684210526316e-05,
1019
+ "loss": 10.351,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.039291643608190374,
1024
+ "grad_norm": 0.09514959156513214,
1025
+ "learning_rate": 3.064842105263158e-05,
1026
+ "loss": 10.3492,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.039568345323741004,
1031
+ "grad_norm": 0.16483455896377563,
1032
+ "learning_rate": 3.012e-05,
1033
+ "loss": 10.3444,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.03984504703929164,
1038
+ "grad_norm": 0.14660082757472992,
1039
+ "learning_rate": 2.9591578947368418e-05,
1040
+ "loss": 10.3414,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.04012174875484228,
1045
+ "grad_norm": 0.14518006145954132,
1046
+ "learning_rate": 2.9063157894736842e-05,
1047
+ "loss": 10.3534,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.040398450470392915,
1052
+ "grad_norm": 0.11700974404811859,
1053
+ "learning_rate": 2.8534736842105264e-05,
1054
+ "loss": 10.3541,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04067515218594355,
1059
+ "grad_norm": 0.1969076544046402,
1060
+ "learning_rate": 2.800631578947368e-05,
1061
+ "loss": 10.3477,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.04095185390149419,
1066
+ "grad_norm": 0.18599028885364532,
1067
+ "learning_rate": 2.7477894736842106e-05,
1068
+ "loss": 10.3502,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.041228555617044825,
1073
+ "grad_norm": 0.12765298783779144,
1074
+ "learning_rate": 2.6949473684210527e-05,
1075
+ "loss": 10.3463,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.04150525733259546,
1080
+ "grad_norm": 0.22577303647994995,
1081
+ "learning_rate": 2.6421052631578945e-05,
1082
+ "loss": 10.3555,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.04150525733259546,
1087
+ "eval_loss": 10.350841522216797,
1088
+ "eval_runtime": 15.8399,
1089
+ "eval_samples_per_second": 96.087,
1090
+ "eval_steps_per_second": 24.053,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4211037437952.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null