dimasik2987 commited on
Commit
e9cab05
·
verified ·
1 Parent(s): 2b91c2d

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 sha256:149f6ec4c2145ed791ada448402a9604046ac1d15b90795d22e553a3d0ac547c
3
  size 239906848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40acdc2ab7ed7138cec4a9cff67727263e134e80441d057bfd384a24838fe0e5
3
  size 239906848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc6ab624d2cb3d757e8bb28f5137f8dc13c3e2db7f16ed9b46719a3bc82931a4
3
  size 122200212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f5b84252a56b504400ff97c31b8090e18a50b83252e0e8c8c3fa5c4c69858ec
3
  size 122200212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e28b8a8412b4ac30b72dc5f43b77bee4c83c89982038652139b7c9e2905be9a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b689923bec1cdfe01581a72892b696bd2913a146f9f41ed70deea83fbaa578c0
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": 0.04449079558253288,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.07524454477050414,
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": 24.901,
732
  "eval_steps_per_second": 6.225,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6849070261862400.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.02783067524433136,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.11286681715575621,
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": 24.901,
732
  "eval_steps_per_second": 6.225,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.07599699021820917,
737
+ "grad_norm": 3.5583584308624268,
738
+ "learning_rate": 5.231368421052631e-05,
739
+ "loss": 1.4636,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.07674943566591422,
744
+ "grad_norm": 0.1338910460472107,
745
+ "learning_rate": 5.178526315789474e-05,
746
+ "loss": 0.0514,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.07750188111361926,
751
+ "grad_norm": 0.21548093855381012,
752
+ "learning_rate": 5.1256842105263165e-05,
753
+ "loss": 0.0055,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0782543265613243,
758
+ "grad_norm": 0.2258404642343521,
759
+ "learning_rate": 5.072842105263158e-05,
760
+ "loss": 0.0067,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.07900677200902935,
765
+ "grad_norm": 0.3479577898979187,
766
+ "learning_rate": 5.02e-05,
767
+ "loss": 0.0025,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0797592174567344,
772
+ "grad_norm": 0.13383802771568298,
773
+ "learning_rate": 4.967157894736842e-05,
774
+ "loss": 0.0074,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.08051166290443942,
779
+ "grad_norm": 0.11670215427875519,
780
+ "learning_rate": 4.914315789473684e-05,
781
+ "loss": 0.0026,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08126410835214447,
786
+ "grad_norm": 0.32123813033103943,
787
+ "learning_rate": 4.861473684210526e-05,
788
+ "loss": 0.0095,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.08201655379984951,
793
+ "grad_norm": 0.05738672614097595,
794
+ "learning_rate": 4.8086315789473686e-05,
795
+ "loss": 0.001,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08276899924755456,
800
+ "grad_norm": 0.05406120792031288,
801
+ "learning_rate": 4.7557894736842104e-05,
802
+ "loss": 0.0016,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0835214446952596,
807
+ "grad_norm": 0.02784488908946514,
808
+ "learning_rate": 4.702947368421053e-05,
809
+ "loss": 0.0016,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.08427389014296463,
814
+ "grad_norm": 0.03466448560357094,
815
+ "learning_rate": 4.6501052631578946e-05,
816
+ "loss": 0.0017,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.08502633559066967,
821
+ "grad_norm": 0.03824542835354805,
822
+ "learning_rate": 4.5972631578947364e-05,
823
+ "loss": 0.0021,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.08577878103837472,
828
+ "grad_norm": 0.15851886570453644,
829
+ "learning_rate": 4.544421052631579e-05,
830
+ "loss": 0.0043,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.08653122648607976,
835
+ "grad_norm": 0.025240371003746986,
836
+ "learning_rate": 4.4915789473684213e-05,
837
+ "loss": 0.0009,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.0872836719337848,
842
+ "grad_norm": 0.019472820684313774,
843
+ "learning_rate": 4.438736842105263e-05,
844
+ "loss": 0.0009,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.08803611738148984,
849
+ "grad_norm": 0.48911502957344055,
850
+ "learning_rate": 4.3858947368421056e-05,
851
+ "loss": 0.0037,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.08878856282919488,
856
+ "grad_norm": 0.1643715500831604,
857
+ "learning_rate": 4.3330526315789474e-05,
858
+ "loss": 0.0056,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.08954100827689992,
863
+ "grad_norm": 0.19596649706363678,
864
+ "learning_rate": 4.280210526315789e-05,
865
+ "loss": 0.0065,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.09029345372460497,
870
+ "grad_norm": 1.3377373218536377,
871
+ "learning_rate": 4.2273684210526317e-05,
872
+ "loss": 0.0621,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.09104589917231001,
877
+ "grad_norm": 0.505384087562561,
878
+ "learning_rate": 4.174526315789474e-05,
879
+ "loss": 0.0104,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.09179834462001504,
884
+ "grad_norm": 0.0544271357357502,
885
+ "learning_rate": 4.121684210526316e-05,
886
+ "loss": 0.0023,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.09255079006772009,
891
+ "grad_norm": 0.16811607778072357,
892
+ "learning_rate": 4.068842105263158e-05,
893
+ "loss": 0.0163,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.09330323551542513,
898
+ "grad_norm": 0.019329270347952843,
899
+ "learning_rate": 4.016e-05,
900
+ "loss": 0.0008,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.09405568096313018,
905
+ "grad_norm": 0.05329417437314987,
906
+ "learning_rate": 3.963157894736842e-05,
907
+ "loss": 0.0027,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.09480812641083522,
912
+ "grad_norm": 0.08204272389411926,
913
+ "learning_rate": 3.9103157894736844e-05,
914
+ "loss": 0.0029,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.09556057185854025,
919
+ "grad_norm": 0.06737394630908966,
920
+ "learning_rate": 3.857473684210526e-05,
921
+ "loss": 0.0014,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0963130173062453,
926
+ "grad_norm": 0.20691591501235962,
927
+ "learning_rate": 3.804631578947369e-05,
928
+ "loss": 0.0039,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.09706546275395034,
933
+ "grad_norm": 0.010593212209641933,
934
+ "learning_rate": 3.7517894736842105e-05,
935
+ "loss": 0.0007,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.09781790820165538,
940
+ "grad_norm": 0.025148313492536545,
941
+ "learning_rate": 3.698947368421052e-05,
942
+ "loss": 0.0014,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.09857035364936043,
947
+ "grad_norm": 0.1723494529724121,
948
+ "learning_rate": 3.646105263157895e-05,
949
+ "loss": 0.0043,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.09932279909706546,
954
+ "grad_norm": 0.01964077726006508,
955
+ "learning_rate": 3.593263157894737e-05,
956
+ "loss": 0.001,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.1000752445447705,
961
+ "grad_norm": 0.2998151481151581,
962
+ "learning_rate": 3.540421052631579e-05,
963
+ "loss": 0.0105,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.10082768999247554,
968
+ "grad_norm": 0.1715938299894333,
969
+ "learning_rate": 3.4875789473684215e-05,
970
+ "loss": 0.0035,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.10158013544018059,
975
+ "grad_norm": 0.028639964759349823,
976
+ "learning_rate": 3.434736842105263e-05,
977
+ "loss": 0.0015,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.10233258088788563,
982
+ "grad_norm": 0.13613921403884888,
983
+ "learning_rate": 3.381894736842105e-05,
984
+ "loss": 0.0029,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.10308502633559068,
989
+ "grad_norm": 0.03546198457479477,
990
+ "learning_rate": 3.329052631578947e-05,
991
+ "loss": 0.0016,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1038374717832957,
996
+ "grad_norm": 0.4500066936016083,
997
+ "learning_rate": 3.27621052631579e-05,
998
+ "loss": 0.0062,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.10458991723100075,
1003
+ "grad_norm": 0.13641779124736786,
1004
+ "learning_rate": 3.223368421052632e-05,
1005
+ "loss": 0.0022,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.1053423626787058,
1010
+ "grad_norm": 0.24456901848316193,
1011
+ "learning_rate": 3.1705263157894736e-05,
1012
+ "loss": 0.0047,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.10609480812641084,
1017
+ "grad_norm": 0.6857782006263733,
1018
+ "learning_rate": 3.117684210526316e-05,
1019
+ "loss": 0.0237,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.10684725357411588,
1024
+ "grad_norm": 0.017228834331035614,
1025
+ "learning_rate": 3.064842105263158e-05,
1026
+ "loss": 0.001,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.10759969902182091,
1031
+ "grad_norm": 0.8723503351211548,
1032
+ "learning_rate": 3.012e-05,
1033
+ "loss": 0.0409,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.10835214446952596,
1038
+ "grad_norm": 0.1626891791820526,
1039
+ "learning_rate": 2.9591578947368418e-05,
1040
+ "loss": 0.0035,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.109104589917231,
1045
+ "grad_norm": 0.020657368004322052,
1046
+ "learning_rate": 2.9063157894736842e-05,
1047
+ "loss": 0.0009,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.10985703536493605,
1052
+ "grad_norm": 0.12785644829273224,
1053
+ "learning_rate": 2.8534736842105264e-05,
1054
+ "loss": 0.0024,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.11060948081264109,
1059
+ "grad_norm": 0.13075271248817444,
1060
+ "learning_rate": 2.800631578947368e-05,
1061
+ "loss": 0.0028,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.11136192626034612,
1066
+ "grad_norm": 0.02945193648338318,
1067
+ "learning_rate": 2.7477894736842106e-05,
1068
+ "loss": 0.0015,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.11211437170805116,
1073
+ "grad_norm": 0.6050726175308228,
1074
+ "learning_rate": 2.6949473684210527e-05,
1075
+ "loss": 0.0216,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.11286681715575621,
1080
+ "grad_norm": 2.671539068222046,
1081
+ "learning_rate": 2.6421052631578945e-05,
1082
+ "loss": 0.0604,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.11286681715575621,
1087
+ "eval_loss": 0.02783067524433136,
1088
+ "eval_runtime": 22.4241,
1089
+ "eval_samples_per_second": 24.973,
1090
+ "eval_steps_per_second": 6.243,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.03394618376192e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null