prxy5605 commited on
Commit
4fa89f7
·
verified ·
1 Parent(s): 66e9d37

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:ac0a7fadeb0f3379f61ba746f75d25a0b31318d0ee8f0c4e474ca91e0286a97e
3
  size 479005064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b2738e9f769086c469fde7d9d1900059bbca4da7384eaee404d033fb274f5f1
3
  size 479005064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2b19bed96bf6518f321a7122e23fdb4c38f85684f97de466817d804e9921469
3
  size 958299770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f930074a8146a7814acdfaafc313b635d4170e046bbc71195275e79dd59e1a5d
3
  size 958299770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4e66a99f91deafedac948a09ccddeb307849c64d78a9bf2bf4b108fe1c2fd85
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69adc1b8f4e534a62df26c83fcefb9fc51905f0dacc6be9dcba4f47c2685cee3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7844517230987549,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.11672016340822877,
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": 10.97,
732
  "eval_steps_per_second": 5.489,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.06703144091648e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7759228944778442,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.17508024511234316,
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": 10.97,
732
  "eval_steps_per_second": 5.489,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.11788736504231107,
737
+ "grad_norm": 0.27881744503974915,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 0.9024,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.11905456667639334,
744
+ "grad_norm": 0.2848488688468933,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 0.8755,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.12022176831047564,
751
+ "grad_norm": 0.2713146507740021,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 0.8695,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.12138896994455792,
758
+ "grad_norm": 0.25380441546440125,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 0.8603,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.12255617157864021,
765
+ "grad_norm": 0.2523921728134155,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 0.766,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1237233732127225,
772
+ "grad_norm": 0.23555214703083038,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 0.8138,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.12489057484680478,
779
+ "grad_norm": 0.2412918657064438,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 0.9006,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.12605777648088706,
786
+ "grad_norm": 0.23593959212303162,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 0.8237,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.12722497811496936,
793
+ "grad_norm": 0.23072870075702667,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 0.7662,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.12839217974905165,
800
+ "grad_norm": 0.24987874925136566,
801
+ "learning_rate": 5e-05,
802
+ "loss": 0.7334,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.12955938138313394,
807
+ "grad_norm": 0.2619277834892273,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 0.8111,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.13072658301721624,
814
+ "grad_norm": 0.25728732347488403,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 0.8008,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.1318937846512985,
821
+ "grad_norm": 0.2542027235031128,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 0.6894,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.1330609862853808,
828
+ "grad_norm": 0.25486239790916443,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 0.7197,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.1342281879194631,
835
+ "grad_norm": 0.2670009434223175,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 0.7636,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.13539538955354538,
842
+ "grad_norm": 0.27421027421951294,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 0.781,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.13656259118762767,
849
+ "grad_norm": 0.2642095386981964,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 0.7648,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.13772979282170994,
856
+ "grad_norm": 0.28716525435447693,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 0.7874,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.13889699445579223,
863
+ "grad_norm": 0.29199421405792236,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 0.8243,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.14006419608987453,
870
+ "grad_norm": 0.2674504518508911,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 0.7611,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.14123139772395682,
877
+ "grad_norm": 0.2917780876159668,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 0.7462,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.1423985993580391,
884
+ "grad_norm": 0.3149389624595642,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 0.754,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.14356580099212138,
891
+ "grad_norm": 0.3116993308067322,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 0.8438,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.14473300262620367,
898
+ "grad_norm": 0.3052745461463928,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 0.8313,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.14590020426028597,
905
+ "grad_norm": 0.3292216360569,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 0.8778,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.14706740589436826,
912
+ "grad_norm": 0.3010333478450775,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 0.8251,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.14823460752845055,
919
+ "grad_norm": 0.3386470675468445,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 0.8236,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.14940180916253282,
926
+ "grad_norm": 0.33097153902053833,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 0.8059,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.1505690107966151,
933
+ "grad_norm": 0.32120153307914734,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 0.7842,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1517362124306974,
940
+ "grad_norm": 0.36916086077690125,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 0.8031,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1529034140647797,
947
+ "grad_norm": 0.32527828216552734,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 0.8087,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.154070615698862,
954
+ "grad_norm": 0.3791372776031494,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 0.8672,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.15523781733294426,
961
+ "grad_norm": 0.3701271712779999,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 0.7371,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.15640501896702655,
968
+ "grad_norm": 0.3659634590148926,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 0.8235,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.15757222060110884,
975
+ "grad_norm": 0.4024992287158966,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 0.9173,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.15873942223519114,
982
+ "grad_norm": 0.42308032512664795,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 0.9053,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.15990662386927343,
989
+ "grad_norm": 0.40175530314445496,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 0.8113,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1610738255033557,
996
+ "grad_norm": 0.36555033922195435,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 0.8684,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.162241027137438,
1003
+ "grad_norm": 0.3812856078147888,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 0.8385,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.16340822877152028,
1010
+ "grad_norm": 0.4847084879875183,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 1.0403,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.16457543040560257,
1017
+ "grad_norm": 0.35007935762405396,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 0.7455,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.16574263203968487,
1024
+ "grad_norm": 0.41641098260879517,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 0.7863,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.16690983367376713,
1031
+ "grad_norm": 0.27946096658706665,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 0.6836,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.16807703530784943,
1038
+ "grad_norm": 0.2813800573348999,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 0.5916,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.16924423694193172,
1045
+ "grad_norm": 0.24183239042758942,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 0.6092,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.170411438576014,
1052
+ "grad_norm": 0.2797646224498749,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 0.5887,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.1715786402100963,
1059
+ "grad_norm": 0.27872341871261597,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 0.6105,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.17274584184417857,
1066
+ "grad_norm": 0.2950071394443512,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 0.6768,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.17391304347826086,
1073
+ "grad_norm": 0.24491213262081146,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 0.6329,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.17508024511234316,
1080
+ "grad_norm": 0.3210446536540985,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 0.661,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.17508024511234316,
1087
+ "eval_loss": 0.7759228944778442,
1088
+ "eval_runtime": 131.4518,
1089
+ "eval_samples_per_second": 10.977,
1090
+ "eval_steps_per_second": 5.493,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.6019698699626086e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null