prxy5606 commited on
Commit
d9261f1
·
verified ·
1 Parent(s): d314c7a

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 sha256:86a039b083a797088d8069ad4ffd87499877d62959d43aa6267a0596a4d2d597
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80ed7601771ea5e5a041abc775afa02738b6a237b8ea6339a6382f47084ffde
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d05220318bb9ebdd78135934303c1fecafc4eb8661b1f0b02f4a0626745bd453
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62247c4a20b3ced7b327e3671ae88932d695abf28c224b7dfe43d182c195734c
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58b3b8c8fcf21ffbd72f95dac146a3c75b0c1b68314ee7e80a22789d747b9ad7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7913a44bd79999a1584a44793663198b5896e2a56707a9690281fe2f6d9416dd
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": 1.6908631324768066,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.05862523816503005,
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": 12.658,
732
  "eval_steps_per_second": 3.168,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4870102800544563e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.631693720817566,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.08793785724754506,
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": 12.658,
732
  "eval_steps_per_second": 3.168,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.059211490546680345,
737
+ "grad_norm": 10.180007934570312,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 8.4237,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.05979774292833065,
744
+ "grad_norm": 7.255772590637207,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 7.707,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.060383995309980946,
751
+ "grad_norm": 2.8105390071868896,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 6.4831,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06097024769163125,
758
+ "grad_norm": 2.000762939453125,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 6.3403,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06155650007328155,
765
+ "grad_norm": 1.9792354106903076,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.6166,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06214275245493185,
772
+ "grad_norm": 2.2282116413116455,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 6.9028,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06272900483658214,
779
+ "grad_norm": 2.1197075843811035,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 5.7175,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.06331525721823245,
786
+ "grad_norm": 2.1858396530151367,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 5.9439,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.06390150959988275,
793
+ "grad_norm": 2.093513011932373,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 5.7939,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.06448776198153305,
800
+ "grad_norm": 2.5304839611053467,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 6.4176,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.06507401436318334,
807
+ "grad_norm": 2.635596513748169,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 6.478,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.06566026674483365,
814
+ "grad_norm": 2.2483584880828857,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 6.2564,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.06624651912648395,
821
+ "grad_norm": 2.1168601512908936,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 6.0574,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.06683277150813426,
828
+ "grad_norm": 2.2489209175109863,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 6.5691,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.06741902388978455,
835
+ "grad_norm": 2.27750563621521,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 6.1844,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.06800527627143485,
842
+ "grad_norm": 2.2860987186431885,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 6.1519,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.06859152865308515,
849
+ "grad_norm": 2.290987968444824,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 6.5961,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.06917778103473546,
856
+ "grad_norm": 2.3825812339782715,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 6.2614,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.06976403341638575,
863
+ "grad_norm": 2.404409408569336,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 6.8128,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.07035028579803605,
870
+ "grad_norm": 2.317049503326416,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 6.3945,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07093653817968636,
877
+ "grad_norm": 2.479034900665283,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 6.4291,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.07152279056133666,
884
+ "grad_norm": 2.488262414932251,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 6.6535,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.07210904294298695,
891
+ "grad_norm": 2.7070815563201904,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 6.4235,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.07269529532463725,
898
+ "grad_norm": 2.623577833175659,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 6.815,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.07328154770628756,
905
+ "grad_norm": 2.7124648094177246,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 6.3577,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.07386780008793786,
912
+ "grad_norm": 2.5578460693359375,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 6.6705,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.07445405246958815,
919
+ "grad_norm": 2.7071213722229004,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 6.3228,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.07504030485123846,
926
+ "grad_norm": 2.724385976791382,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 6.1514,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.07562655723288876,
933
+ "grad_norm": 2.6133148670196533,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 6.0927,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.07621280961453906,
940
+ "grad_norm": 2.5122416019439697,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.5315,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.07679906199618936,
947
+ "grad_norm": 3.1386067867279053,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 6.3387,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.07738531437783966,
954
+ "grad_norm": 2.9565436840057373,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 6.5669,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.07797156675948996,
961
+ "grad_norm": 3.0717828273773193,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 6.9754,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.07855781914114027,
968
+ "grad_norm": 2.854853630065918,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 6.9432,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.07914407152279056,
975
+ "grad_norm": 2.7369515895843506,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 5.9499,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.07973032390444086,
982
+ "grad_norm": 2.9582712650299072,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 6.0952,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.08031657628609117,
989
+ "grad_norm": 3.1780998706817627,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 6.8335,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.08090282866774147,
996
+ "grad_norm": 3.0727474689483643,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 6.2819,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.08148908104939176,
1003
+ "grad_norm": 3.8813369274139404,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 6.7358,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.08207533343104206,
1010
+ "grad_norm": 3.075451612472534,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 6.041,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.08266158581269237,
1017
+ "grad_norm": 3.4926958084106445,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 6.8879,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.08324783819434266,
1024
+ "grad_norm": 3.591356039047241,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 6.7446,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.08383409057599296,
1031
+ "grad_norm": 3.528189182281494,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 6.9325,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.08442034295764327,
1038
+ "grad_norm": 3.581657886505127,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 6.967,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.08500659533929357,
1045
+ "grad_norm": 3.52889347076416,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 6.8557,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.08559284772094386,
1052
+ "grad_norm": 3.518007755279541,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 7.0728,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.08617910010259416,
1059
+ "grad_norm": 3.710296869277954,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 7.4821,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.08676535248424447,
1066
+ "grad_norm": 3.8919053077697754,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 7.2119,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.08735160486589477,
1073
+ "grad_norm": 3.9789481163024902,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 7.3836,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.08793785724754506,
1080
+ "grad_norm": 4.608246803283691,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 8.3462,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.08793785724754506,
1087
+ "eval_loss": 1.631693720817566,
1088
+ "eval_runtime": 227.0982,
1089
+ "eval_samples_per_second": 12.651,
1090
+ "eval_steps_per_second": 3.166,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.226906171829125e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null