bbytxt commited on
Commit
6f2a388
·
verified ·
1 Parent(s): b9e50f4

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:a4bfa4fb6ada7423ed925f8e57ee0cb5e286876fbcc2594f6cb68235e33a3e87
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4869bfd28f574617c3b04ebe53729f517d6fc798b53fa4b9b4034baa51eb800
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ade5085f22f6e104d8848bbf9c1953e65b856ba167a71c7e7c4edf992744d71
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece3470e751bd897267a47dbd90f0dc8c06b1e8f939897bc654d12ffd9d202e9
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:a96c527557a96a55d5198db62dcc69f5947db83b6cbebb4f03c0b65ea3aa6c96
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21d8a004cc15df598b4e2e69aff65ff743e4a5d034e274aeb641620abf89442f
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": 0.40054818987846375,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.46296296296296297,
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": 33.787,
732
  "eval_steps_per_second": 8.447,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.728250925121536e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.38866910338401794,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.6944444444444444,
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": 33.787,
732
  "eval_steps_per_second": 8.447,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.4675925925925926,
737
+ "grad_norm": 0.30973020195961,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.4769,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.4722222222222222,
744
+ "grad_norm": 0.3454133868217468,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.4476,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.47685185185185186,
751
+ "grad_norm": 0.3141106963157654,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.4246,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.48148148148148145,
758
+ "grad_norm": 0.29273855686187744,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.3928,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.4861111111111111,
765
+ "grad_norm": 0.35139960050582886,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.4515,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.49074074074074076,
772
+ "grad_norm": 0.31835365295410156,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.4208,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.49537037037037035,
779
+ "grad_norm": 0.33383437991142273,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.4209,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.5,
786
+ "grad_norm": 0.34722745418548584,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.4656,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.5046296296296297,
793
+ "grad_norm": 0.2982996702194214,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.3507,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.5092592592592593,
800
+ "grad_norm": 0.3275409936904907,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.3617,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.5138888888888888,
807
+ "grad_norm": 0.33099961280822754,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.3517,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.5185185185185185,
814
+ "grad_norm": 0.33550557494163513,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.4334,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.5231481481481481,
821
+ "grad_norm": 0.36219605803489685,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.394,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5277777777777778,
828
+ "grad_norm": 0.3489916920661926,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.4535,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5324074074074074,
835
+ "grad_norm": 0.35915425419807434,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.4384,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5370370370370371,
842
+ "grad_norm": 0.3669782876968384,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.4106,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.5416666666666666,
849
+ "grad_norm": 0.36302924156188965,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.4328,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5462962962962963,
856
+ "grad_norm": 0.36465269327163696,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.3772,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5509259259259259,
863
+ "grad_norm": 0.40110573172569275,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.4015,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5555555555555556,
870
+ "grad_norm": 0.37549349665641785,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.4517,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.5601851851851852,
877
+ "grad_norm": 0.34770068526268005,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.3598,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5648148148148148,
884
+ "grad_norm": 0.37237435579299927,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.4272,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5694444444444444,
891
+ "grad_norm": 0.31195151805877686,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.3269,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.5740740740740741,
898
+ "grad_norm": 0.33469128608703613,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.3795,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.5787037037037037,
905
+ "grad_norm": 0.39495936036109924,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.4441,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5833333333333334,
912
+ "grad_norm": 0.35597342252731323,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.379,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5879629629629629,
919
+ "grad_norm": 0.4018954336643219,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.4938,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5925925925925926,
926
+ "grad_norm": 0.3984406888484955,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.4209,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5972222222222222,
933
+ "grad_norm": 0.4191405475139618,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.444,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.6018518518518519,
940
+ "grad_norm": 0.4371749460697174,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.4234,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.6064814814814815,
947
+ "grad_norm": 0.3813394010066986,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.3846,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.6111111111111112,
954
+ "grad_norm": 0.36820274591445923,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.3551,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.6157407407407407,
961
+ "grad_norm": 0.37040993571281433,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.3445,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.6203703703703703,
968
+ "grad_norm": 0.3780434727668762,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.3451,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.625,
975
+ "grad_norm": 0.48591867089271545,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.433,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.6296296296296297,
982
+ "grad_norm": 0.3953004479408264,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.3709,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.6342592592592593,
989
+ "grad_norm": 0.3976372480392456,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.3897,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6388888888888888,
996
+ "grad_norm": 0.41118407249450684,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.3342,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.6435185185185185,
1003
+ "grad_norm": 0.425074964761734,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.4051,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.6481481481481481,
1010
+ "grad_norm": 0.38811710476875305,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.3067,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.6527777777777778,
1017
+ "grad_norm": 0.446621298789978,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.4242,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.6574074074074074,
1024
+ "grad_norm": 0.4710548222064972,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.3721,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.6620370370370371,
1031
+ "grad_norm": 0.473621129989624,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.3758,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6666666666666666,
1038
+ "grad_norm": 0.4742882251739502,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.4299,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.6712962962962963,
1045
+ "grad_norm": 0.4604876637458801,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.3554,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6759259259259259,
1052
+ "grad_norm": 0.453888863325119,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.3811,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6805555555555556,
1059
+ "grad_norm": 0.43823665380477905,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.3157,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6851851851851852,
1066
+ "grad_norm": 0.4286869764328003,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.3436,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6898148148148148,
1073
+ "grad_norm": 0.4839453399181366,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.3277,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6944444444444444,
1080
+ "grad_norm": 0.44581836462020874,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.3,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6944444444444444,
1087
+ "eval_loss": 0.38866910338401794,
1088
+ "eval_runtime": 10.7686,
1089
+ "eval_samples_per_second": 33.802,
1090
+ "eval_steps_per_second": 8.451,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.088974578548736e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null