abaddon182 commited on
Commit
b0dfca5
·
verified ·
1 Parent(s): a3f6af7

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:f2a6a5eb5d0f01b55bf5b3818d537e74003b77a052ad1c016feb1847244dafc0
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a8d3139c254084ed378d1e1efe9d05eb3c9e3b12d40620f0c3f344f1451c0bb
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:feb91355981dec61999852dc8f57fcfc97b59f0a4dd88b94f535b66304fb3dcb
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b682f1d7046b0ee08712469807bdc1ac1cd398702df19d68151303fad58af96
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c4aa299887e9b2f4f91c78948953289b823e5f532cea1915d4cd0ba02b14f07
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef4b3fdb346afcf6040343fe4c997aeb783086a8f248879051548447581b3430
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": 1.577565312385559,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0160333493666827,
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": 57.998,
732
  "eval_steps_per_second": 14.504,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7728482431795200.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.484871745109558,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.02405002405002405,
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": 57.998,
732
  "eval_steps_per_second": 14.504,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.01619368286034953,
737
+ "grad_norm": 1.0778112411499023,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.7987,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.016354016354016353,
744
+ "grad_norm": 1.4329731464385986,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.2528,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01651434984768318,
751
+ "grad_norm": 2.3502819538116455,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.3122,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.016674683341350006,
758
+ "grad_norm": 3.054696798324585,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.8111,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.016835016835016835,
765
+ "grad_norm": 2.7006399631500244,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.0079,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.016995350328683663,
772
+ "grad_norm": 3.1934356689453125,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.9011,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.017155683822350488,
779
+ "grad_norm": 2.7194902896881104,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.2386,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.017316017316017316,
786
+ "grad_norm": 1.9565664529800415,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.662,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.017476350809684144,
793
+ "grad_norm": 1.5166082382202148,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.062,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.01763668430335097,
800
+ "grad_norm": 1.7787351608276367,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.043,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.017797017797017797,
807
+ "grad_norm": 1.6311932802200317,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.6041,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.017957351290684626,
814
+ "grad_norm": 1.3286525011062622,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.6954,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.01811768478435145,
821
+ "grad_norm": 1.4849814176559448,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.8252,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.01827801827801828,
828
+ "grad_norm": 1.8410348892211914,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.8354,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.018438351771685103,
835
+ "grad_norm": 1.9564002752304077,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.8874,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.01859868526535193,
842
+ "grad_norm": 1.6850190162658691,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.5473,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.01875901875901876,
849
+ "grad_norm": 1.796574354171753,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.7481,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.018919352252685585,
856
+ "grad_norm": 1.8272076845169067,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.8834,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.019079685746352413,
863
+ "grad_norm": 1.3704986572265625,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.3574,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.01924001924001924,
870
+ "grad_norm": 1.4744528532028198,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.6148,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.019400352733686066,
877
+ "grad_norm": 1.5670959949493408,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.7067,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.019560686227352894,
884
+ "grad_norm": 1.4213238954544067,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.2831,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.019721019721019722,
891
+ "grad_norm": 1.4642093181610107,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.5041,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.019881353214686547,
898
+ "grad_norm": 1.4591537714004517,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.4938,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.020041686708353375,
905
+ "grad_norm": 1.5452147722244263,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.574,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.020202020202020204,
912
+ "grad_norm": 1.4701132774353027,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.6096,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.02036235369568703,
919
+ "grad_norm": 1.6247003078460693,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.5613,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.020522687189353857,
926
+ "grad_norm": 1.6164422035217285,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.5354,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.02068302068302068,
933
+ "grad_norm": 1.541204810142517,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.6355,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.02084335417668751,
940
+ "grad_norm": 1.5679917335510254,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.256,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.021003687670354338,
947
+ "grad_norm": 1.5460208654403687,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.4764,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.021164021164021163,
954
+ "grad_norm": 1.5560331344604492,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.3285,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.02132435465768799,
961
+ "grad_norm": 1.600095272064209,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.1649,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.02148468815135482,
968
+ "grad_norm": 1.6068081855773926,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.189,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.021645021645021644,
975
+ "grad_norm": 1.7338483333587646,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.2842,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.021805355138688472,
982
+ "grad_norm": 1.8223528861999512,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.3976,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.0219656886323553,
989
+ "grad_norm": 1.7216356992721558,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.0166,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.022126022126022125,
996
+ "grad_norm": 1.7349539995193481,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.2565,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.022286355619688954,
1003
+ "grad_norm": 1.7386369705200195,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.0638,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.02244668911335578,
1010
+ "grad_norm": 1.9614675045013428,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.2197,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.022607022607022607,
1017
+ "grad_norm": 1.8332651853561401,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2153,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.022767356100689435,
1024
+ "grad_norm": 2.135434150695801,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.1492,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.02292768959435626,
1031
+ "grad_norm": 2.1699466705322266,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.267,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.023088023088023088,
1038
+ "grad_norm": 2.128176689147949,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.0789,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.023248356581689916,
1045
+ "grad_norm": 2.194796323776245,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.2463,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.02340869007535674,
1052
+ "grad_norm": 2.179041624069214,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.0174,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.02356902356902357,
1059
+ "grad_norm": 2.251429796218872,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.0932,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.023729357062690398,
1066
+ "grad_norm": 2.3761861324310303,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.0235,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.023889690556357222,
1073
+ "grad_norm": 2.7878284454345703,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.1111,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.02405002405002405,
1080
+ "grad_norm": 3.860334634780884,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.1455,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.02405002405002405,
1087
+ "eval_loss": 1.484871745109558,
1088
+ "eval_runtime": 181.1474,
1089
+ "eval_samples_per_second": 57.991,
1090
+ "eval_steps_per_second": 14.502,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.15927236476928e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null