aleegis09 commited on
Commit
903c49f
·
verified ·
1 Parent(s): 26b615c

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 sha256:89fc2cbeebd3b531ccbc81fdc2cd2ffc6c4e97fee37876f34c11e99da55a79e1
3
  size 377538512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc3e6669762305774c94c06185ca6824d757077dc2afeb98ddddeff1e882ac0
3
  size 377538512
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99890f8bd82720f722f8cbc22de1a83bd952d78355d221144b221cfa2c98c017
3
  size 192144596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efa9cd350009cae1f73d979a51ed7a41a017e93defe2b0e3f105e9d19dd2b85c
3
  size 192144596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65032fa9a0647ae2b20449ee7f14942bb4fca2836deaff15899fe53730909d8d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e81fc6871cd692ea4a039e488dbba0c61a8b5db16c56d97e1817bf08087504c
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": 1.833712100982666,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.6546644844517185,
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": 21.185,
732
  "eval_steps_per_second": 5.337,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 5.3929253535744e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.714800477027893,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.9819967266775778,
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": 21.185,
732
  "eval_steps_per_second": 5.337,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6612111292962357,
737
+ "grad_norm": 5.072551727294922,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.0206,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.6677577741407529,
744
+ "grad_norm": 4.489765167236328,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.8771,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.67430441898527,
751
+ "grad_norm": 3.398970127105713,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.7019,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.6808510638297872,
758
+ "grad_norm": 4.148207187652588,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.7328,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.6873977086743044,
765
+ "grad_norm": 6.095871925354004,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.6155,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.6939443535188216,
772
+ "grad_norm": 3.8897461891174316,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.8277,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.7004909983633388,
779
+ "grad_norm": 4.919135093688965,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.7958,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.707037643207856,
786
+ "grad_norm": 6.133851051330566,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.8678,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.7135842880523732,
793
+ "grad_norm": 5.558732032775879,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.4112,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7201309328968903,
800
+ "grad_norm": 3.655571460723877,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.8845,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.7266775777414075,
807
+ "grad_norm": 5.17197322845459,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.591,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.7332242225859247,
814
+ "grad_norm": 6.932631015777588,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.9862,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.7397708674304418,
821
+ "grad_norm": 7.251398086547852,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.8668,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.7463175122749591,
828
+ "grad_norm": 6.583548545837402,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.0806,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.7528641571194763,
835
+ "grad_norm": 3.734530448913574,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.8862,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.7594108019639935,
842
+ "grad_norm": 4.668886661529541,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.7792,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.7659574468085106,
849
+ "grad_norm": 4.5727033615112305,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.7567,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.7725040916530278,
856
+ "grad_norm": 5.049441814422607,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.0036,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.779050736497545,
863
+ "grad_norm": 4.456987380981445,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.7486,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.7855973813420621,
870
+ "grad_norm": 4.143889427185059,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.6551,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.7921440261865794,
877
+ "grad_norm": 4.320343971252441,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.9232,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.7986906710310966,
884
+ "grad_norm": 5.44630765914917,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.8575,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.8052373158756138,
891
+ "grad_norm": 4.377072334289551,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.799,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.8117839607201309,
898
+ "grad_norm": 5.06345796585083,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.7233,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.8183306055646481,
905
+ "grad_norm": 4.668278694152832,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.8858,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.8248772504091653,
912
+ "grad_norm": 5.961413383483887,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.8627,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.8314238952536824,
919
+ "grad_norm": 4.456691741943359,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.8775,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.8379705400981997,
926
+ "grad_norm": 5.186953067779541,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.1712,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.8445171849427169,
933
+ "grad_norm": 5.342906951904297,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.9014,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.851063829787234,
940
+ "grad_norm": 4.619450569152832,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.8888,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.8576104746317512,
947
+ "grad_norm": 6.31242561340332,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.0707,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.8641571194762684,
954
+ "grad_norm": 8.822924613952637,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.855,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.8707037643207856,
961
+ "grad_norm": 5.338212013244629,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.667,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.8772504091653028,
968
+ "grad_norm": 4.663907051086426,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.0712,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.88379705400982,
975
+ "grad_norm": 7.675205230712891,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.3015,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.8903436988543372,
982
+ "grad_norm": 6.278077602386475,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.0943,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.8968903436988543,
989
+ "grad_norm": 6.428853988647461,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.9604,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.9034369885433715,
996
+ "grad_norm": 5.31624698638916,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.9479,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.9099836333878887,
1003
+ "grad_norm": 7.327105522155762,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.8141,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.9165302782324058,
1010
+ "grad_norm": 4.801591873168945,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.98,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.9230769230769231,
1017
+ "grad_norm": 4.311253070831299,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.7544,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.9296235679214403,
1024
+ "grad_norm": 5.648926258087158,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.6239,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.9361702127659575,
1031
+ "grad_norm": 4.999743461608887,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.6279,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.9427168576104746,
1038
+ "grad_norm": 4.39159631729126,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.6529,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.9492635024549918,
1045
+ "grad_norm": 3.6927833557128906,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.5418,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.955810147299509,
1052
+ "grad_norm": 5.580817222595215,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.38,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.9623567921440261,
1059
+ "grad_norm": 4.657471179962158,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.4946,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.9689034369885434,
1066
+ "grad_norm": 5.437662601470947,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.7749,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.9754500818330606,
1073
+ "grad_norm": 4.54913330078125,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.3248,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.9819967266775778,
1080
+ "grad_norm": 5.12714958190918,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.5162,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.9819967266775778,
1087
+ "eval_loss": 1.714800477027893,
1088
+ "eval_runtime": 12.1718,
1089
+ "eval_samples_per_second": 21.197,
1090
+ "eval_steps_per_second": 5.34,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 8.0893880303616e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null