aleegis10 commited on
Commit
199a0f0
·
verified ·
1 Parent(s): c0ae603

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:f0bdbe20707d5573de72492b5b52f643c38882423895821ba9ec529b13249754
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86db3458afe12c7ad3b920cc37f7745a06a7eeb34df19540e07d59c335d752ff
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:932c117ce6046b17e536cdfefaabe538916cb836d6b91b5274aea4cf7bba5fb7
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:838bbf33781c9b64e1d2fcc1a9128e55f1ba5d03f9eaaa5f382c6dd0bdfd5eee
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:f003676a6cbf38418e7c7d43282c9aa1379d9623a39594d18b7f56bd6bb4c309
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e666412d3025e90cfce7bcb539f7eda45fa05e8b7620eb1b393343848b465e3
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": 0.28296175599098206,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.023705108450871162,
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": 13.762,
732
  "eval_steps_per_second": 3.442,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4345755040101171e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.2598925232887268,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.035557662676306744,
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": 13.762,
732
  "eval_steps_per_second": 3.442,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.023942159535379873,
737
+ "grad_norm": 8.359138488769531,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.1768,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.024179210619888584,
744
+ "grad_norm": 8.67495346069336,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.3943,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0244162617043973,
751
+ "grad_norm": 9.854082107543945,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.4637,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.02465331278890601,
758
+ "grad_norm": 6.110072612762451,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.7395,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.02489036387341472,
765
+ "grad_norm": 6.735311508178711,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.905,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.025127414957923432,
772
+ "grad_norm": 8.923399925231934,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.8893,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.025364466042432143,
779
+ "grad_norm": 8.221948623657227,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.6142,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.025601517126940854,
786
+ "grad_norm": 8.158872604370117,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.5885,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.02583856821144957,
793
+ "grad_norm": 7.332838535308838,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.0663,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.02607561929595828,
800
+ "grad_norm": 7.769575119018555,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.2486,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.02631267038046699,
807
+ "grad_norm": 7.445107460021973,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.4,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.026549721464975702,
814
+ "grad_norm": 8.416275978088379,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.2037,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.026786772549484413,
821
+ "grad_norm": 10.549809455871582,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.3073,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.027023823633993124,
828
+ "grad_norm": 6.388961315155029,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.7881,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.02726087471850184,
835
+ "grad_norm": 8.752462387084961,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.1797,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.02749792580301055,
842
+ "grad_norm": 8.613337516784668,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.3528,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.02773497688751926,
849
+ "grad_norm": 9.686309814453125,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.5578,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.027972027972027972,
856
+ "grad_norm": 6.918097496032715,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.4049,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.028209079056536683,
863
+ "grad_norm": 8.275176048278809,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.9878,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.028446130141045394,
870
+ "grad_norm": 6.292196273803711,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.0339,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.028683181225554105,
877
+ "grad_norm": 7.8501505851745605,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.453,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.02892023231006282,
884
+ "grad_norm": 5.446768760681152,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.7386,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.02915728339457153,
891
+ "grad_norm": 6.707988739013672,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.8834,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.029394334479080242,
898
+ "grad_norm": 7.342574596405029,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.9934,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.029631385563588953,
905
+ "grad_norm": 7.558194160461426,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.8803,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.029868436648097664,
912
+ "grad_norm": 6.624544620513916,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.8641,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.030105487732606375,
919
+ "grad_norm": 8.050422668457031,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.3738,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.03034253881711509,
926
+ "grad_norm": 8.919082641601562,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.2314,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0305795899016238,
933
+ "grad_norm": 33.773231506347656,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.6851,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.030816640986132512,
940
+ "grad_norm": 10.311910629272461,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.3308,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.031053692070641223,
947
+ "grad_norm": 8.833625793457031,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.1228,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.03129074315514994,
954
+ "grad_norm": 7.480016708374023,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.944,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.031527794239658645,
961
+ "grad_norm": 7.066028118133545,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.6924,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.03176484532416736,
968
+ "grad_norm": 4.683218479156494,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.6277,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03200189640867607,
975
+ "grad_norm": 7.2049078941345215,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.0737,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.03223894749318478,
982
+ "grad_norm": 9.224268913269043,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.0738,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.032475998577693496,
989
+ "grad_norm": 10.263715744018555,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.9315,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.032713049662202204,
996
+ "grad_norm": 9.596421241760254,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.9987,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.03295010074671092,
1003
+ "grad_norm": 7.585577011108398,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.1157,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.033187151831219626,
1010
+ "grad_norm": 6.539881706237793,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.9617,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.03342420291572834,
1017
+ "grad_norm": 9.355979919433594,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.1429,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.03366125400023705,
1024
+ "grad_norm": 9.769394874572754,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.2177,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.03389830508474576,
1031
+ "grad_norm": 10.125142097473145,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.7486,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.03413535616925448,
1038
+ "grad_norm": 8.567256927490234,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.8809,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.034372407253763185,
1045
+ "grad_norm": 9.61689567565918,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.8924,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0346094583382719,
1052
+ "grad_norm": 8.733377456665039,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.7403,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.03484650942278061,
1059
+ "grad_norm": 9.422379493713379,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.7349,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.03508356050728932,
1066
+ "grad_norm": 7.522639751434326,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.978,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.035320611591798036,
1073
+ "grad_norm": 9.866047859191895,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.1348,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.035557662676306744,
1080
+ "grad_norm": 9.662226676940918,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.0662,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.035557662676306744,
1087
+ "eval_loss": 0.2598925232887268,
1088
+ "eval_runtime": 516.1483,
1089
+ "eval_samples_per_second": 13.765,
1090
+ "eval_steps_per_second": 3.443,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.150074508503941e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null