abaddon182 commited on
Commit
4728889
·
verified ·
1 Parent(s): 6736d97

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 sha256:510c2b666f7d331e3e05045aba0a5c647465ae7e5c18bfbd6f50d7205313b346
3
  size 1195453784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d87c610482cb7d5aaf138afe51638c57a3db6265cf909b18dfbd06faf78ce7
3
  size 1195453784
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51f6bc502b4598a4105d59faead834027ce377769b1224cd261d6deee81b8bd7
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc869833bc0a6c15a14cadf68a6ec1e98d9c6ab32704fc96ceb56272c82bb2d
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1626b81ac3b72ae331b96c534d042aecb4635bc1ebe24eac2ebb30ecc6e060a5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dafff0a4ee6da07fed34b8aaf656c1c796305c867701072f6dbfac74b88ebdfb
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": 0.289458304643631,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.008531877226286714,
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": 13.233,
732
  "eval_steps_per_second": 3.308,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.438153808365486e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.24746929109096527,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.012797815839430071,
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": 13.233,
732
  "eval_steps_per_second": 3.308,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.008617195998549581,
737
+ "grad_norm": 0.9032772183418274,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.3579,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.008702514770812448,
744
+ "grad_norm": 0.8081871271133423,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.3355,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.008787833543075316,
751
+ "grad_norm": 0.6597061157226562,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.2763,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.008873152315338183,
758
+ "grad_norm": 0.604412853717804,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.2498,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.008958471087601049,
765
+ "grad_norm": 0.6138935089111328,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.2511,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.009043789859863916,
772
+ "grad_norm": 0.5212016105651855,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.2301,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.009129108632126784,
779
+ "grad_norm": 0.5596919655799866,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.2405,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.009214427404389651,
786
+ "grad_norm": 0.5765125751495361,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.2322,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.009299746176652518,
793
+ "grad_norm": 0.6592385172843933,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.2766,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.009385064948915386,
800
+ "grad_norm": 0.5780729651451111,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.2318,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.009470383721178251,
807
+ "grad_norm": 0.5643982291221619,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.211,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.009555702493441119,
814
+ "grad_norm": 0.620904803276062,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.2637,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.009641021265703986,
821
+ "grad_norm": 0.6117725372314453,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.2407,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.009726340037966854,
828
+ "grad_norm": 0.6310005187988281,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.2699,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.009811658810229721,
835
+ "grad_norm": 0.6059605479240417,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.2172,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.009896977582492588,
842
+ "grad_norm": 0.7402892112731934,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.2434,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.009982296354755456,
849
+ "grad_norm": 0.7294708490371704,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.235,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.010067615127018321,
856
+ "grad_norm": 0.644306480884552,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.2424,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.010152933899281189,
863
+ "grad_norm": 0.6743088960647583,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.2314,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.010238252671544056,
870
+ "grad_norm": 0.7130791544914246,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.2807,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.010323571443806924,
877
+ "grad_norm": 0.7781491875648499,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.2441,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.010408890216069791,
884
+ "grad_norm": 0.7216753363609314,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.2729,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.010494208988332658,
891
+ "grad_norm": 0.7023508548736572,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.2646,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.010579527760595526,
898
+ "grad_norm": 0.72576904296875,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.2596,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.010664846532858391,
905
+ "grad_norm": 0.7103844285011292,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.233,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.010750165305121259,
912
+ "grad_norm": 0.6678680777549744,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.2312,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.010835484077384126,
919
+ "grad_norm": 0.7078672051429749,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.2339,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.010920802849646994,
926
+ "grad_norm": 0.8453111052513123,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.2782,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.011006121621909861,
933
+ "grad_norm": 0.8020609021186829,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.2809,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.011091440394172728,
940
+ "grad_norm": 0.6998770236968994,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.233,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.011176759166435594,
947
+ "grad_norm": 0.758491039276123,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.2558,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.011262077938698462,
954
+ "grad_norm": 0.8167868852615356,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.268,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.011347396710961329,
961
+ "grad_norm": 0.7342557311058044,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.2178,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.011432715483224196,
968
+ "grad_norm": 0.7934457659721375,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.2338,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.011518034255487064,
975
+ "grad_norm": 0.8661943078041077,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.2701,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.011603353027749931,
982
+ "grad_norm": 0.8646010160446167,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.2557,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.011688671800012798,
989
+ "grad_norm": 0.8198699951171875,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.2446,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.011773990572275664,
996
+ "grad_norm": 0.7358266115188599,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.2028,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.011859309344538532,
1003
+ "grad_norm": 0.7880418300628662,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.222,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.011944628116801399,
1010
+ "grad_norm": 0.7976980805397034,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.2108,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.012029946889064266,
1017
+ "grad_norm": 0.8414627313613892,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.2495,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.012115265661327134,
1024
+ "grad_norm": 0.7766191363334656,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.1911,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.012200584433590001,
1031
+ "grad_norm": 0.8738869428634644,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.2331,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.012285903205852869,
1038
+ "grad_norm": 0.9872680306434631,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.2705,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.012371221978115734,
1045
+ "grad_norm": 0.8350234627723694,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.2319,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.012456540750378602,
1052
+ "grad_norm": 1.025537133216858,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.2773,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.012541859522641469,
1059
+ "grad_norm": 0.9157933592796326,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.2232,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.012627178294904336,
1066
+ "grad_norm": 1.1109967231750488,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.2734,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.012712497067167204,
1073
+ "grad_norm": 1.05686616897583,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.2682,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.012797815839430071,
1080
+ "grad_norm": 1.449411392211914,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.3932,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.012797815839430071,
1087
+ "eval_loss": 0.24746929109096527,
1088
+ "eval_runtime": 1491.868,
1089
+ "eval_samples_per_second": 13.232,
1090
+ "eval_steps_per_second": 3.308,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.157230712548229e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null