ancient41 commited on
Commit
c4fa95a
·
verified ·
1 Parent(s): a654c25

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 sha256:24b57cd11e3ec56d1819479eb0cfd29a290f1a379e677845fa83a00104819adc
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b82f637fbbcf9c18388e17a27e644c3ff1d0d44dff9ccb0924da82c5c8232a
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdb44a7844f5cef2d21cabfad70c1eb64c6d5d1e02cba80beba8a6df40ed1f64
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eaeec56bc85ff8d8e8333454c95a6a06d76ecbc2de728340a6f9cf4f93280fa
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:f9e6df8cc6aab8d327734713f68bf4f7da8a4c480516ffd2365e8d9c7bd0a1e7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a4f36987e11361af142b76065c8b4ca44b0deb82d95957e3e64d5a688508174
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": 0.7389817237854004,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.017681902572716825,
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": 13.527,
732
  "eval_steps_per_second": 3.383,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.430999619600384e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6781367659568787,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.026522853859075237,
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": 13.527,
732
  "eval_steps_per_second": 3.383,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.017858721598443993,
737
+ "grad_norm": 8.920741081237793,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 3.3914,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.018035540624171162,
744
+ "grad_norm": 7.691524982452393,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 3.4589,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01821235964989833,
751
+ "grad_norm": 4.382842063903809,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.9892,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.018389178675625496,
758
+ "grad_norm": 4.469934463500977,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 3.1142,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.018565997701352664,
765
+ "grad_norm": 4.711705207824707,
766
+ "learning_rate": 5e-05,
767
+ "loss": 3.1713,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.018742816727079833,
772
+ "grad_norm": 4.239561080932617,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 3.0092,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.018919635752807,
779
+ "grad_norm": 3.846534013748169,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 3.0243,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01909645477853417,
786
+ "grad_norm": 3.866678476333618,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.8102,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.01927327380426134,
793
+ "grad_norm": 3.4842145442962646,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.7249,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.019450092829988507,
800
+ "grad_norm": 3.4887750148773193,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.8563,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.019626911855715676,
807
+ "grad_norm": 3.680882453918457,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.6713,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.019803730881442844,
814
+ "grad_norm": 4.103943347930908,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 3.0004,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.019980549907170013,
821
+ "grad_norm": 3.867415428161621,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.8714,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.020157368932897178,
828
+ "grad_norm": 3.6518120765686035,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.4498,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.020334187958624347,
835
+ "grad_norm": 3.914706230163574,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.7675,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.020511006984351515,
842
+ "grad_norm": 3.9167869091033936,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.8318,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.020687826010078684,
849
+ "grad_norm": 3.727733850479126,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.715,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.020864645035805852,
856
+ "grad_norm": 3.9161274433135986,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.7997,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.02104146406153302,
863
+ "grad_norm": 3.6844944953918457,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.752,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.02121828308726019,
870
+ "grad_norm": 4.133869647979736,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.7113,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.021395102112987358,
877
+ "grad_norm": 3.8387954235076904,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.5577,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.021571921138714527,
884
+ "grad_norm": 3.6142640113830566,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.6402,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.021748740164441695,
891
+ "grad_norm": 3.8690361976623535,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.6052,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.02192555919016886,
898
+ "grad_norm": 3.8395142555236816,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.6495,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.02210237821589603,
905
+ "grad_norm": 4.113121032714844,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.6376,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.022279197241623198,
912
+ "grad_norm": 3.76629376411438,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.5573,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.022456016267350366,
919
+ "grad_norm": 3.7748351097106934,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.6338,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.022632835293077535,
926
+ "grad_norm": 3.8269357681274414,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.7441,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.022809654318804704,
933
+ "grad_norm": 3.811927556991577,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.5824,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.022986473344531872,
940
+ "grad_norm": 3.9410016536712646,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.8725,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.02316329237025904,
947
+ "grad_norm": 3.8563146591186523,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.5051,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.02334011139598621,
954
+ "grad_norm": 3.753028392791748,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.6026,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.023516930421713378,
961
+ "grad_norm": 3.807447910308838,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.4886,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.023693749447440543,
968
+ "grad_norm": 3.8522281646728516,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.5633,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.02387056847316771,
975
+ "grad_norm": 3.8721601963043213,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.5071,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.02404738749889488,
982
+ "grad_norm": 4.0354461669921875,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.7198,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.02422420652462205,
989
+ "grad_norm": 3.5654656887054443,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.4604,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.024401025550349217,
996
+ "grad_norm": 3.723776340484619,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.6183,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.024577844576076386,
1003
+ "grad_norm": 3.5163791179656982,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.4345,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.024754663601803555,
1010
+ "grad_norm": 3.7013096809387207,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.2734,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.024931482627530723,
1017
+ "grad_norm": 3.5966262817382812,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.4084,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.025108301653257892,
1024
+ "grad_norm": 3.8784823417663574,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.5505,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.02528512067898506,
1031
+ "grad_norm": 3.960005760192871,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.3651,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.025461939704712225,
1038
+ "grad_norm": 3.905780792236328,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.4459,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.025638758730439394,
1045
+ "grad_norm": 3.7308545112609863,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.3803,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.025815577756166563,
1052
+ "grad_norm": 4.277618408203125,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.5735,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.02599239678189373,
1059
+ "grad_norm": 4.1843180656433105,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.5866,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0261692158076209,
1066
+ "grad_norm": 3.8520991802215576,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.2892,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.02634603483334807,
1073
+ "grad_norm": 3.938481330871582,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.2478,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.026522853859075237,
1080
+ "grad_norm": 4.657419681549072,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.4547,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.026522853859075237,
1087
+ "eval_loss": 0.6781367659568787,
1088
+ "eval_runtime": 703.6237,
1089
+ "eval_samples_per_second": 13.537,
1090
+ "eval_steps_per_second": 3.385,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.146499429400576e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null