aleegis10 commited on
Commit
4462bfd
·
verified ·
1 Parent(s): 60a40bb

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 sha256:242cc16e60d1a4872203f7d8b4d139e83280bca6f9afe6d6d92a39dbfa91f2b3
3
  size 12589528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a34c2a42adfb6aaa3a534678dae78a3edd2b4365e39310aeabae766d91c2c9c9
3
  size 12589528
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b182fe78b7c43239d88b45432d6131ee9b888b56baeffb1aa3b73bab80d8558a
3
  size 6448570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49793857d5dbbdd3af4d53450390df41f3eda50853025dcf99e0d4a185dabad2
3
  size 6448570
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8ed664226c78e02098bb43f0a9a3262e02c300017ab329fcc77b4092f5b87c1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40f5bc26cb339f0316d455c5912a942dd424ac3b162434efb665bbac44af65ed
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": 24.225305557250977,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.039912193175014966,
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": 283.61,
732
  "eval_steps_per_second": 70.902,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 944815227273216.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 14.149837493896484,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.05986828976252245,
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": 283.61,
732
  "eval_steps_per_second": 70.902,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04031131510676512,
737
+ "grad_norm": 15173.3427734375,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 93.8994,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.04071043703851527,
744
+ "grad_norm": 19899.49609375,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 89.582,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.041109558970265414,
751
+ "grad_norm": 25137.298828125,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 72.3924,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.041508680902015566,
758
+ "grad_norm": 86265.0078125,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 58.8551,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.04190780283376572,
765
+ "grad_norm": 6620.14453125,
766
+ "learning_rate": 5e-05,
767
+ "loss": 57.1258,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.04230692476551586,
772
+ "grad_norm": 3978.382568359375,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 53.8962,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.04270604669726601,
779
+ "grad_norm": 8527.5732421875,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 55.932,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.043105168629016165,
786
+ "grad_norm": 6914.259765625,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 57.8621,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.043504290560766316,
793
+ "grad_norm": 20578.068359375,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 62.593,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.04390341249251646,
800
+ "grad_norm": 14920.2265625,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 68.1114,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.04430253442426661,
807
+ "grad_norm": 41930.08984375,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 68.2349,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.044701656356016764,
814
+ "grad_norm": 24784.23046875,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 61.8663,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.045100778287766916,
821
+ "grad_norm": 6655.806640625,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 58.0144,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.04549990021951706,
828
+ "grad_norm": 11499.470703125,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 59.2773,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.04589902215126721,
835
+ "grad_norm": 15461.00390625,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 62.8515,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.04629814408301736,
842
+ "grad_norm": 18039.513671875,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 61.4904,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.046697266014767515,
849
+ "grad_norm": 83189.375,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 76.6094,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.04709638794651766,
856
+ "grad_norm": 9933.810546875,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 57.0005,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.04749550987826781,
863
+ "grad_norm": 50326.92578125,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 66.0802,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.04789463181001796,
870
+ "grad_norm": 17718.609375,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 57.6921,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.04829375374176811,
877
+ "grad_norm": 30671.853515625,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 48.0764,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.04869287567351826,
884
+ "grad_norm": 62980.0859375,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 52.5336,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.04909199760526841,
891
+ "grad_norm": 36415.1015625,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 57.152,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.04949111953701856,
898
+ "grad_norm": 53034.4296875,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 53.2671,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.049890241468768706,
905
+ "grad_norm": 41480.47265625,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 59.2209,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.05028936340051886,
912
+ "grad_norm": 52756.0390625,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 59.0244,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.05068848533226901,
919
+ "grad_norm": 58621.4609375,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 62.4222,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.05108760726401916,
926
+ "grad_norm": 34545.16015625,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 56.1123,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.051486729195769305,
933
+ "grad_norm": 57221.70703125,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 56.5079,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.05188585112751946,
940
+ "grad_norm": 33589.03515625,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 61.1767,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.05228497305926961,
947
+ "grad_norm": 34117.0234375,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 52.1322,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.05268409499101975,
954
+ "grad_norm": 50370.43359375,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 58.2877,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.053083216922769905,
961
+ "grad_norm": 56908.3359375,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 60.1616,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.053482338854520056,
968
+ "grad_norm": 48866.3984375,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 58.2007,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.05388146078627021,
975
+ "grad_norm": 39187.26171875,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 58.7294,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.05428058271802035,
982
+ "grad_norm": 26180.66015625,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 67.5557,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.054679704649770504,
989
+ "grad_norm": 213279.390625,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 69.8095,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.055078826581520655,
996
+ "grad_norm": 72242.5625,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 75.8229,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.05547794851327081,
1003
+ "grad_norm": 69482.5546875,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 63.0787,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.05587707044502095,
1010
+ "grad_norm": 62033.5390625,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 58.8768,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.0562761923767711,
1017
+ "grad_norm": 29750.419921875,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 72.2296,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.056675314308521255,
1024
+ "grad_norm": 49227.828125,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 77.8471,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.057074436240271406,
1031
+ "grad_norm": 88195.8671875,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 65.1452,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.05747355817202155,
1038
+ "grad_norm": 70083.7421875,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 51.9114,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.0578726801037717,
1045
+ "grad_norm": 32487.505859375,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 55.1692,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.058271802035521854,
1052
+ "grad_norm": 46871.6484375,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 51.7074,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.058670923967272,
1059
+ "grad_norm": 60043.66015625,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 61.5072,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.05907004589902215,
1066
+ "grad_norm": 52521.32421875,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 57.5619,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.0594691678307723,
1073
+ "grad_norm": 50972.00390625,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 61.5767,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.05986828976252245,
1080
+ "grad_norm": 49810.4375,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 80.1615,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.05986828976252245,
1087
+ "eval_loss": 14.149837493896484,
1088
+ "eval_runtime": 14.8445,
1089
+ "eval_samples_per_second": 284.281,
1090
+ "eval_steps_per_second": 71.07,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1417222840909824.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null