0x1202 commited on
Commit
9a5cbc7
·
verified ·
1 Parent(s): c1ef673

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 sha256:76b40a39146d0817313d589bc304460174fdb93fc58ee8b390adf4e0f2dbece2
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d350e187c7fa531f38fb7c639017e0dc3ea91fbd153b61e9086a70693d68a3b7
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ef7e85d5abbbec9f91843d69fb73d3bded66b0f0c8c5dbbdeddf80ca512662b
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b504c862f3f675b6c916812f3cd32399e6ec93e6bfcde65a886aac97ed7261e
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0890005582236f780028dcf538569f4f0aa892b07db901353b441366860363a3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c567fef2c9fdcdfb96e69010e208c4bff7dbda95eea838619aac093ed1b8f867
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": 1.0648125410079956,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.10269576379974327,
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": 13.092,
732
  "eval_steps_per_second": 3.273,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.038415551185608,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.1540436456996149,
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": 13.092,
732
  "eval_steps_per_second": 3.273,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.1037227214377407,
737
+ "grad_norm": 1.3108991384506226,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.9371,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.10474967907573812,
744
+ "grad_norm": 1.371168851852417,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.0909,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10577663671373556,
751
+ "grad_norm": 1.2648215293884277,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.9844,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.10680359435173299,
758
+ "grad_norm": 1.1569675207138062,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.8607,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.10783055198973042,
765
+ "grad_norm": 1.4329310655593872,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.0482,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.10885750962772786,
772
+ "grad_norm": 1.3667007684707642,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.2122,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.10988446726572529,
779
+ "grad_norm": 1.2392832040786743,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.0224,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.11091142490372272,
786
+ "grad_norm": 1.276443600654602,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.943,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.11193838254172016,
793
+ "grad_norm": 1.2456995248794556,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.8238,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.11296534017971759,
800
+ "grad_norm": 1.1732423305511475,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.7917,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.11399229781771501,
807
+ "grad_norm": 1.390889048576355,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.1468,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.11501925545571245,
814
+ "grad_norm": 1.3246679306030273,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.0312,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.11604621309370988,
821
+ "grad_norm": 1.3436546325683594,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.9952,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.11707317073170732,
828
+ "grad_norm": 1.3831197023391724,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.9919,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11810012836970475,
835
+ "grad_norm": 1.3261679410934448,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.0498,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.11912708600770218,
842
+ "grad_norm": 1.2425459623336792,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.8745,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.12015404364569962,
849
+ "grad_norm": 1.4099633693695068,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9697,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.12118100128369705,
856
+ "grad_norm": 1.1804779767990112,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.7732,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.12220795892169448,
863
+ "grad_norm": 1.2373385429382324,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.0115,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.12323491655969192,
870
+ "grad_norm": 1.4665852785110474,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.0504,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.12426187419768935,
877
+ "grad_norm": 1.3025273084640503,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.0018,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.1252888318356868,
884
+ "grad_norm": 1.5236035585403442,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.9602,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.12631578947368421,
891
+ "grad_norm": 1.4784255027770996,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.0923,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12734274711168164,
898
+ "grad_norm": 1.3002736568450928,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.1067,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.12836970474967907,
905
+ "grad_norm": 1.1813057661056519,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.0069,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1293966623876765,
912
+ "grad_norm": 1.4547677040100098,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.34,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.13042362002567395,
919
+ "grad_norm": 1.2443901300430298,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.99,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.13145057766367138,
926
+ "grad_norm": 1.306671380996704,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.0293,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.1324775353016688,
933
+ "grad_norm": 1.114880084991455,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.0155,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.13350449293966624,
940
+ "grad_norm": 1.3259719610214233,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.901,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.13453145057766366,
947
+ "grad_norm": 1.3376728296279907,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.2342,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.1355584082156611,
954
+ "grad_norm": 1.4119170904159546,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.1953,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.13658536585365855,
961
+ "grad_norm": 1.2630945444107056,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.9099,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.13761232349165597,
968
+ "grad_norm": 1.5290549993515015,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.0176,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1386392811296534,
975
+ "grad_norm": 1.2973805665969849,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.8162,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.13966623876765083,
982
+ "grad_norm": 1.369152307510376,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.1737,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.14069319640564826,
989
+ "grad_norm": 1.1779505014419556,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.9875,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1417201540436457,
996
+ "grad_norm": 1.4312304258346558,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.1641,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.14274711168164314,
1003
+ "grad_norm": 1.2555488348007202,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.9312,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.14377406931964057,
1010
+ "grad_norm": 1.1777236461639404,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.0722,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.144801026957638,
1017
+ "grad_norm": 1.284010410308838,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.1465,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.14582798459563542,
1024
+ "grad_norm": 1.186956524848938,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.1312,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.14685494223363285,
1031
+ "grad_norm": 4.312047958374023,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.9123,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.1478818998716303,
1038
+ "grad_norm": 1.267554759979248,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.1334,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.14890885750962773,
1045
+ "grad_norm": 1.4156426191329956,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.2925,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.14993581514762516,
1052
+ "grad_norm": 1.2493308782577515,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.0263,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.1509627727856226,
1059
+ "grad_norm": 1.315033197402954,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.0537,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.15198973042362002,
1066
+ "grad_norm": 1.4786423444747925,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.3493,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.15301668806161745,
1073
+ "grad_norm": 1.4836056232452393,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.4355,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.1540436456996149,
1080
+ "grad_norm": 1.5168051719665527,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.4153,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.1540436456996149,
1087
+ "eval_loss": 1.038415551185608,
1088
+ "eval_runtime": 125.2406,
1089
+ "eval_samples_per_second": 13.095,
1090
+ "eval_steps_per_second": 3.274,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.262770368118784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null