prxy5607 commited on
Commit
18d65c1
·
verified ·
1 Parent(s): 40bba6b

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 sha256:8bb7c2b14470cd6ed3c60d51046b554d19b6d5f16c95bd7e5965ce2ced7c108d
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257056b7c02a9d2eb76e3d8e1aee8e2c5fce051f8107b7e70e2bfa6c1a7b7dd2
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e575fa360c9770ee6ce43c08f2e73b9867c145c3ce9d5e2c73dc6b2e2711a5d
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc297e09224403f7e5383cfa51ea6923fead8d2090d66996425a705cfe7387a8
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3dd3db0c7b9171bc9d75832dcd0835be502b496a6170dca2fc0ea34c4cb38a9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:525b40c4e514fabb8fb880a53a6e88bc04a5e8cae26ff9c7d218974f852254d7
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": 2.4707589149475098,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.2274019329164298,
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": 13.787,
732
  "eval_steps_per_second": 3.461,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4432170156228608e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.341630697250366,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.34110289937464466,
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": 13.787,
732
  "eval_steps_per_second": 3.461,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.2296759522455941,
737
+ "grad_norm": 1.3073029518127441,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.37,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.23194997157475838,
744
+ "grad_norm": 1.3657740354537964,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.3999,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.23422399090392268,
751
+ "grad_norm": 1.253461480140686,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.3091,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.23649801023308697,
758
+ "grad_norm": 1.0211058855056763,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.3138,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.23877202956225127,
765
+ "grad_norm": 0.8298658728599548,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.0126,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.24104604889141557,
772
+ "grad_norm": 0.7955043911933899,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.2312,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.2433200682205799,
779
+ "grad_norm": 0.6754152774810791,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.0947,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.24559408754974418,
786
+ "grad_norm": 0.6781653761863708,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.0386,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.24786810687890848,
793
+ "grad_norm": 0.6811093688011169,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.0824,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.25014212620807275,
800
+ "grad_norm": 0.8755627870559692,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.2296,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.25241614553723707,
807
+ "grad_norm": 0.829145610332489,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.361,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.2546901648664014,
814
+ "grad_norm": 0.7885571122169495,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.138,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.25696418419556566,
821
+ "grad_norm": 0.6788994669914246,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.0723,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.25923820352473,
828
+ "grad_norm": 0.7365356683731079,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.3084,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.26151222285389425,
835
+ "grad_norm": 0.7680405378341675,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.1175,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.2637862421830586,
842
+ "grad_norm": 0.8954876065254211,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.0908,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.26606026151222284,
849
+ "grad_norm": 0.8231341242790222,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.2758,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.26833428084138716,
856
+ "grad_norm": 0.7816740274429321,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.3994,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.27060830017055143,
863
+ "grad_norm": 0.7686096429824829,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.367,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.27288231949971575,
870
+ "grad_norm": 0.8274964690208435,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.3618,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.27515633882888,
877
+ "grad_norm": 0.8358203172683716,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.1838,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.27743035815804434,
884
+ "grad_norm": 1.0523433685302734,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.4431,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.27970437748720867,
891
+ "grad_norm": 0.8998702168464661,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.5009,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.28197839681637293,
898
+ "grad_norm": 0.8731322884559631,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.3193,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.28425241614553726,
905
+ "grad_norm": 0.9921669363975525,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.4642,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.2865264354747015,
912
+ "grad_norm": 0.9523817896842957,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.2686,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.28880045480386585,
919
+ "grad_norm": 0.9201560020446777,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.3529,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.2910744741330301,
926
+ "grad_norm": 1.007020354270935,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.2531,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.29334849346219444,
933
+ "grad_norm": 0.9516400694847107,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.2752,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.2956225127913587,
940
+ "grad_norm": 0.9625292420387268,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.286,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.297896532120523,
947
+ "grad_norm": 0.9690910577774048,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.3002,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.3001705514496873,
954
+ "grad_norm": 0.9300558567047119,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.3713,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.3024445707788516,
961
+ "grad_norm": 1.0282573699951172,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.4672,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.30471859010801594,
968
+ "grad_norm": 1.1509264707565308,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.5568,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.3069926094371802,
975
+ "grad_norm": 1.0650074481964111,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.6764,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.30926662876634453,
982
+ "grad_norm": 1.258753776550293,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.2947,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.3115406480955088,
989
+ "grad_norm": 1.158823847770691,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.2928,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.3138146674246731,
996
+ "grad_norm": 1.1734964847564697,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.4324,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.3160886867538374,
1003
+ "grad_norm": 1.3184300661087036,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.3776,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.3183627060830017,
1010
+ "grad_norm": 1.259461760520935,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.7089,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.320636725412166,
1017
+ "grad_norm": 1.4400967359542847,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.3936,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.3229107447413303,
1024
+ "grad_norm": 1.4404484033584595,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.6887,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.3251847640704946,
1031
+ "grad_norm": 1.6879733800888062,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.7207,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.3274587833996589,
1038
+ "grad_norm": 1.8530641794204712,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.6506,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.3297328027288232,
1045
+ "grad_norm": 1.977170467376709,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.6748,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.3320068220579875,
1052
+ "grad_norm": 2.2924273014068604,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.463,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.3342808413871518,
1059
+ "grad_norm": 2.352557420730591,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.8491,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.3365548607163161,
1066
+ "grad_norm": 2.775940418243408,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.1364,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.3388288800454804,
1073
+ "grad_norm": 4.207704544067383,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.5829,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.34110289937464466,
1080
+ "grad_norm": 8.697121620178223,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 3.9042,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.34110289937464466,
1087
+ "eval_loss": 2.341630697250366,
1088
+ "eval_runtime": 54.0251,
1089
+ "eval_samples_per_second": 13.716,
1090
+ "eval_steps_per_second": 3.443,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.1648255234342912e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null