0x1202 commited on
Commit
c5c7143
·
verified ·
1 Parent(s): ccab046

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 sha256:8da92725721b38458ca32dafd8083bfe2d6839f5939b02efca87ddfb8ac6c0ac
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff73df5195b6f77314ddeaedbd5d8f78b11f9007dc7e87686a82f2b2267e20cf
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6eddb4e5f6d998040d0cdfc11d65f50f015b89cc4f46ff7af061ed0ae1401baf
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276263ead8d39423e1b3b72ed1f181c42a5c1536f66995dd5e76b3fa08ba58ac
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c40deea57d70afdfe99f0a41940bcedbb2c0a6fdf94ee3ab962726a907f4a492
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eddc50e8769556fb3c3fc95024f774efd158beaeec0fa23d88bdd35a54b267f1
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": 10.342180252075195,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.12578616352201258,
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": 476.796,
732
  "eval_steps_per_second": 119.288,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 11210841391104.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.337943077087402,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.18867924528301888,
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": 476.796,
732
  "eval_steps_per_second": 119.288,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.1270440251572327,
737
+ "grad_norm": 0.16829006373882294,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 10.35,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.12830188679245283,
744
+ "grad_norm": 0.10214440524578094,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 10.3491,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.12955974842767295,
751
+ "grad_norm": 0.08292871713638306,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 10.3482,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.13081761006289308,
758
+ "grad_norm": 0.071856290102005,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 10.3474,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.1320754716981132,
765
+ "grad_norm": 0.07028871774673462,
766
+ "learning_rate": 5e-05,
767
+ "loss": 10.3497,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.13333333333333333,
772
+ "grad_norm": 0.07992203533649445,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 10.3471,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.13459119496855346,
779
+ "grad_norm": 0.07728118449449539,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 10.3506,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.13584905660377358,
786
+ "grad_norm": 0.08815820515155792,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 10.3481,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.1371069182389937,
793
+ "grad_norm": 0.09084111452102661,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 10.3504,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.13836477987421383,
800
+ "grad_norm": 0.09387490153312683,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 10.3465,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.13962264150943396,
807
+ "grad_norm": 0.09231863915920258,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 10.3462,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.14088050314465408,
814
+ "grad_norm": 0.09010244160890579,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 10.3449,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.1421383647798742,
821
+ "grad_norm": 0.0757468119263649,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 10.3406,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.14339622641509434,
828
+ "grad_norm": 0.06914759427309036,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 10.3429,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.14465408805031446,
835
+ "grad_norm": 0.06821081787347794,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 10.3403,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.1459119496855346,
842
+ "grad_norm": 0.0743262767791748,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 10.3445,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.1471698113207547,
849
+ "grad_norm": 0.07690567523241043,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 10.3432,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.14842767295597484,
856
+ "grad_norm": 0.062463872134685516,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 10.3418,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.14968553459119496,
863
+ "grad_norm": 0.06534265726804733,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 10.3406,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.1509433962264151,
870
+ "grad_norm": 0.06799394637346268,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 10.3435,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.15220125786163521,
877
+ "grad_norm": 0.07413194328546524,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 10.3407,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.15345911949685534,
884
+ "grad_norm": 0.06097736954689026,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 10.3412,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.15471698113207547,
891
+ "grad_norm": 0.07089071720838547,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 10.3405,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.1559748427672956,
898
+ "grad_norm": 0.07079850137233734,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 10.3408,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.15723270440251572,
905
+ "grad_norm": 0.0693952664732933,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 10.3398,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.15849056603773584,
912
+ "grad_norm": 0.0659995824098587,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 10.3411,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.15974842767295597,
919
+ "grad_norm": 0.06219927966594696,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 10.3386,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.1610062893081761,
926
+ "grad_norm": 0.07468194514513016,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 10.3363,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.16226415094339622,
933
+ "grad_norm": 0.07858281582593918,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 10.3408,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.16352201257861634,
940
+ "grad_norm": 0.08168749511241913,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 10.3399,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.16477987421383647,
947
+ "grad_norm": 0.07804001122713089,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 10.339,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.1660377358490566,
954
+ "grad_norm": 0.0697825625538826,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 10.3375,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.16729559748427672,
961
+ "grad_norm": 0.06571916490793228,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 10.3361,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.16855345911949685,
968
+ "grad_norm": 0.06645193696022034,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 10.3366,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.16981132075471697,
975
+ "grad_norm": 0.06530148535966873,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 10.337,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.1710691823899371,
982
+ "grad_norm": 0.07109314203262329,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 10.3328,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.17232704402515722,
989
+ "grad_norm": 0.0944875180721283,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 10.3338,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.17358490566037735,
996
+ "grad_norm": 0.0718129575252533,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 10.3356,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.17484276729559747,
1003
+ "grad_norm": 0.076311856508255,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 10.3356,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.1761006289308176,
1010
+ "grad_norm": 0.07428840547800064,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 10.3343,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.17735849056603772,
1017
+ "grad_norm": 0.07271865755319595,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 10.3349,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.17861635220125785,
1024
+ "grad_norm": 0.07106521725654602,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 10.3327,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.17987421383647798,
1031
+ "grad_norm": 0.094117172062397,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 10.3336,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.1811320754716981,
1038
+ "grad_norm": 0.06027039885520935,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 10.3339,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.18238993710691823,
1045
+ "grad_norm": 0.1071876809000969,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 10.331,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.18364779874213835,
1052
+ "grad_norm": 0.08291321247816086,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 10.3309,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.18490566037735848,
1059
+ "grad_norm": 0.08659283071756363,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 10.329,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.1861635220125786,
1066
+ "grad_norm": 0.07780143618583679,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 10.329,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.18742138364779873,
1073
+ "grad_norm": 0.09116362035274506,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 10.3259,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.18867924528301888,
1080
+ "grad_norm": 0.15961508452892303,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 10.3215,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.18867924528301888,
1087
+ "eval_loss": 10.337943077087402,
1088
+ "eval_runtime": 2.8074,
1089
+ "eval_samples_per_second": 476.954,
1090
+ "eval_steps_per_second": 119.328,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 16816262086656.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null