prxy5604 commited on
Commit
5782816
·
verified ·
1 Parent(s): 7b364cc

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:e98197d94beb04485b1ced4d846d5db7dd9007f18505cc356c81ef85c5d00105
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48378430ec16c0752db525687fc4fb6978c4447d8643812b3f02c5d558ec96fa
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59e3b30a2c6fa286adfbc06a3bc30f9b794950dae2adade011393d2fda136d64
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05773acce11973723983ffc7cb453ed7e7d615e67e2f7b899eed6c2bf7e1d026
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2eb54d9422b65487b9adf4351cc6093740a6734a259cab8eca25f1a878ae9e69
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:038626d478a8bfb220729f5769ed605fdc646a8eae9addf708c8cdc891c1e865
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": 0.9521790742874146,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.18467220683287167,
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": 33.973,
732
  "eval_steps_per_second": 8.493,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.7214473068544e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8753308653831482,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.2770083102493075,
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": 33.973,
732
  "eval_steps_per_second": 8.493,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.18651892890120036,
737
+ "grad_norm": 2.9484169483184814,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.6928,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.1883656509695291,
744
+ "grad_norm": 2.832914113998413,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.6209,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.1902123730378578,
751
+ "grad_norm": 2.7512717247009277,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.5693,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.19205909510618652,
758
+ "grad_norm": 2.2781260013580322,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.3867,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.19390581717451524,
765
+ "grad_norm": 1.9715394973754883,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.1605,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.19575253924284394,
772
+ "grad_norm": 1.8479387760162354,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.2648,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.19759926131117267,
779
+ "grad_norm": 1.7128658294677734,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.897,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.1994459833795014,
786
+ "grad_norm": 1.5558643341064453,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.1957,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.2012927054478301,
793
+ "grad_norm": 1.7808852195739746,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.0195,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.20313942751615882,
800
+ "grad_norm": 1.6448242664337158,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.9698,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.20498614958448755,
807
+ "grad_norm": 1.762912392616272,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.9359,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.20683287165281625,
814
+ "grad_norm": 1.6164023876190186,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.862,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.20867959372114497,
821
+ "grad_norm": 1.399998664855957,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.8332,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.21052631578947367,
828
+ "grad_norm": 1.2491146326065063,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.8249,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.2123730378578024,
835
+ "grad_norm": 1.3444939851760864,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.8622,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.21421975992613113,
842
+ "grad_norm": 1.4169225692749023,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.9297,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.21606648199445982,
849
+ "grad_norm": 1.327711582183838,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.7771,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.21791320406278855,
856
+ "grad_norm": 1.5130693912506104,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.8894,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.21975992613111728,
863
+ "grad_norm": 1.3980169296264648,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.852,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.22160664819944598,
870
+ "grad_norm": 1.6896843910217285,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.8649,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.2234533702677747,
877
+ "grad_norm": 1.395660638809204,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.8845,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.22530009233610343,
884
+ "grad_norm": 1.4997771978378296,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.8451,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.22714681440443213,
891
+ "grad_norm": 1.3027374744415283,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.7209,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.22899353647276086,
898
+ "grad_norm": 1.3798420429229736,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.8659,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.23084025854108955,
905
+ "grad_norm": 1.323683738708496,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.7054,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.23268698060941828,
912
+ "grad_norm": 1.3361538648605347,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.7994,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.234533702677747,
919
+ "grad_norm": 1.2838674783706665,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.7547,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.2363804247460757,
926
+ "grad_norm": 1.0206528902053833,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.5486,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.23822714681440443,
933
+ "grad_norm": 1.4088810682296753,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.7922,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.24007386888273316,
940
+ "grad_norm": 1.3763893842697144,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.851,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.24192059095106186,
947
+ "grad_norm": 1.3483628034591675,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.7416,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.24376731301939059,
954
+ "grad_norm": 1.5661169290542603,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.8548,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.24561403508771928,
961
+ "grad_norm": 1.3294544219970703,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.7539,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.247460757156048,
968
+ "grad_norm": 1.202335238456726,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.6675,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.24930747922437674,
975
+ "grad_norm": 1.3698365688323975,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.8311,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.25115420129270544,
982
+ "grad_norm": 1.5249780416488647,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.8796,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.2530009233610342,
989
+ "grad_norm": 1.2364747524261475,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.7238,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.2548476454293629,
996
+ "grad_norm": 1.4082618951797485,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.8461,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.2566943674976916,
1003
+ "grad_norm": 1.446083664894104,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.7075,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.2585410895660203,
1010
+ "grad_norm": 1.318787932395935,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.6941,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.26038781163434904,
1017
+ "grad_norm": 1.4672468900680542,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.702,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.26223453370267774,
1024
+ "grad_norm": 1.389514684677124,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.8292,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.26408125577100644,
1031
+ "grad_norm": 1.4377171993255615,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.7546,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.2659279778393352,
1038
+ "grad_norm": 1.5279029607772827,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.8658,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.2677746999076639,
1045
+ "grad_norm": 1.345630168914795,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.6717,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2696214219759926,
1052
+ "grad_norm": 1.4262079000473022,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.6712,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.27146814404432135,
1059
+ "grad_norm": 1.4003041982650757,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.69,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.27331486611265005,
1066
+ "grad_norm": 1.392295479774475,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.675,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.27516158818097874,
1073
+ "grad_norm": 1.505399227142334,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.5828,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.2770083102493075,
1080
+ "grad_norm": 2.01698637008667,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.8298,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.2770083102493075,
1087
+ "eval_loss": 0.8753308653831482,
1088
+ "eval_runtime": 26.858,
1089
+ "eval_samples_per_second": 33.956,
1090
+ "eval_steps_per_second": 8.489,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.0821709602816e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null