aleegis12 commited on
Commit
3137be0
·
verified ·
1 Parent(s): 9587bfd

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:d4cc5725855a18ad58bf29989cb19260a2cccb74d619d9dac418e17a1a2d6a61
3
  size 406863720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf1ca49fb6dc41ffa323a2e24865257f881d8e9ece5b84c336ff32fbdb5f1a35
3
  size 406863720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b491bba7ad5655f4192de1e79e1be9967049139e8885e2e0d44a4d14ef79b211
3
  size 207013892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee9b74f38871d313f1a6f68d677d3d346123b408323ea3625f087c5cd78e21f
3
  size 207013892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b6d12920d34bbbddfed84ee3c0293843b273c2232647c594011490f09b9c86f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1fab577470f5839d21bb8d9e1427036de79188f8962aa180a56ba53b63aecf4
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": 0.36916714906692505,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.003937162880428363,
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": 21.523,
732
  "eval_steps_per_second": 5.381,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7.223665228775424e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3278917670249939,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.005905744320642545,
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": 21.523,
732
  "eval_steps_per_second": 5.381,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.003976534509232647,
737
+ "grad_norm": 0.2698248624801636,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.3903,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0040159061380369305,
744
+ "grad_norm": 0.25083526968955994,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.361,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.004055277766841214,
751
+ "grad_norm": 0.24954238533973694,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.3741,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.004094649395645498,
758
+ "grad_norm": 0.3203243613243103,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.354,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0041340210244497815,
765
+ "grad_norm": 0.28686997294425964,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.3327,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.004173392653254065,
772
+ "grad_norm": 0.26731210947036743,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.3667,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.004212764282058349,
779
+ "grad_norm": 0.21260957419872284,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.3509,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0042521359108626325,
786
+ "grad_norm": 0.19314557313919067,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.3412,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.004291507539666916,
793
+ "grad_norm": 0.1857222020626068,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.3341,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0043308791684712,
800
+ "grad_norm": 0.1851547658443451,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.3304,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0043702507972754835,
807
+ "grad_norm": 0.17488974332809448,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.3413,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.004409622426079767,
814
+ "grad_norm": 0.1782592386007309,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.327,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.004448994054884051,
821
+ "grad_norm": 0.18713821470737457,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.333,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0044883656836883345,
828
+ "grad_norm": 0.18218685686588287,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.3255,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.004527737312492618,
835
+ "grad_norm": 0.17883919179439545,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.3057,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.004567108941296902,
842
+ "grad_norm": 0.19183780252933502,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.3426,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0046064805701011855,
849
+ "grad_norm": 0.18949471414089203,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.3071,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.004645852198905469,
856
+ "grad_norm": 0.2053540199995041,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.3475,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.004685223827709752,
863
+ "grad_norm": 0.1862872689962387,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.3215,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.004724595456514036,
870
+ "grad_norm": 0.1784752458333969,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.3118,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.004763967085318319,
877
+ "grad_norm": 0.2016214281320572,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.3161,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.004803338714122603,
884
+ "grad_norm": 0.19396907091140747,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.3351,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.004842710342926887,
891
+ "grad_norm": 0.19207337498664856,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.3283,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.00488208197173117,
898
+ "grad_norm": 0.19837477803230286,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.3095,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.004921453600535454,
905
+ "grad_norm": 0.2044375091791153,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.3175,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.004960825229339738,
912
+ "grad_norm": 0.19916394352912903,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.3109,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.005000196858144021,
919
+ "grad_norm": 0.20544566214084625,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.3271,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.005039568486948305,
926
+ "grad_norm": 0.20632264018058777,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.2933,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.005078940115752589,
933
+ "grad_norm": 0.21720726788043976,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.2933,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.005118311744556872,
940
+ "grad_norm": 0.22517623007297516,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.3044,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.005157683373361156,
947
+ "grad_norm": 0.2334209382534027,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.3146,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.00519705500216544,
954
+ "grad_norm": 0.2260541021823883,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.298,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.005236426630969723,
961
+ "grad_norm": 0.25719016790390015,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.335,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.005275798259774007,
968
+ "grad_norm": 0.25886377692222595,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.3031,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.005315169888578291,
975
+ "grad_norm": 0.2470293641090393,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.3037,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.005354541517382574,
982
+ "grad_norm": 0.28103408217430115,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.3125,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.005393913146186858,
989
+ "grad_norm": 0.28059205412864685,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.2969,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.005433284774991142,
996
+ "grad_norm": 0.28502798080444336,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.3268,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.005472656403795425,
1003
+ "grad_norm": 0.31838536262512207,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.3314,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.005512028032599709,
1010
+ "grad_norm": 0.33839502930641174,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.3107,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.005551399661403993,
1017
+ "grad_norm": 0.3526189923286438,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.3015,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.005590771290208276,
1024
+ "grad_norm": 0.39796969294548035,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.3616,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.00563014291901256,
1031
+ "grad_norm": 0.46527615189552307,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.3218,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.005669514547816844,
1038
+ "grad_norm": 0.5111784338951111,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.3397,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.005708886176621126,
1045
+ "grad_norm": 0.5502793192863464,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.3911,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.00574825780542541,
1052
+ "grad_norm": 0.545826256275177,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.3407,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.005787629434229694,
1059
+ "grad_norm": 0.5801648497581482,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.3376,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.005827001063033977,
1066
+ "grad_norm": 0.7802667617797852,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.4137,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.005866372691838261,
1073
+ "grad_norm": 0.85842365026474,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.4084,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.005905744320642545,
1080
+ "grad_norm": 1.3954704999923706,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.4737,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.005905744320642545,
1087
+ "eval_loss": 0.3278917670249939,
1088
+ "eval_runtime": 1988.7296,
1089
+ "eval_samples_per_second": 21.51,
1090
+ "eval_steps_per_second": 5.378,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.0793401891946496e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null