aleegis11 commited on
Commit
f9361bc
·
verified ·
1 Parent(s): bf5d3c5

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 sha256:0515274a86def9a46e20cebf981638d68a21e747f39a75bc7b92be6288fc0476
3
  size 72936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0df1308de9fa455193963ae61ccaac30a005f2c93702eaaf3662c7362e9ddc04
3
  size 72936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5537fa7ece3a03bdac328ba0408d4c844403b4c0e34d9fa8f02779fd59d282d5
3
  size 151106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb65bdb81b9892a658122e3e780f56942f66a7a21e21ea2c07fe8f2f5679121
3
  size 151106
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5088160b715ae7c74bda613669dd1cd97290071ca5a047558762e22faf3b8e6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f46373c4cc269d6c7ad14830073ef0e3edcee0b09e55c84ff148f33b52fdc04
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": 12.41977310180664,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.0810810810810811,
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": 130.915,
732
  "eval_steps_per_second": 32.729,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 389884477440.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 12.404990196228027,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.6216216216216215,
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": 130.915,
732
  "eval_steps_per_second": 32.729,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.0918918918918918,
737
+ "grad_norm": 0.14122404158115387,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 12.2385,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.1027027027027028,
744
+ "grad_norm": 0.12666131556034088,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 12.5226,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.1135135135135135,
751
+ "grad_norm": 0.13096508383750916,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 12.4097,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.1243243243243244,
758
+ "grad_norm": 0.1371913105249405,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 12.4364,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.135135135135135,
765
+ "grad_norm": 0.1272585690021515,
766
+ "learning_rate": 5e-05,
767
+ "loss": 12.2685,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.145945945945946,
772
+ "grad_norm": 0.13281095027923584,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 12.6525,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.1567567567567567,
779
+ "grad_norm": 0.13233084976673126,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 12.41,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.1675675675675676,
786
+ "grad_norm": 0.12595127522945404,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 12.3187,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.1783783783783783,
793
+ "grad_norm": 0.13262464106082916,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 12.3318,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.1891891891891893,
800
+ "grad_norm": 0.1319066882133484,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 12.3832,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.2,
807
+ "grad_norm": 0.13990837335586548,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 12.5546,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.2108108108108109,
814
+ "grad_norm": 0.15222130715847015,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 12.4865,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.2216216216216216,
821
+ "grad_norm": 0.13759095966815948,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 12.5329,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.2324324324324325,
828
+ "grad_norm": 0.1364748626947403,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 12.6826,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.2432432432432432,
835
+ "grad_norm": 0.15113554894924164,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 13.3067,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.2540540540540541,
842
+ "grad_norm": 0.11874595284461975,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 11.168,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.2648648648648648,
849
+ "grad_norm": 0.12837743759155273,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 12.5186,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.2756756756756757,
856
+ "grad_norm": 0.1281714290380478,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 12.1515,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.2864864864864864,
863
+ "grad_norm": 0.134039968252182,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 12.5158,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.2972972972972974,
870
+ "grad_norm": 0.12987154722213745,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 12.3258,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.308108108108108,
877
+ "grad_norm": 0.13608668744564056,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 12.4378,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.318918918918919,
884
+ "grad_norm": 0.12630510330200195,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 12.3976,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.3297297297297297,
891
+ "grad_norm": 0.1412682980298996,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 12.3064,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.3405405405405406,
898
+ "grad_norm": 0.13499215245246887,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 12.4562,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.3513513513513513,
905
+ "grad_norm": 0.13783645629882812,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 12.6002,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.3621621621621622,
912
+ "grad_norm": 0.13830523192882538,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 12.3276,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.372972972972973,
919
+ "grad_norm": 0.13799597322940826,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 12.4436,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.3837837837837839,
926
+ "grad_norm": 0.1256716549396515,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 12.3124,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.3945945945945946,
933
+ "grad_norm": 0.14087165892124176,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 12.2521,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.4054054054054055,
940
+ "grad_norm": 0.12737415730953217,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 12.621,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.4162162162162162,
947
+ "grad_norm": 0.13399814069271088,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 12.3941,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.427027027027027,
954
+ "grad_norm": 0.14206911623477936,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 12.5091,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.4378378378378378,
961
+ "grad_norm": 0.13293571770191193,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 12.201,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.4486486486486487,
968
+ "grad_norm": 0.1295592039823532,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 12.2648,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.4594594594594594,
975
+ "grad_norm": 0.14292557537555695,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 12.7591,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.4702702702702704,
982
+ "grad_norm": 0.13217291235923767,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 12.1812,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.481081081081081,
989
+ "grad_norm": 0.13620240986347198,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 12.6606,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.491891891891892,
996
+ "grad_norm": 0.1551385223865509,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 13.6809,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.5027027027027027,
1003
+ "grad_norm": 0.12075534462928772,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 11.1072,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.5135135135135136,
1010
+ "grad_norm": 0.13305996358394623,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 12.6012,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.5243243243243243,
1017
+ "grad_norm": 0.13277041912078857,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 12.2127,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.535135135135135,
1024
+ "grad_norm": 0.13404038548469543,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 12.2417,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.545945945945946,
1031
+ "grad_norm": 0.1381426900625229,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 12.3441,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.5567567567567568,
1038
+ "grad_norm": 0.13211677968502045,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 12.4459,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.5675675675675675,
1045
+ "grad_norm": 0.14307326078414917,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 12.5049,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.5783783783783782,
1052
+ "grad_norm": 0.12959998846054077,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 12.2587,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.5891891891891892,
1059
+ "grad_norm": 0.13357719779014587,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 12.4177,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.6,
1066
+ "grad_norm": 0.13592791557312012,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 12.7112,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.6108108108108108,
1073
+ "grad_norm": 0.1253482550382614,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 11.9976,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.6216216216216215,
1080
+ "grad_norm": 0.13077537715435028,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 12.4394,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.6216216216216215,
1087
+ "eval_loss": 12.404990196228027,
1088
+ "eval_runtime": 1.2008,
1089
+ "eval_samples_per_second": 129.913,
1090
+ "eval_steps_per_second": 32.478,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 584645935104.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null