aleegis12 commited on
Commit
beb9e26
·
verified ·
1 Parent(s): d2c8370

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 sha256:05efe6546f28b7d1358002998d6b537aea441bea5dccc5285c93d1a1d6616940
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84ed7f66bdd7ea55c49b014f2f8b4a60dabd919a9fc88b57d164a0a751f50a60
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b4387d27ec6ad16f82cfd0a31c7039bdd23d2a91f25a8f9ed9cb0ebc54dc9b3
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543303ab22547c189f137c7b9d4934a59746f31934abd5b4d4a11afd2eb121e8
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f551e2bd006f5eb91ed31d223f8117d05e31ce7ac3c17f03c96e7fecf981f80
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9373324f8b79a1a36b872f819f02ede0569c5183d2ed0171367941452eb214e6
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": 0.5313294529914856,
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": 21.776,
732
  "eval_steps_per_second": 5.444,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4.267990668489523e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.4755863547325134,
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": 21.776,
732
  "eval_steps_per_second": 5.444,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.003976534509232647,
737
+ "grad_norm": 0.6821577548980713,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.4472,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0040159061380369305,
744
+ "grad_norm": 0.6033506989479065,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.4505,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.004055277766841214,
751
+ "grad_norm": 0.6802194118499756,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.4243,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.004094649395645498,
758
+ "grad_norm": 1.0940698385238647,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.5355,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0041340210244497815,
765
+ "grad_norm": 1.0095839500427246,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.4859,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.004173392653254065,
772
+ "grad_norm": 0.9586552381515503,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.4559,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.004212764282058349,
779
+ "grad_norm": 1.0491364002227783,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.5536,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0042521359108626325,
786
+ "grad_norm": 1.0424336194992065,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.531,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.004291507539666916,
793
+ "grad_norm": 1.1021971702575684,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.4656,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0043308791684712,
800
+ "grad_norm": 1.0408269166946411,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.4715,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0043702507972754835,
807
+ "grad_norm": 1.21599543094635,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.527,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.004409622426079767,
814
+ "grad_norm": 1.0973793268203735,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.4781,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.004448994054884051,
821
+ "grad_norm": 1.0023589134216309,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.3882,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0044883656836883345,
828
+ "grad_norm": 1.0988465547561646,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.4012,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.004527737312492618,
835
+ "grad_norm": 1.2344098091125488,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.4895,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.004567108941296902,
842
+ "grad_norm": 1.0267789363861084,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.4079,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0046064805701011855,
849
+ "grad_norm": 1.1937060356140137,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.4989,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.004645852198905469,
856
+ "grad_norm": 1.0652450323104858,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.4234,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.004685223827709752,
863
+ "grad_norm": 1.1903423070907593,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.3993,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.004724595456514036,
870
+ "grad_norm": 1.204135537147522,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.3806,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.004763967085318319,
877
+ "grad_norm": 1.1541450023651123,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.4245,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.004803338714122603,
884
+ "grad_norm": 1.1386463642120361,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.4182,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.004842710342926887,
891
+ "grad_norm": 1.179220199584961,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.4101,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.00488208197173117,
898
+ "grad_norm": 1.2795960903167725,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.4203,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.004921453600535454,
905
+ "grad_norm": 1.6313341856002808,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.4771,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.004960825229339738,
912
+ "grad_norm": 1.3297889232635498,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.4054,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.005000196858144021,
919
+ "grad_norm": 1.3898698091506958,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.4196,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.005039568486948305,
926
+ "grad_norm": 1.2108392715454102,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.433,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.005078940115752589,
933
+ "grad_norm": 1.320252776145935,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.4027,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.005118311744556872,
940
+ "grad_norm": 1.3441872596740723,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.3871,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.005157683373361156,
947
+ "grad_norm": 1.3732396364212036,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.4692,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.00519705500216544,
954
+ "grad_norm": 1.471716284751892,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.3845,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.005236426630969723,
961
+ "grad_norm": 1.654649019241333,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.4476,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.005275798259774007,
968
+ "grad_norm": 1.314582109451294,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.3975,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.005315169888578291,
975
+ "grad_norm": 1.2855511903762817,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.3836,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.005354541517382574,
982
+ "grad_norm": 1.5129963159561157,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.4548,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.005393913146186858,
989
+ "grad_norm": 1.40498685836792,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.4161,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.005433284774991142,
996
+ "grad_norm": 1.7466362714767456,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.4721,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.005472656403795425,
1003
+ "grad_norm": 1.5604318380355835,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.4564,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.005512028032599709,
1010
+ "grad_norm": 1.6837966442108154,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.4667,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.005551399661403993,
1017
+ "grad_norm": 1.867175579071045,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.4654,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.005590771290208276,
1024
+ "grad_norm": 2.220432758331299,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.4996,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.00563014291901256,
1031
+ "grad_norm": 2.555483341217041,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.6215,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.005669514547816844,
1038
+ "grad_norm": 3.0226290225982666,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.5752,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.005708886176621126,
1045
+ "grad_norm": 2.8674111366271973,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.5822,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.00574825780542541,
1052
+ "grad_norm": 2.833491563796997,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.6672,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.005787629434229694,
1059
+ "grad_norm": 3.3857784271240234,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.7152,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.005827001063033977,
1066
+ "grad_norm": 3.082288980484009,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.622,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.005866372691838261,
1073
+ "grad_norm": 3.570404291152954,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.6337,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.005905744320642545,
1080
+ "grad_norm": 4.106326580047607,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.7418,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.005905744320642545,
1087
+ "eval_loss": 0.4755863547325134,
1088
+ "eval_runtime": 1963.7539,
1089
+ "eval_samples_per_second": 21.784,
1090
+ "eval_steps_per_second": 5.446,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6.391626802082611e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null