aleegis12 commited on
Commit
11324a6
·
verified ·
1 Parent(s): f04dea9

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:e925965e9015b33cd0a4f57c7fd7eca071ff1e64e2881c61c1febfc3bd44ce93
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b423f2f6e992fb0f159d22883e171f3a27d4b38684b7ba4afea258447c563a0e
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8509441a19a3893b87507d5d4509d1241be4f86edaf8c11b09bf977b486b51fd
3
  size 40177764
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f5c1a942f64b6bc607199a1b7a06232bc956dea9d55de1415d106a600f0d56
3
  size 40177764
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84314ce622eda8a744912c7c539021e57c981a84b1c2e88caf16b5c72d3c9ba3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0613f04a72b35dd857868e3a5974a6f8448c7023bdc3cebc462c038b479c5581
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": 3.0662903785705566,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06554153694904145,
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": 72.371,
732
  "eval_steps_per_second": 18.107,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2484536925487104.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.959265947341919,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.09831230542356219,
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": 72.371,
732
  "eval_steps_per_second": 18.107,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.06619695231853187,
737
+ "grad_norm": 0.5797503590583801,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.7928,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.06685236768802229,
744
+ "grad_norm": 0.5867027640342712,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.8934,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0675077830575127,
751
+ "grad_norm": 0.599848210811615,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.9288,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06816319842700311,
758
+ "grad_norm": 0.5558874607086182,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.8666,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06881861379649352,
765
+ "grad_norm": 0.5201577544212341,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.8844,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06947402916598394,
772
+ "grad_norm": 0.4857221245765686,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.9428,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.07012944453547436,
779
+ "grad_norm": 0.44349125027656555,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.8919,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.07078485990496478,
786
+ "grad_norm": 0.4304451644420624,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.9777,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.07144027527445519,
793
+ "grad_norm": 0.3925478756427765,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.9014,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0720956906439456,
800
+ "grad_norm": 0.39188775420188904,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.9235,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07275110601343601,
807
+ "grad_norm": 0.3767489790916443,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.9342,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07340652138292643,
814
+ "grad_norm": 0.34916725754737854,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.9225,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07406193675241685,
821
+ "grad_norm": 0.37465959787368774,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.7852,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.07471735212190726,
828
+ "grad_norm": 0.3955858051776886,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.7985,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.07537276749139768,
835
+ "grad_norm": 0.351371169090271,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.9127,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.07602818286088808,
842
+ "grad_norm": 0.3373568058013916,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.8525,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0766835982303785,
849
+ "grad_norm": 0.3369169235229492,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.9715,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.07733901359986892,
856
+ "grad_norm": 0.3653274178504944,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.9926,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.07799442896935933,
863
+ "grad_norm": 0.331911563873291,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.9772,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.07864984433884975,
870
+ "grad_norm": 0.3112211525440216,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.8594,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07930525970834017,
877
+ "grad_norm": 0.32111674547195435,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 3.021,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.07996067507783057,
884
+ "grad_norm": 0.31633344292640686,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.9381,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.08061609044732099,
891
+ "grad_norm": 0.3191116452217102,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.9036,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0812715058168114,
898
+ "grad_norm": 0.34067416191101074,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.849,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.08192692118630182,
905
+ "grad_norm": 0.32633650302886963,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.9186,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.08258233655579224,
912
+ "grad_norm": 0.34415149688720703,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.7898,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08323775192528265,
919
+ "grad_norm": 0.35801586508750916,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.907,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.08389316729477306,
926
+ "grad_norm": 0.3405115306377411,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.9063,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.08454858266426347,
933
+ "grad_norm": 0.351954847574234,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.9131,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.08520399803375389,
940
+ "grad_norm": 0.3757033944129944,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.9166,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.08585941340324431,
947
+ "grad_norm": 0.4259479343891144,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.8718,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.08651482877273473,
954
+ "grad_norm": 0.4543251395225525,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.9423,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.08717024414222513,
961
+ "grad_norm": 0.46031734347343445,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.9757,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.08782565951171555,
968
+ "grad_norm": 0.4911552667617798,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.9919,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.08848107488120596,
975
+ "grad_norm": 0.5129150748252869,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.8544,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.08913649025069638,
982
+ "grad_norm": 0.5981971621513367,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 3.117,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.0897919056201868,
989
+ "grad_norm": 0.6168267726898193,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.9377,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.09044732098967721,
996
+ "grad_norm": 0.6700790524482727,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 3.0068,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.09110273635916762,
1003
+ "grad_norm": 0.7470929622650146,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 3.0515,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.09175815172865803,
1010
+ "grad_norm": 0.847628116607666,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.1005,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.09241356709814845,
1017
+ "grad_norm": 0.8086853623390198,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.1197,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09306898246763887,
1024
+ "grad_norm": 0.8996236324310303,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 3.1891,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.09372439783712928,
1031
+ "grad_norm": 0.9424350261688232,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.0676,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0943798132066197,
1038
+ "grad_norm": 1.1057404279708862,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.5385,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.0950352285761101,
1045
+ "grad_norm": 1.0299458503723145,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 3.3891,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.09569064394560052,
1052
+ "grad_norm": 1.2174806594848633,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.335,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.09634605931509094,
1059
+ "grad_norm": 1.1211546659469604,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.1145,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.09700147468458135,
1066
+ "grad_norm": 1.2653746604919434,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.2985,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.09765689005407177,
1073
+ "grad_norm": 1.300657033920288,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.1556,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.09831230542356219,
1080
+ "grad_norm": 2.164646863937378,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 3.6047,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.09831230542356219,
1087
+ "eval_loss": 2.959265947341919,
1088
+ "eval_runtime": 35.4732,
1089
+ "eval_samples_per_second": 72.449,
1090
+ "eval_steps_per_second": 18.126,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3732985828343808.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null