prxy5604 commited on
Commit
a67605c
·
verified ·
1 Parent(s): cec1ad9

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:e8d8ca7b23a1c428af793a87a537ac9d3f23b95daa686a75a7c00f0500ff079d
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a7b0228145b0e49860b0e490b08592876214e35f2a94cd2906ce2cdb67ed6c8
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7edafa7c43ad59f03c50520d727154931ffd64527eadafa202a7e11508f1313e
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd22263dcfe519afb65cb2dcdd5ac1ed02c8f77caefa15015748debeb7a485f9
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:d0e31e37afd19c26fe63a4fe0cf95fe7e01d072d7e4539409bdd070401a42711
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc00561cd4720a7fdc452dd553b5c79b6374e5de7745330ad27423d6c6f228d7
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": 1.5963640213012695,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.14245014245014245,
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": 22.412,
732
  "eval_steps_per_second": 5.613,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4.154039461321114e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.34799063205719,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.21367521367521367,
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": 22.412,
732
  "eval_steps_per_second": 5.613,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.14387464387464388,
737
+ "grad_norm": 1.4451898336410522,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.0918,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.1452991452991453,
744
+ "grad_norm": 1.5431982278823853,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.3001,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.1467236467236467,
751
+ "grad_norm": 1.4764037132263184,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.3387,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.14814814814814814,
758
+ "grad_norm": 1.3215073347091675,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.3939,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.14957264957264957,
765
+ "grad_norm": 0.9795156121253967,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.195,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.150997150997151,
772
+ "grad_norm": 0.8231992721557617,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.2011,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.15242165242165243,
779
+ "grad_norm": 0.7669458985328674,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.2633,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.15384615384615385,
786
+ "grad_norm": 0.7166056632995605,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.1905,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.15527065527065528,
793
+ "grad_norm": 0.6721870303153992,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.1175,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.15669515669515668,
800
+ "grad_norm": 0.6732422709465027,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.1489,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.1581196581196581,
807
+ "grad_norm": 0.658916175365448,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.1334,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.15954415954415954,
814
+ "grad_norm": 0.6812751889228821,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.1186,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.16096866096866097,
821
+ "grad_norm": 0.7162421941757202,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.1049,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.1623931623931624,
828
+ "grad_norm": 0.7175534963607788,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.0275,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.16381766381766383,
835
+ "grad_norm": 0.8070324659347534,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.1026,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.16524216524216523,
842
+ "grad_norm": 0.7852011322975159,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.0646,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.16666666666666666,
849
+ "grad_norm": 0.8045965433120728,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9373,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.16809116809116809,
856
+ "grad_norm": 0.8931590914726257,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.1565,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.16951566951566951,
863
+ "grad_norm": 0.9178715348243713,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.0861,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.17094017094017094,
870
+ "grad_norm": 1.0241934061050415,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.1994,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.17236467236467237,
877
+ "grad_norm": 1.0514984130859375,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.0728,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.1737891737891738,
884
+ "grad_norm": 1.114422082901001,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.12,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.1752136752136752,
891
+ "grad_norm": 1.0793527364730835,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.0203,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.17663817663817663,
898
+ "grad_norm": 1.1782469749450684,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.1031,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.17806267806267806,
905
+ "grad_norm": 1.4030028581619263,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.0422,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1794871794871795,
912
+ "grad_norm": 1.6754884719848633,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.1101,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.18091168091168092,
919
+ "grad_norm": 1.6748223304748535,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.9788,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.18233618233618235,
926
+ "grad_norm": 2.2540535926818848,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.132,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.18376068376068377,
933
+ "grad_norm": 2.2037203311920166,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.0734,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.18518518518518517,
940
+ "grad_norm": 2.2696244716644287,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.0225,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1866096866096866,
947
+ "grad_norm": 2.606853723526001,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.3488,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.18803418803418803,
954
+ "grad_norm": 3.2537319660186768,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.2927,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.18945868945868946,
961
+ "grad_norm": 2.4283738136291504,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.1179,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1908831908831909,
968
+ "grad_norm": 2.3190572261810303,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.2731,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.19230769230769232,
975
+ "grad_norm": 2.494070291519165,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.2296,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.19373219373219372,
982
+ "grad_norm": 2.373368740081787,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.6222,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.19515669515669515,
989
+ "grad_norm": 2.0916032791137695,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.3034,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.19658119658119658,
996
+ "grad_norm": 2.3026416301727295,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.8082,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.198005698005698,
1003
+ "grad_norm": 2.6751773357391357,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.1713,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.19943019943019943,
1010
+ "grad_norm": 3.263648748397827,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.9226,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.20085470085470086,
1017
+ "grad_norm": 2.890190839767456,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.9661,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.2022792022792023,
1024
+ "grad_norm": 3.3623650074005127,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.9155,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.2037037037037037,
1031
+ "grad_norm": 3.7464234828948975,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.2982,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.20512820512820512,
1038
+ "grad_norm": 3.9489314556121826,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.0735,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.20655270655270655,
1045
+ "grad_norm": 4.435914993286133,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.0603,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.20797720797720798,
1052
+ "grad_norm": 5.1594743728637695,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.2006,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2094017094017094,
1059
+ "grad_norm": 4.007395267486572,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.056,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.21082621082621084,
1066
+ "grad_norm": 5.316275119781494,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.989,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.21225071225071226,
1073
+ "grad_norm": 5.518270015716553,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.973,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.21367521367521367,
1080
+ "grad_norm": 5.537274360656738,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.084,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.21367521367521367,
1087
+ "eval_loss": 1.34799063205719,
1088
+ "eval_runtime": 52.7878,
1089
+ "eval_samples_per_second": 22.392,
1090
+ "eval_steps_per_second": 5.607,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6.236238792307507e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null