prxy5608 commited on
Commit
c7c5ebc
·
verified ·
1 Parent(s): fd6601c

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 sha256:38d02d1ee0d4f11502c3709af77d01ebcb0b93981eea36f960ad037196c13e1b
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2653b9b56bfc9057a5d2244607777443b7d1b9cec45f3da19764bb1e240cc767
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31a2fcd5bde721a716e5268bd51c98e46681afece65262bbf3049f14526b54a7
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69c0b99b9203aba346df2a2cf4fb7ba18760a072984d06f802878dc910110245
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af2e58bb47b2e4e0001041dc3a8d1b12ebef229d5783d4a18e98a6b321b056d5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db9f622c82a1c2d65efd555c42e5d372d5e39460ea75ae9daac899e9623656dc
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": 1.5353269577026367,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.03374957813027337,
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": 33.914,
732
  "eval_steps_per_second": 8.482,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.728250925121536e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5126420259475708,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.05062436719541006,
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": 33.914,
732
  "eval_steps_per_second": 8.482,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.03408707391157611,
737
+ "grad_norm": 1.4249728918075562,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.293,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.03442456969287884,
744
+ "grad_norm": 1.43645179271698,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.5217,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.03476206547418157,
751
+ "grad_norm": 1.549728512763977,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.6349,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.03509956125548431,
758
+ "grad_norm": 1.386811375617981,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.5743,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03543705703678704,
765
+ "grad_norm": 1.32630455493927,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.385,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.03577455281808977,
772
+ "grad_norm": 1.1966615915298462,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.1981,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.03611204859939251,
779
+ "grad_norm": 1.3795210123062134,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.4195,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.03644954438069524,
786
+ "grad_norm": 1.3812130689620972,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.3496,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03678704016199798,
793
+ "grad_norm": 1.5323227643966675,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.6077,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.03712453594330071,
800
+ "grad_norm": 1.5685880184173584,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.5661,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03746203172460344,
807
+ "grad_norm": 1.2461915016174316,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.3674,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.03779952750590618,
814
+ "grad_norm": 1.4735571146011353,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.4838,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.03813702328720891,
821
+ "grad_norm": 1.2594475746154785,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.2772,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.038474519068511646,
828
+ "grad_norm": 1.355596899986267,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.5189,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03881201484981438,
835
+ "grad_norm": 1.5534967184066772,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.478,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03914951063111711,
842
+ "grad_norm": 1.2867431640625,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.3196,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.039487006412419846,
849
+ "grad_norm": 1.7533015012741089,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.9202,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.03982450219372258,
856
+ "grad_norm": 1.3565618991851807,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.4292,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.040161997975025315,
863
+ "grad_norm": 1.397993803024292,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.6807,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.040499493756328046,
870
+ "grad_norm": 1.3319307565689087,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.5143,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.04083698953763078,
877
+ "grad_norm": 1.321202278137207,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.3522,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.041174485318933515,
884
+ "grad_norm": 1.4271525144577026,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.5424,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.041511981100236246,
891
+ "grad_norm": 1.3564966917037964,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.7958,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.041849476881538984,
898
+ "grad_norm": 1.2295968532562256,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.4234,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.042186972662841715,
905
+ "grad_norm": 1.4020897150039673,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.4671,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.042524468444144446,
912
+ "grad_norm": 1.62809419631958,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.8034,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.042861964225447184,
919
+ "grad_norm": 1.267198085784912,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.4299,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.043199460006749915,
926
+ "grad_norm": 1.31877601146698,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.551,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.043536955788052646,
933
+ "grad_norm": 1.3092563152313232,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.4684,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.043874451569355384,
940
+ "grad_norm": 1.5711746215820312,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.2988,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.044211947350658115,
947
+ "grad_norm": 1.3491564989089966,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.4796,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.04454944313196085,
954
+ "grad_norm": 1.4088948965072632,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.4395,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.044886938913263584,
961
+ "grad_norm": 1.2712147235870361,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.4685,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.045224434694566315,
968
+ "grad_norm": 1.2743107080459595,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.3902,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.04556193047586905,
975
+ "grad_norm": 1.3566430807113647,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.518,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.045899426257171784,
982
+ "grad_norm": 1.4612895250320435,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.5552,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.04623692203847452,
989
+ "grad_norm": 1.4626133441925049,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.5718,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.04657441781977725,
996
+ "grad_norm": 1.3682875633239746,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.3619,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.046911913601079984,
1003
+ "grad_norm": 1.4876656532287598,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.5829,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.04724940938238272,
1010
+ "grad_norm": 1.537940502166748,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.5279,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.04758690516368545,
1017
+ "grad_norm": 1.0990314483642578,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.1876,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.04792440094498819,
1024
+ "grad_norm": 1.5663527250289917,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.7232,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.04826189672629092,
1031
+ "grad_norm": 1.3516157865524292,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.5107,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.04859939250759365,
1038
+ "grad_norm": 1.4804091453552246,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.4559,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.04893688828889639,
1045
+ "grad_norm": 1.5756516456604004,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.5922,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.04927438407019912,
1052
+ "grad_norm": 1.319180965423584,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.4902,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04961187985150186,
1059
+ "grad_norm": 1.4037140607833862,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.3511,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.04994937563280459,
1066
+ "grad_norm": 1.6963108777999878,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.5755,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.05028687141410732,
1073
+ "grad_norm": 1.6080647706985474,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.6222,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.05062436719541006,
1080
+ "grad_norm": 1.8582013845443726,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.5842,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.05062436719541006,
1087
+ "eval_loss": 1.5126420259475708,
1088
+ "eval_runtime": 147.1818,
1089
+ "eval_samples_per_second": 33.904,
1090
+ "eval_steps_per_second": 8.479,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.088974578548736e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null