prxy5604 commited on
Commit
3520e9b
·
verified ·
1 Parent(s): 41112a8

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:a453118d61d6bfd92fcd7358dcb61d59a1cef301fd71f7e28309a3fd9f94a40e
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f91c8b8ea4d290e4a836d68ceeac006a8d3782043163cadfbbaaa628cf8bd21
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e9c09b267fe320cb44ff08bf57e4c95fc478eee0576d8cb274cb0099ed6fcc9
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be673512acea236170fd1fb221ec410e7b7fe8072a53b9ae44bfe43d0517d4b9
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11a7deb26f719842858a7de6854cce098074e94943e7626ceffa098b093e81e5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41504dcd3e16fe7b8461239f128eaac40e39683a08a3591e3db34b4f3cb1210d
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": 0.3674781024456024,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.008036647110825364,
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": 13.92,
732
  "eval_steps_per_second": 3.481,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4432170156228608e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3388899266719818,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.012054970666238046,
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": 13.92,
732
  "eval_steps_per_second": 3.481,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.008117013581933617,
737
+ "grad_norm": 0.1746017336845398,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.4119,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.00819738005304187,
744
+ "grad_norm": 0.3522207736968994,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.5488,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.008277746524150125,
751
+ "grad_norm": 0.24777081608772278,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.3045,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.008358112995258378,
758
+ "grad_norm": 0.3415620028972626,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.4087,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.008438479466366632,
765
+ "grad_norm": 0.250539630651474,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.3469,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.008518845937474885,
772
+ "grad_norm": 0.31240588426589966,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.3877,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.00859921240858314,
779
+ "grad_norm": 0.29493534564971924,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.3546,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.008679578879691393,
786
+ "grad_norm": 0.24933046102523804,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.3164,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.008759945350799646,
793
+ "grad_norm": 0.3212600350379944,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.4184,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0088403118219079,
800
+ "grad_norm": 0.4264766573905945,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.3748,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.008920678293016154,
807
+ "grad_norm": 0.30657777190208435,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.2886,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.009001044764124408,
814
+ "grad_norm": 0.3119131922721863,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.3675,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.00908141123523266,
821
+ "grad_norm": 0.3247963786125183,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.3164,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.009161777706340914,
828
+ "grad_norm": 0.34584736824035645,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.3701,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.009242144177449169,
835
+ "grad_norm": 0.3761036992073059,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.3521,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.009322510648557422,
842
+ "grad_norm": 0.2861977815628052,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.2289,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.009402877119665675,
849
+ "grad_norm": 0.32266029715538025,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.3258,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.009483243590773929,
856
+ "grad_norm": 0.2621302306652069,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.2928,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.009563610061882184,
863
+ "grad_norm": 0.30788081884384155,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.2959,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.009643976532990437,
870
+ "grad_norm": 0.3848606050014496,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.3143,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.00972434300409869,
877
+ "grad_norm": 0.5152484178543091,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.4244,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.009804709475206943,
884
+ "grad_norm": 0.28096693754196167,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.2511,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.009885075946315196,
891
+ "grad_norm": 0.34794381260871887,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.2989,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.009965442417423451,
898
+ "grad_norm": 0.3060310184955597,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.2905,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.010045808888531705,
905
+ "grad_norm": 0.4070822298526764,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.3016,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.010126175359639958,
912
+ "grad_norm": 0.3588668704032898,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.3573,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.010206541830748211,
919
+ "grad_norm": 0.45010945200920105,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.2986,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.010286908301856466,
926
+ "grad_norm": 0.41504713892936707,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.2613,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.01036727477296472,
933
+ "grad_norm": 0.4334265887737274,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.408,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.010447641244072972,
940
+ "grad_norm": 0.41168826818466187,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.2994,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.010528007715181226,
947
+ "grad_norm": 0.6202244162559509,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.4726,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.01060837418628948,
954
+ "grad_norm": 0.5010877847671509,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.3594,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.010688740657397734,
961
+ "grad_norm": 0.43364813923835754,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.2589,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.010769107128505987,
968
+ "grad_norm": 0.4264422655105591,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.2858,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.01084947359961424,
975
+ "grad_norm": 0.5041791796684265,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.298,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.010929840070722495,
982
+ "grad_norm": 0.5244119167327881,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.3159,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.011010206541830748,
989
+ "grad_norm": 0.5391702651977539,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.4065,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.011090573012939002,
996
+ "grad_norm": 0.5578972101211548,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.4387,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.011170939484047255,
1003
+ "grad_norm": 0.46875637769699097,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.3113,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.01125130595515551,
1010
+ "grad_norm": 0.9138067364692688,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.3789,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.011331672426263763,
1017
+ "grad_norm": 0.4726915955543518,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.2958,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.011412038897372016,
1024
+ "grad_norm": 0.48181626200675964,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.3791,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.01149240536848027,
1031
+ "grad_norm": 0.7033829092979431,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.3671,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.011572771839588524,
1038
+ "grad_norm": 0.5564422011375427,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.3811,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.011653138310696778,
1045
+ "grad_norm": 0.7714976072311401,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.2818,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.011733504781805031,
1052
+ "grad_norm": 0.43348315358161926,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.2385,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.011813871252913284,
1059
+ "grad_norm": 0.5189164280891418,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.2692,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.011894237724021537,
1066
+ "grad_norm": 0.7366738319396973,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.5457,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.011974604195129792,
1073
+ "grad_norm": 0.6651752591133118,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.3807,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.012054970666238046,
1080
+ "grad_norm": 0.49938416481018066,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.2675,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.012054970666238046,
1087
+ "eval_loss": 0.3388899266719818,
1088
+ "eval_runtime": 1504.884,
1089
+ "eval_samples_per_second": 13.926,
1090
+ "eval_steps_per_second": 3.482,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.1648255234342912e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null