prxy5605 commited on
Commit
c8a1b8f
·
verified ·
1 Parent(s): ed1fc82

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:f007a0af61a0a90dd02172186153f3d833d9cb1c28a66b6e47eaab013cdb2a2e
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0dfe99a52094bec1317e8c3d67399d4dc97b7a923512f80b700420a2b1e1113
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fffa428fcbfdba4f25ef2d85bcc9f03269822015e41812d247a6eb46d55cf717
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13a7f6b6c757c5d4874084eab7192d097458743be74de094449e9586eb51799
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21fa84cc33d21f2705d2ad8e4f187f0790b2b3189edae264c40e5d7eccd5ee43
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2ff1c07f216f6cdce9f15eb1c21e37cd6af6bbf35f5b6cdae742662456c83a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.973891019821167,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.03352891869237217,
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": 12.144,
732
  "eval_steps_per_second": 6.073,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.919277548789978,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.050293378038558254,
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": 12.144,
732
  "eval_steps_per_second": 6.073,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.03386420787929589,
737
+ "grad_norm": 2.4231576919555664,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 1.6551,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.034199497066219615,
744
+ "grad_norm": 2.900712251663208,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 2.0897,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.03453478625314334,
751
+ "grad_norm": 1.7243603467941284,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 1.5175,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.03487007544006706,
758
+ "grad_norm": 1.6598199605941772,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 1.7261,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03520536462699078,
765
+ "grad_norm": 1.80154287815094,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 1.5605,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.035540653813914504,
772
+ "grad_norm": 1.6656845808029175,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 1.5951,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.035875943000838226,
779
+ "grad_norm": 1.8260254859924316,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 1.8052,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.03621123218776195,
786
+ "grad_norm": 1.9387423992156982,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 1.9528,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03654652137468566,
793
+ "grad_norm": 1.7920228242874146,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.7059,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.036881810561609385,
800
+ "grad_norm": 1.5748786926269531,
801
+ "learning_rate": 5e-05,
802
+ "loss": 1.6674,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03721709974853311,
807
+ "grad_norm": 1.4134800434112549,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.5574,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.03755238893545683,
814
+ "grad_norm": 1.574621558189392,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 1.4027,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.03788767812238055,
821
+ "grad_norm": 1.5440373420715332,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 1.6197,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.03822296730930427,
828
+ "grad_norm": 1.5774800777435303,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 1.9142,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.038558256496227995,
835
+ "grad_norm": 1.7833162546157837,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.8281,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03889354568315172,
842
+ "grad_norm": 1.6017940044403076,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.7815,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.03922883487007544,
849
+ "grad_norm": 1.4744386672973633,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 1.7268,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.03956412405699916,
856
+ "grad_norm": 1.2313249111175537,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.5412,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.039899413243922884,
863
+ "grad_norm": 1.5644769668579102,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 1.9018,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.040234702430846606,
870
+ "grad_norm": 1.3826490640640259,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 1.677,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.04056999161777033,
877
+ "grad_norm": 1.734617829322815,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 1.806,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.04090528080469405,
884
+ "grad_norm": 1.5642307996749878,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.9275,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.04124056999161777,
891
+ "grad_norm": 1.308278203010559,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.5416,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.041575859178541494,
898
+ "grad_norm": 1.59608793258667,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 1.7504,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.041911148365465216,
905
+ "grad_norm": 1.3959640264511108,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 1.8318,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.04224643755238894,
912
+ "grad_norm": 1.539931058883667,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 1.8151,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.04258172673931266,
919
+ "grad_norm": 1.9125542640686035,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 2.1793,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.04291701592623638,
926
+ "grad_norm": 1.8889496326446533,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 2.041,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0432523051131601,
933
+ "grad_norm": 1.9471142292022705,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.9827,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.04358759430008382,
940
+ "grad_norm": 1.873214602470398,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 1.8718,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.04392288348700754,
947
+ "grad_norm": 1.711531400680542,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 1.8252,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.04425817267393126,
954
+ "grad_norm": 1.5534932613372803,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 1.7072,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.044593461860854985,
961
+ "grad_norm": 1.7707465887069702,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 1.7909,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.04492875104777871,
968
+ "grad_norm": 2.0942959785461426,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 2.2297,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.04526404023470243,
975
+ "grad_norm": 1.8636870384216309,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.9661,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.04559932942162615,
982
+ "grad_norm": 1.750473141670227,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.9891,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.045934618608549874,
989
+ "grad_norm": 1.7958630323410034,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 2.246,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.046269907795473596,
996
+ "grad_norm": 1.7150790691375732,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 2.0096,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.04660519698239732,
1003
+ "grad_norm": 1.850218415260315,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 2.0812,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.04694048616932104,
1010
+ "grad_norm": 1.802883267402649,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 2.0021,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.04727577535624476,
1017
+ "grad_norm": 1.8256604671478271,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 1.806,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.047611064543168484,
1024
+ "grad_norm": 1.7722952365875244,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 2.0219,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.047946353730092206,
1031
+ "grad_norm": 1.784156084060669,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 2.0517,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.04828164291701593,
1038
+ "grad_norm": 1.9192204475402832,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 2.2254,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.04861693210393965,
1045
+ "grad_norm": 1.7217282056808472,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 2.035,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.04895222129086337,
1052
+ "grad_norm": 1.7334017753601074,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 2.037,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.049287510477787094,
1059
+ "grad_norm": 2.0734338760375977,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 2.1014,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.049622799664710816,
1066
+ "grad_norm": 1.4909307956695557,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 1.8301,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.04995808885163453,
1073
+ "grad_norm": 1.5050811767578125,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 1.9028,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.050293378038558254,
1080
+ "grad_norm": 1.7747118473052979,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 1.9659,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.050293378038558254,
1087
+ "eval_loss": 1.919277548789978,
1088
+ "eval_runtime": 414.0216,
1089
+ "eval_samples_per_second": 12.132,
1090
+ "eval_steps_per_second": 6.067,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.262770368118784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null