lesso commited on
Commit
a85ff56
·
verified ·
1 Parent(s): 8d56522

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:a6809709cc6e0b32acb814a9eb2ea10485e2e30a7abfc2c9b4b635a04a03b642
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729425801a16d9eb3cedd8ba8dcad9d1468f3d229ac72825d5f8196e51ceaeed
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fc0b6e6a51ab504fa5b81fae3661f568391ff25aeb91ed011f92a1a5964026e
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010af75d831f82c300e7e41ed6398d510b91a5e41614620a6bba0c142959ad62
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80e2bf3019df065cb5a9f9969cad64bcd1e961e034fab484e16358f1afda784b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f6e6d5f4581cfac81193952f9945589db5e0f5ac9c07959c292ad2bd16af59
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ab3d2b0401484126213dd055d9044edf00d7b06db4fe9dbad6027ee8b5d34b1
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123ecf29cfd4fe3b008c987ce1ef9f63c2ad00365e06a3691aa36827aaded381
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.492374897003174,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.07524454477050414,
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": 14.864,
732
  "eval_steps_per_second": 3.716,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.613269972693811e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.4503767490386963,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.11286681715575621,
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": 14.864,
732
  "eval_steps_per_second": 3.716,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.07599699021820917,
737
+ "grad_norm": 4.632258415222168,
738
+ "learning_rate": 5.3043157894736836e-05,
739
+ "loss": 4.8204,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.07674943566591422,
744
+ "grad_norm": 5.53971004486084,
745
+ "learning_rate": 5.2507368421052635e-05,
746
+ "loss": 5.2553,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.07750188111361926,
751
+ "grad_norm": 3.8668930530548096,
752
+ "learning_rate": 5.197157894736842e-05,
753
+ "loss": 4.3132,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0782543265613243,
758
+ "grad_norm": 5.11984920501709,
759
+ "learning_rate": 5.143578947368421e-05,
760
+ "loss": 4.5635,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.07900677200902935,
765
+ "grad_norm": 4.6450347900390625,
766
+ "learning_rate": 5.09e-05,
767
+ "loss": 3.4141,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0797592174567344,
772
+ "grad_norm": 5.824936389923096,
773
+ "learning_rate": 5.036421052631578e-05,
774
+ "loss": 4.7563,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.08051166290443942,
779
+ "grad_norm": 4.639711380004883,
780
+ "learning_rate": 4.982842105263158e-05,
781
+ "loss": 4.3026,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08126410835214447,
786
+ "grad_norm": 8.702680587768555,
787
+ "learning_rate": 4.9292631578947366e-05,
788
+ "loss": 5.7537,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.08201655379984951,
793
+ "grad_norm": 5.901224613189697,
794
+ "learning_rate": 4.875684210526315e-05,
795
+ "loss": 5.0042,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08276899924755456,
800
+ "grad_norm": 8.818628311157227,
801
+ "learning_rate": 4.822105263157894e-05,
802
+ "loss": 5.3414,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0835214446952596,
807
+ "grad_norm": 7.103747367858887,
808
+ "learning_rate": 4.7685263157894735e-05,
809
+ "loss": 5.2836,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.08427389014296463,
814
+ "grad_norm": 6.621494770050049,
815
+ "learning_rate": 4.714947368421052e-05,
816
+ "loss": 4.9538,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.08502633559066967,
821
+ "grad_norm": 8.953717231750488,
822
+ "learning_rate": 4.661368421052631e-05,
823
+ "loss": 5.1009,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.08577878103837472,
828
+ "grad_norm": 8.522113800048828,
829
+ "learning_rate": 4.6077894736842104e-05,
830
+ "loss": 5.0785,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.08653122648607976,
835
+ "grad_norm": 6.302427291870117,
836
+ "learning_rate": 4.554210526315789e-05,
837
+ "loss": 4.6044,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.0872836719337848,
842
+ "grad_norm": 8.132070541381836,
843
+ "learning_rate": 4.500631578947368e-05,
844
+ "loss": 4.9639,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.08803611738148984,
849
+ "grad_norm": 7.749171733856201,
850
+ "learning_rate": 4.447052631578947e-05,
851
+ "loss": 5.2865,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.08878856282919488,
856
+ "grad_norm": 5.969038963317871,
857
+ "learning_rate": 4.393473684210526e-05,
858
+ "loss": 4.7642,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.08954100827689992,
863
+ "grad_norm": 6.512506484985352,
864
+ "learning_rate": 4.339894736842105e-05,
865
+ "loss": 2.9121,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.09029345372460497,
870
+ "grad_norm": 6.616455554962158,
871
+ "learning_rate": 4.2863157894736835e-05,
872
+ "loss": 5.1259,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.09104589917231001,
877
+ "grad_norm": 8.678909301757812,
878
+ "learning_rate": 4.2327368421052634e-05,
879
+ "loss": 5.4049,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.09179834462001504,
884
+ "grad_norm": 7.853146553039551,
885
+ "learning_rate": 4.179157894736842e-05,
886
+ "loss": 5.1167,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.09255079006772009,
891
+ "grad_norm": 6.326202392578125,
892
+ "learning_rate": 4.1255789473684204e-05,
893
+ "loss": 5.1124,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.09330323551542513,
898
+ "grad_norm": 6.513983726501465,
899
+ "learning_rate": 4.072e-05,
900
+ "loss": 4.8156,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.09405568096313018,
905
+ "grad_norm": 7.685911178588867,
906
+ "learning_rate": 4.018421052631579e-05,
907
+ "loss": 4.3464,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.09480812641083522,
912
+ "grad_norm": 8.669236183166504,
913
+ "learning_rate": 3.9648421052631573e-05,
914
+ "loss": 4.7814,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.09556057185854025,
919
+ "grad_norm": 7.881282806396484,
920
+ "learning_rate": 3.9112631578947365e-05,
921
+ "loss": 5.0522,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0963130173062453,
926
+ "grad_norm": 6.99576473236084,
927
+ "learning_rate": 3.857684210526316e-05,
928
+ "loss": 4.4357,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.09706546275395034,
933
+ "grad_norm": 8.76285171508789,
934
+ "learning_rate": 3.804105263157894e-05,
935
+ "loss": 5.5137,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.09781790820165538,
940
+ "grad_norm": 7.629359245300293,
941
+ "learning_rate": 3.7505263157894734e-05,
942
+ "loss": 4.3788,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.09857035364936043,
947
+ "grad_norm": 9.962780952453613,
948
+ "learning_rate": 3.6969473684210526e-05,
949
+ "loss": 4.5262,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.09932279909706546,
954
+ "grad_norm": 7.68848180770874,
955
+ "learning_rate": 3.643368421052631e-05,
956
+ "loss": 4.803,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.1000752445447705,
961
+ "grad_norm": 12.457582473754883,
962
+ "learning_rate": 3.5897894736842103e-05,
963
+ "loss": 5.286,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.10082768999247554,
968
+ "grad_norm": 10.64576244354248,
969
+ "learning_rate": 3.5362105263157895e-05,
970
+ "loss": 5.5489,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.10158013544018059,
975
+ "grad_norm": 8.363515853881836,
976
+ "learning_rate": 3.482631578947368e-05,
977
+ "loss": 4.724,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.10233258088788563,
982
+ "grad_norm": 9.08327579498291,
983
+ "learning_rate": 3.429052631578947e-05,
984
+ "loss": 4.5964,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.10308502633559068,
989
+ "grad_norm": 10.975964546203613,
990
+ "learning_rate": 3.375473684210526e-05,
991
+ "loss": 4.7091,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1038374717832957,
996
+ "grad_norm": 8.273202896118164,
997
+ "learning_rate": 3.321894736842105e-05,
998
+ "loss": 3.8967,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.10458991723100075,
1003
+ "grad_norm": 10.234407424926758,
1004
+ "learning_rate": 3.268315789473684e-05,
1005
+ "loss": 5.5976,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.1053423626787058,
1010
+ "grad_norm": 8.687202453613281,
1011
+ "learning_rate": 3.2147368421052627e-05,
1012
+ "loss": 4.7047,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.10609480812641084,
1017
+ "grad_norm": 9.25235652923584,
1018
+ "learning_rate": 3.161157894736842e-05,
1019
+ "loss": 4.7048,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.10684725357411588,
1024
+ "grad_norm": 10.904390335083008,
1025
+ "learning_rate": 3.107578947368421e-05,
1026
+ "loss": 5.0487,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.10759969902182091,
1031
+ "grad_norm": 12.776407241821289,
1032
+ "learning_rate": 3.0539999999999996e-05,
1033
+ "loss": 5.6051,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.10835214446952596,
1038
+ "grad_norm": 10.124897003173828,
1039
+ "learning_rate": 3.0004210526315784e-05,
1040
+ "loss": 5.6051,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.109104589917231,
1045
+ "grad_norm": 10.322992324829102,
1046
+ "learning_rate": 2.946842105263158e-05,
1047
+ "loss": 4.5447,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.10985703536493605,
1052
+ "grad_norm": 17.68702507019043,
1053
+ "learning_rate": 2.8932631578947368e-05,
1054
+ "loss": 5.1524,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.11060948081264109,
1059
+ "grad_norm": 14.997350692749023,
1060
+ "learning_rate": 2.8396842105263153e-05,
1061
+ "loss": 5.7192,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.11136192626034612,
1066
+ "grad_norm": 12.031723022460938,
1067
+ "learning_rate": 2.786105263157895e-05,
1068
+ "loss": 5.2456,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.11211437170805116,
1073
+ "grad_norm": 17.6466007232666,
1074
+ "learning_rate": 2.7325263157894737e-05,
1075
+ "loss": 6.2655,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.11286681715575621,
1080
+ "grad_norm": 18.988000869750977,
1081
+ "learning_rate": 2.6789473684210522e-05,
1082
+ "loss": 7.0167,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.11286681715575621,
1087
+ "eval_loss": 2.4503767490386963,
1088
+ "eval_runtime": 37.6662,
1089
+ "eval_samples_per_second": 14.867,
1090
+ "eval_steps_per_second": 3.717,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.437792434153062e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null