lesso commited on
Commit
2389784
·
verified ·
1 Parent(s): a17f849

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:fb11b3e12cf72711df4f978d861daca0b10ce10a7ea5c48d372aa73dec3f1856
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84db1f26700fcba2c2809a8a3925f2f16888dea559f07b6d266e29c2a4c6ec11
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bed2196aa9da18380af75177357ea9db077730c6e988fec6c61577caf6552d8
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4385a3e51894e57e87c35f856e44820202f4ebe6d1ce4b6ec1aae59bff9da419
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6e43d3c8d6986c9e1a007e1fdac2c253fcc5c1234ae978ff400a8bb581968d6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:923d8642169cc1ba03f2ca2921befff4c7c8be4a391b6649c6bdfddc77900338
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63ec375fb052934b7b9a2c8fa3e1e2ff4c96fb3b19637d9f654ac3884647152a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daaa41fca9fd049986fcf3363fbaab5418032d644dd089607cb2ffe0f0da8945
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.6598618030548096,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.3139717425431711,
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": 36.204,
732
  "eval_steps_per_second": 9.186,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1932120607948800.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.542069435119629,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.47095761381475665,
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": 36.204,
732
  "eval_steps_per_second": 9.186,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.31711145996860285,
737
+ "grad_norm": 3.5819578170776367,
738
+ "learning_rate": 5.283473684210526e-05,
739
+ "loss": 1.0256,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.3202511773940345,
744
+ "grad_norm": 6.239628314971924,
745
+ "learning_rate": 5.230105263157895e-05,
746
+ "loss": 2.0302,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.32339089481946626,
751
+ "grad_norm": 6.583393573760986,
752
+ "learning_rate": 5.176736842105263e-05,
753
+ "loss": 1.8993,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.32653061224489793,
758
+ "grad_norm": 6.852742671966553,
759
+ "learning_rate": 5.123368421052632e-05,
760
+ "loss": 1.5832,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.32967032967032966,
765
+ "grad_norm": 6.229090690612793,
766
+ "learning_rate": 5.07e-05,
767
+ "loss": 1.7996,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.3328100470957614,
772
+ "grad_norm": 4.9963908195495605,
773
+ "learning_rate": 5.016631578947368e-05,
774
+ "loss": 1.3517,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.3359497645211931,
779
+ "grad_norm": 6.220682144165039,
780
+ "learning_rate": 4.963263157894737e-05,
781
+ "loss": 2.3754,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.3390894819466248,
786
+ "grad_norm": 5.58546781539917,
787
+ "learning_rate": 4.909894736842105e-05,
788
+ "loss": 1.9693,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.34222919937205654,
793
+ "grad_norm": 5.197764873504639,
794
+ "learning_rate": 4.8565263157894734e-05,
795
+ "loss": 1.1676,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.3453689167974882,
800
+ "grad_norm": 6.040829181671143,
801
+ "learning_rate": 4.803157894736842e-05,
802
+ "loss": 1.9262,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.34850863422291994,
807
+ "grad_norm": 6.036067485809326,
808
+ "learning_rate": 4.749789473684211e-05,
809
+ "loss": 1.875,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.3516483516483517,
814
+ "grad_norm": 5.573509693145752,
815
+ "learning_rate": 4.696421052631579e-05,
816
+ "loss": 1.5932,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.35478806907378335,
821
+ "grad_norm": 5.3029632568359375,
822
+ "learning_rate": 4.643052631578947e-05,
823
+ "loss": 1.3575,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.3579277864992151,
828
+ "grad_norm": 5.437764644622803,
829
+ "learning_rate": 4.589684210526316e-05,
830
+ "loss": 1.6235,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.36106750392464676,
835
+ "grad_norm": 4.923410415649414,
836
+ "learning_rate": 4.536315789473684e-05,
837
+ "loss": 1.3825,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.3642072213500785,
842
+ "grad_norm": 6.01725435256958,
843
+ "learning_rate": 4.482947368421052e-05,
844
+ "loss": 1.4735,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.3673469387755102,
849
+ "grad_norm": 6.325821876525879,
850
+ "learning_rate": 4.429578947368421e-05,
851
+ "loss": 1.6234,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.3704866562009419,
856
+ "grad_norm": 5.018939018249512,
857
+ "learning_rate": 4.3762105263157896e-05,
858
+ "loss": 1.7545,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.37362637362637363,
863
+ "grad_norm": 5.737129211425781,
864
+ "learning_rate": 4.3228421052631576e-05,
865
+ "loss": 1.7748,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.37676609105180536,
870
+ "grad_norm": 5.9904866218566895,
871
+ "learning_rate": 4.269473684210526e-05,
872
+ "loss": 1.4207,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.37990580847723704,
877
+ "grad_norm": 7.162813186645508,
878
+ "learning_rate": 4.216105263157895e-05,
879
+ "loss": 1.5775,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.38304552590266877,
884
+ "grad_norm": 4.571135520935059,
885
+ "learning_rate": 4.162736842105263e-05,
886
+ "loss": 1.6661,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.38618524332810045,
891
+ "grad_norm": 5.065517902374268,
892
+ "learning_rate": 4.109368421052631e-05,
893
+ "loss": 1.5862,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.3893249607535322,
898
+ "grad_norm": 7.399703025817871,
899
+ "learning_rate": 4.0560000000000005e-05,
900
+ "loss": 2.1326,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.3924646781789639,
905
+ "grad_norm": 5.505315780639648,
906
+ "learning_rate": 4.0026315789473685e-05,
907
+ "loss": 1.265,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.3956043956043956,
912
+ "grad_norm": 6.12184476852417,
913
+ "learning_rate": 3.9492631578947365e-05,
914
+ "loss": 1.5402,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.3987441130298273,
919
+ "grad_norm": 6.294252395629883,
920
+ "learning_rate": 3.895894736842105e-05,
921
+ "loss": 1.5752,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.40188383045525905,
926
+ "grad_norm": 6.789506435394287,
927
+ "learning_rate": 3.842526315789474e-05,
928
+ "loss": 1.9103,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.4050235478806907,
933
+ "grad_norm": 6.3864006996154785,
934
+ "learning_rate": 3.789157894736842e-05,
935
+ "loss": 1.7966,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.40816326530612246,
940
+ "grad_norm": 7.398538589477539,
941
+ "learning_rate": 3.73578947368421e-05,
942
+ "loss": 1.9872,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.41130298273155413,
947
+ "grad_norm": 7.464357376098633,
948
+ "learning_rate": 3.682421052631579e-05,
949
+ "loss": 1.8161,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.41444270015698587,
954
+ "grad_norm": 7.386998176574707,
955
+ "learning_rate": 3.6290526315789474e-05,
956
+ "loss": 1.5991,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.4175824175824176,
961
+ "grad_norm": 7.29685115814209,
962
+ "learning_rate": 3.5756842105263154e-05,
963
+ "loss": 1.7373,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.4207221350078493,
968
+ "grad_norm": 6.442423343658447,
969
+ "learning_rate": 3.522315789473684e-05,
970
+ "loss": 1.5062,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.423861852433281,
975
+ "grad_norm": 7.622251987457275,
976
+ "learning_rate": 3.468947368421053e-05,
977
+ "loss": 1.6362,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.42700156985871274,
982
+ "grad_norm": 5.391417503356934,
983
+ "learning_rate": 3.415578947368421e-05,
984
+ "loss": 1.3335,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.4301412872841444,
989
+ "grad_norm": 7.495037078857422,
990
+ "learning_rate": 3.3622105263157895e-05,
991
+ "loss": 2.1399,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.43328100470957615,
996
+ "grad_norm": 8.007742881774902,
997
+ "learning_rate": 3.308842105263158e-05,
998
+ "loss": 1.8728,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.4364207221350079,
1003
+ "grad_norm": 5.115504741668701,
1004
+ "learning_rate": 3.255473684210526e-05,
1005
+ "loss": 1.3832,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.43956043956043955,
1010
+ "grad_norm": 7.03964376449585,
1011
+ "learning_rate": 3.202105263157894e-05,
1012
+ "loss": 1.8599,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.4427001569858713,
1017
+ "grad_norm": 7.27022647857666,
1018
+ "learning_rate": 3.1487368421052636e-05,
1019
+ "loss": 1.5044,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.44583987441130296,
1024
+ "grad_norm": 8.688240051269531,
1025
+ "learning_rate": 3.0953684210526317e-05,
1026
+ "loss": 1.9889,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.4489795918367347,
1031
+ "grad_norm": 7.870269298553467,
1032
+ "learning_rate": 3.0419999999999997e-05,
1033
+ "loss": 1.5771,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.4521193092621664,
1038
+ "grad_norm": 6.881030082702637,
1039
+ "learning_rate": 2.988631578947368e-05,
1040
+ "loss": 1.2406,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.4552590266875981,
1045
+ "grad_norm": 7.38179349899292,
1046
+ "learning_rate": 2.935263157894737e-05,
1047
+ "loss": 1.5986,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.45839874411302983,
1052
+ "grad_norm": 7.3739800453186035,
1053
+ "learning_rate": 2.881894736842105e-05,
1054
+ "loss": 1.5282,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.46153846153846156,
1059
+ "grad_norm": 8.048142433166504,
1060
+ "learning_rate": 2.8285263157894735e-05,
1061
+ "loss": 1.7917,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.46467817896389324,
1066
+ "grad_norm": 8.414251327514648,
1067
+ "learning_rate": 2.775157894736842e-05,
1068
+ "loss": 2.0077,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.46781789638932497,
1073
+ "grad_norm": 10.131597518920898,
1074
+ "learning_rate": 2.7217894736842105e-05,
1075
+ "loss": 2.0688,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.47095761381475665,
1080
+ "grad_norm": 13.612863540649414,
1081
+ "learning_rate": 2.668421052631579e-05,
1082
+ "loss": 1.7537,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.47095761381475665,
1087
+ "eval_loss": 1.542069435119629,
1088
+ "eval_runtime": 3.6868,
1089
+ "eval_samples_per_second": 36.346,
1090
+ "eval_steps_per_second": 9.222,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2898180911923200.0,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null