prxy5608 commited on
Commit
5c83a3a
·
verified ·
1 Parent(s): f71966f

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 sha256:409a0977cb2bfb88e79a7b6e60b0016a835f55f35249db7d9732ce48feac15f8
3
  size 377538512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac5090d56e34d4ac72deeae6675c9a2bce97755807a7dc93076448c524b16e69
3
  size 377538512
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79902cd59d93548830adf1d210f26ae66c005021e72ed786d9a8d6152f8de5bc
3
  size 755298706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6100217f75f7513f8e373751d9fc386e2d29f105f7a2f1cd8e2a6447c06f20db
3
  size 755298706
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0edaf446d02f5e18b72dfff4ac1eb535bb02c4708011a4b1d5c4fd1b9504695
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:367e36d6f0f1b5f233c676830cbac1e64e3ee3fd79fac4888e4bfa7f49d1de92
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": 1.226228952407837,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.5037783375314862,
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": 17.272,
732
  "eval_steps_per_second": 8.662,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6.013111769235456e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1899141073226929,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.7556675062972292,
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": 17.272,
732
  "eval_steps_per_second": 8.662,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.5088161209068011,
737
+ "grad_norm": 0.9275010228157043,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 1.3129,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.5138539042821159,
744
+ "grad_norm": 0.9533458948135376,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 1.2832,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.5188916876574308,
751
+ "grad_norm": 0.7950404286384583,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 1.2729,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.5239294710327456,
758
+ "grad_norm": 0.7813581824302673,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 1.2425,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.5289672544080605,
765
+ "grad_norm": 0.9136513471603394,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 1.3132,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.5340050377833753,
772
+ "grad_norm": 0.7966837286949158,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 1.2751,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.5390428211586902,
779
+ "grad_norm": 0.8216973543167114,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 1.2749,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.5440806045340051,
786
+ "grad_norm": 0.951630711555481,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 1.308,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.5491183879093199,
793
+ "grad_norm": 0.9326642751693726,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.2447,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.5541561712846348,
800
+ "grad_norm": 0.9708240628242493,
801
+ "learning_rate": 5e-05,
802
+ "loss": 1.2911,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.5591939546599496,
807
+ "grad_norm": 0.9061233401298523,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.275,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.5642317380352645,
814
+ "grad_norm": 0.8922585248947144,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 1.2794,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.5692695214105793,
821
+ "grad_norm": 0.8978312611579895,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 1.2773,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5743073047858942,
828
+ "grad_norm": 0.9046211242675781,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 1.2735,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5793450881612091,
835
+ "grad_norm": 0.8805850744247437,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.3408,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5843828715365239,
842
+ "grad_norm": 0.877220869064331,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.2502,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.5894206549118388,
849
+ "grad_norm": 0.9436619281768799,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 1.2536,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5944584382871536,
856
+ "grad_norm": 0.911101758480072,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.2606,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5994962216624685,
863
+ "grad_norm": 0.8994234800338745,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 1.2354,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.6045340050377834,
870
+ "grad_norm": 1.0473874807357788,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 1.2518,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.6095717884130982,
877
+ "grad_norm": 0.9809603691101074,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 1.2468,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.6146095717884131,
884
+ "grad_norm": 0.9014551043510437,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.2181,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.6196473551637279,
891
+ "grad_norm": 3.2279932498931885,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.2466,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.6246851385390428,
898
+ "grad_norm": 1.0879408121109009,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 1.2314,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.6297229219143576,
905
+ "grad_norm": 1.0637506246566772,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 1.2564,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.6347607052896725,
912
+ "grad_norm": 1.1840940713882446,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 1.2296,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.6397984886649875,
919
+ "grad_norm": 1.105326771736145,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 1.2549,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.6448362720403022,
926
+ "grad_norm": 1.0958088636398315,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 1.2328,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.6498740554156172,
933
+ "grad_norm": 1.1396890878677368,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.2363,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.654911838790932,
940
+ "grad_norm": 1.4085423946380615,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 1.2242,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.6599496221662469,
947
+ "grad_norm": 1.1341376304626465,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 1.2563,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.6649874055415617,
954
+ "grad_norm": 1.379789113998413,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 1.2659,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.6700251889168766,
961
+ "grad_norm": 1.2120745182037354,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 1.2329,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.6750629722921915,
968
+ "grad_norm": 1.0146487951278687,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 1.2198,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.6801007556675063,
975
+ "grad_norm": 1.1056286096572876,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.2652,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.6851385390428212,
982
+ "grad_norm": 1.1778992414474487,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.2673,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.690176322418136,
989
+ "grad_norm": 1.3261139392852783,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 1.2619,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6952141057934509,
996
+ "grad_norm": 1.0408475399017334,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 1.3247,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.7002518891687658,
1003
+ "grad_norm": 1.1338088512420654,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 1.2155,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.7052896725440806,
1010
+ "grad_norm": 1.271579623222351,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 1.21,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.7103274559193955,
1017
+ "grad_norm": 1.1375788450241089,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 1.2732,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.7153652392947103,
1024
+ "grad_norm": 1.446244239807129,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 1.2476,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.7204030226700252,
1031
+ "grad_norm": 1.0757509469985962,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 1.2661,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.72544080604534,
1038
+ "grad_norm": 1.2652767896652222,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 1.3227,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.7304785894206549,
1045
+ "grad_norm": 1.3920189142227173,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 1.3374,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.7355163727959698,
1052
+ "grad_norm": 1.432496428489685,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 1.3587,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.7405541561712846,
1059
+ "grad_norm": 2.871924638748169,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 1.4344,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.7455919395465995,
1066
+ "grad_norm": 0.7997872233390808,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 1.2165,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.7506297229219143,
1073
+ "grad_norm": 0.8687345385551453,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 1.2801,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.7556675062972292,
1080
+ "grad_norm": 1.1544013023376465,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 1.2143,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.7556675062972292,
1087
+ "eval_loss": 1.1899141073226929,
1088
+ "eval_runtime": 19.3256,
1089
+ "eval_samples_per_second": 17.335,
1090
+ "eval_steps_per_second": 8.693,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 9.019667653853184e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null