prxy5606 commited on
Commit
ed98d69
·
verified ·
1 Parent(s): fb04b1a

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 sha256:5b258735bbd23b73d01e538aca97708fa23d326e1a364cb6e246331d2d9f5c4d
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b5319b7758ae368d0e017977a7df486045654be9862bb987bf9eeff4c35d625
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:904e0a6327477f0392a43e7f95c5819d819be397e1de60390307609faaefe52d
3
  size 156656510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2bb0298eea4982f8449e3acbfe153a02bde8a5fb3e12f90818c01a532909654
3
  size 156656510
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2478bfa83a16b05a562c1d046b2dd0b745339b79a3479cabbbb55b4ee91c3df
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3777b290d747a73326ea62e9a0df7689c19b1628930513cea225a2ec36a3b863
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": 0.9516631960868835,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.021329920546045968,
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": 40.571,
732
  "eval_steps_per_second": 20.285,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2503078245826560.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9324145913124084,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.03199488081906895,
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": 40.571,
732
  "eval_steps_per_second": 20.285,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.021543219751506425,
737
+ "grad_norm": 0.355265349149704,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 1.0614,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.021756518956966887,
744
+ "grad_norm": 0.3831828534603119,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 0.9951,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.021969818162427344,
751
+ "grad_norm": 0.3315833508968353,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 0.9057,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.022183117367887806,
758
+ "grad_norm": 0.2796443998813629,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 0.8379,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.022396416573348264,
765
+ "grad_norm": 0.3008687496185303,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 0.9172,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.022609715778808725,
772
+ "grad_norm": 0.23267973959445953,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 0.841,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.022823014984269183,
779
+ "grad_norm": 0.2733173668384552,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 0.9093,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.023036314189729644,
786
+ "grad_norm": 0.2535065710544586,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 0.9442,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0232496133951901,
793
+ "grad_norm": 0.2553474009037018,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.0607,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.023462912600650563,
800
+ "grad_norm": 0.2369348704814911,
801
+ "learning_rate": 5e-05,
802
+ "loss": 0.9073,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.02367621180611102,
807
+ "grad_norm": 0.2561231851577759,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.0031,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.023889511011571482,
814
+ "grad_norm": 0.2755792438983917,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 0.9531,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.02410281021703194,
821
+ "grad_norm": 0.3029363751411438,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 0.9881,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0243161094224924,
828
+ "grad_norm": 0.27506956458091736,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 0.9784,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.024529408627952862,
835
+ "grad_norm": 0.30184289813041687,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.0044,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.02474270783341332,
842
+ "grad_norm": 0.33883678913116455,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.0522,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.02495600703887378,
849
+ "grad_norm": 0.30035409331321716,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 0.8848,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.02516930624433424,
856
+ "grad_norm": 0.30106550455093384,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.0947,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.0253826054497947,
863
+ "grad_norm": 0.29889124631881714,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 0.9041,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.02559590465525516,
870
+ "grad_norm": 0.2549803555011749,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 0.9632,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.02580920386071562,
877
+ "grad_norm": 0.27938392758369446,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 0.934,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.026022503066176077,
884
+ "grad_norm": 0.2797248363494873,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 0.9475,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.02623580227163654,
891
+ "grad_norm": 0.28871628642082214,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 0.972,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.026449101477096996,
898
+ "grad_norm": 0.30452898144721985,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 0.8667,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.026662400682557458,
905
+ "grad_norm": 0.2984020411968231,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 0.9119,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.026875699888017916,
912
+ "grad_norm": 0.26833754777908325,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 1.0051,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.027088999093478377,
919
+ "grad_norm": 0.2745654284954071,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 0.9698,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.027302298298938838,
926
+ "grad_norm": 0.28041306138038635,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 0.9021,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.027515597504399296,
933
+ "grad_norm": 0.2919355034828186,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.0522,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.027728896709859757,
940
+ "grad_norm": 0.27209892868995667,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 0.8706,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.027942195915320215,
947
+ "grad_norm": 0.28089284896850586,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 0.8929,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.028155495120780676,
954
+ "grad_norm": 0.26712432503700256,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 0.9431,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.028368794326241134,
961
+ "grad_norm": 0.3111507296562195,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 0.9279,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.028582093531701595,
968
+ "grad_norm": 0.2614944279193878,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 0.8773,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.028795392737162053,
975
+ "grad_norm": 0.2566675543785095,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 0.8574,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.029008691942622514,
982
+ "grad_norm": 0.26692256331443787,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 0.8803,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.029221991148082972,
989
+ "grad_norm": 0.30085262656211853,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 0.8579,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.029435290353543433,
996
+ "grad_norm": 0.3874056935310364,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 0.8966,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.02964858955900389,
1003
+ "grad_norm": 0.3222864866256714,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 0.948,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.029861888764464353,
1010
+ "grad_norm": 0.2842833697795868,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 0.898,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.03007518796992481,
1017
+ "grad_norm": 0.31163346767425537,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 1.0028,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.03028848717538527,
1024
+ "grad_norm": 0.33155760169029236,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 1.0265,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.030501786380845733,
1031
+ "grad_norm": 0.31235241889953613,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 0.9573,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.03071508558630619,
1038
+ "grad_norm": 0.33971816301345825,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 1.0178,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.030928384791766652,
1045
+ "grad_norm": 0.3050580322742462,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 0.8363,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.03114168399722711,
1052
+ "grad_norm": 0.3527008593082428,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 0.9609,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.03135498320268757,
1059
+ "grad_norm": 0.38827890157699585,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 1.0968,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.03156828240814803,
1066
+ "grad_norm": 0.3300125300884247,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 0.8794,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.03178158161360849,
1073
+ "grad_norm": 0.3898104429244995,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 0.7935,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.03199488081906895,
1080
+ "grad_norm": 0.43341726064682007,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 0.8853,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.03199488081906895,
1087
+ "eval_loss": 0.9324145913124084,
1088
+ "eval_runtime": 194.6807,
1089
+ "eval_samples_per_second": 40.559,
1090
+ "eval_steps_per_second": 20.279,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3757707588796416.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null