prxy5605 commited on
Commit
fb1ddf7
·
verified ·
1 Parent(s): 3421237

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 sha256:8f06418b91d3d581e8a7b9a4dfbe0999918766c17a0de39190bc99ed67e921cf
3
  size 226532664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14c5f8003ae439ae23a54b072107e3c7681d77430538995661950d056deb034
3
  size 226532664
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e81a23b25ed6d8d15119861945e256867b31726bd002dc31297da77dd483011
3
  size 115354708
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b1f055ff25ac196c174ec579d783546c29ec1e12a1d30b52d4144416b3593c
3
  size 115354708
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a0bb9d019f346bb0dfb18db7121fc4bf38037b1be5970338f41f1e46b807cc3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90285c09ef99b7ca776742c060e44ccbcd6d27efb35b2feb4348c500f5eeff64
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5312721729278564,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.20512820512820512,
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": 51.494,
732
  "eval_steps_per_second": 12.905,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.48753499930624e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3557584285736084,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.3076923076923077,
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": 51.494,
732
  "eval_steps_per_second": 12.905,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.20717948717948717,
737
+ "grad_norm": 19.73323631286621,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 8.0295,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.20923076923076922,
744
+ "grad_norm": 19.887081146240234,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 7.669,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.21128205128205127,
751
+ "grad_norm": 17.00939178466797,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 7.0407,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.21333333333333335,
758
+ "grad_norm": 14.636185646057129,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 7.5585,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.2153846153846154,
765
+ "grad_norm": 16.119821548461914,
766
+ "learning_rate": 5e-05,
767
+ "loss": 6.7754,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.21743589743589745,
772
+ "grad_norm": 12.749444007873535,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 6.8508,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.2194871794871795,
779
+ "grad_norm": 12.621720314025879,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 6.6114,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.22153846153846155,
786
+ "grad_norm": 12.389793395996094,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 7.09,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.2235897435897436,
793
+ "grad_norm": 13.967874526977539,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 6.773,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.22564102564102564,
800
+ "grad_norm": 13.55045223236084,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 6.1267,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.2276923076923077,
807
+ "grad_norm": 13.088988304138184,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 6.3353,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.22974358974358974,
814
+ "grad_norm": 14.034475326538086,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 6.5768,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.2317948717948718,
821
+ "grad_norm": 12.155129432678223,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.4652,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.23384615384615384,
828
+ "grad_norm": 13.86252498626709,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 6.302,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.2358974358974359,
835
+ "grad_norm": 12.522025108337402,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 5.7517,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.23794871794871794,
842
+ "grad_norm": 13.93448543548584,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 7.1711,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.24,
849
+ "grad_norm": 12.722003936767578,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.7468,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.24205128205128204,
856
+ "grad_norm": 12.285789489746094,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 5.5674,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.2441025641025641,
863
+ "grad_norm": 13.329984664916992,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 6.8977,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.24615384615384617,
870
+ "grad_norm": 12.459861755371094,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 5.1761,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.24820512820512822,
877
+ "grad_norm": 13.116291046142578,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 5.9593,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.25025641025641027,
884
+ "grad_norm": 11.814793586730957,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 5.3207,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.2523076923076923,
891
+ "grad_norm": 12.684826850891113,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.932,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.25435897435897437,
898
+ "grad_norm": 13.912420272827148,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 5.4991,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.2564102564102564,
905
+ "grad_norm": 13.573075294494629,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 5.9587,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.25846153846153846,
912
+ "grad_norm": 12.877527236938477,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 5.6705,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.2605128205128205,
919
+ "grad_norm": 13.240682601928711,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 5.4578,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.26256410256410256,
926
+ "grad_norm": 14.61888313293457,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 6.2122,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.26461538461538464,
933
+ "grad_norm": 13.80810260772705,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 4.3503,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.26666666666666666,
940
+ "grad_norm": 13.312344551086426,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.296,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.26871794871794874,
947
+ "grad_norm": 12.919769287109375,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 5.4403,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.27076923076923076,
954
+ "grad_norm": 15.630560874938965,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 6.103,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.27282051282051284,
961
+ "grad_norm": 13.64303207397461,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 5.2645,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.27487179487179486,
968
+ "grad_norm": 15.118757247924805,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 5.6348,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.27692307692307694,
975
+ "grad_norm": 14.545753479003906,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 5.4571,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.27897435897435896,
982
+ "grad_norm": 16.79315948486328,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 6.2654,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.28102564102564104,
989
+ "grad_norm": 17.019739151000977,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 5.9518,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.28307692307692306,
996
+ "grad_norm": 18.68789291381836,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 6.5252,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.28512820512820514,
1003
+ "grad_norm": 15.538617134094238,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 5.2362,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.28717948717948716,
1010
+ "grad_norm": 16.310075759887695,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 5.5831,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.28923076923076924,
1017
+ "grad_norm": 20.11566162109375,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 6.7928,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.29128205128205126,
1024
+ "grad_norm": 20.536367416381836,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 6.5104,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.29333333333333333,
1031
+ "grad_norm": 17.16673469543457,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 5.1571,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.2953846153846154,
1038
+ "grad_norm": 17.428133010864258,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 5.2561,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.29743589743589743,
1045
+ "grad_norm": 17.67066192626953,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 5.5911,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2994871794871795,
1052
+ "grad_norm": 18.828380584716797,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 5.261,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.30153846153846153,
1059
+ "grad_norm": 23.853103637695312,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 6.4455,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.3035897435897436,
1066
+ "grad_norm": 26.149553298950195,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 7.041,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.30564102564102563,
1073
+ "grad_norm": 30.94405746459961,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 6.2724,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.3076923076923077,
1080
+ "grad_norm": 50.888282775878906,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 8.1747,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.3076923076923077,
1087
+ "eval_loss": 1.3557584285736084,
1088
+ "eval_runtime": 16.0128,
1089
+ "eval_samples_per_second": 51.334,
1090
+ "eval_steps_per_second": 12.865,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.73130249895936e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null