ancient41 commited on
Commit
b885433
·
verified ·
1 Parent(s): e1be4b9

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 sha256:04537a3ab1df9d341979fcd13f94a44b3c7c07cab3cb5a834191081ed49e5ee4
3
  size 224224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b402ea97cecf7630daafab1d167884de1755e3008e8ae21d02009afd74abec21
3
  size 224224
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa71a1a03d4c6e02d42b83d7b04ecd9255ea3b8051351699a7525a873c1535ae
3
  size 458278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ada412790e0c2dbfb0cabf20c5d7d8d845686103b32d84873f368f080f71249
3
  size 458278
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63a3340464902bd64c9c898fa5a2b1da20d5bd8cea6d047e60c0f6f1c7ca8de9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3187ecb0a2a770037fdb56f6a7f9b0386d5164ce7afca984bfa72e860f1c43ae
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": 10.258431434631348,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.033291718684977115,
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": 470.648,
732
  "eval_steps_per_second": 117.685,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 21803131994112.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.249475479125977,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.049937578027465665,
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": 470.648,
732
  "eval_steps_per_second": 117.685,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.03362463587182688,
737
+ "grad_norm": 0.8197965621948242,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 41.1681,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.033957553058676655,
744
+ "grad_norm": 0.7517240643501282,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 41.0561,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.03429047024552642,
751
+ "grad_norm": 0.8323513269424438,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 41.0812,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.034623387432376196,
758
+ "grad_norm": 0.6251527070999146,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 41.0668,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03495630461922597,
765
+ "grad_norm": 0.6447218060493469,
766
+ "learning_rate": 5e-05,
767
+ "loss": 41.0685,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.035289221806075736,
772
+ "grad_norm": 0.557669997215271,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 41.0605,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.03562213899292551,
779
+ "grad_norm": 0.5138564109802246,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 41.0361,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.035955056179775284,
786
+ "grad_norm": 0.6563073396682739,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 41.0354,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03628797336662505,
793
+ "grad_norm": 0.7195301651954651,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 41.0588,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.036620890553474825,
800
+ "grad_norm": 0.5311015844345093,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 41.0414,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03695380774032459,
807
+ "grad_norm": 0.4951725900173187,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 41.0406,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.037286724927174365,
814
+ "grad_norm": 0.6164833307266235,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 41.0404,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.03761964211402414,
821
+ "grad_norm": 0.46018698811531067,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 41.0039,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.037952559300873906,
828
+ "grad_norm": 0.5341908931732178,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 41.0382,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03828547648772368,
835
+ "grad_norm": 0.4417647421360016,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 41.0337,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03861839367457345,
842
+ "grad_norm": 0.44535237550735474,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 41.024,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.03895131086142322,
849
+ "grad_norm": 0.4301574230194092,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 41.0103,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.039284228048272994,
856
+ "grad_norm": 0.3613111972808838,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 41.014,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.03961714523512276,
863
+ "grad_norm": 0.5949000716209412,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 41.0299,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.039950062421972535,
870
+ "grad_norm": 0.4415794014930725,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 41.0279,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.04028297960882231,
877
+ "grad_norm": 0.4477580487728119,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 41.0153,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.040615896795672075,
884
+ "grad_norm": 0.5567710399627686,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 40.9882,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.04094881398252185,
891
+ "grad_norm": 0.3459272086620331,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 41.0131,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.041281731169371616,
898
+ "grad_norm": 0.44242531061172485,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 41.0003,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.04161464835622139,
905
+ "grad_norm": 0.4070902466773987,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 41.0433,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.041947565543071164,
912
+ "grad_norm": 0.49008601903915405,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 40.986,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.04228048272992093,
919
+ "grad_norm": 0.5317264199256897,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 40.9847,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.042613399916770704,
926
+ "grad_norm": 0.44159913063049316,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 41.0029,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.04294631710362047,
933
+ "grad_norm": 0.41397854685783386,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 40.9833,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.043279234290470245,
940
+ "grad_norm": 0.49845272302627563,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 40.985,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.04361215147732002,
947
+ "grad_norm": 0.5296779870986938,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 40.9791,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.043945068664169785,
954
+ "grad_norm": 0.5320541262626648,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 40.9856,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.04427798585101956,
961
+ "grad_norm": 0.4494282007217407,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 41.003,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.04461090303786933,
968
+ "grad_norm": 0.5439767837524414,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 41.0101,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0449438202247191,
975
+ "grad_norm": 0.5443069338798523,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 41.0058,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.045276737411568874,
982
+ "grad_norm": 0.5209833383560181,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 40.9537,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.04560965459841864,
989
+ "grad_norm": 0.6369801759719849,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 41.0231,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.045942571785268414,
996
+ "grad_norm": 0.4558340311050415,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 41.0033,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.04627548897211819,
1003
+ "grad_norm": 0.45617663860321045,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 40.9941,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.046608406158967955,
1010
+ "grad_norm": 0.5451856255531311,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 40.9855,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.04694132334581773,
1017
+ "grad_norm": 0.5882953405380249,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 41.0071,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.047274240532667496,
1024
+ "grad_norm": 0.5545759797096252,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 40.9671,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.04760715771951727,
1031
+ "grad_norm": 0.544330358505249,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 40.984,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.04794007490636704,
1038
+ "grad_norm": 0.5511378049850464,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 40.9916,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.04827299209321681,
1045
+ "grad_norm": 0.5397998094558716,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 40.9731,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.048605909280066584,
1052
+ "grad_norm": 0.5846787691116333,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 40.9536,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04893882646691636,
1059
+ "grad_norm": 0.5194352269172668,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 40.9633,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.049271743653766124,
1066
+ "grad_norm": 0.6024704575538635,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 40.9447,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.0496046608406159,
1073
+ "grad_norm": 0.7204001545906067,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 40.9501,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.049937578027465665,
1080
+ "grad_norm": 0.9084548354148865,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 41.0565,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.049937578027465665,
1087
+ "eval_loss": 10.249475479125977,
1088
+ "eval_runtime": 10.7917,
1089
+ "eval_samples_per_second": 468.788,
1090
+ "eval_steps_per_second": 117.22,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 32650995695616.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null