prxy5604 commited on
Commit
8f3c61f
·
verified ·
1 Parent(s): 6fc050e

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 sha256:235e4f4d6a35d29efd0a6a7b51dff4a21c31ec4c1e639111fa2eab6217f29776
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc7f2ffd8e3ed5b19152bf3cdd8cfee2e35c13f1e15e1fda93acfc7eb3c65f16
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba6c077a6f9cd9c8840c7815cd229f0d729d0326758935b6ad0e1e96a68d6e01
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:567fcc7f8e63ba63d673c73122c8ae9ff616848d4ab4c84afe6d2cf3e2e54854
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98f0b46a055895d37d66fcedbb237bcf5d7d58216e3c9875c0855f56c45a5101
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6589d018f91f97165f298b9b659197fbb9fe8847d828b74d5b8f2a889526405a
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": 0.37808772921562195,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.42328042328042326,
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": 57.706,
732
  "eval_steps_per_second": 14.499,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7728482431795200.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.28232118487358093,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.6349206349206349,
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": 57.706,
732
  "eval_steps_per_second": 14.499,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.4275132275132275,
737
+ "grad_norm": 5.3600993156433105,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.3205,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.43174603174603177,
744
+ "grad_norm": 6.028841495513916,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.5017,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.43597883597883597,
751
+ "grad_norm": 4.099414825439453,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.353,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.4402116402116402,
758
+ "grad_norm": 2.0545854568481445,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.2384,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.4444444444444444,
765
+ "grad_norm": 1.905985951423645,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.227,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.4486772486772487,
772
+ "grad_norm": 1.7632219791412354,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.1731,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.45291005291005293,
779
+ "grad_norm": 2.416924238204956,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.2187,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.45714285714285713,
786
+ "grad_norm": 3.4238765239715576,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.2083,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.4613756613756614,
793
+ "grad_norm": 3.8695147037506104,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.3424,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.4656084656084656,
800
+ "grad_norm": 4.578450679779053,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.4433,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.46984126984126984,
807
+ "grad_norm": 2.018458366394043,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.2119,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.4740740740740741,
814
+ "grad_norm": 1.5531548261642456,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.119,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.4783068783068783,
821
+ "grad_norm": 1.6177637577056885,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.1506,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.48253968253968255,
828
+ "grad_norm": 2.3413093090057373,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.2289,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.48677248677248675,
835
+ "grad_norm": 1.3700860738754272,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.1459,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.491005291005291,
842
+ "grad_norm": 2.018336772918701,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.1954,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.49523809523809526,
849
+ "grad_norm": 2.760356903076172,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.2523,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.49947089947089945,
856
+ "grad_norm": 2.069105625152588,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.1667,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5037037037037037,
863
+ "grad_norm": 3.065279245376587,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.2718,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5079365079365079,
870
+ "grad_norm": 2.663546323776245,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.2049,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.5121693121693122,
877
+ "grad_norm": 3.6617202758789062,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.3423,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5164021164021164,
884
+ "grad_norm": 2.2311642169952393,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.2304,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5206349206349207,
891
+ "grad_norm": 2.969971179962158,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.3168,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.5248677248677248,
898
+ "grad_norm": 2.3839523792266846,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.2692,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.5291005291005291,
905
+ "grad_norm": 2.5839531421661377,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.2391,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5333333333333333,
912
+ "grad_norm": 1.9737006425857544,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.2429,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5375661375661376,
919
+ "grad_norm": 3.182060718536377,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.2493,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5417989417989418,
926
+ "grad_norm": 2.693786859512329,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.2703,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.546031746031746,
933
+ "grad_norm": 2.1067678928375244,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.1772,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5502645502645502,
940
+ "grad_norm": 2.3039276599884033,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.2438,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.5544973544973545,
947
+ "grad_norm": 3.749096155166626,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.2976,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5587301587301587,
954
+ "grad_norm": 3.6726558208465576,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.3084,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.562962962962963,
961
+ "grad_norm": 2.6327967643737793,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.2289,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5671957671957671,
968
+ "grad_norm": 3.0753870010375977,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.2925,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5714285714285714,
975
+ "grad_norm": 2.488861560821533,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.2123,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.5756613756613757,
982
+ "grad_norm": 2.99312162399292,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.3211,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.5798941798941799,
989
+ "grad_norm": 2.0076987743377686,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.1565,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.5841269841269842,
996
+ "grad_norm": 1.608855128288269,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.1192,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.5883597883597883,
1003
+ "grad_norm": 3.0737903118133545,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.2924,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.5925925925925926,
1010
+ "grad_norm": 2.2523465156555176,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.1743,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.5968253968253968,
1017
+ "grad_norm": 3.2285783290863037,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.3134,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.6010582010582011,
1024
+ "grad_norm": 2.174173355102539,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.148,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.6052910052910053,
1031
+ "grad_norm": 3.3965871334075928,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.2652,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6095238095238096,
1038
+ "grad_norm": 2.8393561840057373,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.2028,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.6137566137566137,
1045
+ "grad_norm": 2.0864152908325195,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.1174,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.617989417989418,
1052
+ "grad_norm": 2.6261792182922363,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.1931,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6222222222222222,
1059
+ "grad_norm": 3.022298574447632,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.3043,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6264550264550265,
1066
+ "grad_norm": 4.811581611633301,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.4123,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6306878306878307,
1073
+ "grad_norm": 4.332226276397705,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.3635,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6349206349206349,
1080
+ "grad_norm": 6.92711877822876,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.4042,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6349206349206349,
1087
+ "eval_loss": 0.28232118487358093,
1088
+ "eval_runtime": 6.8934,
1089
+ "eval_samples_per_second": 57.736,
1090
+ "eval_steps_per_second": 14.507,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.15927236476928e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null