lesso commited on
Commit
d11f303
·
verified ·
1 Parent(s): 7160951

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 sha256:00789afdf1298113eb5db8f405596c2943b3740715f3a974fba6eb4cb82ffb85
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61bff498aa85ca873e498a014f88180af58bb8d3c3ea0fed6696690e45479399
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51de54048560f61b1fffadcce54ac9ca17cf9088f9317cae4b99d07672a1993f
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f3b102e4bd52df811f6d5bc62eb64e727bd27a4dd608834ff7e2260f95d18ff
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd41f0eb63f76991fd9773adcdcd219526a8c1ac4271f5e0f155536249e18f2e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43589bf31dcf3a8292666ae1b4d609fe2c8374ff0549ebffa0f2267a003b2261
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a046f3bc9d619a7e62601f3cf33ff02f6ad189db5b564eab88c1bb00e13b059d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7431a5f5e7b667e1ad74dfbaf504ae1d5a622ff6eb54e4f385c161883d2319ba
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3124351501464844,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.003128079202965419,
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": 9.263,
732
  "eval_steps_per_second": 2.316,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.61327403949097e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.270316481590271,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.004692118804448128,
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": 9.263,
732
  "eval_steps_per_second": 2.316,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0031593599949950734,
737
+ "grad_norm": 2.628980875015259,
738
+ "learning_rate": 5.278263157894736e-05,
739
+ "loss": 1.5805,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0031906407870247273,
744
+ "grad_norm": 3.0475142002105713,
745
+ "learning_rate": 5.224947368421053e-05,
746
+ "loss": 2.2909,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0032219215790543817,
751
+ "grad_norm": 3.8600575923919678,
752
+ "learning_rate": 5.171631578947368e-05,
753
+ "loss": 2.6855,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0032532023710840356,
758
+ "grad_norm": 6.607161998748779,
759
+ "learning_rate": 5.1183157894736844e-05,
760
+ "loss": 3.4535,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.00328448316311369,
765
+ "grad_norm": 5.392179012298584,
766
+ "learning_rate": 5.065e-05,
767
+ "loss": 2.8729,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0033157639551433444,
772
+ "grad_norm": 5.193509578704834,
773
+ "learning_rate": 5.011684210526315e-05,
774
+ "loss": 2.9775,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0033470447471729984,
779
+ "grad_norm": 5.64705228805542,
780
+ "learning_rate": 4.958368421052631e-05,
781
+ "loss": 3.152,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0033783255392026527,
786
+ "grad_norm": 6.723267555236816,
787
+ "learning_rate": 4.9050526315789473e-05,
788
+ "loss": 2.7698,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0034096063312323067,
793
+ "grad_norm": 6.680335521697998,
794
+ "learning_rate": 4.851736842105263e-05,
795
+ "loss": 3.5541,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.003440887123261961,
800
+ "grad_norm": 5.122313976287842,
801
+ "learning_rate": 4.798421052631579e-05,
802
+ "loss": 2.6375,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.003472167915291615,
807
+ "grad_norm": 6.740786075592041,
808
+ "learning_rate": 4.745105263157895e-05,
809
+ "loss": 2.9484,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.0035034487073212694,
814
+ "grad_norm": 6.559206962585449,
815
+ "learning_rate": 4.69178947368421e-05,
816
+ "loss": 3.0081,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.0035347294993509234,
821
+ "grad_norm": 6.304297924041748,
822
+ "learning_rate": 4.638473684210526e-05,
823
+ "loss": 2.3097,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0035660102913805778,
828
+ "grad_norm": 7.039328098297119,
829
+ "learning_rate": 4.585157894736842e-05,
830
+ "loss": 2.5406,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.003597291083410232,
835
+ "grad_norm": 6.471532344818115,
836
+ "learning_rate": 4.531842105263158e-05,
837
+ "loss": 2.4596,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.003628571875439886,
842
+ "grad_norm": 5.916082859039307,
843
+ "learning_rate": 4.478526315789473e-05,
844
+ "loss": 3.4104,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0036598526674695405,
849
+ "grad_norm": 6.180294990539551,
850
+ "learning_rate": 4.425210526315789e-05,
851
+ "loss": 2.7326,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0036911334594991944,
856
+ "grad_norm": 5.961937427520752,
857
+ "learning_rate": 4.3718947368421054e-05,
858
+ "loss": 2.6678,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.003722414251528849,
863
+ "grad_norm": 6.331954002380371,
864
+ "learning_rate": 4.318578947368421e-05,
865
+ "loss": 2.4229,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0037536950435585028,
870
+ "grad_norm": 4.922019958496094,
871
+ "learning_rate": 4.265263157894736e-05,
872
+ "loss": 3.1542,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.003784975835588157,
877
+ "grad_norm": 7.65913724899292,
878
+ "learning_rate": 4.211947368421052e-05,
879
+ "loss": 3.0389,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.003816256627617811,
884
+ "grad_norm": 6.049108505249023,
885
+ "learning_rate": 4.1586315789473684e-05,
886
+ "loss": 2.3807,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.0038475374196474655,
891
+ "grad_norm": 5.221220016479492,
892
+ "learning_rate": 4.105315789473684e-05,
893
+ "loss": 2.1381,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.00387881821167712,
898
+ "grad_norm": 5.57716178894043,
899
+ "learning_rate": 4.052e-05,
900
+ "loss": 2.2677,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.003910099003706774,
905
+ "grad_norm": 7.513245582580566,
906
+ "learning_rate": 3.998684210526316e-05,
907
+ "loss": 2.5971,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.003941379795736428,
912
+ "grad_norm": 6.161846160888672,
913
+ "learning_rate": 3.945368421052631e-05,
914
+ "loss": 2.1936,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.003972660587766083,
919
+ "grad_norm": 4.7585530281066895,
920
+ "learning_rate": 3.892052631578947e-05,
921
+ "loss": 1.966,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.004003941379795736,
926
+ "grad_norm": 7.348730087280273,
927
+ "learning_rate": 3.838736842105263e-05,
928
+ "loss": 2.5792,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0040352221718253905,
933
+ "grad_norm": 4.698526382446289,
934
+ "learning_rate": 3.785421052631579e-05,
935
+ "loss": 2.139,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.004066502963855045,
940
+ "grad_norm": 8.570194244384766,
941
+ "learning_rate": 3.732105263157894e-05,
942
+ "loss": 2.1969,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.004097783755884699,
947
+ "grad_norm": 5.913156032562256,
948
+ "learning_rate": 3.67878947368421e-05,
949
+ "loss": 2.7538,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.004129064547914353,
954
+ "grad_norm": 7.469818592071533,
955
+ "learning_rate": 3.6254736842105264e-05,
956
+ "loss": 2.0199,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.004160345339944007,
961
+ "grad_norm": 6.480471134185791,
962
+ "learning_rate": 3.572157894736842e-05,
963
+ "loss": 2.316,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.0041916261319736615,
968
+ "grad_norm": 6.787581443786621,
969
+ "learning_rate": 3.518842105263158e-05,
970
+ "loss": 2.2553,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.004222906924003316,
975
+ "grad_norm": 5.075686454772949,
976
+ "learning_rate": 3.465526315789473e-05,
977
+ "loss": 2.6243,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.00425418771603297,
982
+ "grad_norm": 7.515790939331055,
983
+ "learning_rate": 3.4122105263157894e-05,
984
+ "loss": 2.215,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.004285468508062624,
989
+ "grad_norm": 6.6318840980529785,
990
+ "learning_rate": 3.358894736842105e-05,
991
+ "loss": 2.2177,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.004316749300092278,
996
+ "grad_norm": 5.295938968658447,
997
+ "learning_rate": 3.305578947368421e-05,
998
+ "loss": 2.0566,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.004348030092121933,
1003
+ "grad_norm": 6.72779655456543,
1004
+ "learning_rate": 3.252263157894737e-05,
1005
+ "loss": 2.3354,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.004379310884151587,
1010
+ "grad_norm": 8.442112922668457,
1011
+ "learning_rate": 3.198947368421052e-05,
1012
+ "loss": 3.0371,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.0044105916761812405,
1017
+ "grad_norm": 6.13646125793457,
1018
+ "learning_rate": 3.1456315789473684e-05,
1019
+ "loss": 2.3442,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.004441872468210895,
1024
+ "grad_norm": 6.592789649963379,
1025
+ "learning_rate": 3.092315789473684e-05,
1026
+ "loss": 1.933,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.004473153260240549,
1031
+ "grad_norm": 6.862227439880371,
1032
+ "learning_rate": 3.039e-05,
1033
+ "loss": 2.5313,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.004504434052270204,
1038
+ "grad_norm": 6.412154197692871,
1039
+ "learning_rate": 2.9856842105263153e-05,
1040
+ "loss": 2.1372,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.004535714844299858,
1045
+ "grad_norm": 9.697041511535645,
1046
+ "learning_rate": 2.9323684210526317e-05,
1047
+ "loss": 2.9306,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0045669956363295116,
1052
+ "grad_norm": 5.902824878692627,
1053
+ "learning_rate": 2.879052631578947e-05,
1054
+ "loss": 1.9473,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.004598276428359166,
1059
+ "grad_norm": 7.2379889488220215,
1060
+ "learning_rate": 2.8257368421052628e-05,
1061
+ "loss": 2.64,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.00462955722038882,
1066
+ "grad_norm": 6.2485809326171875,
1067
+ "learning_rate": 2.772421052631579e-05,
1068
+ "loss": 2.1195,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.004660838012418475,
1073
+ "grad_norm": 8.572454452514648,
1074
+ "learning_rate": 2.7191052631578946e-05,
1075
+ "loss": 2.3414,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.004692118804448128,
1080
+ "grad_norm": 8.547698974609375,
1081
+ "learning_rate": 2.6657894736842104e-05,
1082
+ "loss": 2.8386,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.004692118804448128,
1087
+ "eval_loss": 1.270316481590271,
1088
+ "eval_runtime": 1454.4582,
1089
+ "eval_samples_per_second": 9.255,
1090
+ "eval_steps_per_second": 2.314,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.419911059236454e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null