lesso commited on
Commit
692728c
·
verified ·
1 Parent(s): e563cd4

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 sha256:65eeb9518dce5029c3abab2f641c6cd1495f8ffb250fdc802074d0e3b3c0c058
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08fc2eb4e2f0efc377f3065fe0ed16dee5f1c97107e0f748c48fd49f7257cb3e
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a62e67b7e4537383f9b18e1c2ec6d70814909f6ee144dbbc79ca8c69b618ea1
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e068b48dda9e0c302972c72dd4138373aef0f7f0a75b92ca990fa04885f166dd
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5177b99de2ebe2866410b50ce667df81108b0e862df5daeafaa44affc26c45c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c06149525c44ea6d8edf7a015c720bfbce856fe0fc17ae05707281ee481137fc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac9085a964616f2d2af1a309022ca2f10b583138a852293c2266e9df64914089
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:191b4f74b8892fe464b31b446bc6f50032359ce22cb38236d5fdccf47f27920e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7867631912231445,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.2844950213371266,
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": 51.134,
732
  "eval_steps_per_second": 12.783,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6452772253728768.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7382230758666992,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.4267425320056899,
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": 51.134,
732
  "eval_steps_per_second": 12.783,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.28733997155049784,
737
+ "grad_norm": 3.876413583755493,
738
+ "learning_rate": 5.2199052631578945e-05,
739
+ "loss": 1.506,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.2901849217638691,
744
+ "grad_norm": 3.7558364868164062,
745
+ "learning_rate": 5.167178947368422e-05,
746
+ "loss": 1.7346,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.2930298719772404,
751
+ "grad_norm": 4.743800163269043,
752
+ "learning_rate": 5.114452631578948e-05,
753
+ "loss": 2.0661,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.2958748221906117,
758
+ "grad_norm": 5.817846298217773,
759
+ "learning_rate": 5.061726315789474e-05,
760
+ "loss": 1.8006,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.29871977240398295,
765
+ "grad_norm": 7.89326810836792,
766
+ "learning_rate": 5.009e-05,
767
+ "loss": 1.876,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.3015647226173542,
772
+ "grad_norm": 4.653040885925293,
773
+ "learning_rate": 4.9562736842105266e-05,
774
+ "loss": 2.5936,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.30440967283072545,
779
+ "grad_norm": 4.584991931915283,
780
+ "learning_rate": 4.903547368421053e-05,
781
+ "loss": 2.6147,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.30725462304409673,
786
+ "grad_norm": 5.551419258117676,
787
+ "learning_rate": 4.850821052631579e-05,
788
+ "loss": 2.4942,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.310099573257468,
793
+ "grad_norm": 5.248828887939453,
794
+ "learning_rate": 4.7980947368421055e-05,
795
+ "loss": 2.2754,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.3129445234708393,
800
+ "grad_norm": 4.641688346862793,
801
+ "learning_rate": 4.745368421052632e-05,
802
+ "loss": 2.1724,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.3157894736842105,
807
+ "grad_norm": 5.3421196937561035,
808
+ "learning_rate": 4.692642105263158e-05,
809
+ "loss": 1.227,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.3186344238975818,
814
+ "grad_norm": 3.9133739471435547,
815
+ "learning_rate": 4.6399157894736844e-05,
816
+ "loss": 1.6015,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.32147937411095306,
821
+ "grad_norm": 4.454647541046143,
822
+ "learning_rate": 4.5871894736842107e-05,
823
+ "loss": 1.7845,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.32432432432432434,
828
+ "grad_norm": 3.597501516342163,
829
+ "learning_rate": 4.5344631578947376e-05,
830
+ "loss": 1.502,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.32716927453769556,
835
+ "grad_norm": 4.597258567810059,
836
+ "learning_rate": 4.481736842105263e-05,
837
+ "loss": 1.4825,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.33001422475106684,
842
+ "grad_norm": 4.391196250915527,
843
+ "learning_rate": 4.4290105263157895e-05,
844
+ "loss": 1.5272,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.3328591749644381,
849
+ "grad_norm": 4.424014568328857,
850
+ "learning_rate": 4.3762842105263165e-05,
851
+ "loss": 1.9359,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.3357041251778094,
856
+ "grad_norm": 4.372839450836182,
857
+ "learning_rate": 4.323557894736843e-05,
858
+ "loss": 2.0909,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.3385490753911807,
863
+ "grad_norm": 4.121306896209717,
864
+ "learning_rate": 4.2708315789473684e-05,
865
+ "loss": 1.5885,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.3413940256045519,
870
+ "grad_norm": 3.6656622886657715,
871
+ "learning_rate": 4.218105263157895e-05,
872
+ "loss": 1.0627,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.3442389758179232,
877
+ "grad_norm": 4.600314617156982,
878
+ "learning_rate": 4.1653789473684217e-05,
879
+ "loss": 1.4696,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.34708392603129445,
884
+ "grad_norm": 3.4500224590301514,
885
+ "learning_rate": 4.112652631578948e-05,
886
+ "loss": 1.5351,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.34992887624466573,
891
+ "grad_norm": 3.504693031311035,
892
+ "learning_rate": 4.0599263157894736e-05,
893
+ "loss": 1.5592,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.352773826458037,
898
+ "grad_norm": 3.320112943649292,
899
+ "learning_rate": 4.0072000000000005e-05,
900
+ "loss": 1.4447,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.35561877667140823,
905
+ "grad_norm": 5.274588108062744,
906
+ "learning_rate": 3.954473684210527e-05,
907
+ "loss": 1.6083,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.3584637268847795,
912
+ "grad_norm": 4.05495548248291,
913
+ "learning_rate": 3.901747368421053e-05,
914
+ "loss": 1.9941,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.3613086770981508,
919
+ "grad_norm": 4.75917911529541,
920
+ "learning_rate": 3.849021052631579e-05,
921
+ "loss": 1.592,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.36415362731152207,
926
+ "grad_norm": 4.389928340911865,
927
+ "learning_rate": 3.796294736842106e-05,
928
+ "loss": 1.812,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.3669985775248933,
933
+ "grad_norm": 4.688922882080078,
934
+ "learning_rate": 3.743568421052632e-05,
935
+ "loss": 1.9126,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.36984352773826457,
940
+ "grad_norm": 3.168738603591919,
941
+ "learning_rate": 3.6908421052631576e-05,
942
+ "loss": 1.4718,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.37268847795163584,
947
+ "grad_norm": 3.0869128704071045,
948
+ "learning_rate": 3.6381157894736846e-05,
949
+ "loss": 1.1472,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.3755334281650071,
954
+ "grad_norm": 3.687636137008667,
955
+ "learning_rate": 3.585389473684211e-05,
956
+ "loss": 1.6765,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.3783783783783784,
961
+ "grad_norm": 4.952862739562988,
962
+ "learning_rate": 3.532663157894737e-05,
963
+ "loss": 2.0811,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.3812233285917496,
968
+ "grad_norm": 3.6529781818389893,
969
+ "learning_rate": 3.4799368421052634e-05,
970
+ "loss": 1.4349,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.3840682788051209,
975
+ "grad_norm": 4.10825777053833,
976
+ "learning_rate": 3.42721052631579e-05,
977
+ "loss": 2.0628,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.3869132290184922,
982
+ "grad_norm": 3.2980964183807373,
983
+ "learning_rate": 3.374484210526316e-05,
984
+ "loss": 1.0951,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.38975817923186346,
989
+ "grad_norm": 4.034358501434326,
990
+ "learning_rate": 3.321757894736842e-05,
991
+ "loss": 1.9296,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.39260312944523473,
996
+ "grad_norm": 4.9551167488098145,
997
+ "learning_rate": 3.2690315789473686e-05,
998
+ "loss": 2.0927,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.39544807965860596,
1003
+ "grad_norm": 5.580440521240234,
1004
+ "learning_rate": 3.216305263157895e-05,
1005
+ "loss": 1.9642,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.39829302987197723,
1010
+ "grad_norm": 3.773940324783325,
1011
+ "learning_rate": 3.163578947368421e-05,
1012
+ "loss": 1.7335,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.4011379800853485,
1017
+ "grad_norm": 3.043595552444458,
1018
+ "learning_rate": 3.1108526315789475e-05,
1019
+ "loss": 1.0307,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.4039829302987198,
1024
+ "grad_norm": 4.4264912605285645,
1025
+ "learning_rate": 3.058126315789474e-05,
1026
+ "loss": 1.7947,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.406827880512091,
1031
+ "grad_norm": 4.281518459320068,
1032
+ "learning_rate": 3.0054e-05,
1033
+ "loss": 2.0495,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.4096728307254623,
1038
+ "grad_norm": 3.6441235542297363,
1039
+ "learning_rate": 2.9526736842105263e-05,
1040
+ "loss": 1.5132,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.41251778093883357,
1045
+ "grad_norm": 4.037598609924316,
1046
+ "learning_rate": 2.899947368421053e-05,
1047
+ "loss": 1.862,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.41536273115220484,
1052
+ "grad_norm": 2.887089729309082,
1053
+ "learning_rate": 2.847221052631579e-05,
1054
+ "loss": 1.359,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.4182076813655761,
1059
+ "grad_norm": 3.586642026901245,
1060
+ "learning_rate": 2.7944947368421052e-05,
1061
+ "loss": 1.7427,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.42105263157894735,
1066
+ "grad_norm": 4.924892425537109,
1067
+ "learning_rate": 2.741768421052632e-05,
1068
+ "loss": 2.592,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.4238975817923186,
1073
+ "grad_norm": 4.330611705780029,
1074
+ "learning_rate": 2.689042105263158e-05,
1075
+ "loss": 2.1681,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.4267425320056899,
1080
+ "grad_norm": 6.093458652496338,
1081
+ "learning_rate": 2.636315789473684e-05,
1082
+ "loss": 3.1873,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.4267425320056899,
1087
+ "eval_loss": 1.7382230758666992,
1088
+ "eval_runtime": 2.8485,
1089
+ "eval_samples_per_second": 51.958,
1090
+ "eval_steps_per_second": 12.99,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 9599165336125440.0,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null