prxy5604 commited on
Commit
fd26e60
·
verified ·
1 Parent(s): a963088

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 sha256:56c6bf8c7c5ae516931386d3855704d96843a49e5e62de680ed94b30d3398bb4
3
  size 478211024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b18328c96bc0ab780e26434eeb6e9aedcfadaf3d1d054fe8fc4258c7c9cdebc1
3
  size 478211024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:875eef51819bf03f1a1a252f3d10facdf21cdc96229b31b3790107466f06c35f
3
  size 956679634
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d5d967ac0d5d450ee221e39e9838d127f4174097bd3dc11719b4ecd8d463ecc
3
  size 956679634
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:333fb34de7627d3f9e97a4a74f0cc7987acea26fb643cbc10a4a40a965099bd3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b159081cdc30a3c0ed340684fc0f253cf8e92fd70d00d3b12e6d6e68b00953ae
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.0880825519561768,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.6611570247933884,
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": 18.011,
732
  "eval_steps_per_second": 9.041,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 8.101566995654246e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0583877563476562,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.9917355371900827,
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": 18.011,
732
  "eval_steps_per_second": 9.041,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6677685950413224,
737
+ "grad_norm": 1.748067021369934,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 4.4367,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.6743801652892562,
744
+ "grad_norm": 1.8786406517028809,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 5.3412,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.6809917355371901,
751
+ "grad_norm": 1.8346900939941406,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 4.9618,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.687603305785124,
758
+ "grad_norm": 2.015852928161621,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 5.5926,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.6942148760330579,
765
+ "grad_norm": 2.249979019165039,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 4.8259,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.7008264462809918,
772
+ "grad_norm": 2.263035774230957,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 5.104,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.7074380165289256,
779
+ "grad_norm": 2.640855550765991,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 5.146,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.7140495867768595,
786
+ "grad_norm": 3.1351351737976074,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 4.2835,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.7206611570247934,
793
+ "grad_norm": 2.632106304168701,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 4.8549,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7272727272727273,
800
+ "grad_norm": 2.945842742919922,
801
+ "learning_rate": 5e-05,
802
+ "loss": 4.8564,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.7338842975206612,
807
+ "grad_norm": 3.851283550262451,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 5.1433,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.740495867768595,
814
+ "grad_norm": 0.6680141687393188,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 3.4089,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.7471074380165289,
821
+ "grad_norm": 0.7174019813537598,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 3.8666,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.7537190082644628,
828
+ "grad_norm": 0.7039559483528137,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 3.7843,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.7603305785123967,
835
+ "grad_norm": 0.7135390043258667,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 3.8314,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.7669421487603306,
842
+ "grad_norm": 0.7308880686759949,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 4.1674,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.7735537190082644,
849
+ "grad_norm": 0.7223635315895081,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 3.8675,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.7801652892561983,
856
+ "grad_norm": 0.7319607138633728,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 3.9047,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.7867768595041322,
863
+ "grad_norm": 0.7675497531890869,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 4.1523,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.7933884297520661,
870
+ "grad_norm": 0.8165543079376221,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 4.1521,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.8,
877
+ "grad_norm": 0.8304678797721863,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 4.1744,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.8066115702479338,
884
+ "grad_norm": 0.8759053945541382,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 4.2122,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.8132231404958677,
891
+ "grad_norm": 0.8702043890953064,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 4.427,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.8198347107438017,
898
+ "grad_norm": 0.9653429985046387,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 4.2492,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.8264462809917356,
905
+ "grad_norm": 0.9605560302734375,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 4.6257,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.8330578512396695,
912
+ "grad_norm": 0.9582360982894897,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 3.8951,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.8396694214876033,
919
+ "grad_norm": 1.1498273611068726,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 4.4283,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.8462809917355372,
926
+ "grad_norm": 1.1258846521377563,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 4.792,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.8528925619834711,
933
+ "grad_norm": 1.4514033794403076,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 4.5196,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.859504132231405,
940
+ "grad_norm": 1.3290873765945435,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 4.5567,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.8661157024793389,
947
+ "grad_norm": 1.4877480268478394,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 4.5017,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.8727272727272727,
954
+ "grad_norm": 1.3383150100708008,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 4.966,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.8793388429752066,
961
+ "grad_norm": 1.3537639379501343,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 4.9792,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.8859504132231405,
968
+ "grad_norm": 1.4388115406036377,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 4.5168,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.8925619834710744,
975
+ "grad_norm": 1.5659295320510864,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 4.675,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.8991735537190083,
982
+ "grad_norm": 1.614781141281128,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 4.4682,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.9057851239669421,
989
+ "grad_norm": 1.750377893447876,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 4.9327,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.912396694214876,
996
+ "grad_norm": 2.194397449493408,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 5.1882,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.9190082644628099,
1003
+ "grad_norm": 1.799832820892334,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 3.5735,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.9256198347107438,
1010
+ "grad_norm": 1.9374184608459473,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 5.4029,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.9322314049586777,
1017
+ "grad_norm": 2.2784645557403564,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 5.2612,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.9388429752066115,
1024
+ "grad_norm": 2.151506185531616,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 5.2387,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.9454545454545454,
1031
+ "grad_norm": 2.211778163909912,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 5.3567,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.9520661157024793,
1038
+ "grad_norm": 2.3867406845092773,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 4.5479,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.9586776859504132,
1045
+ "grad_norm": 2.5046918392181396,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 4.0853,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.9652892561983472,
1052
+ "grad_norm": 2.8745017051696777,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 4.4699,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.971900826446281,
1059
+ "grad_norm": 3.2906479835510254,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 5.3134,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.9785123966942149,
1066
+ "grad_norm": 3.933941125869751,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 5.3385,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.9851239669421488,
1073
+ "grad_norm": 0.7648929953575134,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 3.8574,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.9917355371900827,
1080
+ "grad_norm": 1.3944673538208008,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 4.5333,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.9917355371900827,
1087
+ "eval_loss": 1.0583877563476562,
1088
+ "eval_runtime": 14.1642,
1089
+ "eval_samples_per_second": 18.003,
1090
+ "eval_steps_per_second": 9.037,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.2086253793050624e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null