prxy5604 commited on
Commit
5f520b4
·
verified ·
1 Parent(s): a6843b1

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 sha256:76c654ad27de6088d16ec1bd4ea3cc4519cb635a2b7ef006586c122050ffcf11
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3745ae08fd96959091add45857fc0c1204b7e58ee678be7a69775aab26c0c15e
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc6ae9cde05c62da705e9b95de3b9ea52cb9d23f7013f203239c9554fb46f0cd
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7edbe26b3c69c06cfc78f50232767ff3f4b1d91b0294ec7c8709d14fbb4801ab
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:702c45c0237a22bb5ce4069004750502f3877aa025892f667028bf6137107874
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85da9d613aa95222784d5e6613c282f60629c1518f05ec7ea3bed566c111315b
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": 6.02884578704834,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.04357298474945534,
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": 11.295,
732
  "eval_steps_per_second": 5.647,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4762717692821504e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.00246524810791,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.06535947712418301,
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": 11.295,
732
  "eval_steps_per_second": 5.647,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04400871459694989,
737
+ "grad_norm": 42.128944396972656,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 5.0307,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.044444444444444446,
744
+ "grad_norm": 19.087020874023438,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 4.9041,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.044880174291938996,
751
+ "grad_norm": 8.862335205078125,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 4.3268,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.04531590413943355,
758
+ "grad_norm": 5.625029563903809,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 4.1794,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0457516339869281,
765
+ "grad_norm": 4.465734958648682,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 3.8786,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.04618736383442266,
772
+ "grad_norm": 4.2806243896484375,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 3.5648,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.046623093681917215,
779
+ "grad_norm": 4.626951217651367,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 3.8994,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.047058823529411764,
786
+ "grad_norm": 4.95627498626709,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 3.6665,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.04749455337690632,
793
+ "grad_norm": 3.974017858505249,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 3.6386,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.04793028322440087,
800
+ "grad_norm": 4.023645877838135,
801
+ "learning_rate": 5e-05,
802
+ "loss": 3.4637,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.048366013071895426,
807
+ "grad_norm": 3.7657175064086914,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 3.6163,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.048801742919389976,
814
+ "grad_norm": 4.199164867401123,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 3.4856,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.04923747276688453,
821
+ "grad_norm": 4.223781108856201,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 3.4757,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.04967320261437908,
828
+ "grad_norm": 4.435927867889404,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 3.3169,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.05010893246187364,
835
+ "grad_norm": 4.904012680053711,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 3.5495,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.050544662309368195,
842
+ "grad_norm": 4.705389022827148,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 3.0275,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.050980392156862744,
849
+ "grad_norm": 5.674432277679443,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 2.4125,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0514161220043573,
856
+ "grad_norm": 5.154523849487305,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 2.4193,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.05185185185185185,
863
+ "grad_norm": 5.284936904907227,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 3.0715,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.05228758169934641,
870
+ "grad_norm": 5.14494514465332,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 2.6556,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.052723311546840956,
877
+ "grad_norm": 5.538849353790283,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 3.0354,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.05315904139433551,
884
+ "grad_norm": 7.487570285797119,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 3.9713,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.05359477124183006,
891
+ "grad_norm": 8.709990501403809,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 4.0759,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.05403050108932462,
898
+ "grad_norm": 8.605923652648926,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 3.5372,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.054466230936819175,
905
+ "grad_norm": 8.194428443908691,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 3.3761,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.054901960784313725,
912
+ "grad_norm": 8.833706855773926,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 3.4749,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.05533769063180828,
919
+ "grad_norm": 8.356715202331543,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 3.1606,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.05577342047930283,
926
+ "grad_norm": 10.272514343261719,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 2.5981,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.05620915032679739,
933
+ "grad_norm": 8.101070404052734,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 3.4551,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.05664488017429194,
940
+ "grad_norm": 8.390080451965332,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 3.329,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.05708061002178649,
947
+ "grad_norm": 7.999818325042725,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 3.1951,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.05751633986928104,
954
+ "grad_norm": 8.268589973449707,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 3.0559,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0579520697167756,
961
+ "grad_norm": 7.182888984680176,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 2.7636,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.058387799564270156,
968
+ "grad_norm": 7.375523567199707,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 2.9165,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.058823529411764705,
975
+ "grad_norm": 7.143980026245117,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 2.835,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.05925925925925926,
982
+ "grad_norm": 7.666155815124512,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 2.9644,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.05969498910675381,
989
+ "grad_norm": 8.490532875061035,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 3.2043,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.06013071895424837,
996
+ "grad_norm": 9.01056957244873,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 3.2254,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.06056644880174292,
1003
+ "grad_norm": 9.418787956237793,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 3.1616,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.06100217864923747,
1010
+ "grad_norm": 10.980050086975098,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 2.756,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.06143790849673202,
1017
+ "grad_norm": 9.275108337402344,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 3.0247,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.06187363834422658,
1024
+ "grad_norm": 9.312789916992188,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 3.2638,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.062309368191721136,
1031
+ "grad_norm": 8.673617362976074,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 3.0619,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.06274509803921569,
1038
+ "grad_norm": 11.994880676269531,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 3.6095,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.06318082788671024,
1045
+ "grad_norm": 12.651790618896484,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 2.9046,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0636165577342048,
1052
+ "grad_norm": 14.072041511535645,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 3.1311,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.06405228758169934,
1059
+ "grad_norm": 11.299721717834473,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 3.4079,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0644880174291939,
1066
+ "grad_norm": 13.439027786254883,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 3.3159,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.06492374727668845,
1073
+ "grad_norm": 21.56414222717285,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 4.244,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.06535947712418301,
1080
+ "grad_norm": 19.723522186279297,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 4.4341,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.06535947712418301,
1087
+ "eval_loss": 4.00246524810791,
1088
+ "eval_runtime": 342.244,
1089
+ "eval_samples_per_second": 11.296,
1090
+ "eval_steps_per_second": 5.648,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2107353360891904e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null