lesso commited on
Commit
ad02a08
·
verified ·
1 Parent(s): 7016058

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 sha256:801fb8d3df79d335f8b9ebaa7e44aba034e5f7eb886dd432cd511f7611d4b667
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2938342f049350028fa5a3ebe92737e98e64ddbaca8f745349a7f9b1095d913
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9e71622339d5f9ed5cf7a894f0e9878835b75859665a33997ff70365f559e45
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5825d5f47fe905c3905e10438f49b302cab8f8becaaf1e0b2d86eb59acf4b58
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf9699cc072a147ea7223575340b99a539ea7103f9f65681346d975c62390506
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd8aadb21627a6138c357bc80663bcf66dbfeffcafb58f6e65d5e7da3e5cb015
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c41bb450efe89fd65fecb2593939b817f9b2794a5d87a632ad90e5ebc9b592b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a1533051e4bee653afc683a4359c329f95831c0354ae8442616cabf80d0caa
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.2756502330303192,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.039658933174697604,
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": 22.367,
732
  "eval_steps_per_second": 5.602,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7007726815150080.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.23389868438243866,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.0594883997620464,
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": 22.367,
732
  "eval_steps_per_second": 5.602,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04005552250644458,
737
+ "grad_norm": 4.0711822509765625,
738
+ "learning_rate": 5.2157368421052626e-05,
739
+ "loss": 0.6342,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.04045211183819155,
744
+ "grad_norm": 1.8220709562301636,
745
+ "learning_rate": 5.163052631578947e-05,
746
+ "loss": 0.2614,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.04084870116993853,
751
+ "grad_norm": 0.1610630750656128,
752
+ "learning_rate": 5.110368421052632e-05,
753
+ "loss": 0.0077,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0412452905016855,
758
+ "grad_norm": 1.660254955291748,
759
+ "learning_rate": 5.057684210526316e-05,
760
+ "loss": 0.2139,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.04164187983343248,
765
+ "grad_norm": 1.2034050226211548,
766
+ "learning_rate": 5.005e-05,
767
+ "loss": 0.1488,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.042038469165179455,
772
+ "grad_norm": 1.123096227645874,
773
+ "learning_rate": 4.9523157894736836e-05,
774
+ "loss": 0.1183,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.042435058496926435,
779
+ "grad_norm": 1.3603556156158447,
780
+ "learning_rate": 4.899631578947368e-05,
781
+ "loss": 0.2229,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.04283164782867341,
786
+ "grad_norm": 1.2517480850219727,
787
+ "learning_rate": 4.846947368421052e-05,
788
+ "loss": 0.1483,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.04322823716042039,
793
+ "grad_norm": 0.9318723082542419,
794
+ "learning_rate": 4.794263157894737e-05,
795
+ "loss": 0.0662,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.04362482649216736,
800
+ "grad_norm": 1.0203633308410645,
801
+ "learning_rate": 4.7415789473684206e-05,
802
+ "loss": 0.1234,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.044021415823914334,
807
+ "grad_norm": 1.8892359733581543,
808
+ "learning_rate": 4.688894736842105e-05,
809
+ "loss": 0.1998,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.044418005155661314,
814
+ "grad_norm": 0.6476733088493347,
815
+ "learning_rate": 4.636210526315789e-05,
816
+ "loss": 0.039,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.04481459448740829,
821
+ "grad_norm": 1.5910590887069702,
822
+ "learning_rate": 4.583526315789473e-05,
823
+ "loss": 0.2231,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.045211183819155266,
828
+ "grad_norm": 1.6052759885787964,
829
+ "learning_rate": 4.530842105263158e-05,
830
+ "loss": 0.2969,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.04560777315090224,
835
+ "grad_norm": 2.3403847217559814,
836
+ "learning_rate": 4.4781578947368416e-05,
837
+ "loss": 0.1473,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.04600436248264922,
842
+ "grad_norm": 3.6207292079925537,
843
+ "learning_rate": 4.425473684210526e-05,
844
+ "loss": 0.5701,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.04640095181439619,
849
+ "grad_norm": 0.6984104514122009,
850
+ "learning_rate": 4.372789473684211e-05,
851
+ "loss": 0.0504,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.04679754114614317,
856
+ "grad_norm": 2.5241734981536865,
857
+ "learning_rate": 4.320105263157895e-05,
858
+ "loss": 0.2509,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.047194130477890145,
863
+ "grad_norm": 1.5402919054031372,
864
+ "learning_rate": 4.2674210526315786e-05,
865
+ "loss": 0.1996,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.04759071980963712,
870
+ "grad_norm": 2.3560476303100586,
871
+ "learning_rate": 4.2147368421052626e-05,
872
+ "loss": 0.3034,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0479873091413841,
877
+ "grad_norm": 1.9385439157485962,
878
+ "learning_rate": 4.162052631578947e-05,
879
+ "loss": 0.3015,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.04838389847313107,
884
+ "grad_norm": 1.4906829595565796,
885
+ "learning_rate": 4.109368421052631e-05,
886
+ "loss": 0.1302,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.04878048780487805,
891
+ "grad_norm": 2.4340176582336426,
892
+ "learning_rate": 4.056684210526316e-05,
893
+ "loss": 0.4329,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.04917707713662502,
898
+ "grad_norm": 2.110347032546997,
899
+ "learning_rate": 4.004e-05,
900
+ "loss": 0.3068,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.049573666468372,
905
+ "grad_norm": 1.2856132984161377,
906
+ "learning_rate": 3.951315789473684e-05,
907
+ "loss": 0.1518,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.049970255800118976,
912
+ "grad_norm": 2.3550281524658203,
913
+ "learning_rate": 3.898631578947368e-05,
914
+ "loss": 0.117,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.050366845131865956,
919
+ "grad_norm": 2.4217026233673096,
920
+ "learning_rate": 3.845947368421052e-05,
921
+ "loss": 0.4333,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.05076343446361293,
926
+ "grad_norm": 1.6932317018508911,
927
+ "learning_rate": 3.7932631578947367e-05,
928
+ "loss": 0.148,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0511600237953599,
933
+ "grad_norm": 1.6000185012817383,
934
+ "learning_rate": 3.7405789473684206e-05,
935
+ "loss": 0.0932,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.05155661312710688,
940
+ "grad_norm": 1.805180311203003,
941
+ "learning_rate": 3.6878947368421045e-05,
942
+ "loss": 0.2301,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.051953202458853855,
947
+ "grad_norm": 2.063298463821411,
948
+ "learning_rate": 3.635210526315789e-05,
949
+ "loss": 0.1673,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.052349791790600834,
954
+ "grad_norm": 2.706456422805786,
955
+ "learning_rate": 3.582526315789474e-05,
956
+ "loss": 0.389,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.05274638112234781,
961
+ "grad_norm": 2.0284225940704346,
962
+ "learning_rate": 3.5298421052631576e-05,
963
+ "loss": 0.1468,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.05314297045409479,
968
+ "grad_norm": 1.6976109743118286,
969
+ "learning_rate": 3.477157894736842e-05,
970
+ "loss": 0.0762,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.05353955978584176,
975
+ "grad_norm": 1.7858450412750244,
976
+ "learning_rate": 3.424473684210526e-05,
977
+ "loss": 0.2102,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.05393614911758874,
982
+ "grad_norm": 1.9341448545455933,
983
+ "learning_rate": 3.37178947368421e-05,
984
+ "loss": 0.2661,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.05433273844933571,
989
+ "grad_norm": 3.936488628387451,
990
+ "learning_rate": 3.319105263157894e-05,
991
+ "loss": 0.6706,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.054729327781082686,
996
+ "grad_norm": 1.7080624103546143,
997
+ "learning_rate": 3.2664210526315786e-05,
998
+ "loss": 0.1062,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.055125917112829666,
1003
+ "grad_norm": 1.5581916570663452,
1004
+ "learning_rate": 3.213736842105263e-05,
1005
+ "loss": 0.0934,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.05552250644457664,
1010
+ "grad_norm": 1.3080987930297852,
1011
+ "learning_rate": 3.161052631578947e-05,
1012
+ "loss": 0.0814,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.05591909577632362,
1017
+ "grad_norm": 2.823137044906616,
1018
+ "learning_rate": 3.108368421052632e-05,
1019
+ "loss": 0.4453,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.05631568510807059,
1024
+ "grad_norm": 0.21419651806354523,
1025
+ "learning_rate": 3.0556842105263156e-05,
1026
+ "loss": 0.0073,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.05671227443981757,
1031
+ "grad_norm": 0.22324123978614807,
1032
+ "learning_rate": 3.0029999999999995e-05,
1033
+ "loss": 0.0051,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.057108863771564544,
1038
+ "grad_norm": 0.2457597404718399,
1039
+ "learning_rate": 2.9503157894736838e-05,
1040
+ "loss": 0.0057,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.057505453103311524,
1045
+ "grad_norm": 3.4714629650115967,
1046
+ "learning_rate": 2.8976315789473684e-05,
1047
+ "loss": 0.5372,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0579020424350585,
1052
+ "grad_norm": 0.028041277080774307,
1053
+ "learning_rate": 2.8449473684210523e-05,
1054
+ "loss": 0.0009,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.05829863176680547,
1059
+ "grad_norm": 1.089476466178894,
1060
+ "learning_rate": 2.7922631578947366e-05,
1061
+ "loss": 0.0318,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.05869522109855245,
1066
+ "grad_norm": 2.4500927925109863,
1067
+ "learning_rate": 2.7395789473684212e-05,
1068
+ "loss": 0.4794,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.05909181043029942,
1073
+ "grad_norm": 0.0174604132771492,
1074
+ "learning_rate": 2.686894736842105e-05,
1075
+ "loss": 0.0006,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.0594883997620464,
1080
+ "grad_norm": 2.791302442550659,
1081
+ "learning_rate": 2.634210526315789e-05,
1082
+ "loss": 0.4109,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.0594883997620464,
1087
+ "eval_loss": 0.23389868438243866,
1088
+ "eval_runtime": 47.3967,
1089
+ "eval_samples_per_second": 22.407,
1090
+ "eval_steps_per_second": 5.612,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.047757213138944e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null