prxy5605 commited on
Commit
ecb31e4
·
verified ·
1 Parent(s): 955615f

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 sha256:01f6d4f7d78fad5d1df0cfe74fb8ed01d399e662ded4f0e2fcf4b193332d09d6
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9180d6823e633bd73b9171374710fd1aa0645c41ae681877c714c6b34b6c79f
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97b2321124f1a01fc2ae4c84d506b82cc58ed7abcc68c2a5664cc4a5cda5b5e4
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6da71b6bd400b715eb9b608f80fe216f0c1227e65daa62986fae2a65ead9c0c
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15d9fd458f796cab82114c3aeeb209b6e8184515b372398f5d42563c66f4c480
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1255dcc8e7d3e3b5f57b938444f1acd2da46f0370053252461f85b890de8dac8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 4.353458881378174,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.03293807641633729,
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": 13.95,
732
  "eval_steps_per_second": 3.49,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4361075721961472e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.6443803310394287,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.04940711462450593,
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": 13.95,
732
  "eval_steps_per_second": 3.49,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.033267457180500656,
737
+ "grad_norm": 1.9534411430358887,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.5377,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.03359683794466403,
744
+ "grad_norm": 3.9449827671051025,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 3.0191,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.03392621870882741,
751
+ "grad_norm": 3.4320390224456787,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.6032,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.034255599472990776,
758
+ "grad_norm": 2.760798692703247,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.862,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03458498023715415,
765
+ "grad_norm": 1.8093721866607666,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.6868,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.03491436100131752,
772
+ "grad_norm": 1.3576546907424927,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.9458,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.035243741765480896,
779
+ "grad_norm": 0.7329630255699158,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.8029,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.03557312252964427,
786
+ "grad_norm": 0.8393235802650452,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.8362,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03590250329380764,
793
+ "grad_norm": 0.7931125164031982,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 3.19,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.036231884057971016,
800
+ "grad_norm": 0.727262020111084,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 3.0535,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.036561264822134384,
807
+ "grad_norm": 0.7600178122520447,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 3.0458,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.03689064558629776,
814
+ "grad_norm": 0.7988314032554626,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 3.0866,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.037220026350461136,
821
+ "grad_norm": 0.8111890554428101,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 3.3127,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.037549407114624504,
828
+ "grad_norm": 0.9296747446060181,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 3.538,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03787878787878788,
835
+ "grad_norm": 0.9645518064498901,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 3.5188,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03820816864295125,
842
+ "grad_norm": 0.877086877822876,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 3.1687,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.038537549407114624,
849
+ "grad_norm": 0.9801080822944641,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 3.5552,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.038866930171278,
856
+ "grad_norm": 0.9617884159088135,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 3.3693,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.03919631093544137,
863
+ "grad_norm": 0.9909358620643616,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 3.3733,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.039525691699604744,
870
+ "grad_norm": 0.9788588285446167,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 3.3048,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.03985507246376811,
877
+ "grad_norm": 0.9471210837364197,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 3.4333,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.04018445322793149,
884
+ "grad_norm": 1.0797932147979736,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 3.5387,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.040513833992094864,
891
+ "grad_norm": 1.0987634658813477,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 3.6053,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.04084321475625823,
898
+ "grad_norm": 1.1885888576507568,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 3.3075,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.04117259552042161,
905
+ "grad_norm": 1.2186295986175537,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 3.8534,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.041501976284584984,
912
+ "grad_norm": 1.1846344470977783,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 3.5999,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.04183135704874835,
919
+ "grad_norm": 1.1363506317138672,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 3.4929,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.04216073781291173,
926
+ "grad_norm": 1.2770732641220093,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 3.5519,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.042490118577075096,
933
+ "grad_norm": 1.1716625690460205,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 3.4708,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.04281949934123847,
940
+ "grad_norm": 1.38254976272583,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 3.806,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.04314888010540185,
947
+ "grad_norm": 1.3303941488265991,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 3.7209,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.043478260869565216,
954
+ "grad_norm": 1.4240809679031372,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 3.7252,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.04380764163372859,
961
+ "grad_norm": 1.4428542852401733,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 3.4899,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.04413702239789196,
968
+ "grad_norm": 1.5575388669967651,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 3.8213,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.044466403162055336,
975
+ "grad_norm": 1.4392671585083008,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 3.8798,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.04479578392621871,
982
+ "grad_norm": 1.4760370254516602,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 3.762,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.04512516469038208,
989
+ "grad_norm": 1.5625317096710205,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 3.8826,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.045454545454545456,
996
+ "grad_norm": 1.865438461303711,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 3.8565,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.045783926218708824,
1003
+ "grad_norm": 1.783351182937622,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.1215,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0461133069828722,
1010
+ "grad_norm": 2.019209861755371,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 4.3478,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.046442687747035576,
1017
+ "grad_norm": 1.9931212663650513,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.7415,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.046772068511198944,
1024
+ "grad_norm": 1.941890835762024,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 4.1205,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.04710144927536232,
1031
+ "grad_norm": 2.1537375450134277,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.9631,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.04743083003952569,
1038
+ "grad_norm": 2.0665690898895264,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 4.0958,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.047760210803689064,
1045
+ "grad_norm": 2.0371243953704834,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 3.8377,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.04808959156785244,
1052
+ "grad_norm": 2.9738543033599854,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 4.5223,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04841897233201581,
1059
+ "grad_norm": 2.5726799964904785,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 4.5206,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.048748353096179184,
1066
+ "grad_norm": 2.7862298488616943,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 4.0664,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.04907773386034255,
1073
+ "grad_norm": 2.910820722579956,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 4.327,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.04940711462450593,
1080
+ "grad_norm": 5.964183330535889,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 4.7147,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.04940711462450593,
1087
+ "eval_loss": 3.6443803310394287,
1088
+ "eval_runtime": 367.3681,
1089
+ "eval_samples_per_second": 13.918,
1090
+ "eval_steps_per_second": 3.482,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.1541613582942208e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null