prxy5606 commited on
Commit
23dfb99
·
verified ·
1 Parent(s): 12ad83c

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:d93b77bbe99c46eda05d21335d34352e5d4047bd2c289ba91c160f64e45ec8a2
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb2ad2412821c284c19399cd0ab72a8bfe67e21547019843ac75285f292276ca
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcfd0cf5a455b8eed5db612cc91ed5f70ce7eb4d6b1485fcca0c006f8f64b70f
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd8c54d20b4fef7ca6cec7e692ee76f5d672cae499a6a8e713795d2dd4e23ad3
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ede1e9de2e627f9aceaad433ca3d8e80a458236d1d9d360e37984ffc9bcec7d5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7317f6ea8a14587206260c7cecd1ae4ef2c0983816323a25b17844b388bb6343
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": 1.1804490089416504,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0847996608013568,
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": 5.39,
732
  "eval_steps_per_second": 1.348,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.2788643293128294e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.166787028312683,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.1271994912020352,
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": 5.39,
732
  "eval_steps_per_second": 1.348,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.08564765740937036,
737
+ "grad_norm": 2.422438144683838,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 4.3436,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.08649565401738393,
744
+ "grad_norm": 2.2779412269592285,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 4.4265,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.08734365062539749,
751
+ "grad_norm": 2.0400304794311523,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 4.1714,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.08819164723341107,
758
+ "grad_norm": 1.880078911781311,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 4.1855,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.08903964384142464,
765
+ "grad_norm": 1.8325084447860718,
766
+ "learning_rate": 5e-05,
767
+ "loss": 4.3204,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0898876404494382,
772
+ "grad_norm": 1.8795162439346313,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 4.4312,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.09073563705745177,
779
+ "grad_norm": 1.8876075744628906,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 4.4647,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.09158363366546533,
786
+ "grad_norm": 1.8472651243209839,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 4.6483,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0924316302734789,
793
+ "grad_norm": 1.9912683963775635,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 4.7963,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.09327962688149248,
800
+ "grad_norm": 2.042919635772705,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.1027,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.09412762348950604,
807
+ "grad_norm": 2.073084592819214,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 4.7349,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.09497562009751961,
814
+ "grad_norm": 2.118652105331421,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 4.3654,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.09582361670553317,
821
+ "grad_norm": 2.092261791229248,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 4.7062,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.09667161331354675,
828
+ "grad_norm": 2.0549087524414062,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 4.8884,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.09751960992156031,
835
+ "grad_norm": 1.9667161703109741,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 5.0113,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09836760652957388,
842
+ "grad_norm": 2.183830499649048,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 4.6784,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.09921560313758745,
849
+ "grad_norm": 2.051776885986328,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.0518,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.10006359974560101,
856
+ "grad_norm": 2.446779251098633,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 4.695,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.10091159635361459,
863
+ "grad_norm": 2.3001549243927,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 4.3205,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.10175959296162815,
870
+ "grad_norm": 2.7006070613861084,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 4.8592,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.10260758956964172,
877
+ "grad_norm": 2.1881604194641113,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 4.6239,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.1034555861776553,
884
+ "grad_norm": 2.380777597427368,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 5.3121,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.10430358278566886,
891
+ "grad_norm": 2.426774024963379,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.1067,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.10515157939368243,
898
+ "grad_norm": 2.5026845932006836,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 4.1341,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.10599957600169599,
905
+ "grad_norm": 2.3385419845581055,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 4.9654,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.10684757260970956,
912
+ "grad_norm": 2.7509677410125732,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 4.3466,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.10769556921772312,
919
+ "grad_norm": 2.9490578174591064,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 5.1551,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.1085435658257367,
926
+ "grad_norm": 2.265023946762085,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 4.798,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.10939156243375027,
933
+ "grad_norm": 2.2808432579040527,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 4.588,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.11023955904176383,
940
+ "grad_norm": 2.5440714359283447,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.2281,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1110875556497774,
947
+ "grad_norm": 2.297882556915283,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 4.8398,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.11193555225779096,
954
+ "grad_norm": 2.478205919265747,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 4.3081,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.11278354886580454,
961
+ "grad_norm": 2.669485330581665,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 4.8905,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.11363154547381811,
968
+ "grad_norm": 2.624321222305298,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 4.794,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.11447954208183167,
975
+ "grad_norm": 2.6909666061401367,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 5.1577,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.11532753868984524,
982
+ "grad_norm": 2.5199904441833496,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 4.4238,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1161755352978588,
989
+ "grad_norm": 2.583390712738037,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 4.7589,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.11702353190587238,
996
+ "grad_norm": 3.0719287395477295,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 5.1474,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.11787152851388595,
1003
+ "grad_norm": 3.1999142169952393,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.6627,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.11871952512189951,
1010
+ "grad_norm": 2.7626335620880127,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 5.1589,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.11956752172991308,
1017
+ "grad_norm": 2.6776087284088135,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 4.9263,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.12041551833792664,
1024
+ "grad_norm": 2.8333215713500977,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 5.1223,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.12126351494594022,
1031
+ "grad_norm": 2.761094093322754,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 4.9352,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.12211151155395378,
1038
+ "grad_norm": 3.142958402633667,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 4.7899,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.12295950816196735,
1045
+ "grad_norm": 3.279120445251465,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.433,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.12380750476998093,
1052
+ "grad_norm": 3.364237070083618,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 4.5097,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.12465550137799448,
1059
+ "grad_norm": 3.385071039199829,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 4.753,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.12550349798600804,
1066
+ "grad_norm": 3.5379798412323,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 4.9349,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.12635149459402162,
1073
+ "grad_norm": 4.043220043182373,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 5.0459,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.1271994912020352,
1080
+ "grad_norm": 4.804100036621094,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 4.3865,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.1271994912020352,
1087
+ "eval_loss": 1.166787028312683,
1088
+ "eval_runtime": 368.1394,
1089
+ "eval_samples_per_second": 5.397,
1090
+ "eval_steps_per_second": 1.35,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.4129302514355405e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null