antimage88 commited on
Commit
8016937
·
verified ·
1 Parent(s): cf67971

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:ce8bb768a803feb2938d2212043c12772bfa7b224dff251c9629bbaf19771139
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76087fedd69f5bddc48ae687e9ecaa06b471d05c7a4c097d8836170b47044e9c
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b46beb38d7752ee2c4d3974fcc33c99797d7670ab580698439d695da07bc735
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b994c1bc566c15772c5b7d926d08e40cef1b777414ee75c125fdf8ebcc1f9311
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:909294f9810662e81c6a6a6bc09408f9404139fa033b543135c104c09c20d1a6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2d16e26b607143a2db1854a45d2fa5fcae48b77287d24997de5ec767b8e12d4
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": 2.215390682220459,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.008809796493700995,
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": 12.413,
732
  "eval_steps_per_second": 3.104,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5034747848543437e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.151653289794922,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.013214694740551492,
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": 12.413,
732
  "eval_steps_per_second": 3.104,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.008897894458638006,
737
+ "grad_norm": 0.9050671458244324,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.2883,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.008985992423575015,
744
+ "grad_norm": 1.1153374910354614,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.3626,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.009074090388512025,
751
+ "grad_norm": 1.0824012756347656,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.0213,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.009162188353449036,
758
+ "grad_norm": 1.352673888206482,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.3118,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.009250286318386045,
765
+ "grad_norm": 1.4655729532241821,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.1875,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.009338384283323056,
772
+ "grad_norm": 2.1609301567077637,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.2598,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.009426482248260065,
779
+ "grad_norm": 1.9131826162338257,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.96,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.009514580213197074,
786
+ "grad_norm": 1.315741777420044,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.8584,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.009602678178134086,
793
+ "grad_norm": 1.335062026977539,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.7208,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.009690776143071095,
800
+ "grad_norm": 1.405185580253601,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.9594,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.009778874108008106,
807
+ "grad_norm": 1.1304210424423218,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.7369,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.009866972072945115,
814
+ "grad_norm": 1.1716078519821167,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.6646,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.009955070037882124,
821
+ "grad_norm": 1.1705647706985474,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.9726,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.010043168002819135,
828
+ "grad_norm": 0.96344393491745,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.8153,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.010131265967756145,
835
+ "grad_norm": 1.2785229682922363,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.0573,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.010219363932693154,
842
+ "grad_norm": 0.9819148778915405,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.1911,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.010307461897630165,
849
+ "grad_norm": 0.9272201657295227,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.7888,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.010395559862567174,
856
+ "grad_norm": 1.0092214345932007,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.7979,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.010483657827504185,
863
+ "grad_norm": 0.9747551679611206,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.1713,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.010571755792441195,
870
+ "grad_norm": 0.7432554364204407,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.7009,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.010659853757378204,
877
+ "grad_norm": 0.921968936920166,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.7757,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.010747951722315215,
884
+ "grad_norm": 1.2300440073013306,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.2349,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.010836049687252224,
891
+ "grad_norm": 0.9479213356971741,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.6906,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.010924147652189235,
898
+ "grad_norm": 1.0780354738235474,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.0537,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.011012245617126245,
905
+ "grad_norm": 1.0302643775939941,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.7242,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.011100343582063254,
912
+ "grad_norm": 0.8660168051719666,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.0556,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.011188441547000265,
919
+ "grad_norm": 0.862213134765625,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.1566,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.011276539511937274,
926
+ "grad_norm": 0.8829602003097534,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.9982,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.011364637476874283,
933
+ "grad_norm": 1.0032317638397217,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.1343,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.011452735441811294,
940
+ "grad_norm": 0.7568157911300659,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.4642,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.011540833406748304,
947
+ "grad_norm": 0.8952288031578064,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.9543,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.011628931371685315,
954
+ "grad_norm": 1.0352801084518433,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.2417,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.011717029336622324,
961
+ "grad_norm": 1.1499708890914917,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.2376,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.011805127301559333,
968
+ "grad_norm": 0.9345830678939819,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.1228,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.011893225266496344,
975
+ "grad_norm": 1.0170817375183105,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.0897,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.011981323231433354,
982
+ "grad_norm": 1.066669225692749,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.1516,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.012069421196370363,
989
+ "grad_norm": 1.1325106620788574,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.1015,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.012157519161307374,
996
+ "grad_norm": 0.9881788492202759,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.2977,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.012245617126244383,
1003
+ "grad_norm": 1.055762767791748,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.4716,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.012333715091181394,
1010
+ "grad_norm": 1.007345199584961,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.5644,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.012421813056118404,
1017
+ "grad_norm": 1.18160879611969,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.4766,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.012509911021055413,
1024
+ "grad_norm": 1.1100205183029175,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.4212,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.012598008985992424,
1031
+ "grad_norm": 1.360809564590454,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.4825,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.012686106950929433,
1038
+ "grad_norm": 1.160150408744812,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.5554,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.012774204915866444,
1045
+ "grad_norm": 1.450110912322998,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.6773,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.012862302880803454,
1052
+ "grad_norm": 1.3221920728683472,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.5966,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.012950400845740463,
1059
+ "grad_norm": 1.7865961790084839,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.9323,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.013038498810677474,
1066
+ "grad_norm": 1.967854380607605,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.7435,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.013126596775614483,
1073
+ "grad_norm": 1.8304901123046875,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.717,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.013214694740551492,
1080
+ "grad_norm": 2.8990800380706787,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 3.4761,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.013214694740551492,
1087
+ "eval_loss": 2.151653289794922,
1088
+ "eval_runtime": 1538.9923,
1089
+ "eval_samples_per_second": 12.422,
1090
+ "eval_steps_per_second": 3.106,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2585384489294234e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null