0x1202 commited on
Commit
d08a923
·
verified ·
1 Parent(s): f67c753

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 sha256:934414cd3f1e0cc8fa69298eab44f5784fa93428d235d858317956a0c5487f08
3
  size 800116456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1563775f500bff5b6f73763477e6fb11baf9a2cddd940220df3667d558268098
3
  size 800116456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f03bae06074dae5438b1779e2cdfd43399ff34becd7f7d89d943966d5646bb75
3
  size 406743412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c2c6c41fabfb173912d11cdb6022eb1961726c8cb6ac12067b5458a9da3d54
3
  size 406743412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ccb126dcaa196e7c6bf49b6225269bb88015edf1bfa789ac32419036d48a391
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1ef9a7f6661480ce1bc40b994a2e44b6131a51ed76fa1cf5d8d0dfcba18317c
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": 1.2783050537109375,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06532745386248572,
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": 11.11,
732
  "eval_steps_per_second": 2.78,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5828232918007808e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1891545057296753,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.09799118079372857,
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": 11.11,
732
  "eval_steps_per_second": 2.78,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.06598072840111056,
737
+ "grad_norm": 1.1558902263641357,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.7719,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.06663400293973543,
744
+ "grad_norm": 1.4872947931289673,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.1378,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.06728727747836027,
751
+ "grad_norm": 1.0422314405441284,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.1045,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06794055201698514,
758
+ "grad_norm": 0.7367865443229675,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.1046,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06859382655561,
765
+ "grad_norm": 0.6021361351013184,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.1328,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06924710109423485,
772
+ "grad_norm": 0.5900995135307312,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.0765,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06990037563285971,
779
+ "grad_norm": 0.6766594052314758,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.0976,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.07055365017148457,
786
+ "grad_norm": 0.6198120713233948,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.1298,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.07120692471010942,
793
+ "grad_norm": 0.5900450944900513,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.0869,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.07186019924873428,
800
+ "grad_norm": 0.6149023175239563,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.0465,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07251347378735913,
807
+ "grad_norm": 0.7566827535629272,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.1044,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.073166748325984,
814
+ "grad_norm": 0.6897150874137878,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.1931,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07382002286460886,
821
+ "grad_norm": 0.6127074360847473,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.1939,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0744732974032337,
828
+ "grad_norm": 0.6431254744529724,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.19,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.07512657194185857,
835
+ "grad_norm": 0.6799481511116028,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.1862,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.07577984648048343,
842
+ "grad_norm": 0.8189933896064758,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.2423,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.07643312101910828,
849
+ "grad_norm": 0.6609489321708679,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.1231,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.07708639555773314,
856
+ "grad_norm": 0.6720132231712341,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.1152,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.07773967009635799,
863
+ "grad_norm": 0.7263075709342957,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.1214,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.07839294463498285,
870
+ "grad_norm": 0.7537389397621155,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.1379,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07904621917360771,
877
+ "grad_norm": 0.7317739725112915,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.0658,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.07969949371223256,
884
+ "grad_norm": 0.7288187146186829,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.0737,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.08035276825085742,
891
+ "grad_norm": 0.7624008059501648,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.1498,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.08100604278948229,
898
+ "grad_norm": 0.8137470483779907,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.1176,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.08165931732810713,
905
+ "grad_norm": 0.8314720988273621,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.1011,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.082312591866732,
912
+ "grad_norm": 0.931859016418457,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.1223,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08296586640535684,
919
+ "grad_norm": 0.8852472901344299,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.1286,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0836191409439817,
926
+ "grad_norm": 0.9761730432510376,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.0655,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.08427241548260657,
933
+ "grad_norm": 1.0209838151931763,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.1098,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.08492569002123142,
940
+ "grad_norm": 1.0987162590026855,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.1064,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.08557896455985628,
947
+ "grad_norm": 1.1544086933135986,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.1352,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.08623223909848114,
954
+ "grad_norm": 1.3515336513519287,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.19,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.08688551363710599,
961
+ "grad_norm": 1.2961175441741943,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.2007,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.08753878817573085,
968
+ "grad_norm": 1.4801435470581055,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.2618,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0881920627143557,
975
+ "grad_norm": 1.4647985696792603,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.1986,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.08884533725298056,
982
+ "grad_norm": 1.6596142053604126,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.2046,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.08949861179160543,
989
+ "grad_norm": 1.9073797464370728,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.3493,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.09015188633023027,
996
+ "grad_norm": 2.077632427215576,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.3231,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.09080516086885514,
1003
+ "grad_norm": 2.0005605220794678,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.1936,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.09145843540748,
1010
+ "grad_norm": 2.0587823390960693,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.2959,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.09211170994610485,
1017
+ "grad_norm": 2.110560655593872,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2369,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09276498448472971,
1024
+ "grad_norm": 2.4109227657318115,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.1992,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.09341825902335456,
1031
+ "grad_norm": 2.4234650135040283,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.4701,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.09407153356197942,
1038
+ "grad_norm": 2.4619882106781006,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.2991,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.09472480810060428,
1045
+ "grad_norm": 2.8142271041870117,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.4536,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.09537808263922913,
1052
+ "grad_norm": 2.967550039291382,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.4966,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.096031357177854,
1059
+ "grad_norm": 3.013756036758423,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.4739,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.09668463171647886,
1066
+ "grad_norm": 3.109238862991333,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.308,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.0973379062551037,
1073
+ "grad_norm": 4.284872055053711,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.7051,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.09799118079372857,
1080
+ "grad_norm": 6.529964923858643,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.6451,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.09799118079372857,
1087
+ "eval_loss": 1.1891545057296753,
1088
+ "eval_runtime": 231.8506,
1089
+ "eval_samples_per_second": 11.119,
1090
+ "eval_steps_per_second": 2.782,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.3722808348717875e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null