prxy5605 commited on
Commit
8c1bf04
·
verified ·
1 Parent(s): e5afd93

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:ba5c0a42eb011e4c70ee33cc47b606662988d97d577d899fa4e4dbacd0bf27ca
3
  size 2772512088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8533d4cbb993f2804160777da3a71a5120c9c17ee1dac4c94888b1587fcf801
3
  size 2772512088
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:196cb194f64e238c1eb42d7c5d0bb7da2653d4a6ba8458f6a0b1e406de00bf0f
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d7cb912a6a97f7658da4daffa66c0f47b8dc64f0e4cd5a8f39ae20811d2702
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26fa9f92a8521bb4e0a4aa4fae86fa3a951d683dee88bc4ab7275be2c0804458
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f6c15cfa53bf5a67dfc41cdc67ba58666010d87a096da4a023553f28c7005e
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": 1.7328815460205078,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.03058805536438021,
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": 11.199,
732
  "eval_steps_per_second": 2.801,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.516056955972485e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4893382787704468,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.045882083046570314,
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": 11.199,
732
  "eval_steps_per_second": 2.801,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.030893935918024012,
737
+ "grad_norm": 3.403585195541382,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.0245,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.031199816471667814,
744
+ "grad_norm": 2.861692190170288,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.2598,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.03150569702531161,
751
+ "grad_norm": 2.4802393913269043,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.1695,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.03181157757895542,
758
+ "grad_norm": 1.9378044605255127,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.9145,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03211745813259922,
765
+ "grad_norm": 1.4322959184646606,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.8235,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.032423338686243024,
772
+ "grad_norm": 1.16599702835083,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.6884,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.03272921923988682,
779
+ "grad_norm": 1.0075457096099854,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.9602,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.03303509979353063,
786
+ "grad_norm": 0.8767214417457581,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.5822,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03334098034717443,
793
+ "grad_norm": 0.7345677614212036,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.4849,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.03364686090081823,
800
+ "grad_norm": 0.716529130935669,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.4651,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03395274145446203,
807
+ "grad_norm": 0.8424416184425354,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.5383,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.03425862200810584,
814
+ "grad_norm": 0.8142195343971252,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.6209,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.03456450256174964,
821
+ "grad_norm": 0.9459176063537598,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.5333,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.034870383115393436,
828
+ "grad_norm": 0.8476396203041077,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.6894,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03517626366903724,
835
+ "grad_norm": 0.7426626682281494,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.7568,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03548214422268104,
842
+ "grad_norm": 0.825305163860321,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.5359,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.035788024776324846,
849
+ "grad_norm": 0.9350717663764954,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.7066,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.036093905329968645,
856
+ "grad_norm": 0.7940431237220764,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.7082,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.03639978588361245,
863
+ "grad_norm": 0.7680913805961609,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.8124,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.03670566643725625,
870
+ "grad_norm": 0.7653080224990845,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.6961,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.037011546990900056,
877
+ "grad_norm": 0.8101035356521606,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.6317,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.037317427544543855,
884
+ "grad_norm": 0.8927367329597473,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.5394,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.03762330809818766,
891
+ "grad_norm": 0.9080514907836914,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.6986,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.03792918865183146,
898
+ "grad_norm": 0.852311909198761,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.5795,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.038235069205475265,
905
+ "grad_norm": 0.9210900068283081,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.6229,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.038540949759119064,
912
+ "grad_norm": 0.9056797027587891,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.6382,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.03884683031276286,
919
+ "grad_norm": 0.908682107925415,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.5159,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.03915271086640667,
926
+ "grad_norm": 0.8237525224685669,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.49,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.03945859142005047,
933
+ "grad_norm": 1.1955904960632324,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.3303,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.039764471973694274,
940
+ "grad_norm": 0.8382641077041626,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.5117,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.04007035252733807,
947
+ "grad_norm": 0.9246025085449219,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.5148,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.04037623308098188,
954
+ "grad_norm": 1.0340871810913086,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.3074,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.04068211363462568,
961
+ "grad_norm": 1.146391749382019,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.1229,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.04098799418826948,
968
+ "grad_norm": 1.129131555557251,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.3915,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.04129387474191328,
975
+ "grad_norm": 1.5985831022262573,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.4084,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.04159975529555709,
982
+ "grad_norm": 1.4572705030441284,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.2106,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.04190563584920089,
989
+ "grad_norm": 1.30101478099823,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.5249,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.042211516402844686,
996
+ "grad_norm": 1.8450788259506226,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.4898,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.04251739695648849,
1003
+ "grad_norm": 1.6386133432388306,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.5043,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.04282327751013229,
1010
+ "grad_norm": 1.6151885986328125,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.3907,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.043129158063776096,
1017
+ "grad_norm": 1.8015573024749756,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2989,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.043435038617419895,
1024
+ "grad_norm": 1.5111910104751587,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.1385,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.0437409191710637,
1031
+ "grad_norm": 1.3911969661712646,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.7062,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0440467997247075,
1038
+ "grad_norm": 1.7869279384613037,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.0596,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.044352680278351306,
1045
+ "grad_norm": 2.3753130435943604,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.1928,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.044658560831995105,
1052
+ "grad_norm": 2.210127353668213,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.0643,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04496444138563891,
1059
+ "grad_norm": 3.039236545562744,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.3409,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.04527032193928271,
1066
+ "grad_norm": 3.6834418773651123,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.9128,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.045576202492926515,
1073
+ "grad_norm": 3.559166193008423,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.0185,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.045882083046570314,
1080
+ "grad_norm": 9.378654479980469,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.7419,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.045882083046570314,
1087
+ "eval_loss": 1.4893382787704468,
1088
+ "eval_runtime": 491.8936,
1089
+ "eval_samples_per_second": 11.193,
1090
+ "eval_steps_per_second": 2.799,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2740854339587277e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null