risolmayo commited on
Commit
1aa289b
·
verified ·
1 Parent(s): 9b2c015

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 sha256:95ca017198e889f2b49ecba5031f599f8aff94d5e4b6700d1b0edda2f8d98ff9
3
  size 1163996488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b7020e3ab87b129cb67493f559ee5fe5c6436749636f83e565158c36c9ebc72
3
  size 1163996488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c577071787452e79d94449ff76435a7595581913be4d251e46e3e31cb8522dd0
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89345749e4f5198b5f9a1becf1382709d116091984cac67f8b29ca9cda462711
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:cd49f4b5c9171d7d413a6308a1432a43aa3be22f5e06b7d1382cc08f11a113b3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62cbde3227a0ffa5d241d2419820cd89d59007138f0bfb451f1f489a2f483fd3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb2481782945fd527fd68f03d6ecc086ae38c0c705bfbe5de3172ab751f2e6c8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6405f9fabb3d2e45adcc13758e2849ef278b423e1ee939354d45ffa4e9327204
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4850772619247437,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.036010082823190494,
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": 13.229,
732
  "eval_steps_per_second": 3.309,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.3537802697100493e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4379560947418213,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.05401512423478574,
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": 13.229,
732
  "eval_steps_per_second": 3.309,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.036370183651422396,
737
+ "grad_norm": 0.31662315130233765,
738
+ "learning_rate": 4.264362337302798e-05,
739
+ "loss": 1.0832,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.036730284479654304,
744
+ "grad_norm": 0.35080909729003906,
745
+ "learning_rate": 4.1983350186928894e-05,
746
+ "loss": 0.964,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.037090385307886206,
751
+ "grad_norm": 0.36373916268348694,
752
+ "learning_rate": 4.132253477269233e-05,
753
+ "loss": 0.9958,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.037450486136118115,
758
+ "grad_norm": 0.4141411781311035,
759
+ "learning_rate": 4.0661357790654345e-05,
760
+ "loss": 1.0403,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03781058696435002,
765
+ "grad_norm": 0.42372411489486694,
766
+ "learning_rate": 4e-05,
767
+ "loss": 1.0866,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.038170687792581925,
772
+ "grad_norm": 0.48200201988220215,
773
+ "learning_rate": 3.933864220934566e-05,
774
+ "loss": 1.0786,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.03853078862081383,
779
+ "grad_norm": 0.4316590130329132,
780
+ "learning_rate": 3.8677465227307676e-05,
781
+ "loss": 0.9489,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.038890889449045736,
786
+ "grad_norm": 0.40134397149086,
787
+ "learning_rate": 3.8016649813071106e-05,
788
+ "loss": 1.0985,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03925099027727764,
793
+ "grad_norm": 0.43675699830055237,
794
+ "learning_rate": 3.735637662697203e-05,
795
+ "loss": 1.0101,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.03961109110550954,
800
+ "grad_norm": 0.38096266984939575,
801
+ "learning_rate": 3.669682618110671e-05,
802
+ "loss": 1.0738,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03997119193374145,
807
+ "grad_norm": 0.31821751594543457,
808
+ "learning_rate": 3.6038178789981494e-05,
809
+ "loss": 1.0365,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.04033129276197335,
814
+ "grad_norm": 0.35773828625679016,
815
+ "learning_rate": 3.538061452121656e-05,
816
+ "loss": 0.9939,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.04069139359020526,
821
+ "grad_norm": 0.33209124207496643,
822
+ "learning_rate": 3.472431314631724e-05,
823
+ "loss": 0.979,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.04105149441843716,
828
+ "grad_norm": 0.3005915582180023,
829
+ "learning_rate": 3.406945409152632e-05,
830
+ "loss": 1.0878,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.04141159524666907,
835
+ "grad_norm": 0.2932342290878296,
836
+ "learning_rate": 3.341621638877064e-05,
837
+ "loss": 1.0154,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.04177169607490097,
842
+ "grad_norm": 0.3328295052051544,
843
+ "learning_rate": 3.276477862671562e-05,
844
+ "loss": 1.156,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.04213179690313288,
849
+ "grad_norm": 0.34108060598373413,
850
+ "learning_rate": 3.21153189019408e-05,
851
+ "loss": 1.3088,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.04249189773136478,
856
+ "grad_norm": 0.319013774394989,
857
+ "learning_rate": 3.146801477025013e-05,
858
+ "loss": 1.3014,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.042851998559596684,
863
+ "grad_norm": 0.3462431728839874,
864
+ "learning_rate": 3.082304319812994e-05,
865
+ "loss": 1.3673,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.04321209938782859,
870
+ "grad_norm": 0.34266746044158936,
871
+ "learning_rate": 3.0180580514368037e-05,
872
+ "loss": 1.4107,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.043572200216060494,
877
+ "grad_norm": 0.31460511684417725,
878
+ "learning_rate": 2.9540802361847212e-05,
879
+ "loss": 1.1764,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0439323010442924,
884
+ "grad_norm": 0.31650468707084656,
885
+ "learning_rate": 2.890388364952623e-05,
886
+ "loss": 1.1812,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.044292401872524305,
891
+ "grad_norm": 0.34145647287368774,
892
+ "learning_rate": 2.8269998504621416e-05,
893
+ "loss": 1.368,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.044652502700756214,
898
+ "grad_norm": 0.3476177155971527,
899
+ "learning_rate": 2.7639320225002108e-05,
900
+ "loss": 1.188,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.045012603528988115,
905
+ "grad_norm": 0.4023088812828064,
906
+ "learning_rate": 2.7012021231812666e-05,
907
+ "loss": 1.5084,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.045372704357220024,
912
+ "grad_norm": 0.39794808626174927,
913
+ "learning_rate": 2.638827302233428e-05,
914
+ "loss": 1.5975,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.045732805185451926,
919
+ "grad_norm": 0.46040594577789307,
920
+ "learning_rate": 2.576824612309934e-05,
921
+ "loss": 1.5714,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.046092906013683835,
926
+ "grad_norm": 0.4382641017436981,
927
+ "learning_rate": 2.5152110043271166e-05,
928
+ "loss": 1.575,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.04645300684191574,
933
+ "grad_norm": 0.4103611409664154,
934
+ "learning_rate": 2.454003322830192e-05,
935
+ "loss": 1.5312,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.04681310767014764,
940
+ "grad_norm": 0.443014919757843,
941
+ "learning_rate": 2.393218301388123e-05,
942
+ "loss": 1.3191,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.04717320849837955,
947
+ "grad_norm": 0.4959178864955902,
948
+ "learning_rate": 2.3328725580188395e-05,
949
+ "loss": 1.5888,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.04753330932661145,
954
+ "grad_norm": 0.5022261738777161,
955
+ "learning_rate": 2.272982590646029e-05,
956
+ "loss": 1.5632,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.04789341015484336,
961
+ "grad_norm": 0.45459896326065063,
962
+ "learning_rate": 2.2135647725887744e-05,
963
+ "loss": 1.5,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.04825351098307526,
968
+ "grad_norm": 0.504411518573761,
969
+ "learning_rate": 2.1546353480852495e-05,
970
+ "loss": 1.6626,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.04861361181130717,
975
+ "grad_norm": 0.5704218149185181,
976
+ "learning_rate": 2.096210427851706e-05,
977
+ "loss": 1.9689,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.04897371263953907,
982
+ "grad_norm": 0.5692024230957031,
983
+ "learning_rate": 2.038305984677969e-05,
984
+ "loss": 1.5937,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.04933381346777098,
989
+ "grad_norm": 0.560541033744812,
990
+ "learning_rate": 1.9809378490606264e-05,
991
+ "loss": 1.7188,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.04969391429600288,
996
+ "grad_norm": 0.5904568433761597,
997
+ "learning_rate": 1.9241217048751406e-05,
998
+ "loss": 1.6569,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.05005401512423478,
1003
+ "grad_norm": 0.6273323893547058,
1004
+ "learning_rate": 1.867873085088026e-05,
1005
+ "loss": 1.9395,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.05041411595246669,
1010
+ "grad_norm": 0.7930026650428772,
1011
+ "learning_rate": 1.8122073675102935e-05,
1012
+ "loss": 1.866,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.05077421678069859,
1017
+ "grad_norm": 0.7339215278625488,
1018
+ "learning_rate": 1.75713977059331e-05,
1019
+ "loss": 1.7738,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.0511343176089305,
1024
+ "grad_norm": 0.7646173238754272,
1025
+ "learning_rate": 1.702685349268226e-05,
1026
+ "loss": 1.8332,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.051494418437162404,
1031
+ "grad_norm": 0.8946234583854675,
1032
+ "learning_rate": 1.648858990830108e-05,
1033
+ "loss": 1.9375,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.05185451926539431,
1038
+ "grad_norm": 1.015981912612915,
1039
+ "learning_rate": 1.5956754108678996e-05,
1040
+ "loss": 2.0351,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.052214620093626214,
1045
+ "grad_norm": 1.0599825382232666,
1046
+ "learning_rate": 1.5431491492413288e-05,
1047
+ "loss": 1.959,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.05257472092185812,
1052
+ "grad_norm": 1.3140443563461304,
1053
+ "learning_rate": 1.491294566105852e-05,
1054
+ "loss": 1.9238,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.052934821750090025,
1059
+ "grad_norm": 1.3724371194839478,
1060
+ "learning_rate": 1.4401258379867335e-05,
1061
+ "loss": 1.8381,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.053294922578321934,
1066
+ "grad_norm": 1.6155120134353638,
1067
+ "learning_rate": 1.3896569539033253e-05,
1068
+ "loss": 1.9153,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.053655023406553835,
1073
+ "grad_norm": 1.8847979307174683,
1074
+ "learning_rate": 1.3399017115446067e-05,
1075
+ "loss": 2.0038,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.05401512423478574,
1080
+ "grad_norm": 2.680107831954956,
1081
+ "learning_rate": 1.2908737134970367e-05,
1082
+ "loss": 2.086,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.05401512423478574,
1087
+ "eval_loss": 1.4379560947418213,
1088
+ "eval_runtime": 352.6306,
1089
+ "eval_samples_per_second": 13.263,
1090
+ "eval_steps_per_second": 3.318,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.0290072838406144e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null