brixeus commited on
Commit
acf0e02
·
verified ·
1 Parent(s): dc3bf5d

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:f35bfa18bdf96d73d0776a4d22831da45517a45fe299a138f453e6fc4fa2b066
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5c4c721fa9253c931faa80ca77c266a6026ff8c589ce0ff7dc94e5ad197359
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f233bbdc9db2c456c625b641f36e2e111c2839bf81277fbd465edb35cea937a
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75122d33d5f1a39ca63f93bf46482abd76de497219072ee1599ab66fa0d80355
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c19603883f401b22c80b09e5759616914515eaed24945964ab2bd875ab59183
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff00dc559515a0d1f85451ec340e8d92f0b326f010d6394af24f97ecea7d08be
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99ca67f9a35cd1c50df3d93bedf5a6642db2c7847c021a0a8d3f44c1bf4993d3
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4002ee03f4202a6a410bde3375cd186d152ce129e8a177eb112bee1f18b1e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.8152918815612793,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.019923295313044778,
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": 13.92,
732
  "eval_steps_per_second": 3.481,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.42188868534272e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7750892639160156,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.029884942969567167,
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": 13.92,
732
  "eval_steps_per_second": 3.481,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.020122528266175225,
737
+ "grad_norm": 0.7810643315315247,
738
+ "learning_rate": 8.715724127386972e-05,
739
+ "loss": 1.3115,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.02032176121930567,
744
+ "grad_norm": 0.9216941595077515,
745
+ "learning_rate": 8.688653405904652e-05,
746
+ "loss": 1.8541,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.02052099417243612,
751
+ "grad_norm": 0.733933687210083,
752
+ "learning_rate": 8.661343332988869e-05,
753
+ "loss": 1.5391,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.02072022712556657,
758
+ "grad_norm": 0.7394716739654541,
759
+ "learning_rate": 8.633795680751116e-05,
760
+ "loss": 1.3938,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.020919460078697015,
765
+ "grad_norm": 0.8477760553359985,
766
+ "learning_rate": 8.606012236719073e-05,
767
+ "loss": 1.9247,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.021118693031827465,
772
+ "grad_norm": 0.669335663318634,
773
+ "learning_rate": 8.577994803720606e-05,
774
+ "loss": 1.728,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.021317925984957912,
779
+ "grad_norm": 0.6468355655670166,
780
+ "learning_rate": 8.549745199766792e-05,
781
+ "loss": 1.3566,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.02151715893808836,
786
+ "grad_norm": 0.6598238945007324,
787
+ "learning_rate": 8.521265257933948e-05,
788
+ "loss": 1.4654,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.02171639189121881,
793
+ "grad_norm": 0.6626983284950256,
794
+ "learning_rate": 8.492556826244687e-05,
795
+ "loss": 1.4336,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.021915624844349255,
800
+ "grad_norm": 0.6764017939567566,
801
+ "learning_rate": 8.463621767547998e-05,
802
+ "loss": 1.3487,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.022114857797479702,
807
+ "grad_norm": 0.8265367150306702,
808
+ "learning_rate": 8.434461959398376e-05,
809
+ "loss": 1.487,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.022314090750610152,
814
+ "grad_norm": 0.6030274629592896,
815
+ "learning_rate": 8.405079293933986e-05,
816
+ "loss": 1.3341,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.0225133237037406,
821
+ "grad_norm": 0.7178739309310913,
822
+ "learning_rate": 8.375475677753881e-05,
823
+ "loss": 1.537,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.022712556656871045,
828
+ "grad_norm": 0.6907858848571777,
829
+ "learning_rate": 8.345653031794292e-05,
830
+ "loss": 1.6211,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.022911789610001496,
835
+ "grad_norm": 0.8321515321731567,
836
+ "learning_rate": 8.315613291203976e-05,
837
+ "loss": 1.6012,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.023111022563131942,
842
+ "grad_norm": 0.7017425894737244,
843
+ "learning_rate": 8.285358405218655e-05,
844
+ "loss": 1.6058,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.02331025551626239,
849
+ "grad_norm": 0.6512852311134338,
850
+ "learning_rate": 8.25489033703452e-05,
851
+ "loss": 1.4762,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.02350948846939284,
856
+ "grad_norm": 0.6753814816474915,
857
+ "learning_rate": 8.224211063680853e-05,
858
+ "loss": 1.3924,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.023708721422523286,
863
+ "grad_norm": 0.6458118557929993,
864
+ "learning_rate": 8.19332257589174e-05,
865
+ "loss": 1.427,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.023907954375653732,
870
+ "grad_norm": 0.7541099786758423,
871
+ "learning_rate": 8.162226877976887e-05,
872
+ "loss": 1.6374,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.024107187328784183,
877
+ "grad_norm": 0.7807430624961853,
878
+ "learning_rate": 8.130925987691569e-05,
879
+ "loss": 1.8552,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.02430642028191463,
884
+ "grad_norm": 0.7646523118019104,
885
+ "learning_rate": 8.099421936105702e-05,
886
+ "loss": 1.5886,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.024505653235045076,
891
+ "grad_norm": 0.7880610823631287,
892
+ "learning_rate": 8.067716767472045e-05,
893
+ "loss": 1.6209,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.024704886188175523,
898
+ "grad_norm": 0.7491058111190796,
899
+ "learning_rate": 8.035812539093557e-05,
900
+ "loss": 1.6557,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.024904119141305973,
905
+ "grad_norm": 0.7884393930435181,
906
+ "learning_rate": 8.003711321189895e-05,
907
+ "loss": 1.768,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.02510335209443642,
912
+ "grad_norm": 0.8286698460578918,
913
+ "learning_rate": 7.971415196763088e-05,
914
+ "loss": 1.7031,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.025302585047566866,
919
+ "grad_norm": 0.9087210297584534,
920
+ "learning_rate": 7.938926261462366e-05,
921
+ "loss": 1.9608,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.025501818000697316,
926
+ "grad_norm": 0.7920821309089661,
927
+ "learning_rate": 7.906246623448183e-05,
928
+ "loss": 1.6142,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.025701050953827763,
933
+ "grad_norm": 0.8957509398460388,
934
+ "learning_rate": 7.873378403255419e-05,
935
+ "loss": 1.7978,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.02590028390695821,
940
+ "grad_norm": 0.6929237246513367,
941
+ "learning_rate": 7.840323733655778e-05,
942
+ "loss": 1.5131,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.02609951686008866,
947
+ "grad_norm": 0.8800172805786133,
948
+ "learning_rate": 7.807084759519405e-05,
949
+ "loss": 1.8921,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.026298749813219106,
954
+ "grad_norm": 0.7827117443084717,
955
+ "learning_rate": 7.773663637675694e-05,
956
+ "loss": 1.7208,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.026497982766349553,
961
+ "grad_norm": 0.7875890135765076,
962
+ "learning_rate": 7.740062536773352e-05,
963
+ "loss": 1.7275,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.026697215719480003,
968
+ "grad_norm": 0.8130915760993958,
969
+ "learning_rate": 7.706283637139658e-05,
970
+ "loss": 1.8376,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.02689644867261045,
975
+ "grad_norm": 0.8318361639976501,
976
+ "learning_rate": 7.672329130639005e-05,
977
+ "loss": 1.8565,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.027095681625740897,
982
+ "grad_norm": 0.8131917715072632,
983
+ "learning_rate": 7.638201220530665e-05,
984
+ "loss": 1.7917,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.027294914578871347,
989
+ "grad_norm": 0.9158076643943787,
990
+ "learning_rate": 7.603902121325813e-05,
991
+ "loss": 1.9982,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.027494147532001793,
996
+ "grad_norm": 0.9296155571937561,
997
+ "learning_rate": 7.569434058643844e-05,
998
+ "loss": 2.0053,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.02769338048513224,
1003
+ "grad_norm": 0.9064381718635559,
1004
+ "learning_rate": 7.534799269067953e-05,
1005
+ "loss": 1.9478,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.02789261343826269,
1010
+ "grad_norm": 0.9871942400932312,
1011
+ "learning_rate": 7.500000000000001e-05,
1012
+ "loss": 2.1819,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.028091846391393137,
1017
+ "grad_norm": 0.8777363300323486,
1018
+ "learning_rate": 7.465038509514688e-05,
1019
+ "loss": 2.0469,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.028291079344523583,
1024
+ "grad_norm": 1.0275037288665771,
1025
+ "learning_rate": 7.42991706621303e-05,
1026
+ "loss": 1.9602,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.028490312297654034,
1031
+ "grad_norm": 0.8730279803276062,
1032
+ "learning_rate": 7.394637949075154e-05,
1033
+ "loss": 1.9302,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.02868954525078448,
1038
+ "grad_norm": 0.8100825548171997,
1039
+ "learning_rate": 7.35920344731241e-05,
1040
+ "loss": 1.6562,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.028888778203914927,
1045
+ "grad_norm": 1.087735652923584,
1046
+ "learning_rate": 7.323615860218843e-05,
1047
+ "loss": 2.1821,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.029088011157045374,
1052
+ "grad_norm": 1.0589756965637207,
1053
+ "learning_rate": 7.287877497021978e-05,
1054
+ "loss": 2.2272,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.029287244110175824,
1059
+ "grad_norm": 1.2219501733779907,
1060
+ "learning_rate": 7.251990676732984e-05,
1061
+ "loss": 2.2479,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.02948647706330627,
1066
+ "grad_norm": 1.0689516067504883,
1067
+ "learning_rate": 7.215957727996207e-05,
1068
+ "loss": 2.2357,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.029685710016436717,
1073
+ "grad_norm": 0.8567739129066467,
1074
+ "learning_rate": 7.179780988938051e-05,
1075
+ "loss": 1.8367,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.029884942969567167,
1080
+ "grad_norm": 1.024474024772644,
1081
+ "learning_rate": 7.143462807015271e-05,
1082
+ "loss": 2.0585,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.029884942969567167,
1087
+ "eval_loss": 1.7750892639160156,
1088
+ "eval_runtime": 607.0219,
1089
+ "eval_samples_per_second": 13.927,
1090
+ "eval_steps_per_second": 3.483,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.13283302801408e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null