aleegis09 commited on
Commit
49772bb
·
verified ·
1 Parent(s): 553813e

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 sha256:8217bd90ad64530b63e45e58d9a5be753fa5c034aba2961dd9eb8dcc634ffef7
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ce0fd3d1ae3b19deddce36b0086fad83506f4c9fd9d5486e16449ec5365f99
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c050325b4fb179afba81060401aae2d9731faeb3832a8d17119861195e42f395
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d1464d6da5c43370515d520ddc3ba4c9c852706dd9873fe3f09f7358f33265
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27c71f7cc4e993e1000accc0cdc8c0b2d908df022408ffb802177bf3a05a23f1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bba4cb37c9f2fe598d7eac79c2a7d7a576a08792ca3bcc41eaa0007d3cadbb7b
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": 0.35996368527412415,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.1173184357541899,
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": 19.765,
732
  "eval_steps_per_second": 4.974,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4.82206444683264e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3512671887874603,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.675977653631285,
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": 19.765,
732
  "eval_steps_per_second": 4.974,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.1284916201117319,
737
+ "grad_norm": 0.49154403805732727,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.2768,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.1396648044692737,
744
+ "grad_norm": 0.4707217514514923,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.1589,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.1508379888268156,
751
+ "grad_norm": 0.46079739928245544,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.193,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.1620111731843576,
758
+ "grad_norm": 0.5139585733413696,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.2307,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.1731843575418994,
765
+ "grad_norm": 0.668438732624054,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.2282,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.1843575418994414,
772
+ "grad_norm": 0.5157988667488098,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.1328,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.1955307262569832,
779
+ "grad_norm": 0.39924243092536926,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.1255,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.2067039106145252,
786
+ "grad_norm": 0.42700207233428955,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.1351,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.217877094972067,
793
+ "grad_norm": 0.48354342579841614,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.1574,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.229050279329609,
800
+ "grad_norm": 0.3663063049316406,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.0886,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.2402234636871508,
807
+ "grad_norm": 0.42423301935195923,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.0983,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.2513966480446927,
814
+ "grad_norm": 0.5446560978889465,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.6438,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.2625698324022347,
821
+ "grad_norm": 0.3894984722137451,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.3759,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.2737430167597765,
828
+ "grad_norm": 0.43923401832580566,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.379,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.2849162011173183,
835
+ "grad_norm": 0.46830540895462036,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.3389,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.2960893854748603,
842
+ "grad_norm": 0.49750062823295593,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.3585,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.3072625698324023,
849
+ "grad_norm": 0.5573229789733887,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.417,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.318435754189944,
856
+ "grad_norm": 0.5657495260238647,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.4298,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.329608938547486,
863
+ "grad_norm": 0.4059884250164032,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.3385,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.3407821229050279,
870
+ "grad_norm": 0.5553444027900696,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.3361,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.3519553072625698,
877
+ "grad_norm": 0.49883168935775757,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.3448,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.3631284916201118,
884
+ "grad_norm": 0.5660603642463684,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.3264,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.3743016759776536,
891
+ "grad_norm": 0.5664513111114502,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.1938,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.3854748603351954,
898
+ "grad_norm": 0.5513072609901428,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.268,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.3966480446927374,
905
+ "grad_norm": 0.5621060132980347,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.1971,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.4078212290502794,
912
+ "grad_norm": 0.5587654113769531,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.2274,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.4189944134078212,
919
+ "grad_norm": 0.6601653695106506,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.3228,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.4301675977653632,
926
+ "grad_norm": 0.4269857704639435,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.1428,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.441340782122905,
933
+ "grad_norm": 0.45998716354370117,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.1673,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.452513966480447,
940
+ "grad_norm": 0.3854297995567322,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.133,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.463687150837989,
947
+ "grad_norm": 0.42208659648895264,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.1362,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.4748603351955307,
954
+ "grad_norm": 0.27260181307792664,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.0687,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.4860335195530725,
961
+ "grad_norm": 0.4132692217826843,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.1212,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.4972067039106145,
968
+ "grad_norm": 0.4734876751899719,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.7753,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.5083798882681565,
975
+ "grad_norm": 0.39801645278930664,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.4977,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.5195530726256983,
982
+ "grad_norm": 0.45366907119750977,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.3853,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.5307262569832403,
989
+ "grad_norm": 0.4831063151359558,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.3221,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.541899441340782,
996
+ "grad_norm": 0.44566017389297485,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.3098,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.553072625698324,
1003
+ "grad_norm": 0.5208490490913391,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.3654,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.564245810055866,
1010
+ "grad_norm": 0.6967378258705139,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.4679,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.5754189944134078,
1017
+ "grad_norm": 0.44668933749198914,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.4452,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.5865921787709496,
1024
+ "grad_norm": 0.5407074689865112,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.4012,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.5977653631284916,
1031
+ "grad_norm": 0.4964157044887543,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.3284,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.6089385474860336,
1038
+ "grad_norm": 0.504605233669281,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.2601,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.6201117318435754,
1045
+ "grad_norm": 0.51454758644104,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.2471,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.6312849162011172,
1052
+ "grad_norm": 0.6736803650856018,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.1578,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.6424581005586592,
1059
+ "grad_norm": 0.5892282724380493,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.2802,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.6536312849162011,
1066
+ "grad_norm": 0.5950078964233398,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.2356,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.6648044692737431,
1073
+ "grad_norm": 0.5183621644973755,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.1884,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.675977653631285,
1080
+ "grad_norm": 0.5445525646209717,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.1198,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.675977653631285,
1087
+ "eval_loss": 0.3512671887874603,
1088
+ "eval_runtime": 7.5681,
1089
+ "eval_samples_per_second": 19.952,
1090
+ "eval_steps_per_second": 5.021,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 7.23734893166592e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null