cimol commited on
Commit
30f10c0
·
verified ·
1 Parent(s): 99ef222

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 sha256:9a30319c4691b1e3aec7550224d2e399b6c280e2c5e3b005082a161e1afb02c1
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a96f02a54478e30857f97f51a8e9ed67267d0f840d9d30742e84aaea36b22b1
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:188a0ffafb85aae2b10b754962d7a9123c96cd5bb7fc30783655b4620c9f7822
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3678b2e95edd89452ec09291533f8ee9cd3631c9b1589bdb9e4d0314a64e3a6c
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fa4ee8888e41398c1be80970ac9e275500bf458118d0f53deff8b4f936ea59c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae1be1182c9a98559f5c36813f763307577ae073673229022e7d8ccbe0e6f5a4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d94dee72c7d02de6c69d9fa4cc2d9dd3225f09ac52c6adcb59ec7bae1df8f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26348e70deb5f7d6cee52f5eb084c0e6829440001a3c6d0128b93cd074af8c2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2259724140167236,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.23161551823972207,
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": 12.967,
732
  "eval_steps_per_second": 3.246,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9819753766059875,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.3474232773595831,
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": 12.967,
732
  "eval_steps_per_second": 3.246,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.2339316734221193,
737
+ "grad_norm": 1.7626456022262573,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 1.9503,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.2362478286045165,
744
+ "grad_norm": 1.505061388015747,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 1.8245,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.23856398378691374,
751
+ "grad_norm": 1.3618402481079102,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 1.7775,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.24088013896931093,
758
+ "grad_norm": 1.3016786575317383,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 1.6679,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.24319629415170815,
765
+ "grad_norm": 1.2957885265350342,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 1.6692,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.24551244933410538,
772
+ "grad_norm": 1.004072666168213,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 1.521,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.2478286045165026,
779
+ "grad_norm": 1.0314702987670898,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 1.6253,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.2501447596988998,
786
+ "grad_norm": 1.1805181503295898,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 1.4228,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.25246091488129707,
793
+ "grad_norm": 1.028948187828064,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 1.4977,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.25477707006369427,
800
+ "grad_norm": 1.0726194381713867,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 1.3065,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.25709322524609146,
807
+ "grad_norm": 1.1146329641342163,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 1.0397,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.2594093804284887,
814
+ "grad_norm": 1.1305572986602783,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 1.2692,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.2617255356108859,
821
+ "grad_norm": 1.2434415817260742,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 1.3937,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.26404169079328316,
828
+ "grad_norm": 1.2750946283340454,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 1.3832,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.26635784597568035,
835
+ "grad_norm": 1.4428255558013916,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 1.134,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.2686740011580776,
842
+ "grad_norm": 1.4373363256454468,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 1.2468,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.2709901563404748,
849
+ "grad_norm": 1.548967719078064,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 1.0152,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.27330631152287205,
856
+ "grad_norm": 1.930369257926941,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 1.2061,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.27562246670526924,
863
+ "grad_norm": 1.7386815547943115,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 1.1742,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.2779386218876665,
870
+ "grad_norm": 1.7060924768447876,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 1.2716,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.2802547770700637,
877
+ "grad_norm": 1.5493820905685425,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 1.2847,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.28257093225246094,
884
+ "grad_norm": 1.513087272644043,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 1.2291,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.28488708743485813,
891
+ "grad_norm": 1.405207633972168,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 1.0475,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.2872032426172554,
898
+ "grad_norm": 1.4663727283477783,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 0.9763,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.2895193977996526,
905
+ "grad_norm": 1.33937406539917,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 0.981,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.2918355529820498,
912
+ "grad_norm": 1.4397436380386353,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 1.1096,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.294151708164447,
919
+ "grad_norm": 1.3392612934112549,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 0.9199,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.2964678633468442,
926
+ "grad_norm": 1.3941303491592407,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 0.885,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.29878401852924147,
933
+ "grad_norm": 1.5315736532211304,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 0.9312,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.30110017371163866,
940
+ "grad_norm": 1.461169719696045,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 0.8541,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.3034163288940359,
947
+ "grad_norm": 1.5014770030975342,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 0.8172,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.3057324840764331,
954
+ "grad_norm": 1.8396813869476318,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 0.8973,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.30804863925883036,
961
+ "grad_norm": 1.7794278860092163,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 0.9055,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.31036479444122755,
968
+ "grad_norm": 1.544495701789856,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 0.8416,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.3126809496236248,
975
+ "grad_norm": 1.71176278591156,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 0.8015,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.314997104806022,
982
+ "grad_norm": 1.837409257888794,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 0.7487,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.31731325998841925,
989
+ "grad_norm": 1.8642661571502686,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 0.8194,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.31962941517081644,
996
+ "grad_norm": 1.9652878046035767,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 0.7471,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.32194557035321364,
1003
+ "grad_norm": 1.8793476819992065,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 0.5699,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.3242617255356109,
1010
+ "grad_norm": 1.8087778091430664,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 0.702,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.3265778807180081,
1017
+ "grad_norm": 1.814977765083313,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 0.6915,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.32889403590040533,
1024
+ "grad_norm": 1.9736248254776,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 0.6077,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.33121019108280253,
1031
+ "grad_norm": 2.0833942890167236,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 0.6608,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.3335263462651998,
1038
+ "grad_norm": 2.1390953063964844,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 0.614,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.335842501447597,
1045
+ "grad_norm": 2.002488851547241,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 0.6135,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.3381586566299942,
1052
+ "grad_norm": 2.446239471435547,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 0.7834,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.3404748118123914,
1059
+ "grad_norm": 2.466515302658081,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 0.7394,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.34279096699478867,
1066
+ "grad_norm": 2.9753072261810303,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 0.6323,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.34510712217718587,
1073
+ "grad_norm": 2.352726459503174,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 0.5433,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.3474232773595831,
1080
+ "grad_norm": 2.822594404220581,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 0.6062,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.3474232773595831,
1087
+ "eval_loss": 0.9819753766059875,
1088
+ "eval_runtime": 56.0681,
1089
+ "eval_samples_per_second": 12.966,
1090
+ "eval_steps_per_second": 3.246,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.262770368118784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null