cimol commited on
Commit
c781464
·
verified ·
1 Parent(s): f50d6d7

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:a8d09943e7d9745ab1369b3c059bb4a830ea7750a148dbaf1b8a54265bd6c0a7
3
  size 850458320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6423242af6b26caff17dba17794a036c5f64b1b64c860b2da8e5af30e3947a04
3
  size 850458320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b9131ce80409e4a204c47a2e2f4b026704b7f490b23ffc30be2bc43eb1b5c23
3
  size 170694996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c801ee514b110c6c420b98c0f6dc98178d726d41e044da45e93f430131a361
3
  size 170694996
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae6b7d186551856ef1754bc6833c74e55d632293a3437e9814029f9bb67577d7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6c5e578e0fc018e74cf4582763afe0bf30b1bd804496a2d7aae41e7192f4c9
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": 3.408945322036743,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.09955201592832255,
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": 27.619,
732
  "eval_steps_per_second": 6.905,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 5.3679054913536e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.092088460922241,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.1493280238924838,
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": 27.619,
732
  "eval_steps_per_second": 6.905,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.10054753608760578,
737
+ "grad_norm": 14.739988327026367,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 15.543,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.101543056246889,
744
+ "grad_norm": 14.073467254638672,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 14.4055,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10253857640617223,
751
+ "grad_norm": 14.246908187866211,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 15.4411,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.10353409656545545,
758
+ "grad_norm": 13.262439727783203,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 15.0254,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.10452961672473868,
765
+ "grad_norm": 12.34248161315918,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 13.5204,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1055251368840219,
772
+ "grad_norm": 12.148157119750977,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 14.7976,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.10652065704330513,
779
+ "grad_norm": 9.811334609985352,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 13.6898,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.10751617720258835,
786
+ "grad_norm": 8.851418495178223,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 12.8406,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.10851169736187158,
793
+ "grad_norm": 7.997482776641846,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 12.559,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.1095072175211548,
800
+ "grad_norm": 7.012176990509033,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 13.1482,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.11050273768043803,
807
+ "grad_norm": 5.911029815673828,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 12.4429,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.11149825783972125,
814
+ "grad_norm": 5.869875907897949,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 12.679,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.11249377799900448,
821
+ "grad_norm": 5.480616092681885,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 12.652,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.1134892981582877,
828
+ "grad_norm": 5.753652095794678,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 11.7755,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11448481831757093,
835
+ "grad_norm": 5.716575622558594,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 11.8642,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.11548033847685416,
842
+ "grad_norm": 5.526679039001465,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 12.2722,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.11647585863613738,
849
+ "grad_norm": 5.610344409942627,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 12.8266,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.1174713787954206,
856
+ "grad_norm": 5.9043121337890625,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 12.3814,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.11846689895470383,
863
+ "grad_norm": 5.58474063873291,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 11.8111,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.11946241911398706,
870
+ "grad_norm": 5.859811305999756,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 13.1579,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.12045793927327028,
877
+ "grad_norm": 5.992862701416016,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 12.3014,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.1214534594325535,
884
+ "grad_norm": 6.183375358581543,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 12.715,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.12244897959183673,
891
+ "grad_norm": 6.381465911865234,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 12.5193,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12344449975111996,
898
+ "grad_norm": 6.7853546142578125,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 12.8658,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.12444001991040318,
905
+ "grad_norm": 6.197251796722412,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 12.6566,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1254355400696864,
912
+ "grad_norm": 6.544679164886475,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 12.6763,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.12643106022896963,
919
+ "grad_norm": 6.188560962677002,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 13.0838,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.12742658038825286,
926
+ "grad_norm": 6.0840864181518555,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 11.9319,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.12842210054753608,
933
+ "grad_norm": 6.259970188140869,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 12.4282,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1294176207068193,
940
+ "grad_norm": 6.152682304382324,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 12.0929,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.13041314086610253,
947
+ "grad_norm": 6.4252190589904785,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 11.9571,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.13140866102538576,
954
+ "grad_norm": 6.551266670227051,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 12.8882,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.13240418118466898,
961
+ "grad_norm": 6.205370903015137,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 12.277,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1333997013439522,
968
+ "grad_norm": 6.562389373779297,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 12.5109,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.13439522150323543,
975
+ "grad_norm": 6.863438129425049,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 12.6608,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.13539074166251866,
982
+ "grad_norm": 7.253135681152344,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 12.1705,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.13638626182180189,
989
+ "grad_norm": 7.326224327087402,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 12.3136,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1373817819810851,
996
+ "grad_norm": 7.456321716308594,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 12.6533,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.13837730214036834,
1003
+ "grad_norm": 7.151755332946777,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 12.5177,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.13937282229965156,
1010
+ "grad_norm": 7.655202388763428,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 12.779,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.14036834245893479,
1017
+ "grad_norm": 7.931726932525635,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 11.0959,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.141363862618218,
1024
+ "grad_norm": 9.08357048034668,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 12.7549,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.14235938277750124,
1031
+ "grad_norm": 10.932563781738281,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 12.3229,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.14335490293678446,
1038
+ "grad_norm": 9.663403511047363,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 11.9616,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.1443504230960677,
1045
+ "grad_norm": 11.70077133178711,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 11.9491,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.1453459432553509,
1052
+ "grad_norm": 11.674589157104492,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 11.1991,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.14634146341463414,
1059
+ "grad_norm": 13.514405250549316,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 11.5043,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.14733698357391736,
1066
+ "grad_norm": 16.926280975341797,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 10.935,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1483325037332006,
1073
+ "grad_norm": 24.73917007446289,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 11.3239,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.1493280238924838,
1080
+ "grad_norm": 47.201995849609375,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 12.6958,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.1493280238924838,
1087
+ "eval_loss": 3.092088460922241,
1088
+ "eval_runtime": 61.7132,
1089
+ "eval_samples_per_second": 27.417,
1090
+ "eval_steps_per_second": 6.854,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 8.0518582370304e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null