cimol commited on
Commit
4430c12
·
verified ·
1 Parent(s): aaf9ff4

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 sha256:0abebb5b8586db64fbc0d6a0b8c4909671256f08d376baf33e1547d2e84705de
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c955165b2642ee08742f1bdd92c983e4c7d73e1a2bb9e2b59cf769197976513
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:286e2ff935aa1a2c6c279fa40dec7121ebc0a08db1bb7c36ab911b6d3aacad00
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d5f64f7f45524ead353e358d4586ee48207485abfc7407abaa16a00bb0f11e
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90c62a70527f62ea48fbf17854240149fc688889f488c4abdd1dfa9e6461b079
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:956d345c3492b62b0f899c0bb0f64afe30aab0b9968e125f4e667a1e8de96e79
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": 3.2521181106567383,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.07611798287345385,
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": 13.853,
732
  "eval_steps_per_second": 3.468,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4351955254889677e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.8477718830108643,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.11417697431018078,
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": 13.853,
732
  "eval_steps_per_second": 3.468,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.07687916270218839,
737
+ "grad_norm": 40.049400329589844,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 11.8576,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.07764034253092293,
744
+ "grad_norm": 33.80797576904297,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 12.1796,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.07840152235965747,
751
+ "grad_norm": 45.65495300292969,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 11.9832,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.07916270218839201,
758
+ "grad_norm": 35.831092834472656,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 12.129,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.07992388201712655,
765
+ "grad_norm": 19.742515563964844,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 11.3112,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.08068506184586108,
772
+ "grad_norm": 12.872544288635254,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 10.8966,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.08144624167459562,
779
+ "grad_norm": 16.163219451904297,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 10.8695,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08220742150333016,
786
+ "grad_norm": 15.760530471801758,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 11.1322,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0829686013320647,
793
+ "grad_norm": 12.737210273742676,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 11.1206,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08372978116079924,
800
+ "grad_norm": 12.96513843536377,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 10.6524,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.08449096098953378,
807
+ "grad_norm": 15.09691333770752,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 10.8931,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.08525214081826832,
814
+ "grad_norm": 12.536844253540039,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 10.828,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.08601332064700286,
821
+ "grad_norm": 12.665741920471191,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 11.0088,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0867745004757374,
828
+ "grad_norm": 11.625788688659668,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 10.7514,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.08753568030447194,
835
+ "grad_norm": 13.06114673614502,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 10.7538,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.08829686013320646,
842
+ "grad_norm": 13.02463150024414,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 10.5935,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.089058039961941,
849
+ "grad_norm": 11.050668716430664,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 10.4296,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.08981921979067554,
856
+ "grad_norm": 11.642556190490723,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 10.5926,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.09058039961941008,
863
+ "grad_norm": 12.23384952545166,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 10.8684,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.09134157944814462,
870
+ "grad_norm": 12.222782135009766,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 11.1264,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.09210275927687916,
877
+ "grad_norm": 11.30429458618164,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 10.1724,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0928639391056137,
884
+ "grad_norm": 14.014923095703125,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 11.1533,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.09362511893434824,
891
+ "grad_norm": 14.214231491088867,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 10.6027,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.09438629876308278,
898
+ "grad_norm": 13.18128776550293,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 10.7151,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.09514747859181731,
905
+ "grad_norm": 12.126294136047363,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 10.0795,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.09590865842055185,
912
+ "grad_norm": 12.301307678222656,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 10.0897,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.09666983824928639,
919
+ "grad_norm": 12.24648666381836,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 10.0434,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.09743101807802093,
926
+ "grad_norm": 13.534128189086914,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 10.5216,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.09819219790675547,
933
+ "grad_norm": 13.032715797424316,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 10.751,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.09895337773549001,
940
+ "grad_norm": 13.36697006225586,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 10.4866,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.09971455756422455,
947
+ "grad_norm": 14.086920738220215,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 10.4804,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.10047573739295909,
954
+ "grad_norm": 13.180987358093262,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 9.7492,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.10123691722169363,
961
+ "grad_norm": 14.282618522644043,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 11.3742,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.10199809705042816,
968
+ "grad_norm": 14.527554512023926,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 10.8801,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1027592768791627,
975
+ "grad_norm": 12.420266151428223,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 9.6681,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.10352045670789724,
982
+ "grad_norm": 15.356304168701172,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 10.354,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.10428163653663178,
989
+ "grad_norm": 13.979833602905273,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 10.2454,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.10504281636536632,
996
+ "grad_norm": 13.443976402282715,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 9.7525,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.10580399619410086,
1003
+ "grad_norm": 13.744975090026855,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 9.7207,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.1065651760228354,
1010
+ "grad_norm": 15.326041221618652,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 9.8803,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.10732635585156994,
1017
+ "grad_norm": 14.626502990722656,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 9.7187,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.10808753568030448,
1024
+ "grad_norm": 15.12524700164795,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 9.5225,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.108848715509039,
1031
+ "grad_norm": 15.535211563110352,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 9.0,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.10960989533777354,
1038
+ "grad_norm": 16.60105323791504,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 9.1394,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.11037107516650808,
1045
+ "grad_norm": 14.278752326965332,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 8.6505,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.11113225499524262,
1052
+ "grad_norm": 17.42091941833496,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 8.7583,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.11189343482397716,
1059
+ "grad_norm": 18.650836944580078,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 9.2693,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.1126546146527117,
1066
+ "grad_norm": 19.8348331451416,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 8.5282,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.11341579448144624,
1073
+ "grad_norm": 22.303525924682617,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 8.885,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.11417697431018078,
1080
+ "grad_norm": 27.490812301635742,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 8.4182,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.11417697431018078,
1087
+ "eval_loss": 2.8477718830108643,
1088
+ "eval_runtime": 159.7361,
1089
+ "eval_samples_per_second": 13.854,
1090
+ "eval_steps_per_second": 3.468,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.1510037676281037e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null