lesso commited on
Commit
a09d8ff
·
verified ·
1 Parent(s): 010d4d4

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:cb610103a64f11ffddf59071f6e7b48e73e9f4f7b6076bbceb75adebad3bf54c
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee0494dedaa482a33b6a81c1751da08afcb91f337a8ea39391437ada6b5489d
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31aad0dbac4224bd9e0e5c6a62650086ee40fe2677dd32d46948ef63ec1d3a70
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9e5fe2afa0d8825a0d9ffb6dc4b78836d49503b3285ae4bb9c3034ffa165111
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:045b75fd050c10a4fe14a1c98e12907f7f4ce5a7257e00e93adf6da74be770bb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8840cdf53a2e22d380d0e8d75bfdf6c53e68f65a2c89b0879bf8d4e6466c776e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fe6f0a2f7a14e66c6816df9a38574183cedfa2cc544d1c8e8e8cea1139c2f76
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef91cf09f7b6a58a39bbfe1ef78ac2fa91c0c15ca1705097a187d272d0433d8d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4105467796325684,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.1119194180190263,
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": 7.759,
732
  "eval_steps_per_second": 1.955,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4.167268761285427e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3877595663070679,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.16787912702853947,
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": 7.759,
732
  "eval_steps_per_second": 1.955,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.11303861219921657,
737
+ "grad_norm": 0.5879180431365967,
738
+ "learning_rate": 5.24178947368421e-05,
739
+ "loss": 1.5242,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.11415780637940683,
744
+ "grad_norm": 0.5801900625228882,
745
+ "learning_rate": 5.1888421052631585e-05,
746
+ "loss": 1.4539,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.1152770005595971,
751
+ "grad_norm": 0.6456881165504456,
752
+ "learning_rate": 5.135894736842106e-05,
753
+ "loss": 1.8406,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.11639619473978735,
758
+ "grad_norm": 0.6166803240776062,
759
+ "learning_rate": 5.082947368421053e-05,
760
+ "loss": 1.8484,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.11751538891997762,
765
+ "grad_norm": 0.6689649820327759,
766
+ "learning_rate": 5.03e-05,
767
+ "loss": 2.47,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.11863458310016788,
772
+ "grad_norm": 0.6608978509902954,
773
+ "learning_rate": 4.977052631578947e-05,
774
+ "loss": 1.9793,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.11975377728035815,
779
+ "grad_norm": 0.6113259792327881,
780
+ "learning_rate": 4.924105263157895e-05,
781
+ "loss": 2.0245,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.1208729714605484,
786
+ "grad_norm": 0.45949867367744446,
787
+ "learning_rate": 4.871157894736843e-05,
788
+ "loss": 1.0876,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.12199216564073867,
793
+ "grad_norm": 0.5350001454353333,
794
+ "learning_rate": 4.81821052631579e-05,
795
+ "loss": 1.6227,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.12311135982092893,
800
+ "grad_norm": 0.5312851667404175,
801
+ "learning_rate": 4.765263157894737e-05,
802
+ "loss": 1.4318,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.1242305540011192,
807
+ "grad_norm": 0.4572623670101166,
808
+ "learning_rate": 4.7123157894736845e-05,
809
+ "loss": 1.0106,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.12534974818130945,
814
+ "grad_norm": 0.5980809330940247,
815
+ "learning_rate": 4.6593684210526316e-05,
816
+ "loss": 1.7434,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.12646894236149972,
821
+ "grad_norm": 0.548912763595581,
822
+ "learning_rate": 4.606421052631579e-05,
823
+ "loss": 1.2903,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.12758813654169,
828
+ "grad_norm": 0.5556053519248962,
829
+ "learning_rate": 4.553473684210527e-05,
830
+ "loss": 1.4555,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.12870733072188026,
835
+ "grad_norm": 0.47583720088005066,
836
+ "learning_rate": 4.500526315789474e-05,
837
+ "loss": 0.9821,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.1298265249020705,
842
+ "grad_norm": 0.5786464810371399,
843
+ "learning_rate": 4.447578947368421e-05,
844
+ "loss": 1.3264,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.13094571908226077,
849
+ "grad_norm": 0.7116870284080505,
850
+ "learning_rate": 4.394631578947369e-05,
851
+ "loss": 1.7898,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.13206491326245104,
856
+ "grad_norm": 0.5318160057067871,
857
+ "learning_rate": 4.341684210526316e-05,
858
+ "loss": 1.2532,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.1331841074426413,
863
+ "grad_norm": 0.6466919183731079,
864
+ "learning_rate": 4.2887368421052636e-05,
865
+ "loss": 1.8143,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.13430330162283155,
870
+ "grad_norm": 0.5290660262107849,
871
+ "learning_rate": 4.2357894736842106e-05,
872
+ "loss": 1.2196,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.13542249580302182,
877
+ "grad_norm": 0.5391547679901123,
878
+ "learning_rate": 4.182842105263158e-05,
879
+ "loss": 1.2362,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.1365416899832121,
884
+ "grad_norm": 0.5914385914802551,
885
+ "learning_rate": 4.1298947368421053e-05,
886
+ "loss": 1.1101,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.13766088416340236,
891
+ "grad_norm": 0.49526429176330566,
892
+ "learning_rate": 4.0769473684210524e-05,
893
+ "loss": 1.0053,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.1387800783435926,
898
+ "grad_norm": 0.5738490223884583,
899
+ "learning_rate": 4.024000000000001e-05,
900
+ "loss": 1.3063,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.13989927252378287,
905
+ "grad_norm": 0.5793554186820984,
906
+ "learning_rate": 3.971052631578948e-05,
907
+ "loss": 1.1082,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.14101846670397314,
912
+ "grad_norm": 0.5960007905960083,
913
+ "learning_rate": 3.918105263157895e-05,
914
+ "loss": 1.2714,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1421376608841634,
919
+ "grad_norm": 0.5454027056694031,
920
+ "learning_rate": 3.865157894736842e-05,
921
+ "loss": 0.9059,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.14325685506435368,
926
+ "grad_norm": 0.5426894426345825,
927
+ "learning_rate": 3.8122105263157896e-05,
928
+ "loss": 0.983,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.14437604924454392,
933
+ "grad_norm": 0.5231617093086243,
934
+ "learning_rate": 3.759263157894737e-05,
935
+ "loss": 0.893,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1454952434247342,
940
+ "grad_norm": 0.5522717237472534,
941
+ "learning_rate": 3.7063157894736844e-05,
942
+ "loss": 0.9089,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.14661443760492446,
947
+ "grad_norm": 0.5636381506919861,
948
+ "learning_rate": 3.653368421052632e-05,
949
+ "loss": 0.8846,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.14773363178511473,
954
+ "grad_norm": 0.6152870655059814,
955
+ "learning_rate": 3.600421052631579e-05,
956
+ "loss": 1.1705,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.14885282596530497,
961
+ "grad_norm": 0.6401809453964233,
962
+ "learning_rate": 3.547473684210526e-05,
963
+ "loss": 1.1054,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.14997202014549524,
968
+ "grad_norm": 0.6023024320602417,
969
+ "learning_rate": 3.494526315789474e-05,
970
+ "loss": 1.0486,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1510912143256855,
975
+ "grad_norm": 0.6276597380638123,
976
+ "learning_rate": 3.4415789473684216e-05,
977
+ "loss": 1.0336,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.15221040850587578,
982
+ "grad_norm": 0.6555151343345642,
983
+ "learning_rate": 3.3886315789473686e-05,
984
+ "loss": 1.1,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.15332960268606602,
989
+ "grad_norm": 0.6589622497558594,
990
+ "learning_rate": 3.3356842105263156e-05,
991
+ "loss": 1.1521,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1544487968662563,
996
+ "grad_norm": 0.6621150970458984,
997
+ "learning_rate": 3.2827368421052634e-05,
998
+ "loss": 1.1907,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.15556799104644656,
1003
+ "grad_norm": 0.7542665004730225,
1004
+ "learning_rate": 3.2297894736842104e-05,
1005
+ "loss": 1.2919,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.15668718522663683,
1010
+ "grad_norm": 0.6534504890441895,
1011
+ "learning_rate": 3.176842105263158e-05,
1012
+ "loss": 1.2927,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1578063794068271,
1017
+ "grad_norm": 0.7612457275390625,
1018
+ "learning_rate": 3.123894736842106e-05,
1019
+ "loss": 1.4274,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.15892557358701734,
1024
+ "grad_norm": 0.7387349009513855,
1025
+ "learning_rate": 3.070947368421053e-05,
1026
+ "loss": 1.1477,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.1600447677672076,
1031
+ "grad_norm": 0.7960942983627319,
1032
+ "learning_rate": 3.018e-05,
1033
+ "loss": 1.1789,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.16116396194739788,
1038
+ "grad_norm": 0.8818754553794861,
1039
+ "learning_rate": 2.9650526315789473e-05,
1040
+ "loss": 1.4173,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.16228315612758815,
1045
+ "grad_norm": 0.8571878671646118,
1046
+ "learning_rate": 2.912105263157895e-05,
1047
+ "loss": 1.3802,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.1634023503077784,
1052
+ "grad_norm": 0.9936959147453308,
1053
+ "learning_rate": 2.8591578947368424e-05,
1054
+ "loss": 1.7175,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.16452154448796866,
1059
+ "grad_norm": 0.9072629809379578,
1060
+ "learning_rate": 2.8062105263157894e-05,
1061
+ "loss": 1.3749,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.16564073866815893,
1066
+ "grad_norm": 1.0150874853134155,
1067
+ "learning_rate": 2.753263157894737e-05,
1068
+ "loss": 1.5923,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1667599328483492,
1073
+ "grad_norm": 1.203032374382019,
1074
+ "learning_rate": 2.7003157894736845e-05,
1075
+ "loss": 1.9182,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.16787912702853947,
1080
+ "grad_norm": 1.8546819686889648,
1081
+ "learning_rate": 2.6473684210526315e-05,
1082
+ "loss": 2.1847,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.16787912702853947,
1087
+ "eval_loss": 1.3877595663070679,
1088
+ "eval_runtime": 48.2138,
1089
+ "eval_samples_per_second": 7.819,
1090
+ "eval_steps_per_second": 1.97,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6.316900610998272e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null