abaddon182 commited on
Commit
4fa1b3e
·
verified ·
1 Parent(s): a8b671e

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 sha256:18e1b2e70c848f0837b936520999f2c9f809d567ea60651f2683e70ff4303440
3
  size 912336848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216bd25fd10aec657e9b28a18e44dd40e724157f3d14b63ddccbfd4f696c0af6
3
  size 912336848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3363c1b5e872594af2d143ab324a4ec5905a48b81c6b6e998d605a173d48d4fd
3
  size 463916180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b7cc0bb8ce8c8f7b7aa74a4a3d552cec3442e5012c1305881e35005c9a7a0c
3
  size 463916180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:900f1c592623f0ad4239cdfa90eb2939023202ba2adb8714516ce3e176a24c87
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68c4e4faf1f18be7217a4e6587c2c2afc7b4efdf4a0109aafb3de669d6bbcea9
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": 0.3164862096309662,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.015429717636167259,
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": 9.337,
732
  "eval_steps_per_second": 2.334,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.32091006533632e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.28457388281822205,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.023144576454250887,
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": 9.337,
732
  "eval_steps_per_second": 2.334,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.015584014812528931,
737
+ "grad_norm": 2.1135852336883545,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.9688,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.015738311988890603,
744
+ "grad_norm": 2.6872575283050537,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.7977,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.015892609165252276,
751
+ "grad_norm": 2.179337739944458,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.899,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.01604690634161395,
758
+ "grad_norm": 2.046647548675537,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.9163,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.01620120351797562,
765
+ "grad_norm": 1.6712251901626587,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.7027,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.016355500694337295,
772
+ "grad_norm": 1.9600069522857666,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.8532,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.016509797870698967,
779
+ "grad_norm": 1.9323686361312866,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.7524,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01666409504706064,
786
+ "grad_norm": 2.2640445232391357,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.6832,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.01681839222342231,
793
+ "grad_norm": 2.8214526176452637,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.2118,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.016972689399783983,
800
+ "grad_norm": 2.3051140308380127,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.928,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.017126986576145656,
807
+ "grad_norm": 2.3470754623413086,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.0268,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.01728128375250733,
814
+ "grad_norm": 2.9669408798217773,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.0276,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.017435580928869,
821
+ "grad_norm": 2.3789660930633545,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.9162,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.017589878105230675,
828
+ "grad_norm": 2.5573084354400635,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.9952,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.017744175281592348,
835
+ "grad_norm": 2.5774619579315186,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.0555,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.01789847245795402,
842
+ "grad_norm": 2.5209386348724365,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.8681,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.018052769634315693,
849
+ "grad_norm": 1.7983317375183105,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.7346,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.018207066810677363,
856
+ "grad_norm": 2.6117846965789795,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.0156,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.018361363987039036,
863
+ "grad_norm": 3.043611764907837,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.1985,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.01851566116340071,
870
+ "grad_norm": 2.4481253623962402,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.7967,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.018669958339762382,
877
+ "grad_norm": 2.736717939376831,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.9689,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.018824255516124055,
884
+ "grad_norm": 2.456480026245117,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.9321,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.018978552692485728,
891
+ "grad_norm": 2.8887879848480225,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.0428,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0191328498688474,
898
+ "grad_norm": 2.726231575012207,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.9577,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.019287147045209074,
905
+ "grad_norm": 3.224410057067871,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.9473,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.019441444221570747,
912
+ "grad_norm": 3.1999216079711914,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.9932,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.01959574139793242,
919
+ "grad_norm": 3.8387598991394043,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.2319,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.01975003857429409,
926
+ "grad_norm": 2.8964102268218994,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.0599,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.019904335750655762,
933
+ "grad_norm": 4.114666938781738,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.3144,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.020058632927017435,
940
+ "grad_norm": 3.177757740020752,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.1104,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.020212930103379108,
947
+ "grad_norm": 3.910651445388794,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.4312,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.02036722727974078,
954
+ "grad_norm": 4.899455547332764,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.3746,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.020521524456102454,
961
+ "grad_norm": 3.068983793258667,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.2063,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.020675821632464127,
968
+ "grad_norm": 4.716024875640869,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.5316,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0208301188088258,
975
+ "grad_norm": 4.213740348815918,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.4885,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.020984415985187473,
982
+ "grad_norm": 3.3666975498199463,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.2577,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.021138713161549142,
989
+ "grad_norm": 3.981973171234131,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.6675,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.021293010337910815,
996
+ "grad_norm": 3.0349082946777344,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.9987,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.021447307514272488,
1003
+ "grad_norm": 4.075341701507568,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.5178,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.02160160469063416,
1010
+ "grad_norm": 5.074423789978027,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.4079,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.021755901866995834,
1017
+ "grad_norm": 3.3979923725128174,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.1321,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.021910199043357507,
1024
+ "grad_norm": 4.806706428527832,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.9998,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.02206449621971918,
1031
+ "grad_norm": 3.5960700511932373,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.6362,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.022218793396080853,
1038
+ "grad_norm": 4.214598178863525,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.5651,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.022373090572442526,
1045
+ "grad_norm": 3.794874668121338,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.4958,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0225273877488042,
1052
+ "grad_norm": 4.378116130828857,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.7681,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.022681684925165868,
1059
+ "grad_norm": 3.5231878757476807,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.2935,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.02283598210152754,
1066
+ "grad_norm": 4.763271808624268,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.5968,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.022990279277889214,
1073
+ "grad_norm": 4.690351963043213,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.4374,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.023144576454250887,
1080
+ "grad_norm": 6.50685977935791,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.9641,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.023144576454250887,
1087
+ "eval_loss": 0.28457388281822205,
1088
+ "eval_runtime": 1168.9033,
1089
+ "eval_samples_per_second": 9.339,
1090
+ "eval_steps_per_second": 2.335,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.48136509800448e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null