nttx commited on
Commit
3604fea
·
verified ·
1 Parent(s): dda606d

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 sha256:2794f115ecf7647a6de9adb317856a63e77984749639ba97d9cbdf91bc87aca7
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:975fbc6dd8160c36ac9eaa551fbbbb305d330fbe9ef19381f4688fdbf082facb
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21eaece1b7a8f0a0542a82464eea7d5251f50c5b2e80831d82b267bd806b0b66
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dce4aeb4d2d8fe26fc5fc408bf45773288abad54fbbe46f82565271a69b993b
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a051c9e2f2c55a5c851b2f1a78d680e9c7c3cc8e39cb52088d27e52c1c3fcec
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7b2652c9f4098c00d7790134303c7a9255f5bb57ea0c1de0a9416873ef76e4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6039547920227051,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.09854644000985464,
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": 10.683,
732
  "eval_steps_per_second": 5.345,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.7046203439828173e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5897608995437622,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.14781966001478197,
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": 10.683,
732
  "eval_steps_per_second": 5.345,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.09953190440995319,
737
+ "grad_norm": 0.06492675840854645,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 0.0378,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.10051736881005174,
744
+ "grad_norm": 0.10757127404212952,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 0.1717,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10150283321015029,
751
+ "grad_norm": 0.139942467212677,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 0.2134,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.10248829761024883,
758
+ "grad_norm": 0.17105042934417725,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 0.242,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.10347376201034737,
765
+ "grad_norm": 0.1677185744047165,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 0.2773,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.10445922641044593,
772
+ "grad_norm": 0.19385424256324768,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 0.4616,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.10544469081054447,
779
+ "grad_norm": 0.19936293363571167,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 0.5253,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.10643015521064302,
786
+ "grad_norm": 0.225832998752594,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 0.6073,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.10741561961074156,
793
+ "grad_norm": 0.20826251804828644,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 0.5133,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.10840108401084012,
800
+ "grad_norm": 0.19744732975959778,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 0.5992,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.10938654841093866,
807
+ "grad_norm": 0.20350094139575958,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 0.5886,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.1103720128110372,
814
+ "grad_norm": 0.2253555953502655,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 0.7352,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.11135747721113574,
821
+ "grad_norm": 0.1978590339422226,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 0.6002,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.1123429416112343,
828
+ "grad_norm": 0.23348231613636017,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 0.5746,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11332840601133284,
835
+ "grad_norm": 0.223561093211174,
836
+ "learning_rate": 5e-05,
837
+ "loss": 0.7063,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.11431387041143139,
842
+ "grad_norm": 0.22021301090717316,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 0.5453,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.11529933481152993,
849
+ "grad_norm": 0.22918701171875,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 0.6408,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.11628479921162849,
856
+ "grad_norm": 0.221017986536026,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 0.6825,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.11727026361172703,
863
+ "grad_norm": 0.24463246762752533,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 0.674,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.11825572801182557,
870
+ "grad_norm": 0.22127676010131836,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 0.5877,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.11924119241192412,
877
+ "grad_norm": 0.25243082642555237,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 0.7659,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.12022665681202267,
884
+ "grad_norm": 0.25524279475212097,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 0.7332,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.12121212121212122,
891
+ "grad_norm": 0.2742602527141571,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 0.8811,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12219758561221976,
898
+ "grad_norm": 0.2482510656118393,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 0.7613,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1231830500123183,
905
+ "grad_norm": 0.2792511284351349,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 0.7514,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.12416851441241686,
912
+ "grad_norm": 0.28039655089378357,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 0.6821,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1251539788125154,
919
+ "grad_norm": 0.3473927080631256,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 0.6593,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.12613944321261394,
926
+ "grad_norm": 0.2565251290798187,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 0.5399,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.1271249076127125,
933
+ "grad_norm": 0.28116095066070557,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 0.6255,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.12811037201281103,
940
+ "grad_norm": 0.28025346994400024,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 0.7028,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1290958364129096,
947
+ "grad_norm": 0.2895910441875458,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 0.7361,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.13008130081300814,
954
+ "grad_norm": 0.2944524884223938,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 0.7275,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.13106676521310667,
961
+ "grad_norm": 0.334114134311676,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 0.8179,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.13205222961320523,
968
+ "grad_norm": 0.3113299012184143,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 0.7505,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.13303769401330376,
975
+ "grad_norm": 0.3196057677268982,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 0.7061,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.13402315841340232,
982
+ "grad_norm": 0.3126354217529297,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 0.7001,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.13500862281350087,
989
+ "grad_norm": 0.31723636388778687,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 0.5961,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1359940872135994,
996
+ "grad_norm": 0.3157641291618347,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 0.5105,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.13697955161369796,
1003
+ "grad_norm": 0.337483286857605,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 0.6706,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.13796501601379652,
1010
+ "grad_norm": 0.35467472672462463,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 0.6632,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.13895048041389504,
1017
+ "grad_norm": 0.3754487633705139,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 0.6372,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.1399359448139936,
1024
+ "grad_norm": 0.3946709930896759,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 0.7413,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.14092140921409213,
1031
+ "grad_norm": 0.37810003757476807,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 0.6634,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.1419068736141907,
1038
+ "grad_norm": 0.3932291567325592,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 0.6756,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.14289233801428924,
1045
+ "grad_norm": 0.42648932337760925,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 0.7081,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.14387780241438777,
1052
+ "grad_norm": 0.46039843559265137,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 0.8046,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.14486326681448633,
1059
+ "grad_norm": 0.4435557425022125,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 0.6347,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.1458487312145849,
1066
+ "grad_norm": 0.509733259677887,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 0.8318,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.14683419561468342,
1073
+ "grad_norm": 0.5783795714378357,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 0.662,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.14781966001478197,
1080
+ "grad_norm": 0.8224442005157471,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 0.6612,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.14781966001478197,
1087
+ "eval_loss": 0.5897608995437622,
1088
+ "eval_runtime": 160.4128,
1089
+ "eval_samples_per_second": 10.654,
1090
+ "eval_steps_per_second": 5.33,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.5531592320273613e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null