nttx commited on
Commit
204ffab
·
verified ·
1 Parent(s): a77ddb6

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 sha256:18207b09f1da82075502b7701e53a340643147d9a691a7b1923f7f056a8783f6
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd3d73af9be97b86c7764e797a94469e72d3b087a9c951ae572f7da0fd076f1
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53304f1f513e0b0bba7251366a481224af2453ca539962737bf3b58872c709cd
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2acc7f305f816bb0d1e0707fd228d3eaf162a35fc0c27459bec122b9517ef1d
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:729c2158603596f8335d0922afde9ff51a60ab04e8efa51b67b2932a431d77f2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9e8e8a173575bcf3e4b40c4ddf1d6609539230814f892471c6f0f5eb62f897
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": 1.7166489362716675,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.04061326022946492,
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": 13.378,
732
  "eval_steps_per_second": 3.345,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4577025175094604,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.06091989034419738,
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": 13.378,
732
  "eval_steps_per_second": 3.345,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04101939283175957,
737
+ "grad_norm": 1.9809935092926025,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.7555,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.04142552543405422,
744
+ "grad_norm": 1.9369913339614868,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.7646,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.04183165803634887,
751
+ "grad_norm": 1.674850344657898,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.7719,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.04223779063864352,
758
+ "grad_norm": 1.4067672491073608,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.705,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.042643923240938165,
765
+ "grad_norm": 1.117656946182251,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.5836,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.043050055843232814,
772
+ "grad_norm": 0.7025765776634216,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.5923,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.04345618844552746,
779
+ "grad_norm": 0.8131675720214844,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.5141,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.04386232104782212,
786
+ "grad_norm": 0.9580807685852051,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.598,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.044268453650116765,
793
+ "grad_norm": 0.8206263780593872,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.5433,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.04467458625241141,
800
+ "grad_norm": 0.697608470916748,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.4524,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.04508071885470606,
807
+ "grad_norm": 0.6470988988876343,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.4266,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.04548685145700071,
814
+ "grad_norm": 0.6238524913787842,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.4186,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.04589298405929536,
821
+ "grad_norm": 0.5966043472290039,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.3564,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.046299116661590006,
828
+ "grad_norm": 0.5739925503730774,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.4389,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.04670524926388466,
835
+ "grad_norm": 0.5564324259757996,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.4113,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.04711138186617931,
842
+ "grad_norm": 0.5870735049247742,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.3268,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.04751751446847396,
849
+ "grad_norm": 0.5620031952857971,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.3327,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.047923647070768606,
856
+ "grad_norm": 0.5979235768318176,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.3915,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.048329779673063254,
863
+ "grad_norm": 0.6064242720603943,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.4333,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0487359122753579,
870
+ "grad_norm": 0.631511926651001,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.3669,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.04914204487765255,
877
+ "grad_norm": 0.6458702683448792,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.4258,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.049548177479947206,
884
+ "grad_norm": 0.6667675971984863,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.4117,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.049954310082241854,
891
+ "grad_norm": 0.6369161605834961,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.3541,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0503604426845365,
898
+ "grad_norm": 0.6958560347557068,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.292,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.05076657528683115,
905
+ "grad_norm": 0.7173919081687927,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.3786,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.0511727078891258,
912
+ "grad_norm": 0.7203386425971985,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.4363,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.05157884049142045,
919
+ "grad_norm": 0.7156944274902344,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.3003,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.051984973093715095,
926
+ "grad_norm": 0.7624905109405518,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.3995,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.05239110569600975,
933
+ "grad_norm": 0.8011417984962463,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.4126,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0527972382983044,
940
+ "grad_norm": 0.7700819969177246,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.3715,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.05320337090059905,
947
+ "grad_norm": 0.8159439563751221,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.4165,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.053609503502893695,
954
+ "grad_norm": 0.8066980838775635,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.3141,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.05401563610518834,
961
+ "grad_norm": 0.928561270236969,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.2663,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.05442176870748299,
968
+ "grad_norm": 0.8653779029846191,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.4253,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.05482790130977764,
975
+ "grad_norm": 0.8156696557998657,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.2435,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.055234033912072295,
982
+ "grad_norm": 0.8434756398200989,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.2682,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.05564016651436694,
989
+ "grad_norm": 0.9540610909461975,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.3011,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.05604629911666159,
996
+ "grad_norm": 0.8743776679039001,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.3464,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.05645243171895624,
1003
+ "grad_norm": 0.8367823362350464,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.2398,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.05685856432125089,
1010
+ "grad_norm": 0.9489424824714661,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.2853,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.057264696923545536,
1017
+ "grad_norm": 0.8658900856971741,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2019,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.057670829525840184,
1024
+ "grad_norm": 0.8773536682128906,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.1453,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.05807696212813484,
1031
+ "grad_norm": 1.0234720706939697,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.3279,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.05848309473042949,
1038
+ "grad_norm": 0.9431840181350708,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.2179,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.058889227332724135,
1045
+ "grad_norm": 0.927308976650238,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.1919,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.059295359935018783,
1052
+ "grad_norm": 0.9419561624526978,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.1926,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.05970149253731343,
1059
+ "grad_norm": 1.0439989566802979,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.2789,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.06010762513960808,
1066
+ "grad_norm": 1.4132856130599976,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.4584,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.06051375774190273,
1073
+ "grad_norm": 1.8904759883880615,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.2134,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.06091989034419738,
1080
+ "grad_norm": 3.5856516361236572,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.8681,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.06091989034419738,
1087
+ "eval_loss": 1.4577025175094604,
1088
+ "eval_runtime": 310.1093,
1089
+ "eval_samples_per_second": 13.373,
1090
+ "eval_steps_per_second": 3.344,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.262770368118784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null