prxy5608 commited on
Commit
2cda745
·
verified ·
1 Parent(s): dbaaeaf

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:ab05564fb44196c5cba92d365a858ab95e05f5d8bc72db4656a1e1bd23149531
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94a5f59e072e4c24b73e93b9831d43ae20919fd6835cc88652151d2894a00a1d
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f54111d2ccd24bd89866b0d094f10aff1f4f7a249c164dd7bad23f974ae3120d
3
  size 281824770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c83c9cd125ba0280fe5df3b8160ccca775be65c201ecbfc458b5306de918ea4
3
  size 281824770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59eafd554f9dd23e02f02cfe6313d07221fb83f041422662ed1b942860089ced
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eebfda5e39a4bf124c7c7464ba0e39635f0dc519b0c89fc544e9ffaa9e3f3511
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 3.239711284637451,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.03716090672612412,
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": 41.272,
732
  "eval_steps_per_second": 20.636,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7747803637874688.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.157715320587158,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.055741360089186176,
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": 41.272,
732
  "eval_steps_per_second": 20.636,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.03753251579338536,
737
+ "grad_norm": 1.8480045795440674,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 3.4696,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0379041248606466,
744
+ "grad_norm": 1.9059332609176636,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 3.5296,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.03827573392790784,
751
+ "grad_norm": 1.69303297996521,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 3.3444,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.03864734299516908,
758
+ "grad_norm": 1.7022647857666016,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 3.4552,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03901895206243032,
765
+ "grad_norm": 1.520664930343628,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 3.2903,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.03939056112969157,
772
+ "grad_norm": 1.3997753858566284,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 3.3293,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.03976217019695281,
779
+ "grad_norm": 1.373949646949768,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 3.3496,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.04013377926421405,
786
+ "grad_norm": 1.4093092679977417,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 3.2133,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.04050538833147529,
793
+ "grad_norm": 1.5684155225753784,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 3.3316,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.04087699739873653,
800
+ "grad_norm": 1.5542587041854858,
801
+ "learning_rate": 5e-05,
802
+ "loss": 3.1965,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.04124860646599777,
807
+ "grad_norm": 1.5495750904083252,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 3.2084,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.04162021553325901,
814
+ "grad_norm": 1.596696138381958,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 3.3498,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.041991824600520256,
821
+ "grad_norm": 1.546371579170227,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 3.3169,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.042363433667781496,
828
+ "grad_norm": 1.6366443634033203,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 3.1769,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.042735042735042736,
835
+ "grad_norm": 1.6571626663208008,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 3.1964,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.043106651802303976,
842
+ "grad_norm": 1.7170463800430298,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 3.2483,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.043478260869565216,
849
+ "grad_norm": 1.6605336666107178,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 3.183,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.043849869936826456,
856
+ "grad_norm": 1.6899641752243042,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 3.1072,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.044221479004087696,
863
+ "grad_norm": 1.6592519283294678,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 3.1128,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.044593088071348944,
870
+ "grad_norm": 1.7209159135818481,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 3.1762,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.044964697138610184,
877
+ "grad_norm": 1.8177850246429443,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 3.2915,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.045336306205871424,
884
+ "grad_norm": 1.829469084739685,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 3.1219,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.045707915273132664,
891
+ "grad_norm": 1.9255375862121582,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 3.2112,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.046079524340393904,
898
+ "grad_norm": 1.9076225757598877,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 3.1843,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.046451133407655144,
905
+ "grad_norm": 1.8772251605987549,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 3.295,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.046822742474916385,
912
+ "grad_norm": 1.8381478786468506,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 3.2535,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.04719435154217763,
919
+ "grad_norm": 1.9620457887649536,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 3.1093,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.04756596060943887,
926
+ "grad_norm": 1.8187255859375,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 3.0412,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.04793756967670011,
933
+ "grad_norm": 2.0452768802642822,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 3.1595,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.04830917874396135,
940
+ "grad_norm": 2.0695669651031494,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 3.0353,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.04868078781122259,
947
+ "grad_norm": 1.918813705444336,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 3.0169,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.04905239687848383,
954
+ "grad_norm": 2.064602851867676,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 3.0316,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.04942400594574508,
961
+ "grad_norm": 2.167141914367676,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 3.244,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.04979561501300632,
968
+ "grad_norm": 2.1696243286132812,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 3.11,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.05016722408026756,
975
+ "grad_norm": 2.138988971710205,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 3.049,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0505388331475288,
982
+ "grad_norm": 2.2165169715881348,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 3.0517,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.05091044221479004,
989
+ "grad_norm": 2.2241313457489014,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 2.9602,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.05128205128205128,
996
+ "grad_norm": 2.334522247314453,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 3.1206,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.05165366034931252,
1003
+ "grad_norm": 2.241197109222412,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 2.9884,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.05202526941657377,
1010
+ "grad_norm": 2.4286975860595703,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 2.8666,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.05239687848383501,
1017
+ "grad_norm": 2.472275495529175,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 2.9763,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.05276848755109625,
1024
+ "grad_norm": 2.541703224182129,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 2.8725,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.05314009661835749,
1031
+ "grad_norm": 2.5989933013916016,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 2.7639,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.05351170568561873,
1038
+ "grad_norm": 2.4298439025878906,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 2.8823,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.05388331475287997,
1045
+ "grad_norm": 2.7883102893829346,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 2.9756,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.05425492382014121,
1052
+ "grad_norm": 3.1214065551757812,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 3.1575,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.054626532887402456,
1059
+ "grad_norm": 2.6867949962615967,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 3.0654,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.054998141954663696,
1066
+ "grad_norm": 2.903306722640991,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 3.3354,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.055369751021924936,
1073
+ "grad_norm": 3.0160841941833496,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 3.333,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.055741360089186176,
1080
+ "grad_norm": 3.1288528442382812,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 3.5297,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.055741360089186176,
1087
+ "eval_loss": 3.157715320587158,
1088
+ "eval_runtime": 109.7254,
1089
+ "eval_samples_per_second": 41.303,
1090
+ "eval_steps_per_second": 20.652,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.1612044853772288e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null