prxy5604 commited on
Commit
a8c7fab
·
verified ·
1 Parent(s): 3492079

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 sha256:7bf72fe3a25c2a331958cbc3c6d8fc82f7dc0c3514d6e7f9f417147095ae13e0
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:032ed4567c2d5052705e521c99c4649e69a7f37cae89df6af8a26c3772f09eec
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b5e67c37828d7e4a34e08c048b8ce57667ccb0473f96fa90f294e335e673812
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773666959323140cb89dd1606f0c93519d52bdaec853f8a9dab9c2185a098921
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:835f4813c77e8e3f1fde6e4627558e0984c9e25f5f23d58302c28f7ed8d8a82f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9e42f79cb12a8ce64715981c4d28346abdd04622340eb1be8f6cdedb01ee90
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": 0.314230740070343,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.33698399326032014,
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": 4.108,
732
  "eval_steps_per_second": 1.027,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.836953552818012e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.287589430809021,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5054759898904801,
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": 4.108,
732
  "eval_steps_per_second": 1.027,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.34035383319292334,
737
+ "grad_norm": 2.035517692565918,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.4091,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.34372367312552654,
744
+ "grad_norm": 1.6589703559875488,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.2788,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.34709351305812974,
751
+ "grad_norm": 1.6942716836929321,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.4311,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.35046335299073295,
758
+ "grad_norm": 1.6722877025604248,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.4587,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.35383319292333615,
765
+ "grad_norm": 1.6814851760864258,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.4119,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.35720303285593935,
772
+ "grad_norm": 1.7735084295272827,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.3435,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.36057287278854255,
779
+ "grad_norm": 1.7777315378189087,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.2643,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.36394271272114576,
786
+ "grad_norm": 1.7229983806610107,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.4055,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.36731255265374896,
793
+ "grad_norm": 1.9317232370376587,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.4089,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.37068239258635216,
800
+ "grad_norm": 1.8933583498001099,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.5829,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.37405223251895536,
807
+ "grad_norm": 1.8013765811920166,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.2522,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.37742207245155857,
814
+ "grad_norm": 1.92638099193573,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.2129,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.38079191238416177,
821
+ "grad_norm": 1.7256003618240356,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.1744,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.38416175231676497,
828
+ "grad_norm": 1.9628052711486816,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.3731,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.3875315922493682,
835
+ "grad_norm": 1.7589800357818604,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.1395,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.3909014321819714,
842
+ "grad_norm": 1.9581555128097534,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.3804,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.3942712721145746,
849
+ "grad_norm": 1.763586163520813,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.2846,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.3976411120471778,
856
+ "grad_norm": 1.9399962425231934,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.3103,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.401010951979781,
863
+ "grad_norm": 2.0409631729125977,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.3013,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.4043807919123842,
870
+ "grad_norm": 1.9230983257293701,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.3784,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.4077506318449874,
877
+ "grad_norm": 1.9140021800994873,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.3676,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.4111204717775906,
884
+ "grad_norm": 1.8744556903839111,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.2209,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.4144903117101938,
891
+ "grad_norm": 1.9762202501296997,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.2086,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.41786015164279694,
898
+ "grad_norm": 1.9981001615524292,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.1732,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.42122999157540014,
905
+ "grad_norm": 2.0948734283447266,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.3828,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.42459983150800334,
912
+ "grad_norm": 1.8933742046356201,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.8188,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.42796967144060655,
919
+ "grad_norm": 1.9235304594039917,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.1265,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.43133951137320975,
926
+ "grad_norm": 2.0142617225646973,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.0303,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.43470935130581295,
933
+ "grad_norm": 1.917381763458252,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.8551,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.43807919123841615,
940
+ "grad_norm": 1.9005807638168335,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.8717,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.44144903117101936,
947
+ "grad_norm": 2.029496192932129,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.1523,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.44481887110362256,
954
+ "grad_norm": 2.0164740085601807,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.1836,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.44818871103622576,
961
+ "grad_norm": 1.8247592449188232,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.9052,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.45155855096882896,
968
+ "grad_norm": 2.021507978439331,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.0794,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.45492839090143217,
975
+ "grad_norm": 1.948276400566101,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.8556,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.45829823083403537,
982
+ "grad_norm": 2.1332807540893555,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.4236,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.46166807076663857,
989
+ "grad_norm": 2.0226590633392334,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.1958,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.4650379106992418,
996
+ "grad_norm": 2.013789176940918,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.1031,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.468407750631845,
1003
+ "grad_norm": 2.3079583644866943,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.32,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.4717775905644482,
1010
+ "grad_norm": 2.1277973651885986,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.1596,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.4751474304970514,
1017
+ "grad_norm": 2.163935661315918,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2472,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.4785172704296546,
1024
+ "grad_norm": 2.427151918411255,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.2116,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.4818871103622578,
1031
+ "grad_norm": 2.2841601371765137,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.1287,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.485256950294861,
1038
+ "grad_norm": 2.5958619117736816,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.1741,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.4886267902274642,
1045
+ "grad_norm": 2.314521312713623,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.0629,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.4919966301600674,
1052
+ "grad_norm": 2.4749999046325684,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.0139,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.4953664700926706,
1059
+ "grad_norm": 2.472071409225464,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.1252,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.4987363100252738,
1066
+ "grad_norm": 2.380768299102783,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.1219,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.502106149957877,
1073
+ "grad_norm": 2.444328546524048,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.1542,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5054759898904801,
1080
+ "grad_norm": 2.586287260055542,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.066,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5054759898904801,
1087
+ "eval_loss": 0.287589430809021,
1088
+ "eval_runtime": 121.6025,
1089
+ "eval_samples_per_second": 4.112,
1090
+ "eval_steps_per_second": 1.028,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.253641581715784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null