prxy5607 commited on
Commit
20bbf1a
·
verified ·
1 Parent(s): 59dabe2

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:cc53fabe0396b4cddbbc8c49bf341ff20aeb1980507c34ed2c8d4dc493dbb1c7
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d494ee90c448cdb28624b85197dec8a5cc5ed447c53ab51f72f955691b42d8d
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9887ebb37de98954b43c3a6a408d19625f846fd774152ebb811364b59989c51c
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe531722ff723df97ca757741b84bd792629399e5cba2ce24bf359a73e18866
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:146a62c8de7ccf0512b0d08844287d2ffbb8a8a610d9d25c830a5dc5edc02c22
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdea5339b81f388534280c6e6c8b249f5e0d0e05bf934196b0ffe25f5750a558
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": 5.114246505399933e-06,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 1.2944983818770226,
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": 13.28,
732
  "eval_steps_per_second": 3.371,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -745,7 +1103,7 @@
745
  "early_stopping_threshold": 0.0
746
  },
747
  "attributes": {
748
- "early_stopping_patience_counter": 1
749
  }
750
  },
751
  "TrainerControl": {
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.50757075775914e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.265722969241324e-06,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.941747572815534,
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": 13.28,
732
  "eval_steps_per_second": 3.371,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.307443365695793,
737
+ "grad_norm": 0.0008209234802052379,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.0,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.3203883495145632,
744
+ "grad_norm": 0.054027754813432693,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.0001,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.3333333333333333,
751
+ "grad_norm": 0.0007307673222385347,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.0,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.3462783171521036,
758
+ "grad_norm": 0.005266569554805756,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.0,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.3592233009708738,
765
+ "grad_norm": 0.0006765456637367606,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.0,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.3721682847896441,
772
+ "grad_norm": 0.0358976311981678,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.0001,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.3851132686084142,
779
+ "grad_norm": 0.0003064029151573777,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.0,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.3980582524271845,
786
+ "grad_norm": 0.00010614845086820424,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.0,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.4110032362459548,
793
+ "grad_norm": 0.00012399001570884138,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.0,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.4239482200647249,
800
+ "grad_norm": 0.003827552078291774,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.0,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.4368932038834952,
807
+ "grad_norm": 0.0005444152629934251,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.0,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.4498381877022655,
814
+ "grad_norm": 0.00020939875685144216,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.0,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.4627831715210355,
821
+ "grad_norm": 0.00023036557831801474,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.0,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.4757281553398058,
828
+ "grad_norm": 0.0022763346787542105,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.0,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.4886731391585761,
835
+ "grad_norm": 0.00015546870417892933,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.0,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.5016181229773462,
842
+ "grad_norm": 0.006108403671532869,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.0,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.5145631067961165,
849
+ "grad_norm": 0.0018249741988256574,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.0,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.5275080906148868,
856
+ "grad_norm": 9.492759272689e-05,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.0,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.5404530744336569,
863
+ "grad_norm": 0.00016195476928260177,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.0,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.5533980582524272,
870
+ "grad_norm": 0.0001234033115906641,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.0,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.5663430420711975,
877
+ "grad_norm": 9.540676546748728e-05,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.0,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.5792880258899675,
884
+ "grad_norm": 0.005599276628345251,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.0,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.5922330097087378,
891
+ "grad_norm": 0.00025100537459366024,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.0,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.6051779935275081,
898
+ "grad_norm": 0.0002124908205587417,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.0,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.6181229773462782,
905
+ "grad_norm": 0.00010561349336057901,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.0,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.6310679611650487,
912
+ "grad_norm": 0.00021081748127471656,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.0,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.6440129449838188,
919
+ "grad_norm": 0.00012433409574441612,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.0,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.6569579288025889,
926
+ "grad_norm": 9.320802928414196e-05,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.0,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.6699029126213594,
933
+ "grad_norm": 9.787802991922945e-05,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.0,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.6828478964401294,
940
+ "grad_norm": 0.0007250069174915552,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.0,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.6957928802588995,
947
+ "grad_norm": 0.0006313190679065883,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.0,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.70873786407767,
954
+ "grad_norm": 0.0002635714190546423,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.0,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.72168284789644,
961
+ "grad_norm": 0.00019160538795404136,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.0,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.7346278317152104,
968
+ "grad_norm": 0.0006658636266365647,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.0,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.7475728155339807,
975
+ "grad_norm": 0.0035931889433413744,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.0,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.7605177993527508,
982
+ "grad_norm": 0.00011197294952580705,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.0,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.773462783171521,
989
+ "grad_norm": 0.0027357996441423893,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.0,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.7864077669902914,
996
+ "grad_norm": 0.0010884864022955298,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.0,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.7993527508090614,
1003
+ "grad_norm": 0.00019315312965773046,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.0,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.8122977346278317,
1010
+ "grad_norm": 8.6668660514988e-05,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.0,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.825242718446602,
1017
+ "grad_norm": 5.9428366512292996e-05,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.0,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.838187702265372,
1024
+ "grad_norm": 0.10113563388586044,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.0005,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.8511326860841424,
1031
+ "grad_norm": 0.002838822780176997,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.0,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.8640776699029127,
1038
+ "grad_norm": 0.0007735037361271679,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.0,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.8770226537216828,
1045
+ "grad_norm": 9.024533937918022e-05,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.0,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.889967637540453,
1052
+ "grad_norm": 0.0010357049759477377,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.0,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.9029126213592233,
1059
+ "grad_norm": 0.00022478362370748073,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.0,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.9158576051779934,
1066
+ "grad_norm": 5.8589426771504804e-05,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.0,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.9288025889967637,
1073
+ "grad_norm": 0.0005812260787934065,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.0,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.941747572815534,
1080
+ "grad_norm": 0.00010281232971465215,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.0,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.941747572815534,
1087
+ "eval_loss": 2.265722969241324e-06,
1088
+ "eval_runtime": 9.7942,
1089
+ "eval_samples_per_second": 13.273,
1090
+ "eval_steps_per_second": 3.369,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1103
  "early_stopping_threshold": 0.0
1104
  },
1105
  "attributes": {
1106
+ "early_stopping_patience_counter": 0
1107
  }
1108
  },
1109
  "TrainerControl": {
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.261827547132068e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null