aleegis12 commited on
Commit
4d1cd60
·
verified ·
1 Parent(s): 20391c8

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 sha256:63222f9575e4a76657789df5414997dce9a2f3795b919aeb972562a9f6606a33
3
  size 121155320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbdfdd14303a3493ed1c88ce4845ca6ae3d3f619f5720ecbe4b52eac39f2c284
3
  size 121155320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88b3161612fce1048a25930d254926d11834ffea594700b1887b17a94c0056ba
3
  size 61896852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8908f21e6d9971e8bea1c14924f7220b74c01ef0d1176236409386695bf173
3
  size 61896852
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e9902bdff7b3e836da8f0c1f2001a2bc19643ce24384c7b211e1ca3e8ac9fff
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6a669540b834525114db676bae55c5b4ac96066b7b06b95d7497c0959fd400
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": 3.7914316654205322,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.1037344398340249,
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": 61.184,
732
  "eval_steps_per_second": 15.296,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6658776367104000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.443917751312256,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.15560165975103735,
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": 61.184,
732
  "eval_steps_per_second": 15.296,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.10477178423236515,
737
+ "grad_norm": 8.166366577148438,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 3.8268,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.10580912863070539,
744
+ "grad_norm": 6.857130527496338,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 3.7574,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10684647302904564,
751
+ "grad_norm": 6.688436985015869,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 3.7533,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.1078838174273859,
758
+ "grad_norm": 6.446659564971924,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 3.9865,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.10892116182572614,
765
+ "grad_norm": 5.080942153930664,
766
+ "learning_rate": 5e-05,
767
+ "loss": 3.4969,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.10995850622406639,
772
+ "grad_norm": 4.44970703125,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 3.5119,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.11099585062240663,
779
+ "grad_norm": 3.998990058898926,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 3.6256,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.11203319502074689,
786
+ "grad_norm": 3.2981390953063965,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 3.4402,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.11307053941908714,
793
+ "grad_norm": 3.044083833694458,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 3.5525,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.11410788381742738,
800
+ "grad_norm": 2.891031503677368,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 3.1974,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.11514522821576763,
807
+ "grad_norm": 2.743988037109375,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 3.2082,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.11618257261410789,
814
+ "grad_norm": 2.7417633533477783,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 3.0046,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.11721991701244813,
821
+ "grad_norm": 2.6141929626464844,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 3.1606,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.11825726141078838,
828
+ "grad_norm": 2.5122275352478027,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 3.4908,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11929460580912864,
835
+ "grad_norm": 2.8065576553344727,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 3.5437,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.12033195020746888,
842
+ "grad_norm": 2.443136692047119,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 3.4685,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.12136929460580913,
849
+ "grad_norm": 2.5843472480773926,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 3.319,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.12240663900414937,
856
+ "grad_norm": 2.6064820289611816,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 3.3902,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.12344398340248963,
863
+ "grad_norm": 2.74259352684021,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 3.81,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.12448132780082988,
870
+ "grad_norm": 2.7329461574554443,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 3.4747,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.12551867219917012,
877
+ "grad_norm": 2.7343878746032715,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 3.5092,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.12655601659751037,
884
+ "grad_norm": 2.749302625656128,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 3.8106,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.1275933609958506,
891
+ "grad_norm": 3.006464719772339,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 3.6465,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12863070539419086,
898
+ "grad_norm": 2.8483219146728516,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 3.3153,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.12966804979253113,
905
+ "grad_norm": 3.621854782104492,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 3.0212,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.13070539419087138,
912
+ "grad_norm": 2.9148917198181152,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 3.2572,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.13174273858921162,
919
+ "grad_norm": 2.9206199645996094,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 3.4323,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.13278008298755187,
926
+ "grad_norm": 3.293531656265259,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 3.4568,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.1338174273858921,
933
+ "grad_norm": 2.9713733196258545,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 3.4724,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.13485477178423236,
940
+ "grad_norm": 3.215953826904297,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 3.6332,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1358921161825726,
947
+ "grad_norm": 3.0868947505950928,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 3.4988,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.13692946058091288,
954
+ "grad_norm": 3.1920242309570312,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 3.3852,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.13796680497925312,
961
+ "grad_norm": 3.4271225929260254,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 3.8709,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.13900414937759337,
968
+ "grad_norm": 3.4510085582733154,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 3.4216,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1400414937759336,
975
+ "grad_norm": 3.2544167041778564,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 3.5809,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.14107883817427386,
982
+ "grad_norm": 3.22052001953125,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 3.2472,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1421161825726141,
989
+ "grad_norm": 3.308317184448242,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 3.5626,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.14315352697095435,
996
+ "grad_norm": 3.3772473335266113,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 3.2607,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.1441908713692946,
1003
+ "grad_norm": 3.1532044410705566,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 3.5309,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.14522821576763487,
1010
+ "grad_norm": 3.440068006515503,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.5348,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1462655601659751,
1017
+ "grad_norm": 3.2612829208374023,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.5397,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.14730290456431536,
1024
+ "grad_norm": 3.7282817363739014,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 3.7273,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.1483402489626556,
1031
+ "grad_norm": 3.4528229236602783,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.3793,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.14937759336099585,
1038
+ "grad_norm": 3.423583507537842,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.2933,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.1504149377593361,
1045
+ "grad_norm": 3.6867237091064453,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 3.8415,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.15145228215767634,
1052
+ "grad_norm": 4.240562438964844,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.9054,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.1524896265560166,
1059
+ "grad_norm": 4.737523078918457,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.7616,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.15352697095435686,
1066
+ "grad_norm": 4.262228965759277,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.6418,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1545643153526971,
1073
+ "grad_norm": 4.715056896209717,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.796,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.15560165975103735,
1080
+ "grad_norm": 6.44474983215332,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 4.0393,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.15560165975103735,
1087
+ "eval_loss": 3.443917751312256,
1088
+ "eval_runtime": 26.554,
1089
+ "eval_samples_per_second": 61.158,
1090
+ "eval_steps_per_second": 15.29,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 9988164550656000.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null