prxy5606 commited on
Commit
b95e738
·
verified ·
1 Parent(s): 39f60e5

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 sha256:0ef1f241f0b3a91cb4fac896139154f1e671f613dd9a1c6b36863e0e5c5643f6
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b11d7048e6c23f23a94e0d0c8825e1ac813b61cb502eed9d5cd2c54c7a2414
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d3fd6aef235d1b075db6384a763843988f18e952af244cf43a68f6aeda5acf8
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a0cffbc5fbbbf53c5133edbd23939bc94fb98056cdd878966f78204cc6bcb1
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5caf90fac8a6e6cc70e9aa7e33a2be18f3d818fc86d3aca5aada65d2b74e0b24
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45748947fb554c8c2bffa935f8506946ac14f3334fb1dc51e42e85332d8ab784
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": 1.0484580993652344,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.796812749003984,
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": 12.721,
732
  "eval_steps_per_second": 3.18,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.49380204068864e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0226194858551025,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.1952191235059761,
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": 12.721,
732
  "eval_steps_per_second": 3.18,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.8047808764940239,
737
+ "grad_norm": 0.3082982003688812,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.9515,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.8127490039840638,
744
+ "grad_norm": 0.1807137280702591,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.1024,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.8207171314741036,
751
+ "grad_norm": 0.17332789301872253,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.1216,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.8286852589641435,
758
+ "grad_norm": 0.17725008726119995,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.0249,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.8366533864541833,
765
+ "grad_norm": 0.1845608800649643,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.9936,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.8446215139442231,
772
+ "grad_norm": 0.24144724011421204,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.0673,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.852589641434263,
779
+ "grad_norm": 0.23575012385845184,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.214,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.8605577689243028,
786
+ "grad_norm": 0.2337813675403595,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.0538,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.8685258964143426,
793
+ "grad_norm": 0.22413738071918488,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.065,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.8764940239043825,
800
+ "grad_norm": 0.22103345394134521,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.0272,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.8844621513944223,
807
+ "grad_norm": 0.25055572390556335,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.1709,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.8924302788844621,
814
+ "grad_norm": 0.24400641024112701,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.9701,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.900398406374502,
821
+ "grad_norm": 0.26395559310913086,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.0888,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.9083665338645418,
828
+ "grad_norm": 0.3101651072502136,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.1487,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.9163346613545816,
835
+ "grad_norm": 0.280747652053833,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.1171,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.9243027888446215,
842
+ "grad_norm": 0.40413448214530945,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.1585,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.9322709163346613,
849
+ "grad_norm": 0.3763766288757324,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9307,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.9402390438247012,
856
+ "grad_norm": 0.36883345246315,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.0472,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.9482071713147411,
863
+ "grad_norm": 0.3642585873603821,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.9853,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.9561752988047809,
870
+ "grad_norm": 0.43915310502052307,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.1615,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.9641434262948207,
877
+ "grad_norm": 0.4310603737831116,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.0356,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.9721115537848606,
884
+ "grad_norm": 0.47499728202819824,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.0468,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.9800796812749004,
891
+ "grad_norm": 0.46576792001724243,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.8957,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.9880478087649402,
898
+ "grad_norm": 0.7518230676651001,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.8025,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.9960159362549801,
905
+ "grad_norm": 0.21898995339870453,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.897,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.00398406374502,
912
+ "grad_norm": 0.49494481086730957,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.4167,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.0119521912350598,
919
+ "grad_norm": 0.14274008572101593,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.924,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.0199203187250996,
926
+ "grad_norm": 0.16929715871810913,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.8777,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.0278884462151394,
933
+ "grad_norm": 0.14793212711811066,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.7854,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.0358565737051793,
940
+ "grad_norm": 0.18344572186470032,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.9512,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.043824701195219,
947
+ "grad_norm": 0.15657907724380493,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.9446,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.051792828685259,
954
+ "grad_norm": 0.15426430106163025,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.9213,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.0597609561752988,
961
+ "grad_norm": 0.20302581787109375,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.0127,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.0677290836653386,
968
+ "grad_norm": 0.164063960313797,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.0012,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.0756972111553784,
975
+ "grad_norm": 0.1688258945941925,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.0375,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.0836653386454183,
982
+ "grad_norm": 0.18732470273971558,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.0868,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.091633466135458,
989
+ "grad_norm": 0.1671607792377472,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.0697,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.099601593625498,
996
+ "grad_norm": 0.17614442110061646,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.1221,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.1075697211155378,
1003
+ "grad_norm": 0.18757355213165283,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.9856,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.1155378486055776,
1010
+ "grad_norm": 0.20143137872219086,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.0339,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.1235059760956174,
1017
+ "grad_norm": 0.19974087178707123,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.0533,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.1314741035856573,
1024
+ "grad_norm": 0.2140830159187317,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.0704,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.139442231075697,
1031
+ "grad_norm": 0.2263874113559723,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.0187,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.1474103585657371,
1038
+ "grad_norm": 0.2369435876607895,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.0188,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.155378486055777,
1045
+ "grad_norm": 0.2371990829706192,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.9108,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.1633466135458168,
1052
+ "grad_norm": 0.25344139337539673,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.9491,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.1713147410358566,
1059
+ "grad_norm": 0.26361140608787537,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.028,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.1792828685258965,
1066
+ "grad_norm": 0.2927485704421997,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.9666,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.1872509960159363,
1073
+ "grad_norm": 0.2782008945941925,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.9223,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.1952191235059761,
1080
+ "grad_norm": 0.30430302023887634,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.9633,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.1952191235059761,
1087
+ "eval_loss": 1.0226194858551025,
1088
+ "eval_runtime": 16.9268,
1089
+ "eval_samples_per_second": 12.525,
1090
+ "eval_steps_per_second": 3.131,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2036944519168e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null