lesso14 commited on
Commit
2f1b737
·
verified ·
1 Parent(s): fdacdba

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 sha256:64cfcbf8deb70233ada8ee9cbc5750a66926222ab890f3f65d42a11c773ef8f2
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f778bddf9cc2d4772ac76d2daa302892e9b642e5484759bc4b7a8679d2ead0
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60429135debff0ec18790fbb9fd0f5a6b7376e798108625f8a79219e7f2c34c7
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35468f1ff79e12bb405e2e68fd9c1abd18cc4175cba16300f57b30c27d35059
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13983572bbf1006470534930bfbea8af43cb265e9bffb9f7f12b382f89411feb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc7c95dd6dd1eea0d9e581e4d8ea44a80e48947277f6f04dc85bfc905f6f4dad
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b2ff91019f251b72cdf781986424ccdfd5ceb7ae633fedb2bccce31d3f61847
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970068ebf9c0dc6a40c93653c563bb0b2ba5296a6c46496b504a3f1343bf3a62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6658266186714172,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.4410143329658214,
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": 3.555,
732
  "eval_steps_per_second": 0.893,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.783292693801861e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6403191685676575,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.6615214994487321,
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": 3.555,
732
  "eval_steps_per_second": 0.893,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.4454244762954796,
737
+ "grad_norm": 4.080659866333008,
738
+ "learning_rate": 5.8634982137913465e-05,
739
+ "loss": 3.2606,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.4498346196251378,
744
+ "grad_norm": 2.8597896099090576,
745
+ "learning_rate": 5.772710650702723e-05,
746
+ "loss": 3.2198,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.45424476295479604,
751
+ "grad_norm": 1.9857066869735718,
752
+ "learning_rate": 5.681848531245195e-05,
753
+ "loss": 3.1464,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.45865490628445427,
758
+ "grad_norm": 1.819825291633606,
759
+ "learning_rate": 5.590936696214972e-05,
760
+ "loss": 3.3014,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.46306504961411243,
765
+ "grad_norm": 1.7104649543762207,
766
+ "learning_rate": 5.5e-05,
767
+ "loss": 3.1921,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.46747519294377066,
772
+ "grad_norm": 1.5252690315246582,
773
+ "learning_rate": 5.409063303785029e-05,
774
+ "loss": 3.0135,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.4718853362734289,
779
+ "grad_norm": 1.5344245433807373,
780
+ "learning_rate": 5.318151468754805e-05,
781
+ "loss": 2.9589,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.4762954796030871,
786
+ "grad_norm": 1.3514833450317383,
787
+ "learning_rate": 5.227289349297277e-05,
788
+ "loss": 2.898,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.4807056229327453,
793
+ "grad_norm": 1.3298234939575195,
794
+ "learning_rate": 5.136501786208654e-05,
795
+ "loss": 2.9296,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.48511576626240355,
800
+ "grad_norm": 1.4843939542770386,
801
+ "learning_rate": 5.045813599902173e-05,
802
+ "loss": 3.2311,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.4895259095920617,
807
+ "grad_norm": 1.3323349952697754,
808
+ "learning_rate": 4.955249583622455e-05,
809
+ "loss": 2.8828,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.49393605292171994,
814
+ "grad_norm": 1.3595972061157227,
815
+ "learning_rate": 4.8648344966672767e-05,
816
+ "loss": 2.9486,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.49834619625137816,
821
+ "grad_norm": 1.3509643077850342,
822
+ "learning_rate": 4.774593057618621e-05,
823
+ "loss": 3.2162,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5027563395810364,
828
+ "grad_norm": 1.3561177253723145,
829
+ "learning_rate": 4.6845499375848686e-05,
830
+ "loss": 2.854,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5071664829106945,
835
+ "grad_norm": 1.4786139726638794,
836
+ "learning_rate": 4.5947297534559625e-05,
837
+ "loss": 3.1804,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5115766262403528,
842
+ "grad_norm": 1.3076729774475098,
843
+ "learning_rate": 4.5051570611733976e-05,
844
+ "loss": 3.134,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.515986769570011,
849
+ "grad_norm": 1.4321703910827637,
850
+ "learning_rate": 4.415856349016859e-05,
851
+ "loss": 2.891,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5203969128996693,
856
+ "grad_norm": 1.3954541683197021,
857
+ "learning_rate": 4.326852030909393e-05,
858
+ "loss": 2.9936,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5248070562293274,
863
+ "grad_norm": 1.3153645992279053,
864
+ "learning_rate": 4.238168439742867e-05,
865
+ "loss": 3.1401,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5292171995589857,
870
+ "grad_norm": 1.3978232145309448,
871
+ "learning_rate": 4.149829820725605e-05,
872
+ "loss": 3.2422,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.5336273428886439,
877
+ "grad_norm": 1.3654237985610962,
878
+ "learning_rate": 4.0618603247539916e-05,
879
+ "loss": 2.9804,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.538037486218302,
884
+ "grad_norm": 1.6010512113571167,
885
+ "learning_rate": 3.9742840018098564e-05,
886
+ "loss": 2.8879,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5424476295479603,
891
+ "grad_norm": 1.2477831840515137,
892
+ "learning_rate": 3.887124794385445e-05,
893
+ "loss": 2.6711,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.5468577728776185,
898
+ "grad_norm": 1.3943934440612793,
899
+ "learning_rate": 3.80040653093779e-05,
900
+ "loss": 3.0408,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.5512679162072768,
905
+ "grad_norm": 1.632759690284729,
906
+ "learning_rate": 3.714152919374241e-05,
907
+ "loss": 3.076,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5556780595369349,
912
+ "grad_norm": 1.3918051719665527,
913
+ "learning_rate": 3.628387540570963e-05,
914
+ "loss": 3.0342,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5600882028665931,
919
+ "grad_norm": 1.2972222566604614,
920
+ "learning_rate": 3.543133841926159e-05,
921
+ "loss": 2.82,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5644983461962514,
926
+ "grad_norm": 1.202620267868042,
927
+ "learning_rate": 3.458415130949785e-05,
928
+ "loss": 2.4912,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5689084895259096,
933
+ "grad_norm": 1.3449923992156982,
934
+ "learning_rate": 3.374254568891514e-05,
935
+ "loss": 3.3369,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5733186328555678,
940
+ "grad_norm": 1.3851882219314575,
941
+ "learning_rate": 3.290675164408669e-05,
942
+ "loss": 2.565,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.577728776185226,
947
+ "grad_norm": 1.2937684059143066,
948
+ "learning_rate": 3.207699767275904e-05,
949
+ "loss": 2.7112,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5821389195148843,
954
+ "grad_norm": 1.4037163257598877,
955
+ "learning_rate": 3.12535106213829e-05,
956
+ "loss": 3.11,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.5865490628445424,
961
+ "grad_norm": 1.3117399215698242,
962
+ "learning_rate": 3.0436515623095647e-05,
963
+ "loss": 2.6965,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5909592061742006,
968
+ "grad_norm": 1.3175640106201172,
969
+ "learning_rate": 2.962623603617218e-05,
970
+ "loss": 2.7956,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5953693495038589,
975
+ "grad_norm": 1.3013272285461426,
976
+ "learning_rate": 2.8822893382960955e-05,
977
+ "loss": 2.6119,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.5997794928335171,
982
+ "grad_norm": 1.3417240381240845,
983
+ "learning_rate": 2.802670728932207e-05,
984
+ "loss": 2.7399,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.6041896361631753,
989
+ "grad_norm": 1.4003099203109741,
990
+ "learning_rate": 2.723789542458361e-05,
991
+ "loss": 3.2267,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6085997794928335,
996
+ "grad_norm": 1.3760734796524048,
997
+ "learning_rate": 2.6456673442033183e-05,
998
+ "loss": 3.064,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.6130099228224918,
1003
+ "grad_norm": 1.4111647605895996,
1004
+ "learning_rate": 2.5683254919960356e-05,
1005
+ "loss": 2.8482,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.61742006615215,
1010
+ "grad_norm": 1.7103841304779053,
1011
+ "learning_rate": 2.4917851303266533e-05,
1012
+ "loss": 1.9783,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.6218302094818081,
1017
+ "grad_norm": 1.6013977527618408,
1018
+ "learning_rate": 2.4160671845658007e-05,
1019
+ "loss": 1.8013,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.6262403528114664,
1024
+ "grad_norm": 1.2906684875488281,
1025
+ "learning_rate": 2.3411923552438105e-05,
1026
+ "loss": 1.0097,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.6306504961411246,
1031
+ "grad_norm": 1.3760795593261719,
1032
+ "learning_rate": 2.2671811123913983e-05,
1033
+ "loss": 1.2116,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6350606394707828,
1038
+ "grad_norm": 1.368346095085144,
1039
+ "learning_rate": 2.194053689943362e-05,
1040
+ "loss": 0.7298,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.639470782800441,
1045
+ "grad_norm": 1.2973005771636963,
1046
+ "learning_rate": 2.121830080206827e-05,
1047
+ "loss": 0.3624,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6438809261300992,
1052
+ "grad_norm": 1.3431459665298462,
1053
+ "learning_rate": 2.0505300283955464e-05,
1054
+ "loss": 0.3439,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6482910694597575,
1059
+ "grad_norm": 2.1608824729919434,
1060
+ "learning_rate": 1.9801730272317585e-05,
1061
+ "loss": 0.3482,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6527012127894156,
1066
+ "grad_norm": 1.9314510822296143,
1067
+ "learning_rate": 1.910778311617072e-05,
1068
+ "loss": 0.3296,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6571113561190739,
1073
+ "grad_norm": 1.8207006454467773,
1074
+ "learning_rate": 1.8423648533738342e-05,
1075
+ "loss": 0.3223,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6615214994487321,
1080
+ "grad_norm": 2.0629324913024902,
1081
+ "learning_rate": 1.7749513560584252e-05,
1082
+ "loss": 0.2425,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6615214994487321,
1087
+ "eval_loss": 0.6403191685676575,
1088
+ "eval_runtime": 116.2907,
1089
+ "eval_samples_per_second": 3.285,
1090
+ "eval_steps_per_second": 0.826,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.178516537738527e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null