aleegis12 commited on
Commit
5ef858f
·
verified ·
1 Parent(s): 4f0c36c

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 sha256:1c4a5c1521d39d34635ae30db4e560764e8e058f479d4c754579093eba81f527
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0ba8cd0142a12d482a0be5ce2bd9031f618878f396eef89a070fb2b0dd564d
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2faad991f6674dadfd8d59d53a1574dd0569810754c7999007efad25bbd821a9
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7acb26a91d2b575ba7ec4bd69af1d0fcae3384c3068fb34e7b62c54260d518b5
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45c67205e9cf0d2da4f99674c5f23dc96e5e32a1cbbce1e9acf0a594b546ed8d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb4008a973bf62a83dc1d1001e5e323f5a53b192ea155d229b04bcd01c373a6
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": 0.6084063053131104,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.1444564824846515,
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": 8.862,
732
  "eval_steps_per_second": 2.219,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.2001619151355904e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.4998982846736908,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.21668472372697725,
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": 8.862,
732
  "eval_steps_per_second": 2.219,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.14590104730949802,
737
+ "grad_norm": 4.636070728302002,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.5325,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.14734561213434452,
744
+ "grad_norm": 4.1496734619140625,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.9369,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.14879017695919106,
751
+ "grad_norm": 2.4670321941375732,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.9469,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.15023474178403756,
758
+ "grad_norm": 2.210479497909546,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.2942,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.15167930660888407,
765
+ "grad_norm": 2.232630729675293,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.081,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1531238714337306,
772
+ "grad_norm": 2.0091922283172607,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.8598,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.1545684362585771,
779
+ "grad_norm": 2.1086859703063965,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.9808,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.1560130010834236,
786
+ "grad_norm": 2.02327823638916,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.8329,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.15745756590827015,
793
+ "grad_norm": 2.1389639377593994,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.9847,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.15890213073311665,
800
+ "grad_norm": 1.9792823791503906,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.9757,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.16034669555796316,
807
+ "grad_norm": 2.118889808654785,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.7645,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.16179126038280967,
814
+ "grad_norm": 1.9891248941421509,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.5004,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.1632358252076562,
821
+ "grad_norm": 2.0828189849853516,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.4636,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.1646803900325027,
828
+ "grad_norm": 1.9011919498443604,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.7825,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.1661249548573492,
835
+ "grad_norm": 2.010429620742798,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.7281,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.16756951968219574,
842
+ "grad_norm": 1.9818568229675293,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.7599,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.16901408450704225,
849
+ "grad_norm": 1.8152260780334473,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.3041,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.17045864933188876,
856
+ "grad_norm": 2.1288044452667236,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.7119,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.1719032141567353,
863
+ "grad_norm": 2.17903995513916,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.0871,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.1733477789815818,
870
+ "grad_norm": 2.110379934310913,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.5574,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.1747923438064283,
877
+ "grad_norm": 2.108875036239624,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.9877,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.17623690863127484,
884
+ "grad_norm": 2.0717296600341797,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.4659,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.17768147345612134,
891
+ "grad_norm": 1.8651466369628906,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.6377,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.17912603828096785,
898
+ "grad_norm": 1.877915620803833,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.6318,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.18057060310581438,
905
+ "grad_norm": 1.8974331617355347,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.8603,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1820151679306609,
912
+ "grad_norm": 1.9938749074935913,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.4837,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1834597327555074,
919
+ "grad_norm": 2.0055007934570312,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.7064,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.18490429758035393,
926
+ "grad_norm": 2.62275767326355,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.9578,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.18634886240520043,
933
+ "grad_norm": 2.875729560852051,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.214,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.18779342723004694,
940
+ "grad_norm": 2.720029354095459,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.026,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.18923799205489347,
947
+ "grad_norm": 3.5830607414245605,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.7676,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.19068255687973998,
954
+ "grad_norm": 2.266727924346924,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.6481,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.19212712170458648,
961
+ "grad_norm": 2.671396493911743,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.7278,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.19357168652943302,
968
+ "grad_norm": 2.5085813999176025,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.915,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.19501625135427952,
975
+ "grad_norm": 2.8505218029022217,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.8356,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.19646081617912603,
982
+ "grad_norm": 3.1037275791168213,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.3404,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.19790538100397256,
989
+ "grad_norm": 3.5762994289398193,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.4602,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.19934994582881907,
996
+ "grad_norm": 3.5494682788848877,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.3281,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.20079451065366558,
1003
+ "grad_norm": 3.5788474082946777,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.1461,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.2022390754785121,
1010
+ "grad_norm": 3.6270062923431396,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.3968,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.20368364030335862,
1017
+ "grad_norm": 3.963440418243408,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.2883,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.20512820512820512,
1024
+ "grad_norm": 4.410841941833496,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.5689,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.20657276995305165,
1031
+ "grad_norm": 4.599275588989258,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.7271,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.20801733477789816,
1038
+ "grad_norm": 5.342073917388916,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.638,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.20946189960274467,
1045
+ "grad_norm": 4.901814937591553,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.4321,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2109064644275912,
1052
+ "grad_norm": 6.531753063201904,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.2965,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2123510292524377,
1059
+ "grad_norm": 9.266947746276855,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.6654,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.2137955940772842,
1066
+ "grad_norm": 9.59514045715332,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.4355,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.21524015890213075,
1073
+ "grad_norm": 8.447040557861328,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.6293,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.21668472372697725,
1080
+ "grad_norm": 16.740819931030273,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 5.5686,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.21668472372697725,
1087
+ "eval_loss": 0.4998982846736908,
1088
+ "eval_runtime": 131.5681,
1089
+ "eval_samples_per_second": 8.862,
1090
+ "eval_steps_per_second": 2.219,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.302031622227886e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null