aleegis11 commited on
Commit
e0f3a87
·
verified ·
1 Parent(s): bda8337

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 sha256:60a544224755e82bbc610a32ff2127670bb703694e0ed1bf9bf6459300545869
3
  size 411094576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ce749abf82b9e3cb78fbfd064194d4dacf358de7103eb4018b28d78ff3b6f5
3
  size 411094576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22e95d20e2fead3967c38bf4189c216a3fe15240150755e4a162c1610bf6a6c0
3
  size 209193332
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40943de1a018dea141f7ca2e04de15db90fed179dc855f9207aa81134b1f2787
3
  size 209193332
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cce9ade4c3f92c6eb28d476379147a3afe884120b10d385ff03f2a1335b835f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b54d62c01702c04cd7132aa08eb717bdf4a18c04ee3c57a4633ca1d0e18325d2
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": 1.3159615993499756,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.08133387555917039,
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": 19.474,
732
  "eval_steps_per_second": 4.871,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6.26343737819136e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1605161428451538,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.12200081333875559,
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": 19.474,
732
  "eval_steps_per_second": 4.871,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0821472143147621,
737
+ "grad_norm": 2.0550525188446045,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.2755,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0829605530703538,
744
+ "grad_norm": 2.024679183959961,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.332,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.08377389182594551,
751
+ "grad_norm": 1.420579433441162,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.2512,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0845872305815372,
758
+ "grad_norm": 1.018290400505066,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.2379,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.08540056933712892,
765
+ "grad_norm": 0.8214701414108276,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.2182,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.08621390809272061,
772
+ "grad_norm": 0.7688771486282349,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.1202,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.08702724684831233,
779
+ "grad_norm": 0.7829757928848267,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.1586,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08784058560390402,
786
+ "grad_norm": 0.7908482551574707,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.1513,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.08865392435949573,
793
+ "grad_norm": 0.8245127201080322,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.1873,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08946726311508743,
800
+ "grad_norm": 0.8461537957191467,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.1589,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.09028060187067914,
807
+ "grad_norm": 0.8592161536216736,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.2259,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.09109394062627084,
814
+ "grad_norm": 0.8966860175132751,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.168,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.09190727938186255,
821
+ "grad_norm": 0.9335092306137085,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.1877,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.09272061813745425,
828
+ "grad_norm": 0.9056230187416077,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.1673,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.09353395689304596,
835
+ "grad_norm": 0.8870036005973816,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.1803,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09434729564863766,
842
+ "grad_norm": 0.8796521425247192,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.1435,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.09516063440422937,
849
+ "grad_norm": 0.9620208144187927,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.247,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.09597397315982106,
856
+ "grad_norm": 0.982358455657959,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.2598,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.09678731191541277,
863
+ "grad_norm": 1.008872151374817,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.1617,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.09760065067100447,
870
+ "grad_norm": 1.0747501850128174,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.3292,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.09841398942659618,
877
+ "grad_norm": 1.1409488916397095,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.2098,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.09922732818218788,
884
+ "grad_norm": 1.0723323822021484,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.1448,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.10004066693777959,
891
+ "grad_norm": 1.1127489805221558,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.3292,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.10085400569337129,
898
+ "grad_norm": 1.2123587131500244,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.1752,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.101667344448963,
905
+ "grad_norm": 1.2362475395202637,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.2633,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1024806832045547,
912
+ "grad_norm": 1.2689555883407593,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.3501,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1032940219601464,
919
+ "grad_norm": 1.2432509660720825,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.1881,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.1041073607157381,
926
+ "grad_norm": 1.3342244625091553,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.2224,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.10492069947132981,
933
+ "grad_norm": 1.5508168935775757,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.1327,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.10573403822692151,
940
+ "grad_norm": 1.4915046691894531,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.1749,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.10654737698251322,
947
+ "grad_norm": 1.7136361598968506,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.1905,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.10736071573810492,
954
+ "grad_norm": 1.7495901584625244,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.1947,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.10817405449369663,
961
+ "grad_norm": 1.9899603128433228,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.1413,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.10898739324928833,
968
+ "grad_norm": 2.017275810241699,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.2073,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.10980073200488004,
975
+ "grad_norm": 2.167989492416382,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.1697,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.11061407076047174,
982
+ "grad_norm": 2.149290084838867,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.0847,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.11142740951606345,
989
+ "grad_norm": 2.4723289012908936,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.264,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.11224074827165514,
996
+ "grad_norm": 2.4806630611419678,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.1523,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.11305408702724686,
1003
+ "grad_norm": 2.612274169921875,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.0612,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.11386742578283855,
1010
+ "grad_norm": 3.0523922443389893,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.0515,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.11468076453843025,
1017
+ "grad_norm": 2.8779609203338623,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.0776,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.11549410329402196,
1024
+ "grad_norm": 2.810849666595459,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.0472,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.11630744204961366,
1031
+ "grad_norm": 3.260906457901001,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.0201,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.11712078080520537,
1038
+ "grad_norm": 3.4329018592834473,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.7933,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.11793411956079707,
1045
+ "grad_norm": 3.347562789916992,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.0614,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.11874745831638878,
1052
+ "grad_norm": 4.097909450531006,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.0916,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.11956079707198047,
1059
+ "grad_norm": 3.529541492462158,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.8505,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.12037413582757218,
1066
+ "grad_norm": 4.165427207946777,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.9878,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.12118747458316388,
1073
+ "grad_norm": 4.062654495239258,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.8192,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.12200081333875559,
1080
+ "grad_norm": 7.141842842102051,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.5491,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.12200081333875559,
1087
+ "eval_loss": 1.1605161428451538,
1088
+ "eval_runtime": 106.3455,
1089
+ "eval_samples_per_second": 19.474,
1090
+ "eval_steps_per_second": 4.871,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 9.39515606728704e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null