prxy5605 commited on
Commit
7959492
·
verified ·
1 Parent(s): 9316d5d

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 sha256:576a1fc57c8b4a85138f5312094b54476c3ed6f58d91d5855b098ddd00cb6bdd
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:597bbcd967757189f428e37ea2dd07ee000abd2ef7ab19ec6946dfb51020ba06
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89586263bcdd5b45ec359fa94212e69e3248afc565be3f1c2114ec4c3b845a55
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe5f253b9a0bc93b059099ffac0a68d21958ecee25eb173d5e32b9ee27b4ee60
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:a004d8ff38579a441a04602b2ff5b6351d6d59a459e9890d18447709b3006d7f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e6842d212195f7b5523160ad2c2443cacfcdae88d00c829f199b81d42de516
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": 1.4711685180664062,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.030483158055174518,
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": 13.482,
732
  "eval_steps_per_second": 3.372,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.434577118649385e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2966549396514893,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.04572473708276177,
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": 13.482,
732
  "eval_steps_per_second": 3.372,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.03078798963572626,
737
+ "grad_norm": 13.523937225341797,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 4.3282,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.031092821216278006,
744
+ "grad_norm": 11.723952293395996,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 6.1989,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.03139765279682975,
751
+ "grad_norm": 8.955606460571289,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 6.6737,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0317024843773815,
758
+ "grad_norm": 6.171177864074707,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 6.355,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03200731595793324,
765
+ "grad_norm": 4.633945465087891,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.1537,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.032312147538484985,
772
+ "grad_norm": 5.904881000518799,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 6.907,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.03261697911903673,
779
+ "grad_norm": 4.719089508056641,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 4.7175,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.03292181069958848,
786
+ "grad_norm": 5.215052604675293,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 5.8148,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.033226642280140224,
793
+ "grad_norm": 4.605810642242432,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 5.9343,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.03353147386069197,
800
+ "grad_norm": 4.18067741394043,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.3571,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03383630544124371,
807
+ "grad_norm": 4.579970836639404,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 5.5399,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.034141137021795456,
814
+ "grad_norm": 5.099072456359863,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 6.4311,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.0344459686023472,
821
+ "grad_norm": 4.4032697677612305,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.6979,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.03475080018289895,
828
+ "grad_norm": 4.820939064025879,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 6.2778,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.035055631763450695,
835
+ "grad_norm": 4.672818183898926,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 6.0629,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03536046334400244,
842
+ "grad_norm": 4.3500237464904785,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 7.1509,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.03566529492455418,
849
+ "grad_norm": 4.337316036224365,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.6693,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.03597012650510593,
856
+ "grad_norm": 3.986161947250366,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 5.3874,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.03627495808565767,
863
+ "grad_norm": 4.089871406555176,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 5.9395,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.03657978966620942,
870
+ "grad_norm": 4.648094177246094,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 5.0568,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.036884621246761166,
877
+ "grad_norm": 4.79482364654541,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 6.2573,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.03718945282731291,
884
+ "grad_norm": 4.585735321044922,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 5.4265,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.037494284407864654,
891
+ "grad_norm": 5.3116559982299805,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 4.9758,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0377991159884164,
898
+ "grad_norm": 4.849041938781738,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 4.6737,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.03810394756896814,
905
+ "grad_norm": 6.232630252838135,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 5.0093,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.038408779149519894,
912
+ "grad_norm": 5.127786159515381,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 5.6108,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.03871361073007164,
919
+ "grad_norm": 5.577056884765625,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 6.0935,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.03901844231062338,
926
+ "grad_norm": 4.655738830566406,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 4.9686,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.039323273891175126,
933
+ "grad_norm": 5.1628618240356445,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 4.5923,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.03962810547172687,
940
+ "grad_norm": 5.173516750335693,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 4.9268,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.039932937052278614,
947
+ "grad_norm": 5.684381484985352,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 4.9674,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.040237768632830365,
954
+ "grad_norm": 5.033452987670898,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 5.1091,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.04054260021338211,
961
+ "grad_norm": 5.16779088973999,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 5.2584,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.04084743179393385,
968
+ "grad_norm": 4.97949743270874,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 3.963,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0411522633744856,
975
+ "grad_norm": 4.999173641204834,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 4.1747,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.04145709495503734,
982
+ "grad_norm": 4.739213466644287,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 4.2939,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.041761926535589085,
989
+ "grad_norm": 4.772510051727295,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 4.4216,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.04206675811614083,
996
+ "grad_norm": 5.0304131507873535,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 4.5226,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.04237158969669258,
1003
+ "grad_norm": 5.028468132019043,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 3.8991,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.042676421277244324,
1010
+ "grad_norm": 4.815616130828857,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.5061,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.04298125285779607,
1017
+ "grad_norm": 5.87587833404541,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.7284,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.04328608443834781,
1024
+ "grad_norm": 5.637801170349121,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 3.7916,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.043590916018899556,
1031
+ "grad_norm": 5.960572242736816,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.6842,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0438957475994513,
1038
+ "grad_norm": 6.362869739532471,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.6665,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.04420057918000305,
1045
+ "grad_norm": 5.614107608795166,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 3.2873,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.044505410760554795,
1052
+ "grad_norm": 6.324036121368408,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.1307,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04481024234110654,
1059
+ "grad_norm": 6.421680927276611,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.4838,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.04511507392165828,
1066
+ "grad_norm": 7.649716854095459,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.5987,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.04541990550221003,
1073
+ "grad_norm": 8.111498832702637,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.9224,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.04572473708276177,
1080
+ "grad_norm": 14.404260635375977,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 3.418,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.04572473708276177,
1087
+ "eval_loss": 1.2966549396514893,
1088
+ "eval_runtime": 409.7214,
1089
+ "eval_samples_per_second": 13.485,
1090
+ "eval_steps_per_second": 3.373,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.153654427498578e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null