nttx commited on
Commit
e41081b
·
verified ·
1 Parent(s): ec4dc8a

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 sha256:845ab66162e290bbc503ead1fc26378054da32e6780091212111a14890d22af2
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92f425f7774472a6acdb3db1c3fd862aef0cf64f3f409c999972402ea146f0a8
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:999444773cb6037a39e0487aa548e8d4905f1c316af750b8a2aa560fe94ed3e5
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42052cc6360266fd1fb716a401ddb0244f66e7957e2125347da514b98153a061
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:116bfafc53348ca05cab17424413b1375849e2553733eacad29d83866b3f7549
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b19e72d3224eb8fba7b2c5af3f09a190b30786cb1e2a04121722f89f0f284b5
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": 1.431005597114563,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.04928536224741252,
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": 13.058,
732
  "eval_steps_per_second": 3.267,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.441732116747387e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3822078704833984,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.07392804337111877,
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": 13.058,
732
  "eval_steps_per_second": 3.267,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04977821586988664,
737
+ "grad_norm": 4.2226433753967285,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.885,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.05027106949236077,
744
+ "grad_norm": 4.225105285644531,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 6.0265,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.050763923114834894,
751
+ "grad_norm": 3.3986520767211914,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 5.7708,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.051256776737309016,
758
+ "grad_norm": 3.3197200298309326,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 5.5425,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.051749630359783146,
765
+ "grad_norm": 3.359449863433838,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.6861,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.05224248398225727,
772
+ "grad_norm": 3.6861770153045654,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 5.8957,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0527353376047314,
779
+ "grad_norm": 3.3729681968688965,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 5.6209,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.05322819122720552,
786
+ "grad_norm": 3.5027880668640137,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 5.3333,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.05372104484967965,
793
+ "grad_norm": 3.4611856937408447,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 5.7229,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.05421389847215377,
800
+ "grad_norm": 3.641321897506714,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 6.0581,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.05470675209462789,
807
+ "grad_norm": 3.8468551635742188,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 5.5633,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.05519960571710202,
814
+ "grad_norm": 3.6477551460266113,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 5.3808,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.055692459339576145,
821
+ "grad_norm": 3.6040382385253906,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.1802,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.056185312962050274,
828
+ "grad_norm": 3.5388293266296387,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 5.441,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.056678166584524396,
835
+ "grad_norm": 3.9764630794525146,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 5.9069,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.05717102020699852,
842
+ "grad_norm": 3.8530142307281494,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 5.4141,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.05766387382947265,
849
+ "grad_norm": 3.6980135440826416,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.2554,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.05815672745194677,
856
+ "grad_norm": 3.621671676635742,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 5.2911,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.0586495810744209,
863
+ "grad_norm": 3.8117148876190186,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 5.4398,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.05914243469689502,
870
+ "grad_norm": 3.9566729068756104,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 5.6742,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.05963528831936915,
877
+ "grad_norm": 3.656689405441284,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 5.3545,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.06012814194184327,
884
+ "grad_norm": 3.7543258666992188,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 5.2922,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.060620995564317395,
891
+ "grad_norm": 3.839445114135742,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.4221,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.061113849186791525,
898
+ "grad_norm": 4.027908802032471,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 5.3428,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.06160670280926565,
905
+ "grad_norm": 3.913569927215576,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 5.5121,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.062099556431739776,
912
+ "grad_norm": 3.884404420852661,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 5.4622,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0625924100542139,
919
+ "grad_norm": 4.357018947601318,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 5.842,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.06308526367668803,
926
+ "grad_norm": 4.205898761749268,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 5.4984,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.06357811729916214,
933
+ "grad_norm": 3.913008213043213,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 5.5454,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.06407097092163627,
940
+ "grad_norm": 4.038344383239746,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.681,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0645638245441104,
947
+ "grad_norm": 3.8500421047210693,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 5.316,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.06505667816658453,
954
+ "grad_norm": 4.233459949493408,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 5.6574,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.06554953178905865,
961
+ "grad_norm": 4.028703689575195,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 5.219,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.06604238541153278,
968
+ "grad_norm": 4.3093109130859375,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 5.5462,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0665352390340069,
975
+ "grad_norm": 4.2733378410339355,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 5.4858,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.06702809265648102,
982
+ "grad_norm": 4.1830878257751465,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 5.1703,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.06752094627895515,
989
+ "grad_norm": 4.2492170333862305,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 5.4769,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.06801379990142928,
996
+ "grad_norm": 4.3830060958862305,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 5.5719,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.06850665352390341,
1003
+ "grad_norm": 4.348109722137451,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 5.3788,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.06899950714637752,
1010
+ "grad_norm": 4.3019232749938965,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 5.5993,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.06949236076885165,
1017
+ "grad_norm": 4.5521559715271,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 5.8097,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.06998521439132578,
1024
+ "grad_norm": 4.503178119659424,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 5.5559,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.0704780680137999,
1031
+ "grad_norm": 4.683341979980469,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 5.5462,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.07097092163627403,
1038
+ "grad_norm": 4.591628074645996,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 5.4505,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.07146377525874816,
1045
+ "grad_norm": 4.827720642089844,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 5.8953,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.07195662888122227,
1052
+ "grad_norm": 4.654827117919922,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 5.7021,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.0724494825036964,
1059
+ "grad_norm": 5.047876358032227,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 5.9535,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.07294233612617053,
1066
+ "grad_norm": 5.1422014236450195,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 5.7735,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.07343518974864466,
1073
+ "grad_norm": 5.423142433166504,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 5.9309,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.07392804337111877,
1080
+ "grad_norm": 5.620732307434082,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 5.6295,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.07392804337111877,
1087
+ "eval_loss": 1.3822078704833984,
1088
+ "eval_runtime": 261.5296,
1089
+ "eval_samples_per_second": 13.065,
1090
+ "eval_steps_per_second": 3.269,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.16080942559658e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null