nttx commited on
Commit
e3f60b4
·
verified ·
1 Parent(s): 1dafff7

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 sha256:152bcf5178bae902efbb92d279755625a7c2375f6096c0084797e4d95db26bf6
3
  size 100690184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148f4ce988b5c02bf74ebc6ca01df7925777fa84d9d2ec6ca8cded5815dc4524
3
  size 100690184
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0877500630210f046d48620d463b8e10a8c11e0f7b68d83aaaa1b372774157f
3
  size 51344890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf9800549a9ad3ee189d21af9b2685853dd24170419b46421dbda504a2d065d2
3
  size 51344890
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2949ee43f9defdb06eb5970686c17ad9c623c8ec8c95c9b6db83b104d37ece68
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc360580b03c9d50be6bb3b01bb9a15a0d21bf35aca127183b7db0a49e12bf42
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": 1.3221343755722046,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.17006802721088435,
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": 86.306,
732
  "eval_steps_per_second": 21.62,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7488474055704576.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2868432998657227,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.25510204081632654,
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": 86.306,
732
  "eval_steps_per_second": 21.62,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.1717687074829932,
737
+ "grad_norm": 32.49237823486328,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.034,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.17346938775510204,
744
+ "grad_norm": 26.757333755493164,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 5.1461,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.17517006802721088,
751
+ "grad_norm": 21.87533950805664,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 5.2722,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.17687074829931973,
758
+ "grad_norm": 22.367048263549805,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 5.4894,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.17857142857142858,
765
+ "grad_norm": 21.383411407470703,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.4114,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.18027210884353742,
772
+ "grad_norm": 22.514957427978516,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 5.4015,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.18197278911564627,
779
+ "grad_norm": 23.984758377075195,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 5.2921,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.1836734693877551,
786
+ "grad_norm": 21.759788513183594,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 5.4827,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.18537414965986396,
793
+ "grad_norm": 20.15304183959961,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 5.5669,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.1870748299319728,
800
+ "grad_norm": 20.60021209716797,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.299,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.18877551020408162,
807
+ "grad_norm": 24.306785583496094,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 5.4923,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.19047619047619047,
814
+ "grad_norm": 19.58234405517578,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 5.5558,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.1921768707482993,
821
+ "grad_norm": 19.0377140045166,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.3701,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.19387755102040816,
828
+ "grad_norm": 20.250268936157227,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 5.4652,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.195578231292517,
835
+ "grad_norm": 20.23456573486328,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 5.5539,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.19727891156462585,
842
+ "grad_norm": 27.842456817626953,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 5.6446,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.1989795918367347,
849
+ "grad_norm": 20.882328033447266,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.5002,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.20068027210884354,
856
+ "grad_norm": 18.743694305419922,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 5.6031,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.20238095238095238,
863
+ "grad_norm": 18.00966453552246,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 5.3068,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.20408163265306123,
870
+ "grad_norm": 16.10498046875,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 5.3238,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.20578231292517007,
877
+ "grad_norm": 18.90121841430664,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 5.4182,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.20748299319727892,
884
+ "grad_norm": 16.165494918823242,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 5.3903,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.20918367346938777,
891
+ "grad_norm": 18.660297393798828,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.4441,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.2108843537414966,
898
+ "grad_norm": 16.453760147094727,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 5.5855,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.21258503401360543,
905
+ "grad_norm": 15.383659362792969,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 5.3182,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.21428571428571427,
912
+ "grad_norm": 18.764667510986328,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 5.3291,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.21598639455782312,
919
+ "grad_norm": 16.44414710998535,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 5.3767,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.21768707482993196,
926
+ "grad_norm": 14.29847240447998,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 5.415,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.2193877551020408,
933
+ "grad_norm": 15.01552963256836,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 5.1709,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.22108843537414966,
940
+ "grad_norm": 16.77971649169922,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.2718,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.2227891156462585,
947
+ "grad_norm": 16.29701805114746,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 5.1363,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.22448979591836735,
954
+ "grad_norm": 16.925735473632812,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 5.1654,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.2261904761904762,
961
+ "grad_norm": 15.25202465057373,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 5.308,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.22789115646258504,
968
+ "grad_norm": 33.06045913696289,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 5.4922,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.22959183673469388,
975
+ "grad_norm": 18.302505493164062,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 5.333,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.23129251700680273,
982
+ "grad_norm": 16.267621994018555,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 5.3612,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.23299319727891157,
989
+ "grad_norm": 16.986467361450195,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 5.0567,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.23469387755102042,
996
+ "grad_norm": 15.164219856262207,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 4.6008,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.23639455782312926,
1003
+ "grad_norm": 21.55219841003418,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.8607,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.23809523809523808,
1010
+ "grad_norm": 20.613637924194336,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 5.1134,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.23979591836734693,
1017
+ "grad_norm": 37.14155578613281,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 4.7279,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.24149659863945577,
1024
+ "grad_norm": 15.671425819396973,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 5.0258,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.24319727891156462,
1031
+ "grad_norm": 20.68080711364746,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 4.6693,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.24489795918367346,
1038
+ "grad_norm": 26.475250244140625,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 4.8914,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.2465986394557823,
1045
+ "grad_norm": 21.820087432861328,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.8816,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.24829931972789115,
1052
+ "grad_norm": 20.836872100830078,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 4.8017,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.25,
1059
+ "grad_norm": 22.175506591796875,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 4.8856,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.25170068027210885,
1066
+ "grad_norm": 30.824220657348633,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 4.717,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.2534013605442177,
1073
+ "grad_norm": 30.54734230041504,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 4.4062,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.25510204081632654,
1080
+ "grad_norm": 27.12770652770996,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 4.5298,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.25510204081632654,
1087
+ "eval_loss": 1.2868432998657227,
1088
+ "eval_runtime": 11.5532,
1089
+ "eval_samples_per_second": 85.69,
1090
+ "eval_steps_per_second": 21.466,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.1232711083556864e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null