0x1202 commited on
Commit
a95008a
·
verified ·
1 Parent(s): f901f32

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 sha256:16750270ab277b7fbbabd2ed89e5344be12d515bf5755b847b2312bc7aea4dfe
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3a48592e84c14c9f630491be23fbcf1dd0d1b7c57d769d94bd2c3975399f8a
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23ba1164b2c165e98b12b2242d6b5ac63ba1e09e7d04be784b1b61ab787a8e21
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7839c723a6614ddbe2c53e20de084af2be038ea14fec252680613e4e460e67d0
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:815777f3787810f86a0bec03cade7f173d0f17fbe8b138ebca07a24d94d69729
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83dd42ab4ea6ce1bb110dbde8e9779377055ccd25f057e57f265c823370d753a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6710785031318665,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.039615727443795185,
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": 12.386,
732
  "eval_steps_per_second": 6.193,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.430998008987648e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.63045334815979,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.05942359116569278,
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": 12.386,
732
  "eval_steps_per_second": 6.193,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04001188471823314,
737
+ "grad_norm": 6.430683135986328,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 2.5807,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.04040804199267109,
744
+ "grad_norm": 6.545248508453369,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 2.5388,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.04080419926710904,
751
+ "grad_norm": 6.790993690490723,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 2.5627,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.041200356541546995,
758
+ "grad_norm": 5.768946170806885,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 2.2582,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.04159651381598495,
765
+ "grad_norm": 7.711808681488037,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 2.291,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0419926710904229,
772
+ "grad_norm": 6.631197452545166,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 2.7122,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.042388828364860846,
779
+ "grad_norm": 6.862368583679199,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 2.6714,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0427849856392988,
786
+ "grad_norm": 6.4192214012146,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 2.5312,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.04318114291373675,
793
+ "grad_norm": 6.572208404541016,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 2.5457,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.043577300188174704,
800
+ "grad_norm": 7.45621919631958,
801
+ "learning_rate": 5e-05,
802
+ "loss": 2.5436,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.04397345746261266,
807
+ "grad_norm": 6.586299419403076,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 2.5885,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.04436961473705061,
814
+ "grad_norm": 7.276597499847412,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 2.1434,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.04476577201148856,
821
+ "grad_norm": 7.623659133911133,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 2.8945,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.045161929285926515,
828
+ "grad_norm": 7.042168617248535,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 2.3028,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.04555808656036447,
835
+ "grad_norm": 7.464590549468994,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 2.3807,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.045954243834802413,
842
+ "grad_norm": 6.643574237823486,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.9407,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.046350401109240366,
849
+ "grad_norm": 6.645323276519775,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 2.3134,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.04674655838367832,
856
+ "grad_norm": 6.613039970397949,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.9895,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.04714271565811627,
863
+ "grad_norm": 7.568057060241699,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 2.5604,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.047538872932554224,
870
+ "grad_norm": 9.300191879272461,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 2.8018,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.04793503020699218,
877
+ "grad_norm": 7.3803791999816895,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 2.5437,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.04833118748143013,
884
+ "grad_norm": 7.900534152984619,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 2.9423,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.04872734475586808,
891
+ "grad_norm": 8.615334510803223,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 2.8762,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.049123502030306035,
898
+ "grad_norm": 8.52196216583252,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 2.9788,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.04951965930474398,
905
+ "grad_norm": 7.072556495666504,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 2.1147,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.04991581657918193,
912
+ "grad_norm": 8.038581848144531,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 2.6251,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.050311973853619886,
919
+ "grad_norm": 8.452302932739258,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 2.7774,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.05070813112805784,
926
+ "grad_norm": 7.472427845001221,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 2.3101,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.05110428840249579,
933
+ "grad_norm": 7.390994548797607,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 2.2508,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.051500445676933744,
940
+ "grad_norm": 6.412713527679443,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 2.2383,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0518966029513717,
947
+ "grad_norm": 9.124238014221191,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 2.7566,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.05229276022580965,
954
+ "grad_norm": 8.466002464294434,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 2.6618,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.052688917500247595,
961
+ "grad_norm": 7.873275279998779,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 2.2592,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.05308507477468555,
968
+ "grad_norm": 7.096005439758301,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 2.0873,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0534812320491235,
975
+ "grad_norm": 10.305582046508789,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 3.0193,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.05387738932356145,
982
+ "grad_norm": 10.208508491516113,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 2.7085,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.054273546597999406,
989
+ "grad_norm": 12.142950057983398,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 2.64,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.05466970387243736,
996
+ "grad_norm": 10.012589454650879,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 2.8601,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.05506586114687531,
1003
+ "grad_norm": 10.026057243347168,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 2.3891,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.055462018421313264,
1010
+ "grad_norm": 9.359071731567383,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 2.8986,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.05585817569575122,
1017
+ "grad_norm": 9.041458129882812,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 2.4639,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.05625433297018916,
1024
+ "grad_norm": 9.14760684967041,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 2.4462,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.056650490244627115,
1031
+ "grad_norm": 9.521930694580078,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 2.3937,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.05704664751906507,
1038
+ "grad_norm": 8.896791458129883,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 2.4117,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.05744280479350302,
1045
+ "grad_norm": 12.4694242477417,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 2.8917,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.05783896206794097,
1052
+ "grad_norm": 9.43685245513916,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 2.1703,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.058235119342378926,
1059
+ "grad_norm": 11.866545677185059,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 2.7334,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.05863127661681688,
1066
+ "grad_norm": 9.459863662719727,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 2.2491,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.05902743389125483,
1073
+ "grad_norm": 13.348437309265137,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 3.0507,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.05942359116569278,
1080
+ "grad_norm": 14.311579704284668,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 3.0234,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.05942359116569278,
1087
+ "eval_loss": 0.63045334815979,
1088
+ "eval_runtime": 343.3222,
1089
+ "eval_samples_per_second": 12.385,
1090
+ "eval_steps_per_second": 6.192,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.146497013481472e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null