prxy5606 commited on
Commit
4f6cae8
·
verified ·
1 Parent(s): a32eb76

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 sha256:21412951cd72e6fd19b3444890979058085dbd36e25bc541914ee500e18256b2
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:669b061b4292b159041df91cf8056bbc9616172471643799714709e40fca80aa
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b75179ebc04cea309056b57e383f0872b70aa175f89efeb6eec80734c30e015
3
  size 278249554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:388b3e917c317ae4bc12fee16e067c82b71e4b4a1d8bc70bfa0f7141d4f7dcb2
3
  size 278249554
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89c0ed57d004d68592d1591b7e8adc3d02bdce29c643e16159cede5771dba770
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70552ba1212ec41a64ccad8b6018d9b4364290ace6154b5f0e2ea5b9e63a18b3
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": 0.9143250584602356,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.17196904557179707,
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": 37.506,
732
  "eval_steps_per_second": 18.753,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7109290324131840.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9018179774284363,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.2579535683576956,
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": 37.506,
732
  "eval_steps_per_second": 18.753,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.17368873602751506,
737
+ "grad_norm": 0.0647941306233406,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 0.5759,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.17540842648323302,
744
+ "grad_norm": 0.07381158322095871,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 0.5957,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.177128116938951,
751
+ "grad_norm": 0.07971695810556412,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 0.6366,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.17884780739466896,
758
+ "grad_norm": 0.073166623711586,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 0.5878,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.18056749785038692,
765
+ "grad_norm": 0.08162125200033188,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 0.6366,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1822871883061049,
772
+ "grad_norm": 0.0808592289686203,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 0.6407,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.18400687876182287,
779
+ "grad_norm": 0.09443782269954681,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 0.6592,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.18572656921754085,
786
+ "grad_norm": 0.08486565947532654,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 0.6987,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.1874462596732588,
793
+ "grad_norm": 0.08635884523391724,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 0.6941,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.18916595012897677,
800
+ "grad_norm": 0.0893407091498375,
801
+ "learning_rate": 5e-05,
802
+ "loss": 0.7226,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.19088564058469476,
807
+ "grad_norm": 0.09018551558256149,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 0.7208,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.19260533104041272,
814
+ "grad_norm": 0.07536663860082626,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 0.5846,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.1943250214961307,
821
+ "grad_norm": 0.08711609989404678,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 0.6862,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.19604471195184867,
828
+ "grad_norm": 0.06564276665449142,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 0.6931,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.19776440240756663,
835
+ "grad_norm": 0.08047173917293549,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 0.7913,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.1994840928632846,
842
+ "grad_norm": 0.08029168099164963,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 0.6937,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.20120378331900257,
849
+ "grad_norm": 0.07913923263549805,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 0.7687,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.20292347377472056,
856
+ "grad_norm": 0.0775957927107811,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 0.7796,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.20464316423043852,
863
+ "grad_norm": 0.07749712467193604,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 0.7374,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.2063628546861565,
870
+ "grad_norm": 0.07898925989866257,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 0.7796,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.20808254514187446,
877
+ "grad_norm": 0.07860884070396423,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 0.7887,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.20980223559759242,
884
+ "grad_norm": 0.077889084815979,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 0.8293,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.2115219260533104,
891
+ "grad_norm": 0.07636513561010361,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 0.7912,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.21324161650902837,
898
+ "grad_norm": 0.07946857064962387,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 0.8765,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.21496130696474636,
905
+ "grad_norm": 0.07615929841995239,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 0.6885,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.21668099742046432,
912
+ "grad_norm": 0.07800007611513138,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 0.7583,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.21840068787618228,
919
+ "grad_norm": 0.0879930779337883,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 0.7962,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.22012037833190026,
926
+ "grad_norm": 0.08408991992473602,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 0.7565,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.22184006878761822,
933
+ "grad_norm": 0.08975850045681,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 0.8412,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.2235597592433362,
940
+ "grad_norm": 0.08965165913105011,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 0.8464,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.22527944969905417,
947
+ "grad_norm": 0.09056264162063599,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 0.663,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.22699914015477213,
954
+ "grad_norm": 0.0920715406537056,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 0.8896,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.22871883061049011,
961
+ "grad_norm": 0.10946381837129593,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 0.7847,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.23043852106620807,
968
+ "grad_norm": 0.10407907515764236,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 0.8615,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.23215821152192606,
975
+ "grad_norm": 0.09890785813331604,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 0.8844,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.23387790197764402,
982
+ "grad_norm": 0.12885335087776184,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 0.7755,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.235597592433362,
989
+ "grad_norm": 0.10378793627023697,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 0.7874,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.23731728288907997,
996
+ "grad_norm": 0.12850679457187653,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 0.7773,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.23903697334479793,
1003
+ "grad_norm": 0.1387593150138855,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 0.8046,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.2407566638005159,
1010
+ "grad_norm": 0.14513392746448517,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 0.9875,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.24247635425623387,
1017
+ "grad_norm": 0.14788322150707245,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 0.9912,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.24419604471195186,
1024
+ "grad_norm": 0.16071070730686188,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 1.2427,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.24591573516766982,
1031
+ "grad_norm": 0.18315501511096954,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 1.3647,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.24763542562338778,
1038
+ "grad_norm": 0.2040652483701706,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 1.3373,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.24935511607910577,
1045
+ "grad_norm": 0.20529639720916748,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 1.421,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2510748065348237,
1052
+ "grad_norm": 0.18773475289344788,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 1.3484,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2527944969905417,
1059
+ "grad_norm": 0.20955699682235718,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 1.3517,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.2545141874462597,
1066
+ "grad_norm": 0.22871288657188416,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 1.4738,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.25623387790197766,
1073
+ "grad_norm": 0.27887439727783203,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 1.8532,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.2579535683576956,
1080
+ "grad_norm": 0.40441471338272095,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 2.2748,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.2579535683576956,
1087
+ "eval_loss": 0.9018179774284363,
1088
+ "eval_runtime": 26.0633,
1089
+ "eval_samples_per_second": 37.601,
1090
+ "eval_steps_per_second": 18.8,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.066393548619776e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null