prxy5608 commited on
Commit
bef0616
·
verified ·
1 Parent(s): 9bf8ab5

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 sha256:907ab6a0ae89db772ae066fb2052a5616b7b71563fa71453ebf2c8e2f0fcd5b2
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2431c21492adadf8d386f6d157cb6ddd19a4deff9958c3e71856170845abbed
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74815f4c6901145dc008341c2caf282cceddf39d2dc5ef73927e806423c85a5e
3
  size 591203178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:844b967ee6b8024991820293e92eabb8ce9d75b32d0036cda6e2ba82ae487514
3
  size 591203178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cf2b2d7ca16a98ed374235967d4dea68bc581943625ddd333bc11a0a503cc75
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df98dcc31574f5bb83e66e0bca03b277b55813524adea9b669dde0b1561d3713
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": 0.6289290189743042,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.09854644000985464,
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": 25.733,
732
  "eval_steps_per_second": 12.874,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.09564631154688e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6193792223930359,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.14781966001478197,
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": 25.733,
732
  "eval_steps_per_second": 12.874,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.09953190440995319,
737
+ "grad_norm": 0.06508608162403107,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 0.0293,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.10051736881005174,
744
+ "grad_norm": 0.10537426918745041,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 0.1911,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10150283321015029,
751
+ "grad_norm": 0.10470440238714218,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 0.2062,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.10248829761024883,
758
+ "grad_norm": 0.1329120248556137,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 0.2705,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.10347376201034737,
765
+ "grad_norm": 0.1280706822872162,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 0.2274,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.10445922641044593,
772
+ "grad_norm": 0.16757312417030334,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 0.4932,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.10544469081054447,
779
+ "grad_norm": 0.1751958429813385,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 0.5401,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.10643015521064302,
786
+ "grad_norm": 0.1717756688594818,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 0.6055,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.10741561961074156,
793
+ "grad_norm": 0.19734135270118713,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 0.5538,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.10840108401084012,
800
+ "grad_norm": 0.18675287067890167,
801
+ "learning_rate": 5e-05,
802
+ "loss": 0.5751,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.10938654841093866,
807
+ "grad_norm": 0.19595959782600403,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 0.5783,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.1103720128110372,
814
+ "grad_norm": 0.20387478172779083,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 0.6778,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.11135747721113574,
821
+ "grad_norm": 0.19632427394390106,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 0.7262,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.1123429416112343,
828
+ "grad_norm": 0.22888943552970886,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 0.6576,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11332840601133284,
835
+ "grad_norm": 0.21430076658725739,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 0.6493,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.11431387041143139,
842
+ "grad_norm": 0.20526853203773499,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 0.66,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.11529933481152993,
849
+ "grad_norm": 0.2236650139093399,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 0.6334,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.11628479921162849,
856
+ "grad_norm": 0.22159314155578613,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 0.7894,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.11727026361172703,
863
+ "grad_norm": 0.22929464280605316,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 0.6049,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.11825572801182557,
870
+ "grad_norm": 0.2338849902153015,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 0.685,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.11924119241192412,
877
+ "grad_norm": 0.2361065298318863,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 0.7811,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.12022665681202267,
884
+ "grad_norm": 0.23754455149173737,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 0.7872,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.12121212121212122,
891
+ "grad_norm": 0.2533068358898163,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 0.7897,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12219758561221976,
898
+ "grad_norm": 0.25761741399765015,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 0.7821,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1231830500123183,
905
+ "grad_norm": 0.262465238571167,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 0.8736,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.12416851441241686,
912
+ "grad_norm": 0.28506287932395935,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 0.7855,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1251539788125154,
919
+ "grad_norm": 0.2701311707496643,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 0.6851,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.12613944321261394,
926
+ "grad_norm": 0.2602234184741974,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 0.6349,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.1271249076127125,
933
+ "grad_norm": 0.26517555117607117,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 0.6741,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.12811037201281103,
940
+ "grad_norm": 0.2652198076248169,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 0.569,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1290958364129096,
947
+ "grad_norm": 0.27912837266921997,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 0.7768,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.13008130081300814,
954
+ "grad_norm": 0.28829455375671387,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 0.6819,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.13106676521310667,
961
+ "grad_norm": 0.2873208522796631,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 0.8448,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.13205222961320523,
968
+ "grad_norm": 0.3321005702018738,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 0.8613,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.13303769401330376,
975
+ "grad_norm": 0.3113601505756378,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 0.757,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.13402315841340232,
982
+ "grad_norm": 0.3224503993988037,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 0.8078,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.13500862281350087,
989
+ "grad_norm": 0.3039480745792389,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 0.5903,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1359940872135994,
996
+ "grad_norm": 0.3399895429611206,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 0.681,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.13697955161369796,
1003
+ "grad_norm": 0.32148513197898865,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 0.6537,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.13796501601379652,
1010
+ "grad_norm": 0.3466744124889374,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 0.7301,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.13895048041389504,
1017
+ "grad_norm": 0.35640135407447815,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 0.7172,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.1399359448139936,
1024
+ "grad_norm": 0.38685786724090576,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 0.7447,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.14092140921409213,
1031
+ "grad_norm": 0.3715401291847229,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 0.6587,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.1419068736141907,
1038
+ "grad_norm": 0.41979506611824036,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 0.7954,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.14289233801428924,
1045
+ "grad_norm": 0.4046609103679657,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 0.7503,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.14387780241438777,
1052
+ "grad_norm": 0.4440525472164154,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 0.8386,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.14486326681448633,
1059
+ "grad_norm": 0.4576321542263031,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 0.6455,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.1458487312145849,
1066
+ "grad_norm": 0.5070066452026367,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 0.8399,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.14683419561468342,
1073
+ "grad_norm": 0.5966192483901978,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 0.7003,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.14781966001478197,
1080
+ "grad_norm": 0.7911564707756042,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 0.6801,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.14781966001478197,
1087
+ "eval_loss": 0.6193792223930359,
1088
+ "eval_runtime": 66.3669,
1089
+ "eval_samples_per_second": 25.751,
1090
+ "eval_steps_per_second": 12.883,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.640067658186752e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null