prxy5607 commited on
Commit
1ccfd1d
·
verified ·
1 Parent(s): c26c61d

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 sha256:7ee55ad480f77a67814781944b1a11bf536d04b4709124a901f4de899624e047
3
  size 180385008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c4d24402912c5517e0f320d186f2ed920f2b8487b128af74d7b899bc82fde8
3
  size 180385008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb08e8eab98d3e78403e50d37e44525ccc4d9209f574b7837686f5cd32485f0d
3
  size 360898938
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58d343013bda9137e5b33ba659ea297a71d9986061071cf767ed4b68c0418a2
3
  size 360898938
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da48cdd24dabbf53a49f70be96c0d5e8e4686bb3546e2b190e65114a035cb3e9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60174f7bcff01864903a2beabc425b08449885747620f68639c8f7b08199eec3
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": 2.111635208129883,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.186219739292365,
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": 41.663,
732
  "eval_steps_per_second": 20.854,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.016945717116928e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7213300466537476,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.27932960893854747,
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": 41.663,
732
  "eval_steps_per_second": 20.854,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.18808193668528864,
737
+ "grad_norm": 2.3293561935424805,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 2.4448,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.18994413407821228,
744
+ "grad_norm": 2.2285311222076416,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 2.4747,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.19180633147113593,
751
+ "grad_norm": 2.032970666885376,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 2.5569,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.19366852886405958,
758
+ "grad_norm": 1.9000310897827148,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 2.2785,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.19553072625698323,
765
+ "grad_norm": 2.129242181777954,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 1.8737,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1973929236499069,
772
+ "grad_norm": 1.6860032081604004,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 1.8208,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.19925512104283055,
779
+ "grad_norm": 1.7974435091018677,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 1.6613,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.2011173184357542,
786
+ "grad_norm": 1.80308198928833,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 1.9122,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.20297951582867785,
793
+ "grad_norm": 1.9534099102020264,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.6929,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.2048417132216015,
800
+ "grad_norm": 1.9603544473648071,
801
+ "learning_rate": 5e-05,
802
+ "loss": 1.7386,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.20670391061452514,
807
+ "grad_norm": 1.875958800315857,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.675,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.2085661080074488,
814
+ "grad_norm": 2.435465097427368,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 1.6366,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.21042830540037244,
821
+ "grad_norm": 2.0310440063476562,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 1.5549,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.2122905027932961,
828
+ "grad_norm": 2.066591501235962,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 1.6041,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.21415270018621974,
835
+ "grad_norm": 2.1647772789001465,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.571,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.21601489757914338,
842
+ "grad_norm": 2.1143767833709717,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.3452,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.21787709497206703,
849
+ "grad_norm": 2.4085280895233154,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 1.5415,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.21973929236499068,
856
+ "grad_norm": 2.171875238418579,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.2254,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.22160148975791433,
863
+ "grad_norm": 2.8386919498443604,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 1.4564,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.22346368715083798,
870
+ "grad_norm": 2.413219928741455,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 1.2426,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.22532588454376165,
877
+ "grad_norm": 2.3246631622314453,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 1.1519,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.2271880819366853,
884
+ "grad_norm": 3.1036009788513184,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.3616,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.22905027932960895,
891
+ "grad_norm": 2.8557889461517334,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.2942,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.2309124767225326,
898
+ "grad_norm": 2.639146089553833,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 1.341,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.23277467411545624,
905
+ "grad_norm": 2.424593210220337,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 1.5446,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.2346368715083799,
912
+ "grad_norm": 2.4945600032806396,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 1.2111,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.23649906890130354,
919
+ "grad_norm": 3.035121440887451,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 1.2049,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.2383612662942272,
926
+ "grad_norm": 3.434382438659668,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 1.301,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.24022346368715083,
933
+ "grad_norm": 2.730940341949463,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.2729,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.24208566108007448,
940
+ "grad_norm": 3.3356800079345703,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 1.3789,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.24394785847299813,
947
+ "grad_norm": 3.292501926422119,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 1.4141,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.24581005586592178,
954
+ "grad_norm": 3.2377631664276123,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 1.2394,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.24767225325884543,
961
+ "grad_norm": 3.1759567260742188,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 1.2913,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.24953445065176907,
968
+ "grad_norm": 2.8026719093322754,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 1.2144,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.25139664804469275,
975
+ "grad_norm": 2.286036968231201,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.3749,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.2532588454376164,
982
+ "grad_norm": 1.9794367551803589,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.7901,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.25512104283054005,
989
+ "grad_norm": 2.388559103012085,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 2.1486,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.2569832402234637,
996
+ "grad_norm": 2.6771240234375,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 1.4815,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.25884543761638734,
1003
+ "grad_norm": 2.727090358734131,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 2.4409,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.260707635009311,
1010
+ "grad_norm": 3.0475521087646484,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 3.0248,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.26256983240223464,
1017
+ "grad_norm": 2.9400222301483154,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 2.5705,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.2644320297951583,
1024
+ "grad_norm": 3.1902108192443848,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 2.8102,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.26629422718808193,
1031
+ "grad_norm": 3.4387946128845215,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 2.7094,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.2681564245810056,
1038
+ "grad_norm": 3.343712329864502,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 2.5977,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.27001862197392923,
1045
+ "grad_norm": 3.5541982650756836,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 2.6829,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2718808193668529,
1052
+ "grad_norm": 3.7226669788360596,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 2.748,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2737430167597765,
1059
+ "grad_norm": 3.643068790435791,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 2.8173,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.2756052141527002,
1066
+ "grad_norm": 4.142628192901611,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 2.7241,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.2774674115456238,
1073
+ "grad_norm": 4.557801246643066,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 2.8083,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.27932960893854747,
1080
+ "grad_norm": 5.352628707885742,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 3.1628,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.27932960893854747,
1087
+ "eval_loss": 1.7213300466537476,
1088
+ "eval_runtime": 21.823,
1089
+ "eval_samples_per_second": 41.47,
1090
+ "eval_steps_per_second": 20.758,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.022916161634304e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null