lesso commited on
Commit
6121355
·
verified ·
1 Parent(s): 03deaea

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 sha256:56ca02ae00f469427d65e61ded0c1dcddd0a34ec7e661a5393d7ab445167639d
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5291ec521c4ffa0f6091cddc747315cbf4c9a929679ec85bd1e336e78285313
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27703d2bee1509d91f2490636887178cfa7509e768f1de0bff2007498ed069ed
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97abbfb5bdbe157285163dc12c6ab1fb09f57b6499d8424fee0d83db4b7d10fb
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fa4063d4290f16beac79f3aa566bb00b018b35be5590c10175754ea800098b6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb3272b647dedb061d06dda8a662cd98ad3318b7d10b09d9a8cd15bb2de3fbb6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6b2f615f21faa4fde4442b48613d92f84c55cd5ef4fb4d04d8e3f819305ce14
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d606eeb1aa97b417de3c30d0a970be83ac979e2c7cc0fa41135c63d459909e5
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.440127968788147,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.007669299792928906,
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": 8.926,
732
  "eval_steps_per_second": 2.232,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.720599010960998e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.42113959789276123,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.011503949689393358,
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": 8.926,
732
  "eval_steps_per_second": 2.232,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.007745992790858195,
737
+ "grad_norm": 1.8733649253845215,
738
+ "learning_rate": 5.262631578947368e-05,
739
+ "loss": 0.6206,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.007822685788787484,
744
+ "grad_norm": 2.0493202209472656,
745
+ "learning_rate": 5.209473684210527e-05,
746
+ "loss": 0.7471,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.007899378786716772,
751
+ "grad_norm": 2.0362370014190674,
752
+ "learning_rate": 5.1563157894736844e-05,
753
+ "loss": 0.7268,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.007976071784646061,
758
+ "grad_norm": 1.9288749694824219,
759
+ "learning_rate": 5.1031578947368426e-05,
760
+ "loss": 0.7642,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.00805276478257535,
765
+ "grad_norm": 2.0815563201904297,
766
+ "learning_rate": 5.05e-05,
767
+ "loss": 0.8756,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.00812945778050464,
772
+ "grad_norm": 1.9933137893676758,
773
+ "learning_rate": 4.9968421052631576e-05,
774
+ "loss": 0.8304,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.008206150778433929,
779
+ "grad_norm": 2.1648061275482178,
780
+ "learning_rate": 4.943684210526316e-05,
781
+ "loss": 0.9223,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.008282843776363218,
786
+ "grad_norm": 2.3177595138549805,
787
+ "learning_rate": 4.890526315789474e-05,
788
+ "loss": 0.948,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.008359536774292508,
793
+ "grad_norm": 2.23612380027771,
794
+ "learning_rate": 4.8373684210526316e-05,
795
+ "loss": 0.9409,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.008436229772221797,
800
+ "grad_norm": 2.223040819168091,
801
+ "learning_rate": 4.784210526315789e-05,
802
+ "loss": 0.87,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.008512922770151084,
807
+ "grad_norm": 2.4170846939086914,
808
+ "learning_rate": 4.731052631578947e-05,
809
+ "loss": 1.1148,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.008589615768080374,
814
+ "grad_norm": 2.3110735416412354,
815
+ "learning_rate": 4.6778947368421055e-05,
816
+ "loss": 0.8786,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.008666308766009663,
821
+ "grad_norm": 2.4310617446899414,
822
+ "learning_rate": 4.624736842105263e-05,
823
+ "loss": 1.0341,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.008743001763938952,
828
+ "grad_norm": 2.200124979019165,
829
+ "learning_rate": 4.571578947368421e-05,
830
+ "loss": 0.7784,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.008819694761868242,
835
+ "grad_norm": 2.390054225921631,
836
+ "learning_rate": 4.518421052631579e-05,
837
+ "loss": 1.023,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.00889638775979753,
842
+ "grad_norm": 2.4751944541931152,
843
+ "learning_rate": 4.465263157894737e-05,
844
+ "loss": 0.9556,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.00897308075772682,
849
+ "grad_norm": 2.436793565750122,
850
+ "learning_rate": 4.412105263157895e-05,
851
+ "loss": 0.925,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.00904977375565611,
856
+ "grad_norm": 2.3760292530059814,
857
+ "learning_rate": 4.358947368421053e-05,
858
+ "loss": 0.9526,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.009126466753585397,
863
+ "grad_norm": 2.374337673187256,
864
+ "learning_rate": 4.30578947368421e-05,
865
+ "loss": 0.9207,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.009203159751514686,
870
+ "grad_norm": 2.51969575881958,
871
+ "learning_rate": 4.2526315789473685e-05,
872
+ "loss": 1.02,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.009279852749443976,
877
+ "grad_norm": 2.4088480472564697,
878
+ "learning_rate": 4.199473684210527e-05,
879
+ "loss": 0.8181,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.009356545747373265,
884
+ "grad_norm": 2.4922304153442383,
885
+ "learning_rate": 4.146315789473684e-05,
886
+ "loss": 0.9914,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.009433238745302554,
891
+ "grad_norm": 2.3393707275390625,
892
+ "learning_rate": 4.093157894736842e-05,
893
+ "loss": 0.7759,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.009509931743231843,
898
+ "grad_norm": 2.5839779376983643,
899
+ "learning_rate": 4.0400000000000006e-05,
900
+ "loss": 1.0214,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.009586624741161133,
905
+ "grad_norm": 2.4506092071533203,
906
+ "learning_rate": 3.986842105263158e-05,
907
+ "loss": 0.855,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.00966331773909042,
912
+ "grad_norm": 2.4262022972106934,
913
+ "learning_rate": 3.933684210526316e-05,
914
+ "loss": 0.8241,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.00974001073701971,
919
+ "grad_norm": 2.5004682540893555,
920
+ "learning_rate": 3.880526315789473e-05,
921
+ "loss": 0.9218,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.009816703734948999,
926
+ "grad_norm": 2.6074700355529785,
927
+ "learning_rate": 3.827368421052632e-05,
928
+ "loss": 0.9807,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.009893396732878288,
933
+ "grad_norm": 2.718700885772705,
934
+ "learning_rate": 3.7742105263157896e-05,
935
+ "loss": 0.9063,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.009970089730807577,
940
+ "grad_norm": 2.606994152069092,
941
+ "learning_rate": 3.721052631578947e-05,
942
+ "loss": 0.9736,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.010046782728736867,
947
+ "grad_norm": 2.6007425785064697,
948
+ "learning_rate": 3.6678947368421054e-05,
949
+ "loss": 0.7695,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.010123475726666156,
954
+ "grad_norm": 2.5476109981536865,
955
+ "learning_rate": 3.6147368421052636e-05,
956
+ "loss": 0.9192,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.010200168724595445,
961
+ "grad_norm": 2.781832695007324,
962
+ "learning_rate": 3.561578947368421e-05,
963
+ "loss": 0.8568,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.010276861722524733,
968
+ "grad_norm": 2.917055130004883,
969
+ "learning_rate": 3.508421052631579e-05,
970
+ "loss": 0.8224,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.010353554720454022,
975
+ "grad_norm": 2.823812246322632,
976
+ "learning_rate": 3.455263157894737e-05,
977
+ "loss": 0.8036,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.010430247718383311,
982
+ "grad_norm": 2.640902042388916,
983
+ "learning_rate": 3.402105263157895e-05,
984
+ "loss": 0.6993,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.0105069407163126,
989
+ "grad_norm": 2.8832485675811768,
990
+ "learning_rate": 3.3489473684210526e-05,
991
+ "loss": 0.9251,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.01058363371424189,
996
+ "grad_norm": 3.0635344982147217,
997
+ "learning_rate": 3.295789473684211e-05,
998
+ "loss": 0.748,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.01066032671217118,
1003
+ "grad_norm": 2.7239019870758057,
1004
+ "learning_rate": 3.242631578947368e-05,
1005
+ "loss": 0.618,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.010737019710100468,
1010
+ "grad_norm": 2.9448680877685547,
1011
+ "learning_rate": 3.1894736842105265e-05,
1012
+ "loss": 0.7113,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.010813712708029758,
1017
+ "grad_norm": 3.097717523574829,
1018
+ "learning_rate": 3.136315789473685e-05,
1019
+ "loss": 0.6319,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.010890405705959045,
1024
+ "grad_norm": 3.3616809844970703,
1025
+ "learning_rate": 3.083157894736842e-05,
1026
+ "loss": 0.6926,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.010967098703888335,
1031
+ "grad_norm": 3.4757049083709717,
1032
+ "learning_rate": 3.0299999999999998e-05,
1033
+ "loss": 0.7907,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.011043791701817624,
1038
+ "grad_norm": 3.6388909816741943,
1039
+ "learning_rate": 2.9768421052631577e-05,
1040
+ "loss": 0.7275,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.011120484699746913,
1045
+ "grad_norm": 4.052596569061279,
1046
+ "learning_rate": 2.923684210526316e-05,
1047
+ "loss": 0.7223,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.011197177697676202,
1052
+ "grad_norm": 3.550902843475342,
1053
+ "learning_rate": 2.8705263157894737e-05,
1054
+ "loss": 0.6771,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.011273870695605492,
1059
+ "grad_norm": 5.376113414764404,
1060
+ "learning_rate": 2.8173684210526313e-05,
1061
+ "loss": 0.9857,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.011350563693534781,
1066
+ "grad_norm": 5.5364508628845215,
1067
+ "learning_rate": 2.7642105263157898e-05,
1068
+ "loss": 1.0402,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.011427256691464069,
1073
+ "grad_norm": 5.848127365112305,
1074
+ "learning_rate": 2.7110526315789473e-05,
1075
+ "loss": 0.7402,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.011503949689393358,
1080
+ "grad_norm": 7.648379325866699,
1081
+ "learning_rate": 2.6578947368421052e-05,
1082
+ "loss": 1.2402,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.011503949689393358,
1087
+ "eval_loss": 0.42113959789276123,
1088
+ "eval_runtime": 615.654,
1089
+ "eval_samples_per_second": 8.917,
1090
+ "eval_steps_per_second": 2.23,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.563011021196493e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null