dimasik87 commited on
Commit
d5bdf0a
·
verified ·
1 Parent(s): 8de4339

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:d2dd847e3e6b8ed03e7183d92ecdd1f139f7e66083113600ad35b89e95ca6198
3
  size 37762064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c6958e68bf6d6c92015ce8e9be4195ae7b16f627baf5485594b0ee33a909bae
3
  size 37762064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b6241aae57201ba542e86952042e511a0f6db6296b51c02e5f8c49bb5ee92ae
3
  size 19283770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56967f9ded61ca6666ae1a6bd0552c9b5ea249ab466a290c8193936f31f613ae
3
  size 19283770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75047a3f05c8c8a85262212b7d8b05a265b016854281fba9242a89c3a2375907
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72aafa81663c0c6fc4fe6b1f569b5ab64542065c04722319094c8e1ed1411152
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c41bb450efe89fd65fecb2593939b817f9b2794a5d87a632ad90e5ebc9b592b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a1533051e4bee653afc683a4359c329f95831c0354ae8442616cabf80d0caa
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 3.0753159523010254,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.05683432793407218,
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": 153.356,
732
  "eval_steps_per_second": 38.494,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -745,7 +1103,7 @@
745
  "early_stopping_threshold": 0.0
746
  },
747
  "attributes": {
748
- "early_stopping_patience_counter": 1
749
  }
750
  },
751
  "TrainerControl": {
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 690333067247616.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
  "best_metric": 3.0753159523010254,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.08525149190110827,
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": 153.356,
732
  "eval_steps_per_second": 38.494,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0574026712134129,
737
+ "grad_norm": 3419.945068359375,
738
+ "learning_rate": 5.2157368421052626e-05,
739
+ "loss": 5.8349,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.057971014492753624,
744
+ "grad_norm": 1727.98828125,
745
+ "learning_rate": 5.163052631578947e-05,
746
+ "loss": 5.4662,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.05853935777209435,
751
+ "grad_norm": 1844.83935546875,
752
+ "learning_rate": 5.110368421052632e-05,
753
+ "loss": 6.3172,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.05910770105143507,
758
+ "grad_norm": 9686.3046875,
759
+ "learning_rate": 5.057684210526316e-05,
760
+ "loss": 5.7766,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.059676044330775786,
765
+ "grad_norm": 2436.735107421875,
766
+ "learning_rate": 5.005e-05,
767
+ "loss": 5.8656,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06024438761011651,
772
+ "grad_norm": 1130.5428466796875,
773
+ "learning_rate": 4.9523157894736836e-05,
774
+ "loss": 5.2702,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06081273088945723,
779
+ "grad_norm": 2296.957763671875,
780
+ "learning_rate": 4.899631578947368e-05,
781
+ "loss": 5.6202,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.061381074168797956,
786
+ "grad_norm": 1173.076171875,
787
+ "learning_rate": 4.846947368421052e-05,
788
+ "loss": 5.3879,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.06194941744813868,
793
+ "grad_norm": 1607.265869140625,
794
+ "learning_rate": 4.794263157894737e-05,
795
+ "loss": 5.0738,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0625177607274794,
800
+ "grad_norm": 4334.3232421875,
801
+ "learning_rate": 4.7415789473684206e-05,
802
+ "loss": 4.2186,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.06308610400682012,
807
+ "grad_norm": 2118.742431640625,
808
+ "learning_rate": 4.688894736842105e-05,
809
+ "loss": 5.6198,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.06365444728616085,
814
+ "grad_norm": 1551.3619384765625,
815
+ "learning_rate": 4.636210526315789e-05,
816
+ "loss": 6.8043,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.06422279056550156,
821
+ "grad_norm": 702.0730590820312,
822
+ "learning_rate": 4.583526315789473e-05,
823
+ "loss": 6.608,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.06479113384484228,
828
+ "grad_norm": 1598.27880859375,
829
+ "learning_rate": 4.530842105263158e-05,
830
+ "loss": 6.6213,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.06535947712418301,
835
+ "grad_norm": 5966.04052734375,
836
+ "learning_rate": 4.4781578947368416e-05,
837
+ "loss": 6.2056,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.06592782040352373,
842
+ "grad_norm": 956.0686645507812,
843
+ "learning_rate": 4.425473684210526e-05,
844
+ "loss": 5.1067,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.06649616368286446,
849
+ "grad_norm": 1855.626953125,
850
+ "learning_rate": 4.372789473684211e-05,
851
+ "loss": 5.4279,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.06706450696220517,
856
+ "grad_norm": 2943.97509765625,
857
+ "learning_rate": 4.320105263157895e-05,
858
+ "loss": 6.017,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.06763285024154589,
863
+ "grad_norm": 1935.6732177734375,
864
+ "learning_rate": 4.2674210526315786e-05,
865
+ "loss": 6.2161,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.06820119352088662,
870
+ "grad_norm": 5743.24658203125,
871
+ "learning_rate": 4.2147368421052626e-05,
872
+ "loss": 5.4059,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.06876953680022733,
877
+ "grad_norm": 1168.8848876953125,
878
+ "learning_rate": 4.162052631578947e-05,
879
+ "loss": 6.2903,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.06933788007956806,
884
+ "grad_norm": 671.617431640625,
885
+ "learning_rate": 4.109368421052631e-05,
886
+ "loss": 6.1396,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.06990622335890878,
891
+ "grad_norm": 1641.0462646484375,
892
+ "learning_rate": 4.056684210526316e-05,
893
+ "loss": 7.0481,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0704745666382495,
898
+ "grad_norm": 3586.08056640625,
899
+ "learning_rate": 4.004e-05,
900
+ "loss": 5.9496,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.07104290991759023,
905
+ "grad_norm": 2702.98291015625,
906
+ "learning_rate": 3.951315789473684e-05,
907
+ "loss": 6.0844,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.07161125319693094,
912
+ "grad_norm": 582.7030029296875,
913
+ "learning_rate": 3.898631578947368e-05,
914
+ "loss": 6.6881,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.07217959647627167,
919
+ "grad_norm": 657.8681640625,
920
+ "learning_rate": 3.845947368421052e-05,
921
+ "loss": 5.9414,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.07274793975561239,
926
+ "grad_norm": 2687.12060546875,
927
+ "learning_rate": 3.7932631578947367e-05,
928
+ "loss": 6.3036,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0733162830349531,
933
+ "grad_norm": 435.34735107421875,
934
+ "learning_rate": 3.7405789473684206e-05,
935
+ "loss": 5.9903,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.07388462631429384,
940
+ "grad_norm": 907.7950439453125,
941
+ "learning_rate": 3.6878947368421045e-05,
942
+ "loss": 6.7038,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.07445296959363455,
947
+ "grad_norm": 2316.88671875,
948
+ "learning_rate": 3.635210526315789e-05,
949
+ "loss": 5.9808,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.07502131287297528,
954
+ "grad_norm": 1586.42236328125,
955
+ "learning_rate": 3.582526315789474e-05,
956
+ "loss": 6.9101,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.075589656152316,
961
+ "grad_norm": 2593.992431640625,
962
+ "learning_rate": 3.5298421052631576e-05,
963
+ "loss": 7.1485,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.07615799943165671,
968
+ "grad_norm": 1395.7069091796875,
969
+ "learning_rate": 3.477157894736842e-05,
970
+ "loss": 5.8599,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.07672634271099744,
975
+ "grad_norm": 7057.3466796875,
976
+ "learning_rate": 3.424473684210526e-05,
977
+ "loss": 7.2593,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.07729468599033816,
982
+ "grad_norm": 1391.8118896484375,
983
+ "learning_rate": 3.37178947368421e-05,
984
+ "loss": 7.1002,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.07786302926967889,
989
+ "grad_norm": 894.3593139648438,
990
+ "learning_rate": 3.319105263157894e-05,
991
+ "loss": 6.5116,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.0784313725490196,
996
+ "grad_norm": 2753.335693359375,
997
+ "learning_rate": 3.2664210526315786e-05,
998
+ "loss": 6.1126,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.07899971582836032,
1003
+ "grad_norm": 1995.2767333984375,
1004
+ "learning_rate": 3.213736842105263e-05,
1005
+ "loss": 6.9582,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.07956805910770105,
1010
+ "grad_norm": 4567.09326171875,
1011
+ "learning_rate": 3.161052631578947e-05,
1012
+ "loss": 5.9279,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.08013640238704177,
1017
+ "grad_norm": 1267.830078125,
1018
+ "learning_rate": 3.108368421052632e-05,
1019
+ "loss": 6.9802,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.0807047456663825,
1024
+ "grad_norm": 7844.79931640625,
1025
+ "learning_rate": 3.0556842105263156e-05,
1026
+ "loss": 6.4206,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.08127308894572322,
1031
+ "grad_norm": 636.5696411132812,
1032
+ "learning_rate": 3.0029999999999995e-05,
1033
+ "loss": 6.6095,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.08184143222506395,
1038
+ "grad_norm": 1482.0384521484375,
1039
+ "learning_rate": 2.9503157894736838e-05,
1040
+ "loss": 7.5612,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.08240977550440466,
1045
+ "grad_norm": 1560.4576416015625,
1046
+ "learning_rate": 2.8976315789473684e-05,
1047
+ "loss": 5.6336,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.08297811878374538,
1052
+ "grad_norm": 1849.3775634765625,
1053
+ "learning_rate": 2.8449473684210523e-05,
1054
+ "loss": 6.6312,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.08354646206308611,
1059
+ "grad_norm": 1492.502685546875,
1060
+ "learning_rate": 2.7922631578947366e-05,
1061
+ "loss": 7.2458,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.08411480534242682,
1066
+ "grad_norm": 12098.3876953125,
1067
+ "learning_rate": 2.7395789473684212e-05,
1068
+ "loss": 7.6165,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.08468314862176755,
1073
+ "grad_norm": 1023.9256591796875,
1074
+ "learning_rate": 2.686894736842105e-05,
1075
+ "loss": 6.1149,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.08525149190110827,
1080
+ "grad_norm": 1017.314208984375,
1081
+ "learning_rate": 2.634210526315789e-05,
1082
+ "loss": 6.3853,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.08525149190110827,
1087
+ "eval_loss": 3.0933151245117188,
1088
+ "eval_runtime": 4.7277,
1089
+ "eval_samples_per_second": 156.735,
1090
+ "eval_steps_per_second": 39.342,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1103
  "early_stopping_threshold": 0.0
1104
  },
1105
  "attributes": {
1106
+ "early_stopping_patience_counter": 2
1107
  }
1108
  },
1109
  "TrainerControl": {
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1033863740522496.0,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null