lesso commited on
Commit
54ca720
·
verified ·
1 Parent(s): f816a41

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:ff9fb6fdd06c0354c57032442050ed03a37c280be2c4f704ee62f9cc62899fd8
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f78277002de0a0c826cab7407827311c655ca894cf49702964bbe9e4aed7c1
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d4c67e2656b06ef142d745ee0d6907c5eb126b85d60ded9e612aebd711d73c5
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e81116bc4f36a9e18f495e6432531ff08fb189109af0d65c178e17eeab1559
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:435ebe9f67fe8be3959a9ab7877acd7468708d2ee3e5fa8995d392ccb5057b4a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7959d547f47b0ab48adc46b73e7b9a87135e746b11e67f6fe3c011584ba83e
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": 0.5977502465248108,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.01015950421619425,
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": 7.986,
732
  "eval_steps_per_second": 1.998,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.829574095444378e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5625200271606445,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.015239256324291375,
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": 7.986,
732
  "eval_steps_per_second": 1.998,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.010261099258356192,
737
+ "grad_norm": 1.7353254556655884,
738
+ "learning_rate": 5.2157368421052626e-05,
739
+ "loss": 0.6462,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.010362694300518135,
744
+ "grad_norm": 1.8115421533584595,
745
+ "learning_rate": 5.163052631578947e-05,
746
+ "loss": 0.7568,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.010464289342680077,
751
+ "grad_norm": 2.0411505699157715,
752
+ "learning_rate": 5.110368421052632e-05,
753
+ "loss": 0.8423,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.01056588438484202,
758
+ "grad_norm": 1.840236783027649,
759
+ "learning_rate": 5.057684210526316e-05,
760
+ "loss": 0.6614,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.010667479427003962,
765
+ "grad_norm": 2.0278501510620117,
766
+ "learning_rate": 5.005e-05,
767
+ "loss": 0.9404,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.010769074469165904,
772
+ "grad_norm": 2.038224935531616,
773
+ "learning_rate": 4.9523157894736836e-05,
774
+ "loss": 0.7997,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.010870669511327848,
779
+ "grad_norm": 1.961540937423706,
780
+ "learning_rate": 4.899631578947368e-05,
781
+ "loss": 0.88,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01097226455348979,
786
+ "grad_norm": 1.8542038202285767,
787
+ "learning_rate": 4.846947368421052e-05,
788
+ "loss": 0.7586,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.011073859595651733,
793
+ "grad_norm": 2.5004920959472656,
794
+ "learning_rate": 4.794263157894737e-05,
795
+ "loss": 1.1421,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.011175454637813675,
800
+ "grad_norm": 2.2767207622528076,
801
+ "learning_rate": 4.7415789473684206e-05,
802
+ "loss": 0.8825,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.011277049679975617,
807
+ "grad_norm": 2.6416478157043457,
808
+ "learning_rate": 4.688894736842105e-05,
809
+ "loss": 1.0648,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.01137864472213756,
814
+ "grad_norm": 2.6188547611236572,
815
+ "learning_rate": 4.636210526315789e-05,
816
+ "loss": 1.0757,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.011480239764299502,
821
+ "grad_norm": 2.7085273265838623,
822
+ "learning_rate": 4.583526315789473e-05,
823
+ "loss": 1.0747,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.011581834806461445,
828
+ "grad_norm": 2.96585750579834,
829
+ "learning_rate": 4.530842105263158e-05,
830
+ "loss": 1.1136,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.011683429848623387,
835
+ "grad_norm": 3.3075642585754395,
836
+ "learning_rate": 4.4781578947368416e-05,
837
+ "loss": 1.1926,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.011785024890785329,
842
+ "grad_norm": 2.8126935958862305,
843
+ "learning_rate": 4.425473684210526e-05,
844
+ "loss": 1.2221,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.011886619932947273,
849
+ "grad_norm": 2.7019283771514893,
850
+ "learning_rate": 4.372789473684211e-05,
851
+ "loss": 1.0727,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.011988214975109214,
856
+ "grad_norm": 3.095580577850342,
857
+ "learning_rate": 4.320105263157895e-05,
858
+ "loss": 1.0674,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.012089810017271158,
863
+ "grad_norm": 3.138235330581665,
864
+ "learning_rate": 4.2674210526315786e-05,
865
+ "loss": 1.3973,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0121914050594331,
870
+ "grad_norm": 2.981416702270508,
871
+ "learning_rate": 4.2147368421052626e-05,
872
+ "loss": 1.2259,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.012293000101595042,
877
+ "grad_norm": 2.793827772140503,
878
+ "learning_rate": 4.162052631578947e-05,
879
+ "loss": 1.1706,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.012394595143756985,
884
+ "grad_norm": 3.055459976196289,
885
+ "learning_rate": 4.109368421052631e-05,
886
+ "loss": 1.1658,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.012496190185918927,
891
+ "grad_norm": 2.991947889328003,
892
+ "learning_rate": 4.056684210526316e-05,
893
+ "loss": 1.1881,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.01259778522808087,
898
+ "grad_norm": 2.9653897285461426,
899
+ "learning_rate": 4.004e-05,
900
+ "loss": 1.1678,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.012699380270242812,
905
+ "grad_norm": 2.954136371612549,
906
+ "learning_rate": 3.951315789473684e-05,
907
+ "loss": 1.0478,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.012800975312404754,
912
+ "grad_norm": 3.4325461387634277,
913
+ "learning_rate": 3.898631578947368e-05,
914
+ "loss": 1.2497,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.012902570354566698,
919
+ "grad_norm": 4.589744567871094,
920
+ "learning_rate": 3.845947368421052e-05,
921
+ "loss": 1.2284,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.01300416539672864,
926
+ "grad_norm": 3.4360063076019287,
927
+ "learning_rate": 3.7932631578947367e-05,
928
+ "loss": 1.1895,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.013105760438890583,
933
+ "grad_norm": 3.6225502490997314,
934
+ "learning_rate": 3.7405789473684206e-05,
935
+ "loss": 1.182,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.013207355481052525,
940
+ "grad_norm": 3.9139211177825928,
941
+ "learning_rate": 3.6878947368421045e-05,
942
+ "loss": 1.4435,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.013308950523214466,
947
+ "grad_norm": 3.7881407737731934,
948
+ "learning_rate": 3.635210526315789e-05,
949
+ "loss": 1.1918,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.01341054556537641,
954
+ "grad_norm": 3.863058567047119,
955
+ "learning_rate": 3.582526315789474e-05,
956
+ "loss": 1.1332,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.013512140607538352,
961
+ "grad_norm": 3.9372336864471436,
962
+ "learning_rate": 3.5298421052631576e-05,
963
+ "loss": 1.0857,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.013613735649700295,
968
+ "grad_norm": 4.330385684967041,
969
+ "learning_rate": 3.477157894736842e-05,
970
+ "loss": 1.1804,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.013715330691862237,
975
+ "grad_norm": 4.239872455596924,
976
+ "learning_rate": 3.424473684210526e-05,
977
+ "loss": 1.2745,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.013816925734024179,
982
+ "grad_norm": 4.237067699432373,
983
+ "learning_rate": 3.37178947368421e-05,
984
+ "loss": 1.0984,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.013918520776186123,
989
+ "grad_norm": 4.873085975646973,
990
+ "learning_rate": 3.319105263157894e-05,
991
+ "loss": 1.4904,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.014020115818348064,
996
+ "grad_norm": 5.1811842918396,
997
+ "learning_rate": 3.2664210526315786e-05,
998
+ "loss": 1.3309,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.014121710860510008,
1003
+ "grad_norm": 5.059803009033203,
1004
+ "learning_rate": 3.213736842105263e-05,
1005
+ "loss": 1.1333,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.01422330590267195,
1010
+ "grad_norm": 5.975893974304199,
1011
+ "learning_rate": 3.161052631578947e-05,
1012
+ "loss": 1.387,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.014324900944833891,
1017
+ "grad_norm": 6.209765911102295,
1018
+ "learning_rate": 3.108368421052632e-05,
1019
+ "loss": 1.681,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.014426495986995835,
1024
+ "grad_norm": 5.893293857574463,
1025
+ "learning_rate": 3.0556842105263156e-05,
1026
+ "loss": 1.4305,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.014528091029157777,
1031
+ "grad_norm": 8.19773006439209,
1032
+ "learning_rate": 3.0029999999999995e-05,
1033
+ "loss": 1.5269,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.01462968607131972,
1038
+ "grad_norm": 7.0231547355651855,
1039
+ "learning_rate": 2.9503157894736838e-05,
1040
+ "loss": 1.4278,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.014731281113481662,
1045
+ "grad_norm": 6.790130615234375,
1046
+ "learning_rate": 2.8976315789473684e-05,
1047
+ "loss": 1.2506,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.014832876155643604,
1052
+ "grad_norm": 6.087902069091797,
1053
+ "learning_rate": 2.8449473684210523e-05,
1054
+ "loss": 0.8843,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.014934471197805547,
1059
+ "grad_norm": 7.544525623321533,
1060
+ "learning_rate": 2.7922631578947366e-05,
1061
+ "loss": 0.9716,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.01503606623996749,
1066
+ "grad_norm": 7.611911296844482,
1067
+ "learning_rate": 2.7395789473684212e-05,
1068
+ "loss": 1.0314,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.015137661282129433,
1073
+ "grad_norm": 8.211386680603027,
1074
+ "learning_rate": 2.686894736842105e-05,
1075
+ "loss": 0.9311,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.015239256324291375,
1080
+ "grad_norm": 12.661590576171875,
1081
+ "learning_rate": 2.634210526315789e-05,
1082
+ "loss": 0.8717,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.015239256324291375,
1087
+ "eval_loss": 0.5625200271606445,
1088
+ "eval_runtime": 517.8623,
1089
+ "eval_samples_per_second": 8.004,
1090
+ "eval_steps_per_second": 2.002,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.762256349220045e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null