cilooor commited on
Commit
4b0c58c
·
verified ·
1 Parent(s): c7b712d

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 sha256:6e94674495c060d58a1b74c9205c6b002c1b3a6ba3ace098c7e5580555da355a
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:679bd3053ac66c8745ea96ad6ced489ad2c7a515871f3425e975019435bcadaf
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ee83da3cdbc377d4213520c4f199853dc662e6643c71576e41c75a0e02ec6a1
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cefa8fd1c70707b513603fc78c3738f88b3aa578510a099f63e2392d36e71eb
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f6ab49a62a76d626a212277e13b56a15da5e986df0305cc6df512f8924d90f3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f753d11c176ed0c902455080e1a29f2b289d441ec142e3e573e93ff6a2d2a465
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b0f0591a54513981f9045153a7608f989005ce4fb6ed2c798b085bae23c1094
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed88ff7cbe02e7c054abfce3510882248a01917e1eb8cf2c358f612dd7312357
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1515552997589111,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.20512820512820512,
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": 58.01,
732
  "eval_steps_per_second": 14.538,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7728482431795200.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0141979455947876,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.3076923076923077,
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": 58.01,
732
  "eval_steps_per_second": 14.538,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.20717948717948717,
737
+ "grad_norm": 4.50919246673584,
738
+ "learning_rate": 4.797407629465648e-05,
739
+ "loss": 1.2885,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.20923076923076922,
744
+ "grad_norm": 6.05592155456543,
745
+ "learning_rate": 4.7231268960295003e-05,
746
+ "loss": 1.4065,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.21128205128205127,
751
+ "grad_norm": 5.091554164886475,
752
+ "learning_rate": 4.648785161927887e-05,
753
+ "loss": 1.268,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.21333333333333335,
758
+ "grad_norm": 4.259462833404541,
759
+ "learning_rate": 4.574402751448614e-05,
760
+ "loss": 1.046,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.2153846153846154,
765
+ "grad_norm": 3.6176483631134033,
766
+ "learning_rate": 4.5e-05,
767
+ "loss": 1.1023,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.21743589743589745,
772
+ "grad_norm": 3.611823558807373,
773
+ "learning_rate": 4.425597248551387e-05,
774
+ "loss": 1.0479,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.2194871794871795,
779
+ "grad_norm": 3.323308229446411,
780
+ "learning_rate": 4.3512148380721134e-05,
781
+ "loss": 0.9585,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.22153846153846155,
786
+ "grad_norm": 4.524669647216797,
787
+ "learning_rate": 4.2768731039704995e-05,
788
+ "loss": 1.0296,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.2235897435897436,
793
+ "grad_norm": 3.505427122116089,
794
+ "learning_rate": 4.202592370534353e-05,
795
+ "loss": 0.9292,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.22564102564102564,
800
+ "grad_norm": 3.5585756301879883,
801
+ "learning_rate": 4.128392945374505e-05,
802
+ "loss": 0.9728,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.2276923076923077,
807
+ "grad_norm": 3.7664172649383545,
808
+ "learning_rate": 4.0542951138729184e-05,
809
+ "loss": 0.9758,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.22974358974358974,
814
+ "grad_norm": 4.599196910858154,
815
+ "learning_rate": 3.980319133636863e-05,
816
+ "loss": 1.1582,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.2317948717948718,
821
+ "grad_norm": 4.041998386383057,
822
+ "learning_rate": 3.9064852289606895e-05,
823
+ "loss": 1.0611,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.23384615384615384,
828
+ "grad_norm": 3.943880796432495,
829
+ "learning_rate": 3.832813585296711e-05,
830
+ "loss": 0.9005,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.2358974358974359,
835
+ "grad_norm": 3.5077383518218994,
836
+ "learning_rate": 3.759324343736697e-05,
837
+ "loss": 0.8112,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.23794871794871794,
842
+ "grad_norm": 4.734447956085205,
843
+ "learning_rate": 3.686037595505507e-05,
844
+ "loss": 1.1426,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.24,
849
+ "grad_norm": 4.118103504180908,
850
+ "learning_rate": 3.612973376468339e-05,
851
+ "loss": 0.9013,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.24205128205128204,
856
+ "grad_norm": 3.065751314163208,
857
+ "learning_rate": 3.54015166165314e-05,
858
+ "loss": 0.785,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.2441025641025641,
863
+ "grad_norm": 3.1846020221710205,
864
+ "learning_rate": 3.4675923597896184e-05,
865
+ "loss": 0.7896,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.24615384615384617,
870
+ "grad_norm": 3.586343765258789,
871
+ "learning_rate": 3.395315307866404e-05,
872
+ "loss": 0.7547,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.24820512820512822,
877
+ "grad_norm": 4.758388042449951,
878
+ "learning_rate": 3.3233402657078116e-05,
879
+ "loss": 0.9681,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.25025641025641027,
884
+ "grad_norm": 3.6196420192718506,
885
+ "learning_rate": 3.2516869105717005e-05,
886
+ "loss": 0.8987,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.2523076923076923,
891
+ "grad_norm": 3.955955982208252,
892
+ "learning_rate": 3.1803748317699093e-05,
893
+ "loss": 1.0556,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.25435897435897437,
898
+ "grad_norm": 3.116633415222168,
899
+ "learning_rate": 3.1094235253127374e-05,
900
+ "loss": 0.8184,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.2564102564102564,
905
+ "grad_norm": 4.157810688018799,
906
+ "learning_rate": 3.038852388578925e-05,
907
+ "loss": 1.1041,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.25846153846153846,
912
+ "grad_norm": 3.966348171234131,
913
+ "learning_rate": 2.9686807150126064e-05,
914
+ "loss": 0.9008,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.2605128205128205,
919
+ "grad_norm": 3.4155445098876953,
920
+ "learning_rate": 2.8989276888486755e-05,
921
+ "loss": 0.6458,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.26256410256410256,
926
+ "grad_norm": 4.159134387969971,
927
+ "learning_rate": 2.829612379868006e-05,
928
+ "loss": 0.9501,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.26461538461538464,
933
+ "grad_norm": 3.794668197631836,
934
+ "learning_rate": 2.760753738183966e-05,
935
+ "loss": 0.8481,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.26666666666666666,
940
+ "grad_norm": 4.275190830230713,
941
+ "learning_rate": 2.6923705890616385e-05,
942
+ "loss": 1.208,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.26871794871794874,
947
+ "grad_norm": 3.748812198638916,
948
+ "learning_rate": 2.6244816277711943e-05,
949
+ "loss": 0.9425,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.27076923076923076,
954
+ "grad_norm": 3.8495140075683594,
955
+ "learning_rate": 2.5571054144767825e-05,
956
+ "loss": 0.8654,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.27282051282051284,
961
+ "grad_norm": 4.287474632263184,
962
+ "learning_rate": 2.4902603691623712e-05,
963
+ "loss": 0.875,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.27487179487179486,
968
+ "grad_norm": 9.102813720703125,
969
+ "learning_rate": 2.4239647665959058e-05,
970
+ "loss": 1.0287,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.27692307692307694,
975
+ "grad_norm": 3.8762168884277344,
976
+ "learning_rate": 2.358236731333169e-05,
977
+ "loss": 0.9363,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.27897435897435896,
982
+ "grad_norm": 3.4290077686309814,
983
+ "learning_rate": 2.293094232762715e-05,
984
+ "loss": 0.6294,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.28102564102564104,
989
+ "grad_norm": 9.14670467376709,
990
+ "learning_rate": 2.2285550801932047e-05,
991
+ "loss": 1.0454,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.28307692307692306,
996
+ "grad_norm": 4.820080280303955,
997
+ "learning_rate": 2.164636917984533e-05,
998
+ "loss": 0.9701,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.28512820512820514,
1003
+ "grad_norm": 6.127867698669434,
1004
+ "learning_rate": 2.1013572207240293e-05,
1005
+ "loss": 1.0712,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.28717948717948716,
1010
+ "grad_norm": 5.588995456695557,
1011
+ "learning_rate": 2.03873328844908e-05,
1012
+ "loss": 1.0372,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.28923076923076924,
1017
+ "grad_norm": 4.87202262878418,
1018
+ "learning_rate": 1.9767822419174733e-05,
1019
+ "loss": 0.9822,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.29128205128205126,
1024
+ "grad_norm": 5.483069896697998,
1025
+ "learning_rate": 1.915521017926754e-05,
1026
+ "loss": 0.9312,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.29333333333333333,
1031
+ "grad_norm": 4.585220813751221,
1032
+ "learning_rate": 1.8549663646838714e-05,
1033
+ "loss": 1.0824,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.2953846153846154,
1038
+ "grad_norm": 4.174553394317627,
1039
+ "learning_rate": 1.7951348372263872e-05,
1040
+ "loss": 0.8914,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.29743589743589743,
1045
+ "grad_norm": 5.107333183288574,
1046
+ "learning_rate": 1.7360427928964948e-05,
1047
+ "loss": 1.0994,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2994871794871795,
1052
+ "grad_norm": 8.027003288269043,
1053
+ "learning_rate": 1.6777063868690835e-05,
1054
+ "loss": 1.0736,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.30153846153846153,
1059
+ "grad_norm": 6.4182562828063965,
1060
+ "learning_rate": 1.6201415677350752e-05,
1061
+ "loss": 1.1778,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.3035897435897436,
1066
+ "grad_norm": 6.836369037628174,
1067
+ "learning_rate": 1.563364073141241e-05,
1068
+ "loss": 1.1001,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.30564102564102563,
1073
+ "grad_norm": 11.28016471862793,
1074
+ "learning_rate": 1.5073894254876825e-05,
1075
+ "loss": 1.5729,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.3076923076923077,
1080
+ "grad_norm": 25.214658737182617,
1081
+ "learning_rate": 1.452232927684166e-05,
1082
+ "loss": 3.5538,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.3076923076923077,
1087
+ "eval_loss": 1.0141979455947876,
1088
+ "eval_runtime": 14.1919,
1089
+ "eval_samples_per_second": 57.921,
1090
+ "eval_steps_per_second": 14.515,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.15927236476928e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null