prxy5608 commited on
Commit
e59f3aa
·
verified ·
1 Parent(s): 76fd483

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:b49208aa255c00ada44031b259a1164965c2344298444b06f6e88250c60605a8
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da54134d203dece3743a02238bf6fdce05f28508e3415ef44b2496106d8727f
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:191d6bf9ff433e31726bcd3e5b025f58576be34dc075398a3a005fdb2b03c4d7
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9efbfc5a18c171c1347ec7e409d1f80fb651bb029486280dddca773fda8e536c
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d541ecdf61ef38f5798c7042c75364b3eabb04b21a9249fe985b313b9de80b0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c8f49ae7d1b0c7244ec5f9891b6336e8dd63d15c3a7223d7539af234aae23c3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab2cd78272b68f09e2dc52972598555d6d03b008e6b8b306b1bab47c2e80a621
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88004fe81ddcc4e2df673ef2a68c651d0c3f66e5c526887263eba26939791c56
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.2679302394390106,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.7743362831858407,
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": 10.6,
732
  "eval_steps_per_second": 2.678,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.430998008987648e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.2263110727071762,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 2.663716814159292,
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": 10.6,
732
  "eval_steps_per_second": 2.678,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.7920353982300885,
737
+ "grad_norm": 5.6379547119140625,
738
+ "learning_rate": 3.928454234674747e-05,
739
+ "loss": 0.6571,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.8097345132743363,
744
+ "grad_norm": 6.8352885246276855,
745
+ "learning_rate": 3.832773180720475e-05,
746
+ "loss": 0.6342,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.827433628318584,
751
+ "grad_norm": 4.388557434082031,
752
+ "learning_rate": 3.73754211492421e-05,
753
+ "loss": 0.5032,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.8451327433628317,
758
+ "grad_norm": 4.776178359985352,
759
+ "learning_rate": 3.642797750674629e-05,
760
+ "loss": 0.4031,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.8628318584070795,
765
+ "grad_norm": 8.055367469787598,
766
+ "learning_rate": 3.5485766137276894e-05,
767
+ "loss": 0.6053,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.8805309734513274,
772
+ "grad_norm": 6.032299041748047,
773
+ "learning_rate": 3.4549150281252636e-05,
774
+ "loss": 0.5773,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.8982300884955752,
779
+ "grad_norm": 7.200865745544434,
780
+ "learning_rate": 3.361849102191533e-05,
781
+ "loss": 0.497,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.915929203539823,
786
+ "grad_norm": 6.174206733703613,
787
+ "learning_rate": 3.2694147146125345e-05,
788
+ "loss": 0.4945,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.9336283185840708,
793
+ "grad_norm": 8.304489135742188,
794
+ "learning_rate": 3.177647500604252e-05,
795
+ "loss": 0.5834,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.9513274336283186,
800
+ "grad_norm": 5.608364582061768,
801
+ "learning_rate": 3.086582838174551e-05,
802
+ "loss": 0.4771,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.9690265486725664,
807
+ "grad_norm": 7.852937698364258,
808
+ "learning_rate": 2.996255834484296e-05,
809
+ "loss": 0.4913,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.9867256637168142,
814
+ "grad_norm": 9.713995933532715,
815
+ "learning_rate": 2.9067013123128613e-05,
816
+ "loss": 0.6423,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 2.0088495575221237,
821
+ "grad_norm": 8.310989379882812,
822
+ "learning_rate": 2.8179537966332887e-05,
823
+ "loss": 0.5832,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 2.0265486725663715,
828
+ "grad_norm": 3.7431464195251465,
829
+ "learning_rate": 2.7300475013022663e-05,
830
+ "loss": 0.2774,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 2.0442477876106193,
835
+ "grad_norm": 3.602764844894409,
836
+ "learning_rate": 2.6430163158700115e-05,
837
+ "loss": 0.2663,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 2.061946902654867,
842
+ "grad_norm": 4.605719089508057,
843
+ "learning_rate": 2.556893792515227e-05,
844
+ "loss": 0.2502,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 2.079646017699115,
849
+ "grad_norm": 2.8502187728881836,
850
+ "learning_rate": 2.471713133110078e-05,
851
+ "loss": 0.219,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 2.0973451327433628,
856
+ "grad_norm": 2.774047613143921,
857
+ "learning_rate": 2.3875071764202563e-05,
858
+ "loss": 0.1839,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 2.1150442477876106,
863
+ "grad_norm": 3.8455257415771484,
864
+ "learning_rate": 2.3043083854449988e-05,
865
+ "loss": 0.2419,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 2.1327433628318584,
870
+ "grad_norm": 5.175693511962891,
871
+ "learning_rate": 2.2221488349019903e-05,
872
+ "loss": 0.192,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 2.150442477876106,
877
+ "grad_norm": 3.1044692993164062,
878
+ "learning_rate": 2.1410601988619394e-05,
879
+ "loss": 0.1589,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 2.168141592920354,
884
+ "grad_norm": 6.46194314956665,
885
+ "learning_rate": 2.061073738537635e-05,
886
+ "loss": 0.2275,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 2.185840707964602,
891
+ "grad_norm": 4.672300815582275,
892
+ "learning_rate": 1.982220290232143e-05,
893
+ "loss": 0.2475,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 2.2035398230088497,
898
+ "grad_norm": 5.018974304199219,
899
+ "learning_rate": 1.9045302534508297e-05,
900
+ "loss": 0.2665,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 2.2212389380530975,
905
+ "grad_norm": 8.109318733215332,
906
+ "learning_rate": 1.8280335791817733e-05,
907
+ "loss": 0.4599,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 2.2389380530973453,
912
+ "grad_norm": 5.888927459716797,
913
+ "learning_rate": 1.7527597583490822e-05,
914
+ "loss": 0.3197,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 2.256637168141593,
919
+ "grad_norm": 6.209958076477051,
920
+ "learning_rate": 1.678737810443593e-05,
921
+ "loss": 0.4531,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 2.274336283185841,
926
+ "grad_norm": 3.8774378299713135,
927
+ "learning_rate": 1.605996272335291e-05,
928
+ "loss": 0.2294,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 2.2920353982300883,
933
+ "grad_norm": 4.786031723022461,
934
+ "learning_rate": 1.5345631872718214e-05,
935
+ "loss": 0.2806,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 2.309734513274336,
940
+ "grad_norm": 6.043717384338379,
941
+ "learning_rate": 1.4644660940672627e-05,
942
+ "loss": 0.187,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 2.327433628318584,
947
+ "grad_norm": 4.6054606437683105,
948
+ "learning_rate": 1.3957320164854059e-05,
949
+ "loss": 0.2062,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 2.3451327433628317,
954
+ "grad_norm": 5.415921211242676,
955
+ "learning_rate": 1.3283874528215733e-05,
956
+ "loss": 0.2537,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 2.3628318584070795,
961
+ "grad_norm": 2.9057247638702393,
962
+ "learning_rate": 1.2624583656870154e-05,
963
+ "loss": 0.1775,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 2.3805309734513274,
968
+ "grad_norm": 3.5282516479492188,
969
+ "learning_rate": 1.1979701719998453e-05,
970
+ "loss": 0.1577,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 2.398230088495575,
975
+ "grad_norm": 5.042332172393799,
976
+ "learning_rate": 1.134947733186315e-05,
977
+ "loss": 0.1807,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 2.415929203539823,
982
+ "grad_norm": 4.14683198928833,
983
+ "learning_rate": 1.0734153455962765e-05,
984
+ "loss": 0.2114,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 2.433628318584071,
989
+ "grad_norm": 4.2411980628967285,
990
+ "learning_rate": 1.013396731136465e-05,
991
+ "loss": 0.2662,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 2.4513274336283186,
996
+ "grad_norm": 2.8422842025756836,
997
+ "learning_rate": 9.549150281252633e-06,
998
+ "loss": 0.2022,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 2.4690265486725664,
1003
+ "grad_norm": 5.191140174865723,
1004
+ "learning_rate": 8.97992782372432e-06,
1005
+ "loss": 0.2508,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 2.4867256637168142,
1010
+ "grad_norm": 7.143102645874023,
1011
+ "learning_rate": 8.426519384872733e-06,
1012
+ "loss": 0.3408,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 2.504424778761062,
1017
+ "grad_norm": 3.898927927017212,
1018
+ "learning_rate": 7.889138314185678e-06,
1019
+ "loss": 0.2535,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 2.52212389380531,
1024
+ "grad_norm": 3.8761115074157715,
1025
+ "learning_rate": 7.367991782295391e-06,
1026
+ "loss": 0.2149,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 2.5398230088495577,
1031
+ "grad_norm": 3.058852434158325,
1032
+ "learning_rate": 6.863280701110408e-06,
1033
+ "loss": 0.1875,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 2.557522123893805,
1038
+ "grad_norm": 1.8599612712860107,
1039
+ "learning_rate": 6.375199646360142e-06,
1040
+ "loss": 0.1232,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 2.5752212389380533,
1045
+ "grad_norm": 6.451328277587891,
1046
+ "learning_rate": 5.903936782582253e-06,
1047
+ "loss": 0.2049,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 2.5929203539823007,
1052
+ "grad_norm": 3.4158663749694824,
1053
+ "learning_rate": 5.449673790581611e-06,
1054
+ "loss": 0.1678,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 2.6106194690265485,
1059
+ "grad_norm": 3.9194419384002686,
1060
+ "learning_rate": 5.012585797388936e-06,
1061
+ "loss": 0.1724,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 2.6283185840707963,
1066
+ "grad_norm": 5.876561164855957,
1067
+ "learning_rate": 4.592841308745932e-06,
1068
+ "loss": 0.2246,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 2.646017699115044,
1073
+ "grad_norm": 2.878607749938965,
1074
+ "learning_rate": 4.190602144143207e-06,
1075
+ "loss": 0.1746,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 2.663716814159292,
1080
+ "grad_norm": 2.6272075176239014,
1081
+ "learning_rate": 3.8060233744356633e-06,
1082
+ "loss": 0.1676,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 2.663716814159292,
1087
+ "eval_loss": 0.2263110727071762,
1088
+ "eval_runtime": 8.962,
1089
+ "eval_samples_per_second": 10.6,
1090
+ "eval_steps_per_second": 2.678,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.146497013481472e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null