prxy5604 commited on
Commit
52694df
·
verified ·
1 Parent(s): 9d38f83

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 sha256:0ddab7c69343af5caaf93f4dd233507d377a61423c08eed952aaf6eb143e3c4a
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f98e84be3487d165123da055103aed64790b00906c1d50ee57b29efd714296
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03927b2315418b9b1552330c82fc7339cac8b8bada3c102c9d809c63c84c705d
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:857ee2683f3c6ebe78295c3710748f36f7ae3645306a1941da2fcd39b7062d4d
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1112b86ea2ccf53bf6fa78c0004230219252ce4c3cbcafa985b4b3e0cd872dfb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6581d67ca4ed2f5a4cd94cb1144d5b53fa0b531592cef48aad6e306ec7ae9823
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.871712327003479,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.4645760743321719,
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": 10.247,
732
  "eval_steps_per_second": 2.569,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.937323333779456e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8703346848487854,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.6968641114982579,
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": 10.247,
732
  "eval_steps_per_second": 2.569,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.4692218350754936,
737
+ "grad_norm": 0.11145634204149246,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.7969,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.4738675958188153,
744
+ "grad_norm": 0.12094812095165253,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.8162,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.47851335656213706,
751
+ "grad_norm": 0.12575285136699677,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.9359,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.4831591173054588,
758
+ "grad_norm": 0.1298871636390686,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.8214,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.4878048780487805,
765
+ "grad_norm": 0.1339699625968933,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.9323,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.4924506387921022,
772
+ "grad_norm": 0.11761663109064102,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.748,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.49709639953542395,
779
+ "grad_norm": 0.11723273247480392,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.83,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.5017421602787456,
786
+ "grad_norm": 0.10937295109033585,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.869,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.5063879210220673,
793
+ "grad_norm": 0.11733722686767578,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.8163,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.5110336817653891,
800
+ "grad_norm": 0.11457250267267227,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.8858,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.5156794425087108,
807
+ "grad_norm": 0.11726170033216476,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.9477,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.5203252032520326,
814
+ "grad_norm": 0.10370782017707825,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.8283,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.5249709639953543,
821
+ "grad_norm": 0.11202286928892136,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.888,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5296167247386759,
828
+ "grad_norm": 0.11793085932731628,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.8826,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5342624854819977,
835
+ "grad_norm": 0.10904623568058014,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.8906,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5389082462253194,
842
+ "grad_norm": 0.10171744227409363,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.7867,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.5435540069686411,
849
+ "grad_norm": 0.10408619046211243,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9097,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5481997677119629,
856
+ "grad_norm": 0.1031450629234314,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.8447,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5528455284552846,
863
+ "grad_norm": 0.11930621415376663,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.8626,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5574912891986062,
870
+ "grad_norm": 0.1154748946428299,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.8797,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.562137049941928,
877
+ "grad_norm": 0.10599689930677414,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.6912,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5667828106852497,
884
+ "grad_norm": 0.10911935567855835,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.6975,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5714285714285714,
891
+ "grad_norm": 0.12081928551197052,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.8419,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.5760743321718932,
898
+ "grad_norm": 0.13225339353084564,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.7519,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.5807200929152149,
905
+ "grad_norm": 0.12407319992780685,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.8843,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5853658536585366,
912
+ "grad_norm": 0.14300796389579773,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.7694,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5900116144018583,
919
+ "grad_norm": 0.15102261304855347,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.8374,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.59465737514518,
926
+ "grad_norm": 0.15869556367397308,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.7161,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5993031358885017,
933
+ "grad_norm": 0.14537778496742249,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.7727,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.6039488966318235,
940
+ "grad_norm": 0.15524469316005707,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.8891,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.6085946573751452,
947
+ "grad_norm": 0.15899863839149475,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.6929,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.6132404181184669,
954
+ "grad_norm": 0.1513189971446991,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.7647,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.6178861788617886,
961
+ "grad_norm": 0.16603240370750427,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.7718,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.6225319396051103,
968
+ "grad_norm": 0.18982014060020447,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.0007,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.627177700348432,
975
+ "grad_norm": 0.15879637002944946,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.8562,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.6318234610917538,
982
+ "grad_norm": 0.1893901377916336,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.7898,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.6364692218350755,
989
+ "grad_norm": 0.19009214639663696,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.8707,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6411149825783972,
996
+ "grad_norm": 0.18650825321674347,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.9732,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.645760743321719,
1003
+ "grad_norm": 0.19181600213050842,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.7562,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.6504065040650406,
1010
+ "grad_norm": 0.22567430138587952,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.8456,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.6550522648083623,
1017
+ "grad_norm": 0.2378416806459427,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.8294,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.6596980255516841,
1024
+ "grad_norm": 0.238148033618927,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.9285,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.6643437862950058,
1031
+ "grad_norm": 0.2520192861557007,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.891,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6689895470383276,
1038
+ "grad_norm": 0.2329062968492508,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.8908,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.6736353077816493,
1045
+ "grad_norm": 0.33517736196517944,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.1426,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6782810685249709,
1052
+ "grad_norm": 0.2958681881427765,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.0457,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6829268292682927,
1059
+ "grad_norm": 0.31920844316482544,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.1051,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6875725900116144,
1066
+ "grad_norm": 0.44857126474380493,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.978,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6922183507549361,
1073
+ "grad_norm": 0.39416614174842834,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.1277,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6968641114982579,
1080
+ "grad_norm": 0.7254365086555481,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.3075,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6968641114982579,
1087
+ "eval_loss": 0.8703346848487854,
1088
+ "eval_runtime": 35.163,
1089
+ "eval_samples_per_second": 10.323,
1090
+ "eval_steps_per_second": 2.588,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.8899887529590784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null