aleegis09 commited on
Commit
d8c6b83
·
verified ·
1 Parent(s): eb6107b

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:cf66f197c76d9ffbb7357a17c5135c75db4bf6aa8901a3ed50cd31dcedad28d8
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764fd81d8cf511b22e3e959f6d9d425f67b67dd451575c84cd4f7f56ae0282cf
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8cbe3b0be9f2be70fb27928ef08b234378922af443804ae1d1023d40160dbec
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c940f027a8406afa93a7025f16a3a97c4d994c6a6de409a623af23f456c1b593
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a6a64193a8e1ec00e11a24476ecf24116de6bd64cad7d59b62f526f6a0b949b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c9c6732e8fc83081e03161d12978e5ac406e72671f9e6acceaa2b7f957794f
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": 0.7298057675361633,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0033729372380703424,
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": 12.852,
732
  "eval_steps_per_second": 3.213,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.488881143649403e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6794349551200867,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.005059405857105514,
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": 12.852,
732
  "eval_steps_per_second": 3.213,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.003406666610451046,
737
+ "grad_norm": 3.111365556716919,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.4397,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0034403959828317493,
744
+ "grad_norm": 2.9476871490478516,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 3.0504,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.003474125355212453,
751
+ "grad_norm": 3.170501470565796,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.9921,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0035078547275931562,
758
+ "grad_norm": 2.601001739501953,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.141,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.00354158409997386,
765
+ "grad_norm": 2.606767177581787,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.7474,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.003575313472354563,
772
+ "grad_norm": 2.6180262565612793,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.7362,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.003609042844735267,
779
+ "grad_norm": 2.7048604488372803,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.2784,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.00364277221711597,
786
+ "grad_norm": 2.458204507827759,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.3686,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0036765015894966733,
793
+ "grad_norm": 3.105318307876587,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.9872,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.003710230961877377,
800
+ "grad_norm": 2.9087324142456055,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.5763,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.00374396033425808,
807
+ "grad_norm": 3.3524820804595947,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.5951,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.003777689706638784,
814
+ "grad_norm": 3.0980982780456543,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.4949,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.003811419079019487,
821
+ "grad_norm": 2.9690330028533936,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.6124,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0038451484514001907,
828
+ "grad_norm": 2.8932576179504395,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.5953,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.003878877823780894,
835
+ "grad_norm": 3.3136117458343506,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.3985,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.003912607196161598,
842
+ "grad_norm": 3.411710262298584,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.7487,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.003946336568542301,
849
+ "grad_norm": 3.244392156600952,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.6008,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.003980065940923004,
856
+ "grad_norm": 3.0537939071655273,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.5601,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.004013795313303707,
863
+ "grad_norm": 2.933382034301758,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.6705,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.004047524685684411,
870
+ "grad_norm": 3.036072015762329,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.166,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.004081254058065115,
877
+ "grad_norm": 3.252941608428955,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.0373,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.004114983430445818,
884
+ "grad_norm": 2.9841160774230957,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.2531,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.004148712802826521,
891
+ "grad_norm": 3.5263969898223877,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.7147,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.004182442175207225,
898
+ "grad_norm": 3.2517738342285156,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.377,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.0042161715475879285,
905
+ "grad_norm": 3.267925977706909,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.0617,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.004249900919968632,
912
+ "grad_norm": 3.7262022495269775,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.6081,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.004283630292349335,
919
+ "grad_norm": 3.4712376594543457,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.4889,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.004317359664730038,
926
+ "grad_norm": 3.6753430366516113,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.5376,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.004351089037110742,
933
+ "grad_norm": 3.4343435764312744,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.2512,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0043848184094914455,
940
+ "grad_norm": 4.201005935668945,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.1652,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.004418547781872149,
947
+ "grad_norm": 4.135227680206299,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.0392,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.004452277154252852,
954
+ "grad_norm": 4.8751044273376465,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.9728,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.004486006526633556,
961
+ "grad_norm": 4.290978908538818,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.1564,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.004519735899014259,
968
+ "grad_norm": 4.898470878601074,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.3571,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0045534652713949625,
975
+ "grad_norm": 4.462129592895508,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.3667,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.004587194643775666,
982
+ "grad_norm": 4.757960319519043,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.6919,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.004620924016156369,
989
+ "grad_norm": 4.8541154861450195,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.6552,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.004654653388537073,
996
+ "grad_norm": 5.870574474334717,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 3.091,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.004688382760917776,
1003
+ "grad_norm": 5.609764575958252,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.515,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0047221121332984796,
1010
+ "grad_norm": 5.161116123199463,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.5369,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.004755841505679183,
1017
+ "grad_norm": 8.233118057250977,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.0189,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.004789570878059887,
1024
+ "grad_norm": 6.386716365814209,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.9592,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.00482330025044059,
1031
+ "grad_norm": 7.640812873840332,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.1168,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.004857029622821293,
1038
+ "grad_norm": 8.133594512939453,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.0273,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.004890758995201997,
1045
+ "grad_norm": 8.013106346130371,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.2874,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0049244883675827,
1052
+ "grad_norm": 8.809735298156738,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.9128,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.004958217739963404,
1059
+ "grad_norm": 9.66916275024414,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.5167,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.004991947112344107,
1066
+ "grad_norm": 10.982966423034668,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.11,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.00502567648472481,
1073
+ "grad_norm": 11.521635055541992,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.9937,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.005059405857105514,
1080
+ "grad_norm": 20.632587432861328,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 4.7432,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.005059405857105514,
1087
+ "eval_loss": 0.6794349551200867,
1088
+ "eval_runtime": 3882.3594,
1089
+ "eval_samples_per_second": 12.862,
1090
+ "eval_steps_per_second": 3.216,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2369007566848e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null