nttx commited on
Commit
1af7bba
·
verified ·
1 Parent(s): 73ae4cb

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 sha256:992593a3b21d41d52708bb1fd5a32490a7eb855a864fe925cde967c99f6b8d25
3
  size 226532664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ed5e226c2be43b215abe6d5568d343b9b283cf33e6cbb3ea932654b4c605b80
3
  size 226532664
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fcd460d463e8581c13fc2ee10f6f5cca20c0fda172a4f4d68e0fdfa8f3967b6
3
  size 115354708
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94caf2968240f46b7bdb328513f1370308ddb86e5b4bbacd30e37cddfa58cdc
3
  size 115354708
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c587c09dee842368aabfa7ed09a47877b4a8242dc52aee978ec27f053bbd164
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65c24f9f1b28d4c773184519817845af693332cc1868ce9cb434209afa0298ea
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": 1.440259575843811,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.09678199854827002,
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": 49.685,
732
  "eval_steps_per_second": 12.421,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.5435045367906304e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3589195013046265,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.14517299782240503,
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": 49.685,
732
  "eval_steps_per_second": 12.421,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.09774981853375272,
737
+ "grad_norm": 4.391490936279297,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 4.3234,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.09871763851923543,
744
+ "grad_norm": 4.863372802734375,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 4.5842,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.09968545850471812,
751
+ "grad_norm": 4.380272388458252,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 5.2117,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.10065327849020082,
758
+ "grad_norm": 3.587648868560791,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 4.6927,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.10162109847568353,
765
+ "grad_norm": 2.9153084754943848,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.0881,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.10258891846116622,
772
+ "grad_norm": 2.8398003578186035,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 5.2936,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.10355673844664892,
779
+ "grad_norm": 2.9500510692596436,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 4.7048,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.10452455843213163,
786
+ "grad_norm": 3.102827548980713,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 5.011,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.10549237841761433,
793
+ "grad_norm": 2.6776440143585205,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 5.2105,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.10646019840309702,
800
+ "grad_norm": 2.703883647918701,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.2939,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.10742801838857972,
807
+ "grad_norm": 3.025521993637085,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 5.4026,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.10839583837406243,
814
+ "grad_norm": 2.7225425243377686,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 4.9054,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.10936365835954512,
821
+ "grad_norm": 3.217029571533203,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.2622,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.11033147834502782,
828
+ "grad_norm": 3.098397731781006,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 5.8714,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11129929833051053,
835
+ "grad_norm": 3.2830111980438232,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 5.5096,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.11226711831599323,
842
+ "grad_norm": 2.994551420211792,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 5.0694,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.11323493830147592,
849
+ "grad_norm": 3.101209878921509,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.1881,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.11420275828695862,
856
+ "grad_norm": 2.929673433303833,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 5.6943,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.11517057827244133,
863
+ "grad_norm": 3.033630132675171,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 5.4362,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.11613839825792402,
870
+ "grad_norm": 3.13434100151062,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 5.5646,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.11710621824340672,
877
+ "grad_norm": 3.506950616836548,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 6.2031,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.11807403822888943,
884
+ "grad_norm": 3.3511886596679688,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 5.4874,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.11904185821437213,
891
+ "grad_norm": 3.6331543922424316,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 6.1683,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12000967819985482,
898
+ "grad_norm": 3.1168124675750732,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 5.632,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.12097749818533753,
905
+ "grad_norm": 3.6517815589904785,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 5.8436,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.12194531817082023,
912
+ "grad_norm": 3.773366689682007,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 6.1431,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.12291313815630293,
919
+ "grad_norm": 3.5142552852630615,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 5.4809,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.12388095814178562,
926
+ "grad_norm": 3.4593284130096436,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 6.3835,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.12484877812726833,
933
+ "grad_norm": 3.3765344619750977,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 5.012,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.12581659811275103,
940
+ "grad_norm": 3.6987054347991943,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.3808,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.12678441809823374,
947
+ "grad_norm": 3.6943674087524414,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 5.8744,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.12775223808371644,
954
+ "grad_norm": 3.6965532302856445,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 5.6185,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.12872005806919912,
961
+ "grad_norm": 3.9772191047668457,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 6.216,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.12968787805468182,
968
+ "grad_norm": 3.817161798477173,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 5.969,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.13065569804016453,
975
+ "grad_norm": 4.254046440124512,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 5.9868,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.13162351802564723,
982
+ "grad_norm": 4.440921783447266,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 5.606,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.13259133801112993,
989
+ "grad_norm": 4.226521015167236,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 6.016,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.13355915799661264,
996
+ "grad_norm": 4.549649715423584,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 5.8866,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.13452697798209534,
1003
+ "grad_norm": 4.75260591506958,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 5.8661,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.13549479796757802,
1010
+ "grad_norm": 4.542957782745361,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 6.1137,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.13646261795306072,
1017
+ "grad_norm": 4.724084377288818,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 5.776,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.13743043793854343,
1024
+ "grad_norm": 5.398897647857666,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 5.752,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.13839825792402613,
1031
+ "grad_norm": 5.055912017822266,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 5.7374,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.13936607790950883,
1038
+ "grad_norm": 5.0658769607543945,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 6.0132,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.14033389789499154,
1045
+ "grad_norm": 5.335988521575928,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 6.2013,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.14130171788047424,
1052
+ "grad_norm": 5.163208484649658,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 6.1269,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.14226953786595692,
1059
+ "grad_norm": 6.244584560394287,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 6.0443,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.14323735785143962,
1066
+ "grad_norm": 6.147749423980713,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 5.9714,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.14420517783692233,
1073
+ "grad_norm": 6.914193153381348,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 5.44,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.14517299782240503,
1080
+ "grad_norm": 8.9144868850708,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 5.953,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.14517299782240503,
1087
+ "eval_loss": 1.3589195013046265,
1088
+ "eval_runtime": 34.9514,
1089
+ "eval_samples_per_second": 49.783,
1090
+ "eval_steps_per_second": 12.446,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.812147386436813e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null