arcwarden46 commited on
Commit
3f40bab
·
verified ·
1 Parent(s): 2fce322

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:f7dba328f61d463b8b6c1657f4efcd6fefc75140d52c477eacdea90f0143ef27
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32e1717246a85d5e38a0f835d2a1e33984e80fd00d065a7bcfb4c26dff39255d
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:720acd8ea7a774b6a4d2ab675213dd2e17497867a26d3f3f2e43a1c245e8c3f9
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beb8147f3616c14c14aff3f166de71f5815101439fb946c77535a28b27ac2fe3
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5aa842aabe316d141460f050df09c17a6f6755ec62b0e2e5c24b5a33945e42ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68c22f10c9bdfb43f232e556143d278d3a84f2a24410d5a891ac18d77a48076a
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": 2.0097198486328125,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.02608071982786725,
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": 13.771,
732
  "eval_steps_per_second": 3.444,
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": 1.7088080644607544,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.039121079741800874,
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": 13.771,
732
  "eval_steps_per_second": 3.444,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.026341527026145922,
737
+ "grad_norm": 22.687538146972656,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 9.6004,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.026602334224424595,
744
+ "grad_norm": 19.59461212158203,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 8.6654,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.02686314142270327,
751
+ "grad_norm": 13.891752243041992,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 8.2593,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.027123948620981938,
758
+ "grad_norm": 10.809483528137207,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 7.4113,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.02738475581926061,
765
+ "grad_norm": 10.051604270935059,
766
+ "learning_rate": 5e-05,
767
+ "loss": 7.5772,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.027645563017539284,
772
+ "grad_norm": 10.854872703552246,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 7.7146,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.027906370215817957,
779
+ "grad_norm": 10.533751487731934,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 6.9586,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.02816717741409663,
786
+ "grad_norm": 11.13151741027832,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 7.2954,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.028427984612375303,
793
+ "grad_norm": 11.318047523498535,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 7.2726,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.028688791810653973,
800
+ "grad_norm": 11.068788528442383,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 6.8083,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.028949599008932646,
807
+ "grad_norm": 10.888313293457031,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 6.7556,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.02921040620721132,
814
+ "grad_norm": 10.240464210510254,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 6.4259,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.029471213405489992,
821
+ "grad_norm": 10.37086296081543,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 6.1604,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.029732020603768665,
828
+ "grad_norm": 11.893575668334961,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 6.8082,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.029992827802047338,
835
+ "grad_norm": 12.003168106079102,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 6.3759,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.030253635000326008,
842
+ "grad_norm": 12.625334739685059,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 6.5815,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.03051444219860468,
849
+ "grad_norm": 12.851235389709473,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 6.7071,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.030775249396883354,
856
+ "grad_norm": 12.898778915405273,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 6.8533,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.031036056595162027,
863
+ "grad_norm": 14.243744850158691,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 7.0537,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.031296863793440696,
870
+ "grad_norm": 11.919962882995605,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 6.4851,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.03155767099171937,
877
+ "grad_norm": 12.9480619430542,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 6.4566,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.03181847818999804,
884
+ "grad_norm": 12.840946197509766,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 6.2002,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.032079285388276715,
891
+ "grad_norm": 12.152085304260254,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 6.1678,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.03234009258655539,
898
+ "grad_norm": 13.635071754455566,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 6.5239,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.03260089978483406,
905
+ "grad_norm": 12.257086753845215,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 6.0963,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.032861706983112735,
912
+ "grad_norm": 13.802964210510254,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 6.4496,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.03312251418139141,
919
+ "grad_norm": 13.266039848327637,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 6.4984,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.03338332137967008,
926
+ "grad_norm": 11.946686744689941,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 6.2973,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.033644128577948754,
933
+ "grad_norm": 14.231830596923828,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 6.9088,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.03390493577622743,
940
+ "grad_norm": 12.960298538208008,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 6.6555,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0341657429745061,
947
+ "grad_norm": 14.096085548400879,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 6.8805,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.034426550172784766,
954
+ "grad_norm": 14.523974418640137,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 6.7666,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.03468735737106344,
961
+ "grad_norm": 14.790218353271484,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 6.7825,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.03494816456934211,
968
+ "grad_norm": 13.652941703796387,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 6.6213,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.035208971767620785,
975
+ "grad_norm": 15.05577564239502,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 6.7036,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.03546977896589946,
982
+ "grad_norm": 13.610404968261719,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 6.4015,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.03573058616417813,
989
+ "grad_norm": 14.335271835327148,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 6.9272,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.035991393362456804,
996
+ "grad_norm": 16.21661376953125,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 6.8389,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.03625220056073548,
1003
+ "grad_norm": 15.185527801513672,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 7.0456,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.03651300775901415,
1010
+ "grad_norm": 14.693958282470703,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 6.7648,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.03677381495729282,
1017
+ "grad_norm": 15.471109390258789,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 7.0808,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.037034622155571496,
1024
+ "grad_norm": 14.067039489746094,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 6.6511,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.03729542935385017,
1031
+ "grad_norm": 17.071073532104492,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 7.1006,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.037556236552128835,
1038
+ "grad_norm": 15.53573989868164,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 7.0855,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.03781704375040751,
1045
+ "grad_norm": 15.090848922729492,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 6.6323,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.03807785094868618,
1052
+ "grad_norm": 16.284835815429688,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 7.2749,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.038338658146964855,
1059
+ "grad_norm": 16.655628204345703,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 6.8157,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.03859946534524353,
1066
+ "grad_norm": 15.952491760253906,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 6.8284,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.0388602725435222,
1073
+ "grad_norm": 15.237507820129395,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 6.9314,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.039121079741800874,
1080
+ "grad_norm": 21.894411087036133,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 7.7673,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.039121079741800874,
1087
+ "eval_loss": 1.7088080644607544,
1088
+ "eval_runtime": 469.0356,
1089
+ "eval_samples_per_second": 13.769,
1090
+ "eval_steps_per_second": 3.443,
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