prxy5606 commited on
Commit
9ab32d9
·
verified ·
1 Parent(s): 7e94d4b

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 sha256:5116d3bec13e687d8ef4597838ecbc7db8d547c7329eb0cc759c6ccbde00cbdf
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8737c571679da770c54145bcad64fe5f5fe605906d57af5cd9ea5a33914d1219
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef0e2753ffcd187783dca0f4dcd0ed6865afce071788d0b921f1d0053616769e
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad6e0730ab7f76a2361c0db407b1fb2531a95de56a76bb3fee1a677961663771
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d68b0d1e95502cbd9a90afd80df31b3c61f572313298df32576640984b53316
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b372b4860139de9716b871c38355ec02a48fe50be1c9636b5038786baa8a4a8
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": 0.0033941082656383514,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.007366482504604052,
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": 12.687,
732
  "eval_steps_per_second": 3.172,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5763966897894195e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.0017171857180073857,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.011049723756906077,
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": 12.687,
732
  "eval_steps_per_second": 3.172,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.007440147329650092,
737
+ "grad_norm": 0.11829923838376999,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.0247,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0075138121546961326,
744
+ "grad_norm": 0.2091480791568756,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.0088,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.007587476979742173,
751
+ "grad_norm": 0.1110382229089737,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.0021,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.007661141804788213,
758
+ "grad_norm": 0.012496083974838257,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.0001,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0077348066298342545,
765
+ "grad_norm": 0.0018954469123855233,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.0001,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.007808471454880295,
772
+ "grad_norm": 0.09856453537940979,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.0011,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.007882136279926335,
779
+ "grad_norm": 0.05144748464226723,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.0006,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.007955801104972376,
786
+ "grad_norm": 0.023395325988531113,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.0002,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.008029465930018416,
793
+ "grad_norm": 0.007794566918164492,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.0002,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.008103130755064457,
800
+ "grad_norm": 0.19280481338500977,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.002,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.008176795580110497,
807
+ "grad_norm": 0.10028093308210373,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.0016,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.008250460405156538,
814
+ "grad_norm": 0.00195652456022799,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.0001,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.008324125230202577,
821
+ "grad_norm": 0.03706127777695656,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.0005,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.008397790055248619,
828
+ "grad_norm": 0.05740731209516525,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.0006,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.00847145488029466,
835
+ "grad_norm": 0.014088164083659649,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.0002,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.0085451197053407,
842
+ "grad_norm": 0.012177246622741222,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.0002,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.00861878453038674,
849
+ "grad_norm": 0.02699141949415207,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.0004,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.00869244935543278,
856
+ "grad_norm": 0.111921526491642,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.0016,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.008766114180478821,
863
+ "grad_norm": 0.003571714274585247,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.0001,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.008839779005524863,
870
+ "grad_norm": 0.002393726957961917,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.0001,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.008913443830570902,
877
+ "grad_norm": 0.04804624989628792,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.0004,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.008987108655616943,
884
+ "grad_norm": 0.010899403132498264,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.0002,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.009060773480662983,
891
+ "grad_norm": 0.1602235734462738,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.003,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.009134438305709024,
898
+ "grad_norm": 0.017247473821043968,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.0003,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.009208103130755065,
905
+ "grad_norm": 0.05777062848210335,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.0003,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.009281767955801105,
912
+ "grad_norm": 0.0014383806847035885,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.0001,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.009355432780847146,
919
+ "grad_norm": 0.10282876342535019,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.0017,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.009429097605893185,
926
+ "grad_norm": 0.002600087784230709,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.0,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.009502762430939227,
933
+ "grad_norm": 0.1263400763273239,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.0038,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.009576427255985266,
940
+ "grad_norm": 0.10259674489498138,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.0012,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.009650092081031307,
947
+ "grad_norm": 0.0640677884221077,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.0022,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.009723756906077349,
954
+ "grad_norm": 0.0023545536678284407,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.0001,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.009797421731123388,
961
+ "grad_norm": 0.0071535371243953705,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.0002,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.00987108655616943,
968
+ "grad_norm": 0.03181946277618408,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.0003,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.009944751381215469,
975
+ "grad_norm": 0.010810406878590584,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.0002,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.01001841620626151,
982
+ "grad_norm": 0.12009802460670471,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.0042,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.010092081031307551,
989
+ "grad_norm": 0.14293478429317474,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.0107,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.01016574585635359,
996
+ "grad_norm": 0.035140279680490494,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.0004,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.010239410681399632,
1003
+ "grad_norm": 0.0029654952231794596,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.0001,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.010313075506445672,
1010
+ "grad_norm": 0.0072612278163433075,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.0002,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.010386740331491713,
1017
+ "grad_norm": 0.0034849776420742273,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.0001,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.010460405156537754,
1024
+ "grad_norm": 0.007106333505362272,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.0001,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.010534069981583793,
1031
+ "grad_norm": 0.014908818528056145,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.0003,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.010607734806629835,
1038
+ "grad_norm": 0.3296809792518616,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.0043,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.010681399631675874,
1045
+ "grad_norm": 0.01654644124209881,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.0004,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.010755064456721915,
1052
+ "grad_norm": 0.8910931348800659,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.0156,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.010828729281767955,
1059
+ "grad_norm": 0.0547972172498703,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.001,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.010902394106813996,
1066
+ "grad_norm": 0.00392822315916419,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.0001,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.010976058931860037,
1073
+ "grad_norm": 0.0017114396905526519,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.0001,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.011049723756906077,
1080
+ "grad_norm": 0.19709661602973938,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.0023,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.011049723756906077,
1087
+ "eval_loss": 0.0017171857180073857,
1088
+ "eval_runtime": 1804.6367,
1089
+ "eval_samples_per_second": 12.67,
1090
+ "eval_steps_per_second": 3.167,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.3570524667904e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null