prxy5604 commited on
Commit
3ed7301
·
verified ·
1 Parent(s): 5ed1b4c

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:bf7c8abf35ebfba60e0ad49615a0abf6d39bc15301a396dc238abc9c0d37f070
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c426ce17241aa68be76fe480de6a9ca75c7649b9de1b2466ae9a03ea034724fb
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:901f3f7c2c06facae89d1a6cc8daa1bf1b4ff31c30b076a12bd40182d492e128
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b81287d38be36bcb8cac6c50e0894d51d08f78ba8a2efc551faa6fd38bf7ce5
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbafaeca249c2eeef1f72eb825c52e6c8d3fbd0592af9531150da19aa92920c7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b99d06239b0d1c1d2c6410e25a49a688233dc3388710479b06a74c0a7128d97
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": 2.059274911880493,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.01805706031058144,
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": 13.519,
732
  "eval_steps_per_second": 3.38,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.35249644224512e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.012115478515625,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.027085590465872156,
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": 13.519,
732
  "eval_steps_per_second": 3.38,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.018237630913687252,
737
+ "grad_norm": 0.3895765542984009,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.2459,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.018418201516793065,
744
+ "grad_norm": 0.4267996549606323,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.9942,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.018598772119898882,
751
+ "grad_norm": 0.39692366123199463,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.1023,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.018779342723004695,
758
+ "grad_norm": 0.373115599155426,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.9709,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.01895991332611051,
765
+ "grad_norm": 0.38031432032585144,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.0388,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.019140483929216325,
772
+ "grad_norm": 0.4079199433326721,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.2443,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.01932105453232214,
779
+ "grad_norm": 0.34905269742012024,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.0283,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01950162513542795,
786
+ "grad_norm": 0.4155385196208954,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.0262,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.01968219573853377,
793
+ "grad_norm": 0.43362778425216675,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.9427,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.01986276634163958,
800
+ "grad_norm": 0.37069815397262573,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.9019,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.020043336944745395,
807
+ "grad_norm": 0.3514178693294525,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.8921,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.020223907547851208,
814
+ "grad_norm": 0.3448438048362732,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.9658,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.020404478150957025,
821
+ "grad_norm": 0.373558908700943,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.0503,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.020585048754062838,
828
+ "grad_norm": 0.3926731050014496,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.9073,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.02076561935716865,
835
+ "grad_norm": 0.40110158920288086,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.0409,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.020946189960274468,
842
+ "grad_norm": 0.37772661447525024,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.9971,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.02112676056338028,
849
+ "grad_norm": 0.40943604707717896,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.878,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.021307331166486095,
856
+ "grad_norm": 0.4381054937839508,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.0748,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.02148790176959191,
863
+ "grad_norm": 0.4295724034309387,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.1721,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.021668472372697724,
870
+ "grad_norm": 0.4464626908302307,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.0626,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.021849042975803538,
877
+ "grad_norm": 0.43986180424690247,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.9922,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.022029613578909354,
884
+ "grad_norm": 0.4166202247142792,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.9705,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.022210184182015168,
891
+ "grad_norm": 0.4246368110179901,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.9834,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.02239075478512098,
898
+ "grad_norm": 0.4012325406074524,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.9898,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.022571325388226798,
905
+ "grad_norm": 0.44190362095832825,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.0085,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.02275189599133261,
912
+ "grad_norm": 0.4317069947719574,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.9294,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.022932466594438424,
919
+ "grad_norm": 0.4211461544036865,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.8911,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.02311303719754424,
926
+ "grad_norm": 0.4544403851032257,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.9197,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.023293607800650054,
933
+ "grad_norm": 0.43215247988700867,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.9928,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.023474178403755867,
940
+ "grad_norm": 0.43440431356430054,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.9714,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.023654749006861684,
947
+ "grad_norm": 0.4638649523258209,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.9549,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.023835319609967497,
954
+ "grad_norm": 0.4485500156879425,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.7946,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.02401589021307331,
961
+ "grad_norm": 0.471426784992218,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.0043,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.024196460816179127,
968
+ "grad_norm": 0.4864135980606079,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.9737,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.02437703141928494,
975
+ "grad_norm": 0.49553418159484863,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.9599,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.024557602022390754,
982
+ "grad_norm": 0.48198094964027405,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.7155,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.02473817262549657,
989
+ "grad_norm": 0.5210572481155396,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.0872,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.024918743228602384,
996
+ "grad_norm": 0.517304539680481,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.8473,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.025099313831708197,
1003
+ "grad_norm": 0.5049439668655396,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.9836,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.025279884434814014,
1010
+ "grad_norm": 0.5623946189880371,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.9298,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.025460455037919827,
1017
+ "grad_norm": 0.5387139320373535,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.0437,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.02564102564102564,
1024
+ "grad_norm": 0.5679649114608765,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.0832,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.025821596244131457,
1031
+ "grad_norm": 0.5492368340492249,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.9627,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.02600216684723727,
1038
+ "grad_norm": 0.5792611241340637,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.9441,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.026182737450343083,
1045
+ "grad_norm": 0.566913902759552,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.9718,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0263633080534489,
1052
+ "grad_norm": 0.6455346941947937,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.1376,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.026543878656554713,
1059
+ "grad_norm": 0.6583056449890137,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.143,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.026724449259660527,
1066
+ "grad_norm": 0.6932365298271179,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.1724,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.026905019862766343,
1073
+ "grad_norm": 0.735855221748352,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.5011,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.027085590465872156,
1080
+ "grad_norm": 0.8176823258399963,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.5626,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.027085590465872156,
1087
+ "eval_loss": 2.012115478515625,
1088
+ "eval_runtime": 689.2055,
1089
+ "eval_samples_per_second": 13.533,
1090
+ "eval_steps_per_second": 3.384,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.02874466336768e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null