aleegis10 commited on
Commit
1cbe7de
·
verified ·
1 Parent(s): 566d2b8

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 sha256:9632c3f5d63d51d3992c794629028c67ec28ba1711a22e31b9bb602dcf2edd43
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c03c3f6885c61010bc2f6bed712b50002fd5d7d64d1d213a8261a38afa804d1
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa7baab703147d5348542bc7c233f9ba860dc62b6d5cf14ee7cd844693788389
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67b74c7f1f89335c541385ea4369835801995a333d13237997004124f529ebd6
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:d66d53a0bf06857857d3fb6212234e574708a9d5a0de8ab767a4f6cfc1da5448
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdc877e09dea6ad330de543ce2acee1dc31e1e793a70a57f3defff122f04abc5
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": 0.7334732413291931,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.013219644391565867,
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": 9.923,
732
  "eval_steps_per_second": 2.481,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.8793252811440128e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7003475427627563,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.019829466587348802,
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": 9.923,
732
  "eval_steps_per_second": 2.481,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.013351840835481526,
737
+ "grad_norm": 0.24181707203388214,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.596,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.013484037279397185,
744
+ "grad_norm": 0.23782025277614594,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.5794,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.013616233723312842,
751
+ "grad_norm": 0.2528301775455475,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.5885,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0137484301672285,
758
+ "grad_norm": 0.21014751493930817,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.5951,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.01388062661114416,
765
+ "grad_norm": 0.22236773371696472,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.7092,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.014012823055059818,
772
+ "grad_norm": 0.21512827277183533,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.6623,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.014145019498975477,
779
+ "grad_norm": 0.21951237320899963,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.6856,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.014277215942891136,
786
+ "grad_norm": 0.21105462312698364,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.5825,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.014409412386806795,
793
+ "grad_norm": 0.27910059690475464,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.8379,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.014541608830722454,
800
+ "grad_norm": 0.2623700499534607,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.7664,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.014673805274638112,
807
+ "grad_norm": 0.24401693046092987,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.6521,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.014806001718553771,
814
+ "grad_norm": 0.2733868658542633,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.6896,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.01493819816246943,
821
+ "grad_norm": 0.29973694682121277,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.8034,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.015070394606385089,
828
+ "grad_norm": 0.2729474604129791,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.721,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.015202591050300748,
835
+ "grad_norm": 0.3053736686706543,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.7217,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.015334787494216406,
842
+ "grad_norm": 0.30556952953338623,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.736,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.015466983938132063,
849
+ "grad_norm": 0.356710284948349,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.8814,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.015599180382047722,
856
+ "grad_norm": 0.28044766187667847,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.7973,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.015731376825963383,
863
+ "grad_norm": 0.26613718271255493,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.7435,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.01586357326987904,
870
+ "grad_norm": 0.2693482041358948,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.7187,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0159957697137947,
877
+ "grad_norm": 0.278363436460495,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.6341,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.01612796615771036,
884
+ "grad_norm": 0.2664760947227478,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.6746,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.016260162601626018,
891
+ "grad_norm": 0.2626112103462219,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.6684,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.016392359045541673,
898
+ "grad_norm": 0.2720891237258911,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.7468,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.016524555489457332,
905
+ "grad_norm": 0.32452595233917236,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.8739,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.01665675193337299,
912
+ "grad_norm": 0.2681269943714142,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.6395,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.01678894837728865,
919
+ "grad_norm": 0.2877364158630371,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.7308,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.01692114482120431,
926
+ "grad_norm": 0.28337937593460083,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.6387,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.017053341265119967,
933
+ "grad_norm": 0.3185059428215027,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.8061,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.017185537709035626,
940
+ "grad_norm": 0.2694532573223114,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.6599,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.017317734152951285,
947
+ "grad_norm": 0.3253261148929596,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.7728,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.017449930596866944,
954
+ "grad_norm": 0.3177144229412079,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.7772,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.017582127040782602,
961
+ "grad_norm": 0.2779819071292877,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.6469,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.01771432348469826,
968
+ "grad_norm": 0.29959800839424133,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.6401,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.01784651992861392,
975
+ "grad_norm": 0.3584449887275696,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.8156,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.01797871637252958,
982
+ "grad_norm": 0.3743143677711487,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.7496,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.018110912816445238,
989
+ "grad_norm": 0.37764647603034973,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.8135,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.018243109260360896,
996
+ "grad_norm": 0.34589067101478577,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.7126,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.018375305704276555,
1003
+ "grad_norm": 0.3663211762905121,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.7474,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.018507502148192214,
1010
+ "grad_norm": 0.3387898802757263,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.6598,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.018639698592107873,
1017
+ "grad_norm": 0.44442814588546753,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.7162,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.01877189503602353,
1024
+ "grad_norm": 0.38971763849258423,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.7364,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.01890409147993919,
1031
+ "grad_norm": 0.3823245167732239,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.7215,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.01903628792385485,
1038
+ "grad_norm": 0.40516719222068787,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.7439,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.019168484367770508,
1045
+ "grad_norm": 0.3880475163459778,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.7098,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.019300680811686167,
1052
+ "grad_norm": 0.39626526832580566,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.6337,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.019432877255601826,
1059
+ "grad_norm": 0.40710315108299255,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.6118,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.019565073699517484,
1066
+ "grad_norm": 0.40455126762390137,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.5703,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.019697270143433143,
1073
+ "grad_norm": 0.4407866299152374,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.5417,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.019829466587348802,
1080
+ "grad_norm": 0.6249489188194275,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.5839,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.019829466587348802,
1087
+ "eval_loss": 0.7003475427627563,
1088
+ "eval_runtime": 1285.1101,
1089
+ "eval_samples_per_second": 9.914,
1090
+ "eval_steps_per_second": 2.478,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.8073460836912333e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null