aleegis12 commited on
Commit
84ddf77
·
verified ·
1 Parent(s): d237fc9

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 sha256:556a9b2c5ae3fa951f2b69a59821ee5233f44df4b096cabb91717fe09bc43fe8
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c9e3549c6d0e93e871fd80cebdb966eadfcce5640b86a174e400c817c18aa9
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56dcf87ad436c3f7a5046324d753bb17be53a38d8858fe196d269d765c3ef39f
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87969e6e37a40dd52663668a7de89dfa18c9995675f555591c8083ab023003f3
3
  size 71077780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93cdd237605912b17a727d29ea7b8967fd7ccb7c03aecc8b38c8d516ee4963fa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0314c050e12719a3e8fa98f8fa4d89e0b0670a278a4e272c409caf48dcfd3968
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": 1.208489179611206,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.026072220049537218,
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": 53.065,
732
  "eval_steps_per_second": 13.266,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7779006079303680.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1554970741271973,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.03910833007430583,
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": 53.065,
732
  "eval_steps_per_second": 13.266,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.02633294225003259,
737
+ "grad_norm": 0.23943422734737396,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.6074,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.02659366445052796,
744
+ "grad_norm": 0.2698066830635071,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.6667,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.026854386651023333,
751
+ "grad_norm": 0.3144571781158447,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.6565,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.027115108851518705,
758
+ "grad_norm": 0.3979966342449188,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.8356,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.02737583105201408,
765
+ "grad_norm": 0.4503781199455261,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.9748,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.027636553252509452,
772
+ "grad_norm": 0.5786712169647217,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.1058,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.027897275453004824,
779
+ "grad_norm": 0.32917410135269165,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.5485,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.028157997653500196,
786
+ "grad_norm": 0.33912646770477295,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.6711,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.028418719853995567,
793
+ "grad_norm": 0.39111921191215515,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.7746,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.02867944205449094,
800
+ "grad_norm": 0.4260513484477997,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.7831,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.02894016425498631,
807
+ "grad_norm": 0.4411897361278534,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.7796,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.029200886455481686,
814
+ "grad_norm": 0.3865686357021332,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.7789,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.029461608655977058,
821
+ "grad_norm": 0.4978114068508148,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.9771,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.02972233085647243,
828
+ "grad_norm": 0.3962376117706299,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.8194,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.0299830530569678,
835
+ "grad_norm": 0.4375857412815094,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.7682,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.030243775257463173,
842
+ "grad_norm": 0.39728087186813354,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.9565,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.030504497457958545,
849
+ "grad_norm": 0.3799859285354614,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.6758,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.030765219658453916,
856
+ "grad_norm": 0.4195021092891693,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.9369,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.031025941858949288,
863
+ "grad_norm": 0.5685878396034241,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.0809,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.03128666405944466,
870
+ "grad_norm": 0.5001601576805115,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.9264,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.03154738625994003,
877
+ "grad_norm": 0.44179967045783997,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.8189,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.03180810846043541,
884
+ "grad_norm": 0.6032936573028564,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.1387,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.032068830660930775,
891
+ "grad_norm": 0.44836997985839844,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.8341,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.03232955286142615,
898
+ "grad_norm": 0.4814024567604065,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.9537,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.032590275061921525,
905
+ "grad_norm": 0.47974511981010437,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.9061,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.032850997262416894,
912
+ "grad_norm": 0.47077134251594543,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.9726,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.03311171946291227,
919
+ "grad_norm": 0.5297815799713135,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.0529,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.03337244166340764,
926
+ "grad_norm": 0.4989417493343353,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.7863,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.03363316386390301,
933
+ "grad_norm": 0.5272191762924194,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.0456,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.03389388606439838,
940
+ "grad_norm": 0.5070304274559021,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.0125,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.034154608264893756,
947
+ "grad_norm": 0.5110166668891907,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.9601,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.03441533046538913,
954
+ "grad_norm": 0.5463582277297974,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.9332,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0346760526658845,
961
+ "grad_norm": 0.6532591581344604,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.3011,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.034936774866379874,
968
+ "grad_norm": 0.6177405118942261,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.263,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03519749706687524,
975
+ "grad_norm": 0.5766922235488892,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.9751,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.03545821926737062,
982
+ "grad_norm": 0.803145706653595,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.3461,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.035718941467865986,
989
+ "grad_norm": 0.7031037211418152,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.2256,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.03597966366836136,
996
+ "grad_norm": 0.6013728976249695,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.0497,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.036240385868856737,
1003
+ "grad_norm": 0.6633033156394958,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.3325,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.036501108069352105,
1010
+ "grad_norm": 0.673442006111145,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.3843,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.03676183026984748,
1017
+ "grad_norm": 0.6998249888420105,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2616,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.03702255247034285,
1024
+ "grad_norm": 0.6411647796630859,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.4398,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.03728327467083822,
1031
+ "grad_norm": 0.8868160247802734,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.4594,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.03754399687133359,
1038
+ "grad_norm": 0.6770927309989929,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.4373,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.03780471907182897,
1045
+ "grad_norm": 0.7107117772102356,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.5668,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.038065441272324335,
1052
+ "grad_norm": 0.7627034187316895,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.7207,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.03832616347281971,
1059
+ "grad_norm": 0.7622539401054382,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.489,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.038586885673315086,
1066
+ "grad_norm": 1.0797394514083862,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.9712,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.038847607873810454,
1073
+ "grad_norm": 1.0472699403762817,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.3663,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.03910833007430583,
1080
+ "grad_norm": 1.3272120952606201,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.6601,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.03910833007430583,
1087
+ "eval_loss": 1.1554970741271973,
1088
+ "eval_runtime": 121.5932,
1089
+ "eval_samples_per_second": 53.128,
1090
+ "eval_steps_per_second": 13.282,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.162557862182912e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null