alchemist69 commited on
Commit
2964aea
·
verified ·
1 Parent(s): 4ad1ab5

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 sha256:7d7cff9d4327afeb000b5b05832fedcb91871760c8ff57863f0aed7487c1fde4
3
  size 402688040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3768a80444b1a8954b1c5e6de41d08633550efe074f9a91b6d69bd8deebb364c
3
  size 402688040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:381a4d6c28f109116e7c4c2f22a836ee91b225b0afc2cfa1688a9a5aaa5ad981
3
  size 204773716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b418cd62874ab097b6fc3c81b0785a9b9b75cddda403db4e1b756806238c1b
3
  size 204773716
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7687a5793c4b8e8d4311c07dc43b2fe1967f6bc0b63e6bfc5f526d06f8e57f8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ef2d152e19b658fad19180c2d8f7228f31bce3373e8bc3f5a864902d41be02
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": 1.2084108591079712,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.006460156981814658,
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": 20.858,
732
  "eval_steps_per_second": 5.215,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7.5168001032192e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1874948740005493,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.009690235472721987,
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": 20.858,
732
  "eval_steps_per_second": 5.215,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.006524758551632805,
737
+ "grad_norm": 3.4843358993530273,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.6168,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0065893601214509516,
744
+ "grad_norm": 3.8861405849456787,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 6.3586,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.006653961691269097,
751
+ "grad_norm": 2.971803665161133,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 5.0865,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.006718563261087244,
758
+ "grad_norm": 3.0318257808685303,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 5.5612,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.006783164830905391,
765
+ "grad_norm": 3.5478341579437256,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.2137,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.006847766400723538,
772
+ "grad_norm": 2.6239843368530273,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 5.2318,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.006912367970541684,
779
+ "grad_norm": 2.3321309089660645,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 5.1254,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.006976969540359831,
786
+ "grad_norm": 2.8829903602600098,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 5.9701,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.007041571110177977,
793
+ "grad_norm": 2.490107297897339,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 5.769,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.007106172679996124,
800
+ "grad_norm": 2.349179267883301,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 4.4389,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.00717077424981427,
807
+ "grad_norm": 2.7239201068878174,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 5.6202,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.007235375819632417,
814
+ "grad_norm": 2.6781179904937744,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 5.2065,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.007299977389450564,
821
+ "grad_norm": 2.4534177780151367,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.6998,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.007364578959268711,
828
+ "grad_norm": 2.5321333408355713,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 5.4947,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.007429180529086856,
835
+ "grad_norm": 2.607844829559326,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 5.8001,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.007493782098905003,
842
+ "grad_norm": 2.3122150897979736,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 4.9553,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.00755838366872315,
849
+ "grad_norm": 2.250380039215088,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.2205,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.007622985238541297,
856
+ "grad_norm": 2.468526601791382,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 4.6147,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.007687586808359443,
863
+ "grad_norm": 1.8496919870376587,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 4.2098,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.00775218837817759,
870
+ "grad_norm": 2.204216718673706,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 4.9424,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.007816789947995737,
877
+ "grad_norm": 2.0269930362701416,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 4.7408,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.007881391517813884,
884
+ "grad_norm": 1.8584880828857422,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 4.6493,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.00794599308763203,
891
+ "grad_norm": 1.816282868385315,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 4.4366,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.008010594657450175,
898
+ "grad_norm": 2.3344907760620117,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 4.3588,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.008075196227268322,
905
+ "grad_norm": 2.0682172775268555,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 4.8055,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.008139797797086469,
912
+ "grad_norm": 2.1689302921295166,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 4.0556,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.008204399366904615,
919
+ "grad_norm": 2.067401170730591,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 4.7142,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.008269000936722762,
926
+ "grad_norm": 7.7647857666015625,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 4.8426,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.008333602506540909,
933
+ "grad_norm": 2.160715103149414,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 4.603,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.008398204076359056,
940
+ "grad_norm": 1.9710527658462524,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 4.0396,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.008462805646177202,
947
+ "grad_norm": 2.086228132247925,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 4.4088,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.008527407215995349,
954
+ "grad_norm": 2.2000558376312256,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 4.2839,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.008592008785813496,
961
+ "grad_norm": 1.9736944437026978,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 3.9798,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.008656610355631643,
968
+ "grad_norm": 2.1108694076538086,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 4.3453,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.00872121192544979,
975
+ "grad_norm": 1.995061993598938,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 3.778,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.008785813495267934,
982
+ "grad_norm": 1.9363799095153809,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 4.0557,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.008850415065086081,
989
+ "grad_norm": 2.284677505493164,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 3.7238,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.008915016634904228,
996
+ "grad_norm": 2.3371708393096924,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 4.1719,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.008979618204722374,
1003
+ "grad_norm": 2.2452025413513184,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.2773,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.009044219774540521,
1010
+ "grad_norm": 2.058542490005493,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 4.0987,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.009108821344358668,
1017
+ "grad_norm": 2.1121418476104736,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 4.2697,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.009173422914176815,
1024
+ "grad_norm": 2.3986308574676514,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 4.3015,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.009238024483994961,
1031
+ "grad_norm": 2.138062000274658,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 4.197,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.009302626053813108,
1038
+ "grad_norm": 2.2229645252227783,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 4.1962,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.009367227623631255,
1045
+ "grad_norm": 2.1185944080352783,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.2305,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.009431829193449402,
1052
+ "grad_norm": 2.213833808898926,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 4.5891,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.009496430763267547,
1059
+ "grad_norm": 2.2524938583374023,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 4.1974,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.009561032333085693,
1066
+ "grad_norm": 2.3482871055603027,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.9867,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.00962563390290384,
1073
+ "grad_norm": 2.639533281326294,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 4.3864,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.009690235472721987,
1080
+ "grad_norm": 2.1051063537597656,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 3.6859,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.009690235472721987,
1087
+ "eval_loss": 1.1874948740005493,
1088
+ "eval_runtime": 1250.6184,
1089
+ "eval_samples_per_second": 20.846,
1090
+ "eval_steps_per_second": 5.212,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.12752001548288e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null