bbytxt commited on
Commit
527ff2e
·
verified ·
1 Parent(s): 7b0544b

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 sha256:1a6dbb471de673b351cb915886d172d0cead6d12c8105a9a196c9776e74c0b60
3
  size 478211024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb473041d20d3446bed9d19751cff516974e1db13cc14da5ffaad55dc17fe18
3
  size 478211024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f06b526546b12361129cbf9907b53b58ec8d7ba4d40b2c4f114439d18c42bc34
3
  size 956679634
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30520bd398f7e3e077f3aee00df1c1e8a34d1fe616b55d0c5b1b5945a8e45b0
3
  size 956679634
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:333fb34de7627d3f9e97a4a74f0cc7987acea26fb643cbc10a4a40a965099bd3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b159081cdc30a3c0ed340684fc0f253cf8e92fd70d00d3b12e6d6e68b00953ae
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.090095043182373,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.6611570247933884,
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": 17.987,
732
  "eval_steps_per_second": 9.029,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 8.101566995654246e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0575369596481323,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.9917355371900827,
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": 17.987,
732
  "eval_steps_per_second": 9.029,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6677685950413224,
737
+ "grad_norm": 1.766390323638916,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 4.463,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.6743801652892562,
744
+ "grad_norm": 1.9048361778259277,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 5.3703,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.6809917355371901,
751
+ "grad_norm": 1.8197228908538818,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 4.9689,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.687603305785124,
758
+ "grad_norm": 2.086484432220459,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 5.6172,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.6942148760330579,
765
+ "grad_norm": 2.267761707305908,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 4.8357,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.7008264462809918,
772
+ "grad_norm": 2.259352445602417,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 5.1136,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.7074380165289256,
779
+ "grad_norm": 2.6360812187194824,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 5.1514,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.7140495867768595,
786
+ "grad_norm": 2.8661835193634033,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 4.3032,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.7206611570247934,
793
+ "grad_norm": 2.702547073364258,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 4.8666,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7272727272727273,
800
+ "grad_norm": 2.970484495162964,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 4.8789,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.7338842975206612,
807
+ "grad_norm": 3.8799359798431396,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 5.1477,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.740495867768595,
814
+ "grad_norm": 0.6784772276878357,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 3.4236,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.7471074380165289,
821
+ "grad_norm": 0.7395262718200684,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 3.885,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.7537190082644628,
828
+ "grad_norm": 0.7164163589477539,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 3.8037,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.7603305785123967,
835
+ "grad_norm": 0.7306711077690125,
836
+ "learning_rate": 5e-05,
837
+ "loss": 3.8429,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.7669421487603306,
842
+ "grad_norm": 0.7196017503738403,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 4.1837,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.7735537190082644,
849
+ "grad_norm": 0.7127442359924316,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 3.8733,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.7801652892561983,
856
+ "grad_norm": 0.7182602882385254,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 3.9125,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.7867768595041322,
863
+ "grad_norm": 0.7722130417823792,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 4.1602,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.7933884297520661,
870
+ "grad_norm": 0.8073102831840515,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 4.1581,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.8,
877
+ "grad_norm": 0.8239835500717163,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 4.1797,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.8066115702479338,
884
+ "grad_norm": 0.8800137639045715,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 4.2168,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.8132231404958677,
891
+ "grad_norm": 0.8760910034179688,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 4.4288,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.8198347107438017,
898
+ "grad_norm": 0.9671458601951599,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 4.2465,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.8264462809917356,
905
+ "grad_norm": 0.9589430689811707,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 4.6314,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.8330578512396695,
912
+ "grad_norm": 0.9631523489952087,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 3.8995,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.8396694214876033,
919
+ "grad_norm": 1.1293405294418335,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 4.4208,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.8462809917355372,
926
+ "grad_norm": 1.1248273849487305,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 4.797,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.8528925619834711,
933
+ "grad_norm": 1.1502659320831299,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 4.5282,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.859504132231405,
940
+ "grad_norm": 1.3296188116073608,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 4.5665,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.8661157024793389,
947
+ "grad_norm": 1.222717523574829,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 4.4934,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.8727272727272727,
954
+ "grad_norm": 1.3489303588867188,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 4.9627,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.8793388429752066,
961
+ "grad_norm": 1.3762129545211792,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 4.9849,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.8859504132231405,
968
+ "grad_norm": 1.4506964683532715,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 4.5126,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.8925619834710744,
975
+ "grad_norm": 1.541321039199829,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 4.6768,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.8991735537190083,
982
+ "grad_norm": 1.6167188882827759,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 4.4696,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.9057851239669421,
989
+ "grad_norm": 1.765872597694397,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 4.9427,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.912396694214876,
996
+ "grad_norm": 1.81801438331604,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 5.1971,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.9190082644628099,
1003
+ "grad_norm": 1.7761266231536865,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 3.5547,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.9256198347107438,
1010
+ "grad_norm": 1.9924731254577637,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 5.4103,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.9322314049586777,
1017
+ "grad_norm": 2.269597291946411,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 5.2679,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.9388429752066115,
1024
+ "grad_norm": 2.1679582595825195,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 5.2392,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.9454545454545454,
1031
+ "grad_norm": 2.2235004901885986,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 5.3694,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.9520661157024793,
1038
+ "grad_norm": 2.366504430770874,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 4.5467,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.9586776859504132,
1045
+ "grad_norm": 2.4724178314208984,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 4.0637,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.9652892561983472,
1052
+ "grad_norm": 2.8730733394622803,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 4.465,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.971900826446281,
1059
+ "grad_norm": 3.2861361503601074,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 5.3115,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.9785123966942149,
1066
+ "grad_norm": 3.9318833351135254,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 5.3298,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.9851239669421488,
1073
+ "grad_norm": 0.7852454781532288,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 3.8637,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.9917355371900827,
1080
+ "grad_norm": 1.412460446357727,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 4.5326,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.9917355371900827,
1087
+ "eval_loss": 1.0575369596481323,
1088
+ "eval_runtime": 14.1494,
1089
+ "eval_samples_per_second": 18.022,
1090
+ "eval_steps_per_second": 9.046,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.2086253793050624e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null