0x1202 commited on
Commit
4c4ffa7
·
verified ·
1 Parent(s): 18ed885

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 sha256:5eff7e8051fe45024575fdca206a173050e5c610c8a3d8b09e8f1124eed870b9
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaabce04424669950de7c27705489f87312a1d9d6dafa924b47c2b63db60a6d5
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80fd4c24803380408f98dd6164edcfd4cbcbfe058b05b084bca4093a8f4c34c5
3
  size 156656510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e976b93fa894c51854f8621322b197c294ddcb086f0b4bf2d81c60a7bdb902a4
3
  size 156656510
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a52d446061c552ad02ca4ad278b8432cb824065d17599182ec3d5d4dbc32405
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5dd7b2179b65085a9026b46679a44e71f6057ecf7409b0f3684bf5fb48b88d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5487265586853027,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.13314447592068,
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": 36.002,
732
  "eval_steps_per_second": 18.122,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4939716760436736.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4917516708374023,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.6997167138810199,
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": 36.002,
732
  "eval_steps_per_second": 18.122,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.1444759206798867,
737
+ "grad_norm": 0.2477850615978241,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 1.4764,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.1558073654390935,
744
+ "grad_norm": 0.30012187361717224,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 1.3427,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.1671388101983002,
751
+ "grad_norm": 0.2721880376338959,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 1.4597,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.178470254957507,
758
+ "grad_norm": 0.30785053968429565,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 1.4804,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.1898016997167138,
765
+ "grad_norm": 0.34216204285621643,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 1.6197,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.2011331444759206,
772
+ "grad_norm": 0.3311666250228882,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 1.6815,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.2124645892351276,
779
+ "grad_norm": 0.30523356795310974,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 1.5614,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.2237960339943343,
786
+ "grad_norm": 0.34505927562713623,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 1.4657,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.2351274787535411,
793
+ "grad_norm": 0.36857518553733826,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.539,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.246458923512748,
800
+ "grad_norm": 0.4266189932823181,
801
+ "learning_rate": 5e-05,
802
+ "loss": 1.473,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.2577903682719547,
807
+ "grad_norm": 0.2451467663049698,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.5531,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.2691218130311614,
814
+ "grad_norm": 0.21580742299556732,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 1.4198,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.2804532577903682,
821
+ "grad_norm": 0.24123479425907135,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 1.4452,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.291784702549575,
828
+ "grad_norm": 0.2361007034778595,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 1.5802,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.3031161473087818,
835
+ "grad_norm": 0.23018887639045715,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.4528,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.3144475920679888,
842
+ "grad_norm": 0.2591703534126282,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.4171,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.3257790368271953,
849
+ "grad_norm": 0.22410644590854645,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 1.4474,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.3371104815864023,
856
+ "grad_norm": 0.25192803144454956,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.4302,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.348441926345609,
863
+ "grad_norm": 0.2527298331260681,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 1.4655,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.3597733711048159,
870
+ "grad_norm": 0.2601375877857208,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 1.4757,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.3711048158640227,
877
+ "grad_norm": 0.23596332967281342,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 1.4582,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.3824362606232294,
884
+ "grad_norm": 0.24836811423301697,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.4937,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.3937677053824362,
891
+ "grad_norm": 0.3072097897529602,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.4214,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.405099150141643,
898
+ "grad_norm": 0.28567826747894287,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 1.4633,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.41643059490085,
905
+ "grad_norm": 0.2974615693092346,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 1.4091,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.4277620396600565,
912
+ "grad_norm": 0.28619298338890076,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 1.3751,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.4390934844192635,
919
+ "grad_norm": 0.2666260600090027,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 1.4802,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.4504249291784703,
926
+ "grad_norm": 0.3570886552333832,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 1.3981,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.461756373937677,
933
+ "grad_norm": 0.3145367503166199,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.5997,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.4730878186968839,
940
+ "grad_norm": 0.3386094868183136,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 1.4661,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.4844192634560907,
947
+ "grad_norm": 0.3534667491912842,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 1.4785,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.4957507082152974,
954
+ "grad_norm": 0.3897930383682251,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 1.415,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.5070821529745042,
961
+ "grad_norm": 0.23832640051841736,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 1.4344,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.5184135977337112,
968
+ "grad_norm": 0.23151782155036926,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 1.4103,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.5297450424929178,
975
+ "grad_norm": 0.22246257960796356,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.4704,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.5410764872521248,
982
+ "grad_norm": 0.20327092707157135,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.5477,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.5524079320113313,
989
+ "grad_norm": 0.2647717297077179,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 1.4549,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.5637393767705383,
996
+ "grad_norm": 0.28701451420783997,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 1.3741,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.575070821529745,
1003
+ "grad_norm": 0.23964330554008484,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 1.355,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.5864022662889519,
1010
+ "grad_norm": 0.2663789689540863,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 1.348,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.5977337110481586,
1017
+ "grad_norm": 0.26375189423561096,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 1.5205,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.6090651558073654,
1024
+ "grad_norm": 0.2846963107585907,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 1.5513,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.6203966005665722,
1031
+ "grad_norm": 0.2618456184864044,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 1.4012,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.631728045325779,
1038
+ "grad_norm": 0.2383047491312027,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 1.3704,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.643059490084986,
1045
+ "grad_norm": 0.30709442496299744,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 1.525,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.6543909348441925,
1052
+ "grad_norm": 0.2546956539154053,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 1.4563,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.6657223796033995,
1059
+ "grad_norm": 0.27411651611328125,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 1.3791,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.677053824362606,
1066
+ "grad_norm": 0.24941976368427277,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 1.4491,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.688385269121813,
1073
+ "grad_norm": 0.3089727461338043,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 1.5384,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.6997167138810199,
1080
+ "grad_norm": 0.2955828309059143,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 1.5034,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.6997167138810199,
1087
+ "eval_loss": 1.4917516708374023,
1088
+ "eval_runtime": 4.1358,
1089
+ "eval_samples_per_second": 36.027,
1090
+ "eval_steps_per_second": 18.135,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 7411892805697536.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null