prxy5605 commited on
Commit
b05acbe
·
verified ·
1 Parent(s): 93ef059

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:e46deb5f47b2e75f7005e553797a8003f2e3a5c5fd95560fdb21f5d24903afa6
3
  size 479005064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5fe6b323c5c431a9fe7b2365551383c668bafa20bc59e25ea23a6657a3129b
3
  size 479005064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e9dd8ccca39ba5c7932daded2fdbbcc9cc65f07a1f100149ba68981fa8f3f69
3
  size 958299770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773f4b8f81ceb2f8000c773274a54429e4c401251fe8651f27e8c748a5822267
3
  size 958299770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f9f0802e6e749168560e6c9986384a27f97e33cdb8b8f802220fa706649da58
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b0efd76b5c1399691974b27a501e9bc8dc25c0878f7e420c5dee32746036bf
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": 5.2339911460876465,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.015228426395939,
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": 18.93,
732
  "eval_steps_per_second": 9.465,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 5.681942422880256e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 5.212484836578369,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.5228426395939088,
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": 18.93,
732
  "eval_steps_per_second": 9.465,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.0253807106598984,
737
+ "grad_norm": 0.36876264214515686,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 5.3701,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.0355329949238579,
744
+ "grad_norm": 0.37881383299827576,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 5.1475,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.0456852791878173,
751
+ "grad_norm": 0.4124298691749573,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 5.2639,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.0558375634517767,
758
+ "grad_norm": 0.4313642680644989,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 5.2658,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.0659898477157361,
765
+ "grad_norm": 0.3469761312007904,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 5.1731,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.0761421319796955,
772
+ "grad_norm": 0.34174656867980957,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 5.2532,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.0862944162436547,
779
+ "grad_norm": 0.37279707193374634,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 5.3232,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.0964467005076142,
786
+ "grad_norm": 0.34107351303100586,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 5.2014,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.1065989847715736,
793
+ "grad_norm": 0.44603461027145386,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 5.274,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.116751269035533,
800
+ "grad_norm": 0.43816447257995605,
801
+ "learning_rate": 5e-05,
802
+ "loss": 5.2644,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.1269035532994924,
807
+ "grad_norm": 0.42787858843803406,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 5.182,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.1370558375634519,
814
+ "grad_norm": 0.4469396471977234,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 5.1906,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.1472081218274113,
821
+ "grad_norm": 0.47741401195526123,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 5.208,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.1573604060913705,
828
+ "grad_norm": 0.5933973789215088,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 5.056,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.16751269035533,
835
+ "grad_norm": 0.5861052870750427,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 5.1204,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.1776649746192893,
842
+ "grad_norm": 0.6024320125579834,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 5.1356,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.1878172588832487,
849
+ "grad_norm": 0.5369526147842407,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 5.2165,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.1979695431472082,
856
+ "grad_norm": 0.4957830309867859,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 5.1409,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.2081218274111676,
863
+ "grad_norm": 0.5669883489608765,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 5.1294,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.218274111675127,
870
+ "grad_norm": 0.6567976474761963,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 5.127,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.2284263959390862,
877
+ "grad_norm": 0.7601398825645447,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 4.9877,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.2385786802030456,
884
+ "grad_norm": 0.8807834982872009,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 5.2077,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.248730964467005,
891
+ "grad_norm": 0.9801356196403503,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 4.9937,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.2588832487309645,
898
+ "grad_norm": 0.7310280799865723,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 5.2336,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.2690355329949239,
905
+ "grad_norm": 0.560065507888794,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 5.4395,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.2791878172588833,
912
+ "grad_norm": 0.39355024695396423,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 5.0604,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.2893401015228427,
919
+ "grad_norm": 0.3939688503742218,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 5.2652,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.299492385786802,
926
+ "grad_norm": 0.38597550988197327,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 5.1938,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.3096446700507614,
933
+ "grad_norm": 0.4252302050590515,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 5.1874,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.3197969543147208,
940
+ "grad_norm": 0.4855193793773651,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 5.273,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.3299492385786802,
947
+ "grad_norm": 0.5743886232376099,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 5.2788,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.3401015228426396,
954
+ "grad_norm": 0.4098842740058899,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 5.1825,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.350253807106599,
961
+ "grad_norm": 0.3755365014076233,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 5.1837,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.3604060913705585,
968
+ "grad_norm": 0.4349859356880188,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 5.2206,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.3705583756345177,
975
+ "grad_norm": 0.48483696579933167,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 5.2736,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.380710659898477,
982
+ "grad_norm": 0.5594541430473328,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 5.1473,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.3908629441624365,
989
+ "grad_norm": 0.478778213262558,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 5.1136,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.401015228426396,
996
+ "grad_norm": 0.47473740577697754,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 5.1958,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.4111675126903553,
1003
+ "grad_norm": 0.504795491695404,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 5.0851,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.4213197969543148,
1010
+ "grad_norm": 0.4611382484436035,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 5.1284,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.4314720812182742,
1017
+ "grad_norm": 0.49524998664855957,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 5.2106,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.4416243654822334,
1024
+ "grad_norm": 0.4873555302619934,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 5.1443,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.451776649746193,
1031
+ "grad_norm": 0.5808872580528259,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 5.0184,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.4619289340101522,
1038
+ "grad_norm": 0.695599377155304,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 5.2417,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.4720812182741116,
1045
+ "grad_norm": 0.7416836023330688,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 5.0167,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.482233502538071,
1052
+ "grad_norm": 0.9077966213226318,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 5.3683,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.4923857868020305,
1059
+ "grad_norm": 0.7044989466667175,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 4.8825,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.50253807106599,
1066
+ "grad_norm": 0.5296655893325806,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 5.17,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.512690355329949,
1073
+ "grad_norm": 0.47559142112731934,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 5.4245,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.5228426395939088,
1080
+ "grad_norm": 0.4813889265060425,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 5.1568,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.5228426395939088,
1087
+ "eval_loss": 5.212484836578369,
1088
+ "eval_runtime": 8.7715,
1089
+ "eval_samples_per_second": 18.925,
1090
+ "eval_steps_per_second": 9.462,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 8.527359598657536e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null