0x1202 commited on
Commit
bcf4e79
·
verified ·
1 Parent(s): ef3868f

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 sha256:54ed7b8b42d40f11c2f580c9cd262dde4db53db7ceb1f262a12f59ade9e7c817
3
  size 800116456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccefee88c54541f301311c86f1be0803483435c3b0c9c054cd730f79b3d434f8
3
  size 800116456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06ad5de9ed4603ab87a7f8290603f0e90d2034d9825d3520c566ea9bf2cc046e
3
  size 1600457770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540ff9580f88d769a1b032df546ce751b81e4def2d9abbd50c573c15b1dadcc2
3
  size 1600457770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9471442a7716775dcadd3b7b25518aa54b25a0063da9ab1ee48e034cea1d67dd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087da13190edd4196442c151ef6484e93ffd9a7810a35817267db14c20356567
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": 4.623364448547363,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.039545229856648545,
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": 10.865,
732
  "eval_steps_per_second": 5.434,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5671904691657114e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.9510750770568848,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.05931784478497281,
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": 10.865,
732
  "eval_steps_per_second": 5.434,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.039940682155215027,
737
+ "grad_norm": 18.333959579467773,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 3.9954,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.040336134453781515,
744
+ "grad_norm": 19.20036506652832,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 3.7772,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.040731586752348,
751
+ "grad_norm": 12.907011985778809,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 3.6466,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.041127039050914485,
758
+ "grad_norm": 9.121061325073242,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 3.3037,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.04152249134948097,
765
+ "grad_norm": 6.192619323730469,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 3.4751,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.041917943648047455,
772
+ "grad_norm": 5.470525741577148,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 3.2908,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.04231339594661394,
779
+ "grad_norm": 4.912865161895752,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 3.3674,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.042708848245180425,
786
+ "grad_norm": 6.219501495361328,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 3.3247,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.043104300543746914,
793
+ "grad_norm": 5.533361911773682,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 3.2192,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.043499752842313395,
800
+ "grad_norm": 5.150146961212158,
801
+ "learning_rate": 5e-05,
802
+ "loss": 3.2276,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.043895205140879884,
807
+ "grad_norm": 6.297917366027832,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 3.2143,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.044290657439446365,
814
+ "grad_norm": 4.9847092628479,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 3.3206,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.044686109738012854,
821
+ "grad_norm": 5.420544624328613,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 3.3323,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.045081562036579335,
828
+ "grad_norm": 5.19870138168335,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 3.4153,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.045477014335145824,
835
+ "grad_norm": 5.492611408233643,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 3.4046,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.045872466633712305,
842
+ "grad_norm": 5.3474626541137695,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 3.3075,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.046267918932278794,
849
+ "grad_norm": 5.2586565017700195,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 3.2221,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.04666337123084528,
856
+ "grad_norm": 5.411025524139404,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 3.395,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.047058823529411764,
863
+ "grad_norm": 5.472652912139893,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 3.5103,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.04745427582797825,
870
+ "grad_norm": 6.056737899780273,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 3.3631,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.047849728126544734,
877
+ "grad_norm": 5.721058368682861,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 3.6028,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.04824518042511122,
884
+ "grad_norm": 5.954742908477783,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 3.2906,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.048640632723677704,
891
+ "grad_norm": 6.200694561004639,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 3.6514,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.04903608502224419,
898
+ "grad_norm": 5.939252853393555,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 3.3949,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.049431537320810674,
905
+ "grad_norm": 5.715896129608154,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 3.4874,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.04982698961937716,
912
+ "grad_norm": 6.621534824371338,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 3.622,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.05022244191794365,
919
+ "grad_norm": 5.691868782043457,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 3.3411,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.05061789421651013,
926
+ "grad_norm": 7.734787940979004,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 3.4587,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.05101334651507662,
933
+ "grad_norm": 7.939478397369385,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 3.657,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0514087988136431,
940
+ "grad_norm": 6.357771873474121,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 3.768,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.05180425111220959,
947
+ "grad_norm": 6.53624153137207,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 3.7699,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.05219970341077607,
954
+ "grad_norm": 6.4100775718688965,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 3.4689,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.05259515570934256,
961
+ "grad_norm": 7.020034313201904,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 3.8192,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.05299060800790904,
968
+ "grad_norm": 5.715200424194336,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 3.504,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.05338606030647553,
975
+ "grad_norm": 7.633635520935059,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 3.4469,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.05378151260504202,
982
+ "grad_norm": 7.177755832672119,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 3.7712,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.0541769649036085,
989
+ "grad_norm": 7.435923099517822,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 3.4619,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.05457241720217499,
996
+ "grad_norm": 6.788026332855225,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 3.618,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.05496786950074147,
1003
+ "grad_norm": 7.051691055297852,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 3.6792,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.05536332179930796,
1010
+ "grad_norm": 7.430070400238037,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 3.7134,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.05575877409787444,
1017
+ "grad_norm": 8.32129192352295,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 3.6942,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.05615422639644093,
1024
+ "grad_norm": 7.975091457366943,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 3.6997,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.05654967869500741,
1031
+ "grad_norm": 7.947182655334473,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 3.5279,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0569451309935739,
1038
+ "grad_norm": 9.00294017791748,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 4.1178,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.05734058329214039,
1045
+ "grad_norm": 9.13553524017334,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 4.1206,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.05773603559070687,
1052
+ "grad_norm": 10.592865943908691,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 3.7745,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.05813148788927336,
1059
+ "grad_norm": 8.685091972351074,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 4.1589,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.05852694018783984,
1066
+ "grad_norm": 9.462773323059082,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 4.2342,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.05892239248640633,
1073
+ "grad_norm": 16.12278938293457,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 4.337,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.05931784478497281,
1080
+ "grad_norm": 25.154678344726562,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 4.3972,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.05931784478497281,
1087
+ "eval_loss": 3.9510750770568848,
1088
+ "eval_runtime": 391.2119,
1089
+ "eval_samples_per_second": 10.887,
1090
+ "eval_steps_per_second": 5.445,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.3488316009191834e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null