prxy5608 commited on
Commit
4816754
·
verified ·
1 Parent(s): eda9ab4

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 sha256:54b586d914bffe43989e64a7a972d734576515979b4fd3b18b410242cc15573d
3
  size 100690184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8514c2f55d3b25ec05e07d90a510688bb82e78ef326ad00dd6b3da6dc1a7e6
3
  size 100690184
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f4495a22a16797e10343a829912403dc1dc1970f8c08be4ce5fe6ab67419ada
3
  size 201488570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01700589404a3f7567f3562fb0e2fda71fca10cf39f83bf336183530ceedad81
3
  size 201488570
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e526310bce373701d6e61cd66e48906c34b08712cbadfdc8f13b3315f09997e3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c35c9a41778ec8fb45ffcbb61b3e4601f70cb4f1b3ac3540f9f1bb412c0fb5
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": 0.7785072326660156,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.18181818181818182,
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": 59.24,
732
  "eval_steps_per_second": 29.652,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7451217965875200.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6896986961364746,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.2727272727272727,
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": 59.24,
732
  "eval_steps_per_second": 29.652,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.18363636363636363,
737
+ "grad_norm": 83.87976837158203,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 2.4931,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.18545454545454546,
744
+ "grad_norm": 62.57492446899414,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 2.7229,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.18727272727272729,
751
+ "grad_norm": 44.38495635986328,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 2.6211,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.1890909090909091,
758
+ "grad_norm": 54.712833404541016,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 2.1997,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.19090909090909092,
765
+ "grad_norm": 49.44144058227539,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 2.1469,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.19272727272727272,
772
+ "grad_norm": 44.76526641845703,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 2.7389,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.19454545454545455,
779
+ "grad_norm": 47.95205307006836,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 2.6509,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.19636363636363635,
786
+ "grad_norm": 43.48308181762695,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 2.8425,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.19818181818181818,
793
+ "grad_norm": 45.31011962890625,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 2.9956,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.2,
800
+ "grad_norm": 47.43437957763672,
801
+ "learning_rate": 5e-05,
802
+ "loss": 2.7493,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.2018181818181818,
807
+ "grad_norm": 40.40293502807617,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 2.8543,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.20363636363636364,
814
+ "grad_norm": 49.42204666137695,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 3.1348,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.20545454545454545,
821
+ "grad_norm": 42.550025939941406,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 2.4712,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.20727272727272728,
828
+ "grad_norm": 39.86064147949219,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 2.49,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.20909090909090908,
835
+ "grad_norm": 39.12519454956055,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 2.7172,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.2109090909090909,
842
+ "grad_norm": 33.93404769897461,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 2.3934,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.21272727272727274,
849
+ "grad_norm": 42.115943908691406,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 2.597,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.21454545454545454,
856
+ "grad_norm": 61.48637771606445,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 2.6182,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.21636363636363637,
863
+ "grad_norm": 37.781768798828125,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 2.5236,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.21818181818181817,
870
+ "grad_norm": 40.604156494140625,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 3.1361,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.22,
877
+ "grad_norm": 43.32360076904297,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 3.1341,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.22181818181818183,
884
+ "grad_norm": 40.844425201416016,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 2.4682,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.22363636363636363,
891
+ "grad_norm": 80.41752624511719,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 2.5737,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.22545454545454546,
898
+ "grad_norm": 48.227821350097656,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 3.3177,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.22727272727272727,
905
+ "grad_norm": 45.7944221496582,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 2.9183,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.2290909090909091,
912
+ "grad_norm": 51.166900634765625,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 2.6203,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.2309090909090909,
919
+ "grad_norm": 46.844322204589844,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 2.8397,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.23272727272727273,
926
+ "grad_norm": 61.02446365356445,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 2.8248,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.23454545454545456,
933
+ "grad_norm": 65.25340270996094,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 3.2427,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.23636363636363636,
940
+ "grad_norm": 60.50672912597656,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 3.0476,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.2381818181818182,
947
+ "grad_norm": 58.63713836669922,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 3.0828,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.24,
954
+ "grad_norm": 69.12300872802734,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 3.5299,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.24181818181818182,
961
+ "grad_norm": 43.3862419128418,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 2.9089,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.24363636363636362,
968
+ "grad_norm": 55.379859924316406,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 2.5253,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.24545454545454545,
975
+ "grad_norm": 46.44770812988281,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 2.6508,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.24727272727272728,
982
+ "grad_norm": 94.80418395996094,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 3.1445,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.24909090909090909,
989
+ "grad_norm": 45.59507369995117,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 2.6856,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.2509090909090909,
996
+ "grad_norm": 41.788909912109375,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 3.0028,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.25272727272727274,
1003
+ "grad_norm": 48.725833892822266,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 3.396,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.2545454545454545,
1010
+ "grad_norm": 41.74631881713867,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 3.4218,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.25636363636363635,
1017
+ "grad_norm": 39.308189392089844,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 2.4569,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.2581818181818182,
1024
+ "grad_norm": 48.53035354614258,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 3.0169,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.26,
1031
+ "grad_norm": 58.768245697021484,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 3.017,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.26181818181818184,
1038
+ "grad_norm": 42.100189208984375,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 2.8048,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.2636363636363636,
1045
+ "grad_norm": 48.90083312988281,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 2.9452,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.26545454545454544,
1052
+ "grad_norm": 57.28050231933594,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 3.3012,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2672727272727273,
1059
+ "grad_norm": 41.389217376708984,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 3.5768,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.2690909090909091,
1066
+ "grad_norm": 40.396934509277344,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 3.341,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.27090909090909093,
1073
+ "grad_norm": 42.712406158447266,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 3.2837,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.2727272727272727,
1080
+ "grad_norm": 51.320068359375,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 3.9642,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.2727272727272727,
1087
+ "eval_loss": 0.6896986961364746,
1088
+ "eval_runtime": 15.5088,
1089
+ "eval_samples_per_second": 59.772,
1090
+ "eval_steps_per_second": 29.918,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.11768269488128e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null