prxy5605 commited on
Commit
63309bc
·
verified ·
1 Parent(s): 90f4b9f

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 sha256:81a973d193312053a869634fc411f23cac12be03c65cb382078adb109f64ad29
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70984448dad236418db59dd100d00dddf6a6c0b5352c37ef88f0e4b552eb21ea
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63d173bb78399bc7edd07e12400a5df44ea2f231a2e2d8796c67cffd263e3b8b
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1ddcf3d25041495a3a365b6d54cdf63cb8ace0060e1e13a906220a6b27bd0cc
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:736ae02480f4960d6d5b47c03465d751c29b956ca31cb3049640818aca2810e1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d55c64147f73ae2a01dd020ef6dff0dd325bc80a0ff17e1d73c1f7d88c69605
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": 0.9467170834541321,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.34305317324185247,
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": 11.932,
732
  "eval_steps_per_second": 5.978,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4739279492572774e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8594623804092407,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5145797598627787,
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": 11.932,
732
  "eval_steps_per_second": 5.978,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.346483704974271,
737
+ "grad_norm": 6.344611644744873,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 4.4591,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.34991423670668953,
744
+ "grad_norm": 5.29261589050293,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 4.3903,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.35334476843910806,
751
+ "grad_norm": 3.7538249492645264,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 4.1005,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.3567753001715266,
758
+ "grad_norm": 3.1446287631988525,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 3.7796,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.3602058319039451,
765
+ "grad_norm": 2.960186719894409,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 3.916,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.36363636363636365,
772
+ "grad_norm": 3.2721056938171387,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 3.9345,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.3670668953687822,
779
+ "grad_norm": 3.109593629837036,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 3.6805,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.3704974271012007,
786
+ "grad_norm": 3.3663551807403564,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 4.1047,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.37392795883361923,
793
+ "grad_norm": 3.3839170932769775,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 3.7359,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.37735849056603776,
800
+ "grad_norm": 3.2243165969848633,
801
+ "learning_rate": 5e-05,
802
+ "loss": 3.369,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.38078902229845624,
807
+ "grad_norm": 3.484187364578247,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 3.868,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.38421955403087477,
814
+ "grad_norm": 3.4150843620300293,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 3.5268,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.3876500857632933,
821
+ "grad_norm": 3.528571367263794,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 3.4223,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.3910806174957118,
828
+ "grad_norm": 3.6814565658569336,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 3.5602,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.39451114922813035,
835
+ "grad_norm": 3.4944686889648438,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 3.3631,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.3979416809605489,
842
+ "grad_norm": 3.5598247051239014,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 3.2197,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.4013722126929674,
849
+ "grad_norm": 3.637119770050049,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 3.6207,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.40480274442538594,
856
+ "grad_norm": 3.621417760848999,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 3.66,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.40823327615780447,
863
+ "grad_norm": 3.71958065032959,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 3.4363,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.411663807890223,
870
+ "grad_norm": 3.881575107574463,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 3.6837,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.41509433962264153,
877
+ "grad_norm": 3.5961995124816895,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 3.4126,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.41852487135506006,
884
+ "grad_norm": 3.635561943054199,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 3.4925,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.4219554030874786,
891
+ "grad_norm": 3.558687448501587,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 3.1293,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.42538593481989706,
898
+ "grad_norm": 3.7333993911743164,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 3.1551,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.4288164665523156,
905
+ "grad_norm": 4.045219898223877,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 3.5025,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.4322469982847341,
912
+ "grad_norm": 4.082742691040039,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 3.7588,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.43567753001715265,
919
+ "grad_norm": 4.03236722946167,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 3.6083,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.4391080617495712,
926
+ "grad_norm": 4.0244879722595215,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 3.5657,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.4425385934819897,
933
+ "grad_norm": 3.9571797847747803,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 3.5047,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.44596912521440824,
940
+ "grad_norm": 4.1520161628723145,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 3.4308,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.44939965694682676,
947
+ "grad_norm": 3.731208086013794,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 3.3306,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.4528301886792453,
954
+ "grad_norm": 4.370545864105225,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 3.4649,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.4562607204116638,
961
+ "grad_norm": 4.4801025390625,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 3.3989,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.45969125214408235,
968
+ "grad_norm": 4.434890270233154,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 3.3249,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.4631217838765009,
975
+ "grad_norm": 4.163226127624512,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 3.2922,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.4665523156089194,
982
+ "grad_norm": 4.4532151222229,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 3.7554,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.4699828473413379,
989
+ "grad_norm": 4.65369987487793,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 3.5652,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.4734133790737564,
996
+ "grad_norm": 4.77457857131958,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 3.6568,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.47684391080617494,
1003
+ "grad_norm": 4.440027713775635,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 3.459,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.48027444253859347,
1010
+ "grad_norm": 5.082893371582031,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 3.4999,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.483704974271012,
1017
+ "grad_norm": 4.5789103507995605,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 3.4001,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.48713550600343053,
1024
+ "grad_norm": 4.885765552520752,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 3.5424,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.49056603773584906,
1031
+ "grad_norm": 5.264125347137451,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 3.5362,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.4939965694682676,
1038
+ "grad_norm": 4.9319539070129395,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 3.3161,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.4974271012006861,
1045
+ "grad_norm": 5.442240238189697,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 3.5072,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.5008576329331046,
1052
+ "grad_norm": 5.463189125061035,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 3.3095,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.5042881646655232,
1059
+ "grad_norm": 5.8514862060546875,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 3.3437,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.5077186963979416,
1066
+ "grad_norm": 6.340907096862793,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 3.4434,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.5111492281303602,
1073
+ "grad_norm": 7.861410140991211,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 4.1433,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5145797598627787,
1080
+ "grad_norm": 8.327228546142578,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 4.0453,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5145797598627787,
1087
+ "eval_loss": 0.8594623804092407,
1088
+ "eval_runtime": 41.113,
1089
+ "eval_samples_per_second": 11.943,
1090
+ "eval_steps_per_second": 5.984,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2144694189083853e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null