aleegis09 commited on
Commit
fa7b1d0
·
verified ·
1 Parent(s): 649e3f9

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 sha256:64b637a8b68ca754daaa572b554283b357e408e38725060576d01a1855f1ee54
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb4a3845cec732435eae19bd9fc490107dc5f0c27b8f7194cef6f882da91ebc
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75ba79923f0d2081ef950d62190f8a6aa30895e9cc5d3ea228f7057b0231d4e8
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f553ab6f623b7e1c8d4d1f4cd96d060d55b5f04704dbd939ccbb64fff708151
3
  size 71077780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bdce1b62653920efb107d01fbfbbc15f020eb094e3e32bf1adf2353b4c8c89d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e419abb33e5965a9108b65ed539b0cf588c2eee884f45c1f0d98c9563d107696
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.6617826223373413,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.007699711260827719,
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": 61.146,
732
  "eval_steps_per_second": 15.288,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7263840113786880.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6281191110610962,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.011549566891241578,
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": 61.146,
732
  "eval_steps_per_second": 15.288,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.007776708373435996,
737
+ "grad_norm": 0.35076311230659485,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.089,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.007853705486044273,
744
+ "grad_norm": 0.650016725063324,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.3453,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.00793070259865255,
751
+ "grad_norm": 0.7631750106811523,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.526,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.008007699711260828,
758
+ "grad_norm": 0.3784090578556061,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.7359,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.008084696823869105,
765
+ "grad_norm": 0.36930137872695923,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.9003,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.008161693936477383,
772
+ "grad_norm": 0.35330313444137573,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.4841,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.008238691049085659,
779
+ "grad_norm": 0.4115749001502991,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.6368,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.008315688161693936,
786
+ "grad_norm": 0.4099835753440857,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.4487,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.008392685274302213,
793
+ "grad_norm": 0.44452518224716187,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.6096,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.00846968238691049,
800
+ "grad_norm": 0.43074649572372437,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.6728,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.008546679499518768,
807
+ "grad_norm": 0.4479566812515259,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.7046,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.008623676612127045,
814
+ "grad_norm": 0.39167529344558716,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.6256,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.008700673724735323,
821
+ "grad_norm": 0.3582574129104614,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.6341,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0087776708373436,
828
+ "grad_norm": 0.38528570532798767,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.7033,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.008854667949951878,
835
+ "grad_norm": 0.4378786087036133,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.7897,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.008931665062560153,
842
+ "grad_norm": 0.37775465846061707,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.4565,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.00900866217516843,
849
+ "grad_norm": 0.4391094446182251,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.5815,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.009085659287776708,
856
+ "grad_norm": 0.3900553584098816,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.3528,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.009162656400384986,
863
+ "grad_norm": 0.33789750933647156,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.3735,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.009239653512993263,
870
+ "grad_norm": 0.447671502828598,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.7737,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.00931665062560154,
877
+ "grad_norm": 0.33383631706237793,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.6931,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.009393647738209818,
884
+ "grad_norm": 0.37362706661224365,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.32,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.009470644850818095,
891
+ "grad_norm": 0.3910726010799408,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.7376,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.00954764196342637,
898
+ "grad_norm": 0.40764570236206055,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.5815,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.009624639076034648,
905
+ "grad_norm": 0.3827970623970032,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.9008,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.009701636188642926,
912
+ "grad_norm": 0.3509701192378998,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.618,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.009778633301251203,
919
+ "grad_norm": 0.39370638132095337,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.499,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.00985563041385948,
926
+ "grad_norm": 0.4084733724594116,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.7108,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.009932627526467758,
933
+ "grad_norm": 0.3492693603038788,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.7682,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.010009624639076035,
940
+ "grad_norm": 0.30398228764533997,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.3685,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.010086621751684312,
947
+ "grad_norm": 0.36415332555770874,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.9469,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.01016361886429259,
954
+ "grad_norm": 0.31978699564933777,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.5461,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.010240615976900866,
961
+ "grad_norm": 0.35391509532928467,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.5201,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.010317613089509143,
968
+ "grad_norm": 0.4085399806499481,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.9432,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.01039461020211742,
975
+ "grad_norm": 0.3640378713607788,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.7573,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.010471607314725698,
982
+ "grad_norm": 0.3177947998046875,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.4524,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.010548604427333975,
989
+ "grad_norm": 0.3547707796096802,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.9194,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.010625601539942253,
996
+ "grad_norm": 0.3579770028591156,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.9036,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.01070259865255053,
1003
+ "grad_norm": 0.34160175919532776,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.6782,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.010779595765158807,
1010
+ "grad_norm": 0.3050762116909027,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.8355,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.010856592877767083,
1017
+ "grad_norm": 0.37603259086608887,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.5958,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.01093358999037536,
1024
+ "grad_norm": 0.39835038781166077,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.5733,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.011010587102983638,
1031
+ "grad_norm": 0.3856360912322998,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.6747,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.011087584215591915,
1038
+ "grad_norm": 0.3523198664188385,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.7633,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.011164581328200193,
1045
+ "grad_norm": 0.42687007784843445,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.5168,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.01124157844080847,
1052
+ "grad_norm": 0.3382810056209564,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.6476,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.011318575553416747,
1059
+ "grad_norm": 0.3363308608531952,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.7707,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.011395572666025025,
1066
+ "grad_norm": 0.3740534782409668,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.8251,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.011472569778633302,
1073
+ "grad_norm": 0.3728982210159302,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.8595,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.011549566891241578,
1080
+ "grad_norm": 0.6287648677825928,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.6698,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.011549566891241578,
1087
+ "eval_loss": 1.6281191110610962,
1088
+ "eval_runtime": 358.2264,
1089
+ "eval_samples_per_second": 61.062,
1090
+ "eval_steps_per_second": 15.267,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.09043462701056e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null