prxy5606 commited on
Commit
f63ea7b
·
verified ·
1 Parent(s): 443716d

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 sha256:6ab08cc8753db5b404a2dfbd2b62e687875538097eba9b61d80ff01ed41df61e
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48091c9a54fd90c725dbd9f460f68dd6dbaf04b09e02dc0f4e9559453c0a84a3
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e7ab145ad6c579a887fcbd334b4c33d3305a5b01bc768a7e95455d1319a8f33
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b35b633d34e013f822223091de3899221c70dfaa3ddc5653974a233c329874f
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:c90e39b11f3d39e6f2ff97c62e509cf60b136ec4942d26e54d564b21cacb4466
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4232f17d96925690067667b7fa4983410eb7f180b0b2200a6138930747d01dd
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": 1.7128827571868896,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.006625258799171843,
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": 57.855,
732
  "eval_steps_per_second": 14.465,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6903223937925120.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7021275758743286,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.009937888198757764,
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": 57.855,
732
  "eval_steps_per_second": 14.465,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0066915113871635614,
737
+ "grad_norm": 0.10286074876785278,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.6876,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.006757763975155279,
744
+ "grad_norm": 0.1276087909936905,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.7571,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.006824016563146998,
751
+ "grad_norm": 0.1294441670179367,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.6832,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.006890269151138716,
758
+ "grad_norm": 0.1463458240032196,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.9144,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.006956521739130435,
765
+ "grad_norm": 0.11742586642503738,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.881,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.007022774327122153,
772
+ "grad_norm": 0.1266813427209854,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.7635,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.007089026915113872,
779
+ "grad_norm": 0.12258177995681763,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.8283,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.00715527950310559,
786
+ "grad_norm": 0.12947456538677216,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.8947,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.007221532091097309,
793
+ "grad_norm": 0.12223499268293381,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.8042,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.007287784679089027,
800
+ "grad_norm": 0.1189243420958519,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.9209,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0073540372670807454,
807
+ "grad_norm": 0.13120344281196594,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.8912,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.007420289855072463,
814
+ "grad_norm": 0.12762673199176788,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.8247,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.007486542443064182,
821
+ "grad_norm": 0.12652021646499634,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.7644,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0075527950310559,
828
+ "grad_norm": 0.12737470865249634,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.8092,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.007619047619047619,
835
+ "grad_norm": 0.12595722079277039,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.8327,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.007685300207039338,
842
+ "grad_norm": 0.13216738402843475,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.7842,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.007751552795031056,
849
+ "grad_norm": 0.11884083598852158,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.755,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.007817805383022774,
856
+ "grad_norm": 0.12388221174478531,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.8129,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.007884057971014493,
863
+ "grad_norm": 0.127731591463089,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.6589,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.007950310559006211,
870
+ "grad_norm": 0.12784713506698608,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.7914,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.00801656314699793,
877
+ "grad_norm": 0.13297195732593536,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.8241,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.008082815734989647,
884
+ "grad_norm": 0.12336255609989166,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.6607,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.008149068322981366,
891
+ "grad_norm": 0.1255303919315338,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.6559,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.008215320910973085,
898
+ "grad_norm": 0.12798646092414856,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.7108,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.008281573498964804,
905
+ "grad_norm": 0.1266174167394638,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.7344,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.008347826086956521,
912
+ "grad_norm": 0.12649928033351898,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.6957,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.00841407867494824,
919
+ "grad_norm": 0.13522803783416748,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.6892,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.008480331262939959,
926
+ "grad_norm": 0.14272339642047882,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.8254,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.008546583850931678,
933
+ "grad_norm": 0.12243382632732391,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.597,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.008612836438923395,
940
+ "grad_norm": 0.1254020780324936,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.731,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.008679089026915113,
947
+ "grad_norm": 0.12628696858882904,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.7534,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.008745341614906832,
954
+ "grad_norm": 0.12439960241317749,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.696,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.008811594202898551,
961
+ "grad_norm": 0.12046002596616745,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.7372,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.00887784679089027,
968
+ "grad_norm": 0.12436595559120178,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.6194,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.008944099378881987,
975
+ "grad_norm": 0.1323857605457306,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.6794,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.009010351966873706,
982
+ "grad_norm": 0.13171963393688202,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.7782,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.009076604554865425,
989
+ "grad_norm": 0.13648442924022675,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.7369,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.009142857142857144,
996
+ "grad_norm": 0.14303649961948395,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.7502,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.00920910973084886,
1003
+ "grad_norm": 0.1271563470363617,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.6775,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.00927536231884058,
1010
+ "grad_norm": 0.13029299676418304,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.7709,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.009341614906832298,
1017
+ "grad_norm": 0.13401445746421814,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.6546,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.009407867494824017,
1024
+ "grad_norm": 0.1321835070848465,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.7146,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.009474120082815734,
1031
+ "grad_norm": 0.1340716928243637,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.7886,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.009540372670807453,
1038
+ "grad_norm": 0.1321353018283844,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.7399,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.009606625258799172,
1045
+ "grad_norm": 0.1309817135334015,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.7183,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.00967287784679089,
1052
+ "grad_norm": 0.14503782987594604,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.7645,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.009739130434782608,
1059
+ "grad_norm": 0.14578962326049805,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.6109,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.009805383022774327,
1066
+ "grad_norm": 0.15625157952308655,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.524,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.009871635610766046,
1073
+ "grad_norm": 0.18671369552612305,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.4527,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.009937888198757764,
1080
+ "grad_norm": 0.3633573651313782,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.4227,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.009937888198757764,
1087
+ "eval_loss": 1.7021275758743286,
1088
+ "eval_runtime": 439.8227,
1089
+ "eval_samples_per_second": 57.798,
1090
+ "eval_steps_per_second": 14.451,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.035483590688768e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null