aleegis11 commited on
Commit
d66f4b5
·
verified ·
1 Parent(s): cc4e01d

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 sha256:1f8f33545b6182ea7ca6a2dbf446e76b07eb01c663cf20623fd2f013550305e7
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6bb0e1bb2fbf04140bfa58f64e579d4511edd2cd7d85d248a51df6e8bc6f55e
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5de4c8bdb760f4248d51b31f1de49e48465bb25866b0b18e48d9ad51076dd0d8
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f43ca0d40e6ff9498287df2fd04fd296ad1b6824907e04dce984b2d81a2cad
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19b2182cb83953982dabebc5b984012ec639efeb23d44240d09561e5c1fab864
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d11fd250d467037f6d5558c43ba391bc178b1a22aabba4062e8737df6fb0aed
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": 2.177105188369751,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.14732965009208104,
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": 34.026,
732
  "eval_steps_per_second": 8.506,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.728250925121536e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.1498870849609375,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.22099447513812154,
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": 34.026,
732
  "eval_steps_per_second": 8.506,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.14880294659300183,
737
+ "grad_norm": 0.5215460062026978,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.0475,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.15027624309392265,
744
+ "grad_norm": 0.6095430850982666,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.0592,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.15174953959484347,
751
+ "grad_norm": 0.5464235544204712,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.0183,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.15322283609576426,
758
+ "grad_norm": 0.5505194664001465,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.0362,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.15469613259668508,
765
+ "grad_norm": 0.5168222188949585,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.1467,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1561694290976059,
772
+ "grad_norm": 0.5152841806411743,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.1926,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.1576427255985267,
779
+ "grad_norm": 0.49555912613868713,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.0815,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.1591160220994475,
786
+ "grad_norm": 0.4678058624267578,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.1123,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.16058931860036832,
793
+ "grad_norm": 0.4995936453342438,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.0178,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.16206261510128914,
800
+ "grad_norm": 0.4865174889564514,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.0839,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.16353591160220995,
807
+ "grad_norm": 0.46470630168914795,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.1032,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.16500920810313074,
814
+ "grad_norm": 0.4676339626312256,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.2317,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.16648250460405156,
821
+ "grad_norm": 0.48408418893814087,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.1775,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.16795580110497238,
828
+ "grad_norm": 0.5317076444625854,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.207,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.1694290976058932,
835
+ "grad_norm": 0.5113919973373413,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.1026,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.170902394106814,
842
+ "grad_norm": 0.5057461261749268,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.1784,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.1723756906077348,
849
+ "grad_norm": 0.5517849326133728,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.1082,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.17384898710865562,
856
+ "grad_norm": 0.5440712571144104,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.1231,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.17532228360957644,
863
+ "grad_norm": 0.5332390666007996,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.1617,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.17679558011049723,
870
+ "grad_norm": 0.5297031998634338,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.1625,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.17826887661141805,
877
+ "grad_norm": 0.5557818412780762,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.2473,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.17974217311233887,
884
+ "grad_norm": 0.5619638562202454,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.1909,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.18121546961325966,
891
+ "grad_norm": 0.5676457285881042,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.2397,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.18268876611418047,
898
+ "grad_norm": 0.5630333423614502,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.1458,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1841620626151013,
905
+ "grad_norm": 0.5573937892913818,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.1902,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1856353591160221,
912
+ "grad_norm": 0.5926021933555603,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.2485,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1871086556169429,
919
+ "grad_norm": 0.5963653326034546,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.1565,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.18858195211786372,
926
+ "grad_norm": 0.6477805376052856,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.3577,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.19005524861878453,
933
+ "grad_norm": 0.5789662599563599,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.16,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.19152854511970535,
940
+ "grad_norm": 0.5775110721588135,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.1837,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.19300184162062614,
947
+ "grad_norm": 0.6224007606506348,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.3447,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.19447513812154696,
954
+ "grad_norm": 0.6071020364761353,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.3363,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.19594843462246778,
961
+ "grad_norm": 0.5970646142959595,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.2286,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1974217311233886,
968
+ "grad_norm": 0.5931335091590881,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.2033,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.19889502762430938,
975
+ "grad_norm": 0.6456011533737183,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.3814,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.2003683241252302,
982
+ "grad_norm": 0.6193873882293701,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.1756,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.20184162062615102,
989
+ "grad_norm": 0.611831545829773,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.2781,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.20331491712707184,
996
+ "grad_norm": 0.6075538992881775,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.2085,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.20478821362799263,
1003
+ "grad_norm": 0.6648210883140564,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.2603,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.20626151012891344,
1010
+ "grad_norm": 0.6589313745498657,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.3493,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.20773480662983426,
1017
+ "grad_norm": 0.6778343915939331,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.2593,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.20920810313075505,
1024
+ "grad_norm": 0.6866799592971802,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.2085,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.21068139963167587,
1031
+ "grad_norm": 0.6959302425384521,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.1706,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.2121546961325967,
1038
+ "grad_norm": 0.6998744010925293,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.349,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.2136279926335175,
1045
+ "grad_norm": 0.7252722382545471,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.2642,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2151012891344383,
1052
+ "grad_norm": 0.7717849016189575,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.2799,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2165745856353591,
1059
+ "grad_norm": 0.7438363432884216,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.1361,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.21804788213627993,
1066
+ "grad_norm": 0.8306782245635986,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.2135,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.21952117863720075,
1073
+ "grad_norm": 0.8231614828109741,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.228,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.22099447513812154,
1080
+ "grad_norm": 0.8910000920295715,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.0673,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.22099447513812154,
1087
+ "eval_loss": 2.1498870849609375,
1088
+ "eval_runtime": 33.6508,
1089
+ "eval_samples_per_second": 33.996,
1090
+ "eval_steps_per_second": 8.499,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.088974578548736e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null