aleegis11 commited on
Commit
ad676f0
·
verified ·
1 Parent(s): c79a4b2

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 sha256:60e336f5eca6e61e067420944d22de1e90655466de8959edd3dd818ba745f581
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcb32ca33838626bcea03724e987cf148da66afb6d9d321847a7c775706836ae
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7d1e1416e22b52ce1e3efb6df2bfc8d41fbe19af0ccfacefee0c57ec659ad37
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5931f37b7279e2c1d7e213176a8757802d3af174794a51d4d29f4d9d9de2f6d9
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:c627e4e6f76b7352254079127d51cf6d7082a1df2dd7921b14a58f2a0cfc60fc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3641659bac30633584daeb206124fa7e0853a22ce5b8ea6d570e0d75fc7804e
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": 1.2312716245651245,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.13740982480247338,
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": 35.785,
732
  "eval_steps_per_second": 8.961,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.246701636550656e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.163150668144226,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.20611473720371007,
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": 35.785,
732
  "eval_steps_per_second": 8.961,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.1387839230504981,
737
+ "grad_norm": 0.2255360633134842,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.7779,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.14015802129852284,
744
+ "grad_norm": 0.23751790821552277,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.8338,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.14153211954654757,
751
+ "grad_norm": 0.2663083076477051,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.9188,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.1429062177945723,
758
+ "grad_norm": 0.22981339693069458,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.8188,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.14428031604259706,
765
+ "grad_norm": 0.236619770526886,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.8803,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1456544142906218,
772
+ "grad_norm": 0.23290015757083893,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.9059,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.14702851253864652,
779
+ "grad_norm": 0.19473782181739807,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.8494,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.14840261078667125,
786
+ "grad_norm": 0.26345762610435486,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.8652,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.14977670903469598,
793
+ "grad_norm": 0.17493213713169098,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.8151,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.1511508072827207,
800
+ "grad_norm": 0.18951790034770966,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.8168,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.15252490553074544,
807
+ "grad_norm": 0.18956202268600464,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.8934,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.1538990037787702,
814
+ "grad_norm": 0.212601900100708,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.9969,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.15527310202679492,
821
+ "grad_norm": 0.15459412336349487,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.8822,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.15664720027481965,
828
+ "grad_norm": 0.18324562907218933,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.9027,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.15802129852284438,
835
+ "grad_norm": 0.18034571409225464,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.9191,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.1593953967708691,
842
+ "grad_norm": 0.16426022350788116,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.9042,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.16076949501889384,
849
+ "grad_norm": 0.15972800552845,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.8766,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.16214359326691857,
856
+ "grad_norm": 0.15054263174533844,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.9411,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.16351769151494333,
863
+ "grad_norm": 0.15989775955677032,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.9101,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.16489178976296806,
870
+ "grad_norm": 0.169904425740242,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.8387,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.1662658880109928,
877
+ "grad_norm": 0.16550658643245697,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.9908,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.16763998625901752,
884
+ "grad_norm": 0.1593722254037857,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.8916,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.16901408450704225,
891
+ "grad_norm": 0.1593838334083557,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.9206,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.17038818275506698,
898
+ "grad_norm": 0.152430459856987,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.881,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1717622810030917,
905
+ "grad_norm": 0.18957607448101044,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.0454,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.17313637925111647,
912
+ "grad_norm": 0.18225038051605225,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.0129,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1745104774991412,
919
+ "grad_norm": 0.1942896544933319,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.0398,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.17588457574716593,
926
+ "grad_norm": 0.20318052172660828,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.0716,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.17725867399519066,
933
+ "grad_norm": 0.23516058921813965,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.0764,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1786327722432154,
940
+ "grad_norm": 0.22030310332775116,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.0809,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.18000687049124012,
947
+ "grad_norm": 0.2949303090572357,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.311,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.18138096873926485,
954
+ "grad_norm": 0.2638658583164215,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.1203,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.1827550669872896,
961
+ "grad_norm": 0.21188068389892578,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.8101,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.18412916523531433,
968
+ "grad_norm": 1.5809319019317627,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 3.1598,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.18550326348333906,
975
+ "grad_norm": 1.4560643434524536,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.7776,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.1868773617313638,
982
+ "grad_norm": 4.069778919219971,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.8172,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.18825145997938852,
989
+ "grad_norm": 3.78922700881958,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.4094,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.18962555822741325,
996
+ "grad_norm": 0.9479630589485168,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.7767,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.19099965647543798,
1003
+ "grad_norm": 0.9855109453201294,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.6067,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.19237375472346271,
1010
+ "grad_norm": 3.8103370666503906,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.5768,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.19374785297148747,
1017
+ "grad_norm": 3.6094367504119873,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.1034,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.1951219512195122,
1024
+ "grad_norm": 0.40120404958724976,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.0799,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.19649604946753693,
1031
+ "grad_norm": 0.2957104444503784,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.8669,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.19787014771556166,
1038
+ "grad_norm": 0.3517855107784271,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.1585,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.1992442459635864,
1045
+ "grad_norm": 0.2185845673084259,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.8003,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.20061834421161112,
1052
+ "grad_norm": 0.2852717638015747,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.8969,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.20199244245963585,
1059
+ "grad_norm": 0.2719075679779053,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.8089,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.2033665407076606,
1066
+ "grad_norm": 0.33422502875328064,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.2115,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.20474063895568534,
1073
+ "grad_norm": 0.29944148659706116,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.0766,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.20611473720371007,
1080
+ "grad_norm": 0.36896276473999023,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.3203,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.20611473720371007,
1087
+ "eval_loss": 1.163150668144226,
1088
+ "eval_runtime": 34.2819,
1089
+ "eval_samples_per_second": 35.762,
1090
+ "eval_steps_per_second": 8.955,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.876921334366208e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null