prxy5606 commited on
Commit
03c4067
·
verified ·
1 Parent(s): 0e1fdd5

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 sha256:51424c28086f94e19dc131077ecadd0d4390629ed8f6408bdb3d22bfd68141b7
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053fb5047a1147faa850e4fa68da0dced2f8a74d096439ad3cc186952fbad822
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:950bbaa108344976f14cf502a4c69a9af03ac17552ceab8f01a16e60c4680880
3
  size 156656510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:542979aee16612859c4869883b781a2c37e3118ea0e9dd492a4723c670023f7b
3
  size 156656510
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf69b39deaf4ceca685dfbcc23736d2b58b7133cb9b3922c08857d6baece73ab
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b41a52b97ddb68065be69b6fe530ce0d6a484a406f1702250b019f3cdfff6d5
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": 1.9593321084976196,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.017115960633290545,
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": 37.872,
732
  "eval_steps_per_second": 18.936,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3850414190493696.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.9431641101837158,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.025673940949935817,
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": 37.872,
732
  "eval_steps_per_second": 18.936,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.01728712023962345,
737
+ "grad_norm": 0.11763519048690796,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 1.8203,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.017458279845956354,
744
+ "grad_norm": 0.1114693209528923,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 1.8145,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01762943945228926,
751
+ "grad_norm": 0.1230073869228363,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 1.8229,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.017800599058622166,
758
+ "grad_norm": 0.11512916535139084,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 1.7874,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.01797175866495507,
765
+ "grad_norm": 0.10919209569692612,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 1.7337,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.018142918271287976,
772
+ "grad_norm": 0.1077539324760437,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 1.8302,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.01831407787762088,
779
+ "grad_norm": 0.11689794063568115,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 1.9384,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01848523748395379,
786
+ "grad_norm": 0.11336947977542877,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 1.7964,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.018656397090286693,
793
+ "grad_norm": 0.12187959998846054,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.9133,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.018827556696619598,
800
+ "grad_norm": 0.11696886271238327,
801
+ "learning_rate": 5e-05,
802
+ "loss": 1.8401,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.018998716302952502,
807
+ "grad_norm": 0.12245535105466843,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.9705,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.01916987590928541,
814
+ "grad_norm": 0.128287672996521,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 1.9326,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.019341035515618315,
821
+ "grad_norm": 0.1252676546573639,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 1.9558,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.01951219512195122,
828
+ "grad_norm": 0.11466590315103531,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 1.8353,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.019683354728284124,
835
+ "grad_norm": 0.10190092772245407,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.796,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.01985451433461703,
842
+ "grad_norm": 0.12567828595638275,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.9864,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.020025673940949937,
849
+ "grad_norm": 0.11949620395898819,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 2.049,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.02019683354728284,
856
+ "grad_norm": 0.09391652792692184,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.7955,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.020367993153615746,
863
+ "grad_norm": 0.10908495634794235,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 1.9891,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.02053915275994865,
870
+ "grad_norm": 0.10338300466537476,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 1.9437,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.02071031236628156,
877
+ "grad_norm": 0.09718688577413559,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 1.8637,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.020881471972614463,
884
+ "grad_norm": 0.10134649276733398,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.996,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.021052631578947368,
891
+ "grad_norm": 0.09256803244352341,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.8434,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.021223791185280273,
898
+ "grad_norm": 0.1016881987452507,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 1.9534,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.02139495079161318,
905
+ "grad_norm": 0.09520836174488068,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 1.8564,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.021566110397946085,
912
+ "grad_norm": 0.10661575943231583,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 2.0337,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.02173727000427899,
919
+ "grad_norm": 0.10315674543380737,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 2.0366,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.021908429610611894,
926
+ "grad_norm": 0.10116354376077652,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 1.9307,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.022079589216944803,
933
+ "grad_norm": 0.09762448072433472,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.9752,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.022250748823277707,
940
+ "grad_norm": 0.09820623695850372,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 1.9644,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.022421908429610612,
947
+ "grad_norm": 0.10763833671808243,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 2.062,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.022593068035943516,
954
+ "grad_norm": 0.10071827471256256,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 1.9037,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.022764227642276424,
961
+ "grad_norm": 0.10233649611473083,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 2.01,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.02293538724860933,
968
+ "grad_norm": 0.10517492145299911,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 1.9178,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.023106546854942234,
975
+ "grad_norm": 0.1058327928185463,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.8554,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.02327770646127514,
982
+ "grad_norm": 0.11381185799837112,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.9393,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.023448866067608043,
989
+ "grad_norm": 0.12022625654935837,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 1.9708,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.02362002567394095,
996
+ "grad_norm": 0.12125593423843384,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 1.8177,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.023791185280273856,
1003
+ "grad_norm": 0.12773887813091278,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 2.058,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.02396234488660676,
1010
+ "grad_norm": 0.12078281491994858,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 2.0104,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.024133504492939665,
1017
+ "grad_norm": 0.13929595053195953,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 1.8098,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.024304664099272573,
1024
+ "grad_norm": 0.1575964242219925,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 1.7819,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.024475823705605478,
1031
+ "grad_norm": 0.16842733323574066,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 1.9769,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.024646983311938382,
1038
+ "grad_norm": 0.16018804907798767,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 1.8699,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.024818142918271287,
1045
+ "grad_norm": 0.1840139478445053,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 1.8096,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.024989302524604195,
1052
+ "grad_norm": 0.1963106095790863,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 1.9096,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.0251604621309371,
1059
+ "grad_norm": 0.26290199160575867,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 2.0225,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.025331621737270004,
1066
+ "grad_norm": 0.36925578117370605,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 2.1319,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.02550278134360291,
1073
+ "grad_norm": 0.43525442481040955,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 2.0081,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.025673940949935817,
1080
+ "grad_norm": 0.6942906379699707,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 2.3969,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.025673940949935817,
1087
+ "eval_loss": 1.9431641101837158,
1088
+ "eval_runtime": 259.5615,
1089
+ "eval_samples_per_second": 37.91,
1090
+ "eval_steps_per_second": 18.955,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5784891945910272.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null