nttx commited on
Commit
45abceb
·
verified ·
1 Parent(s): 671fa28

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 sha256:557f788ac8f9f84fb1529be7c94cd42b90c8100cb0ecb95b27ccc921b56ff6fb
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba41519dbde25d164865dc5e9497d8d36c30bb018f110d9411127e54e162951
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99104d29dfdc693f297ee344b476497765ac2850f0e40c790993caede0c0321a
3
  size 281824770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75742939dfcba11593731f81af812aa425082535e6d1eba914d56402eff7256d
3
  size 281824770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:662ed273284082075a9a8743bf567e4a0231d807d0b53d1e58173ef5539ba37d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:291c3b3e9fab4bfdf2e16adafa2beaea748a242782596ed00204a4801baff9a7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.066779136657715,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.005909990839514199,
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": 41.706,
732
  "eval_steps_per_second": 20.853,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7728482431795200.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.0016629695892334,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.008864986259271299,
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": 41.706,
732
  "eval_steps_per_second": 20.853,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.005969090747909341,
737
+ "grad_norm": 4.6523542404174805,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 2.4316,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.006028190656304483,
744
+ "grad_norm": 3.620638847351074,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 2.1098,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.006087290564699625,
751
+ "grad_norm": 3.4210116863250732,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 2.4399,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.006146390473094766,
758
+ "grad_norm": 3.1519083976745605,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 2.0912,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.006205490381489908,
765
+ "grad_norm": 2.7077889442443848,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 2.0573,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.00626459028988505,
772
+ "grad_norm": 3.0147182941436768,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 2.0726,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0063236901982801925,
779
+ "grad_norm": 3.317253351211548,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 1.97,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0063827901066753345,
786
+ "grad_norm": 3.3307950496673584,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 2.5252,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.006441890015070477,
793
+ "grad_norm": 3.0444374084472656,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 2.2743,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.006500989923465619,
800
+ "grad_norm": 2.982682704925537,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 2.3016,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.006560089831860761,
807
+ "grad_norm": 2.6371850967407227,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 2.0164,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.006619189740255903,
814
+ "grad_norm": 2.7763266563415527,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 2.0413,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.006678289648651045,
821
+ "grad_norm": 3.169642448425293,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 1.9156,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.006737389557046187,
828
+ "grad_norm": 2.8326120376586914,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 1.9181,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.006796489465441329,
835
+ "grad_norm": 2.9549639225006104,
836
+ "learning_rate": 5e-05,
837
+ "loss": 2.2077,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.006855589373836471,
842
+ "grad_norm": 2.7871503829956055,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 1.8016,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.006914689282231612,
849
+ "grad_norm": 2.778618812561035,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 2.1039,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.006973789190626754,
856
+ "grad_norm": 3.4482669830322266,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 2.248,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.007032889099021896,
863
+ "grad_norm": 2.6852567195892334,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 1.8628,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.007091989007417038,
870
+ "grad_norm": 2.594987154006958,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 1.975,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.00715108891581218,
877
+ "grad_norm": 3.144756555557251,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 2.2441,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.007210188824207322,
884
+ "grad_norm": 2.6541213989257812,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 2.1649,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.007269288732602464,
891
+ "grad_norm": 2.779205083847046,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 1.8455,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0073283886409976065,
898
+ "grad_norm": 2.9109785556793213,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 1.7731,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.0073874885493927485,
905
+ "grad_norm": 3.254918098449707,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 2.2217,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.007446588457787891,
912
+ "grad_norm": 3.0662970542907715,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 2.0891,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.007505688366183033,
919
+ "grad_norm": 3.069082021713257,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 1.9835,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.007564788274578175,
926
+ "grad_norm": 2.814826726913452,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 2.012,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.007623888182973317,
933
+ "grad_norm": 2.723910093307495,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 2.1048,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.007682988091368459,
940
+ "grad_norm": 2.600010395050049,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 1.6493,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0077420879997636,
947
+ "grad_norm": 4.922942638397217,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 2.025,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.007801187908158742,
954
+ "grad_norm": 3.4721429347991943,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 2.492,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.007860287816553884,
961
+ "grad_norm": 2.9339911937713623,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 1.8878,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.007919387724949026,
968
+ "grad_norm": 2.507004976272583,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 1.6928,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.007978487633344168,
975
+ "grad_norm": 2.646677017211914,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 1.9123,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.00803758754173931,
982
+ "grad_norm": 3.230515956878662,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 2.1234,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.008096687450134452,
989
+ "grad_norm": 2.8240675926208496,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 2.0608,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.008155787358529594,
996
+ "grad_norm": 3.0936813354492188,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 1.9963,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.008214887266924736,
1003
+ "grad_norm": 2.895601272583008,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 1.9524,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.008273987175319878,
1010
+ "grad_norm": 2.7313430309295654,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 1.848,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.00833308708371502,
1017
+ "grad_norm": 2.8361904621124268,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 1.9554,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.008392186992110163,
1024
+ "grad_norm": 2.7524335384368896,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 1.9239,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.008451286900505305,
1031
+ "grad_norm": 3.083930492401123,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 1.9522,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.008510386808900447,
1038
+ "grad_norm": 2.8543131351470947,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 1.9891,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.008569486717295589,
1045
+ "grad_norm": 2.8486130237579346,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 2.052,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.00862858662569073,
1052
+ "grad_norm": 2.6929166316986084,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 1.9629,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.008687686534085873,
1059
+ "grad_norm": 3.058091163635254,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 1.9577,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.008746786442481015,
1066
+ "grad_norm": 3.2105419635772705,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 2.0027,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.008805886350876157,
1073
+ "grad_norm": 2.93302845954895,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 1.977,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.008864986259271299,
1080
+ "grad_norm": 3.1761159896850586,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 1.8015,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.008864986259271299,
1087
+ "eval_loss": 2.0016629695892334,
1088
+ "eval_runtime": 684.7232,
1089
+ "eval_samples_per_second": 41.62,
1090
+ "eval_steps_per_second": 20.81,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.15927236476928e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null