prxy5605 commited on
Commit
8b71cb8
·
verified ·
1 Parent(s): 67cbb69

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:cfa6aecdf945141616491475645884311f932238d1e8c1d4201968d1f3981a8a
3
  size 478211024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2936a2a917b5a5c6a0ff7271ca5e7d2cef92a929290aa0529179b1721c9bd964
3
  size 478211024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d09d40ce238bfc441f2153dda41de263418f8734256ad7e473a9489f9b81f48c
3
  size 243337876
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d76b3de574c3f2c92a4e84b5353bd47e8ff47690014c79320c0e8e264f3d3612
3
  size 243337876
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b42c68f97d7b0018168f6a95c4a6b98ecdff94459b024c8d4b3f57391e3802e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841d38bf09523a37963fde18fced9537b8682f7f857b2dfda22db9787168b5f4
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": 1.2805209159851074,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.172514619883041,
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": 10.099,
732
  "eval_steps_per_second": 2.525,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.510781724131328e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2639923095703125,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.7573099415204678,
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": 10.099,
732
  "eval_steps_per_second": 2.525,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.1842105263157894,
737
+ "grad_norm": 1.3263887166976929,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.1145,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.195906432748538,
744
+ "grad_norm": 0.7568484544754028,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 4.7292,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.2076023391812865,
751
+ "grad_norm": 0.7868157029151917,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 4.9724,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.219298245614035,
758
+ "grad_norm": 0.8283912539482117,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 4.5678,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.2309941520467835,
765
+ "grad_norm": 0.7498999238014221,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.1414,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.2426900584795322,
772
+ "grad_norm": 0.7905023097991943,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 4.3368,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.2543859649122808,
779
+ "grad_norm": 0.6527309417724609,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 4.9133,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.2660818713450293,
786
+ "grad_norm": 0.6032450199127197,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 4.579,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.2777777777777777,
793
+ "grad_norm": 0.6000065207481384,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 4.4797,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.2894736842105263,
800
+ "grad_norm": 0.6161346435546875,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.2997,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.301169590643275,
807
+ "grad_norm": 0.6743441224098206,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 4.7612,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.3128654970760234,
814
+ "grad_norm": 0.6210641860961914,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 4.8589,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.3245614035087718,
821
+ "grad_norm": 0.7048709988594055,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.5511,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.3362573099415205,
828
+ "grad_norm": 0.690811812877655,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 4.4486,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.3479532163742691,
835
+ "grad_norm": 0.7149151563644409,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 4.888,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.3596491228070176,
842
+ "grad_norm": 0.6492061614990234,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 5.1674,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.371345029239766,
849
+ "grad_norm": 0.6934666633605957,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 4.7724,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.3830409356725146,
856
+ "grad_norm": 0.6952803134918213,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 4.8122,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.3947368421052633,
863
+ "grad_norm": 0.7041831016540527,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 4.9574,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.4064327485380117,
870
+ "grad_norm": 0.7406746745109558,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 4.6055,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.4181286549707601,
877
+ "grad_norm": 0.7634146809577942,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 4.9763,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.4298245614035088,
884
+ "grad_norm": 0.8683531284332275,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 4.6887,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.4415204678362574,
891
+ "grad_norm": 0.7926579713821411,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.0066,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.4532163742690059,
898
+ "grad_norm": 0.8141331672668457,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 4.7194,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.4649122807017543,
905
+ "grad_norm": 0.7802368998527527,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 3.9383,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.476608187134503,
912
+ "grad_norm": 0.8326878547668457,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 4.421,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.4883040935672516,
919
+ "grad_norm": 0.8888916969299316,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 4.3634,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.5,
926
+ "grad_norm": 0.7237643599510193,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 4.7557,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.5116959064327484,
933
+ "grad_norm": 0.6778761744499207,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 4.5118,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.523391812865497,
940
+ "grad_norm": 0.7118635773658752,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.1603,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.5350877192982457,
947
+ "grad_norm": 0.685716450214386,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 4.7323,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.5467836257309941,
954
+ "grad_norm": 0.8787785172462463,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 4.9417,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.5584795321637426,
961
+ "grad_norm": 0.7456165552139282,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 4.9567,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.5701754385964912,
968
+ "grad_norm": 0.6835184097290039,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 4.5495,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.5818713450292399,
975
+ "grad_norm": 0.6832260489463806,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 4.9867,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.5935672514619883,
982
+ "grad_norm": 0.7048373818397522,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 5.1378,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.6052631578947367,
989
+ "grad_norm": 0.7293301224708557,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 4.7399,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.6169590643274854,
996
+ "grad_norm": 0.6833894848823547,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 5.0154,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.628654970760234,
1003
+ "grad_norm": 0.7147215008735657,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.7814,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.6403508771929824,
1010
+ "grad_norm": 0.7362138032913208,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 4.9131,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.6520467836257309,
1017
+ "grad_norm": 0.7377339005470276,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 4.7527,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.6637426900584795,
1024
+ "grad_norm": 0.7660468220710754,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 4.462,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.6754385964912282,
1031
+ "grad_norm": 0.7579042315483093,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 4.8809,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.6871345029239766,
1038
+ "grad_norm": 0.7728883028030396,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 4.9308,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.698830409356725,
1045
+ "grad_norm": 0.7957561612129211,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.9666,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.7105263157894737,
1052
+ "grad_norm": 0.8299893140792847,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 4.5053,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.7222222222222223,
1059
+ "grad_norm": 0.8418483734130859,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 4.1139,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.7339181286549707,
1066
+ "grad_norm": 0.8716121315956116,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.5639,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.7456140350877192,
1073
+ "grad_norm": 0.7277250289916992,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 4.8218,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.7573099415204678,
1080
+ "grad_norm": 0.7173898220062256,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 4.4455,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.7573099415204678,
1087
+ "eval_loss": 1.2639923095703125,
1088
+ "eval_runtime": 14.2483,
1089
+ "eval_samples_per_second": 10.106,
1090
+ "eval_steps_per_second": 2.527,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.266172586196992e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null