batrider32 commited on
Commit
4314800
·
verified ·
1 Parent(s): 56e741d

Training in progress, step 143, 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:a772895af0674c78f529613d48a13ce4a19de3178dff579381098d72e364e8e1
3
  size 402688040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84d61d681e7e80a9027a05abbd3a463c98a575c021aea95af1a1e4813b45de98
3
  size 402688040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01333238274b901d8cd95b330bc3df0142cf6822d763a8a45263daca612ed886
3
  size 204773716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5345b5a03311b455c7178d4e06ea9c75c66758b8c741b9db13b9962b54b52d1d
3
  size 204773716
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6af98e185be937357e78b4c9c80cfd4aa5d1cae1c41626e2afa41fe33ab55ef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de5528c051419207a57bdf2e3420692f5f38e624c4d233b5792724e1b23c77d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8dfd303229c43ed639c6c8c36fd4adecd086350683b07b23836cce1239ae5af
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d0666cc1e6439413c664e0cac65ac761c70b1daa12efc6cd9fa745898334af
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.5695301294326782,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.7017543859649122,
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 +731,307 @@
731
  "eval_samples_per_second": 13.539,
732
  "eval_steps_per_second": 3.385,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -754,12 +1055,12 @@
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
- "should_training_stop": false
758
  },
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7.761096106573824e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
  "best_metric": 0.5695301294326782,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.0035087719298246,
5
  "eval_steps": 50,
6
+ "global_step": 143,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
731
  "eval_samples_per_second": 13.539,
732
  "eval_steps_per_second": 3.385,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.7087719298245614,
737
+ "grad_norm": 1.0373730659484863,
738
+ "learning_rate": 2.2652592093878666e-05,
739
+ "loss": 2.3607,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.7157894736842105,
744
+ "grad_norm": 1.2274401187896729,
745
+ "learning_rate": 2.16715775847379e-05,
746
+ "loss": 2.7221,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.7228070175438597,
751
+ "grad_norm": 1.1129260063171387,
752
+ "learning_rate": 2.070636822698877e-05,
753
+ "loss": 2.4914,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.7298245614035088,
758
+ "grad_norm": 1.1670178174972534,
759
+ "learning_rate": 1.9757502535618137e-05,
760
+ "loss": 2.4814,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.7368421052631579,
765
+ "grad_norm": 1.482865810394287,
766
+ "learning_rate": 1.8825509907063327e-05,
767
+ "loss": 1.9552,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.743859649122807,
772
+ "grad_norm": 0.42632055282592773,
773
+ "learning_rate": 1.7910910323848433e-05,
774
+ "loss": 1.8684,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.7508771929824561,
779
+ "grad_norm": 0.4803990423679352,
780
+ "learning_rate": 1.7014214064472643e-05,
781
+ "loss": 1.8988,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.7578947368421053,
786
+ "grad_norm": 0.5016773343086243,
787
+ "learning_rate": 1.6135921418712956e-05,
788
+ "loss": 2.142,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.7649122807017544,
793
+ "grad_norm": 0.5679965019226074,
794
+ "learning_rate": 1.5276522408499567e-05,
795
+ "loss": 2.0002,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7719298245614035,
800
+ "grad_norm": 0.5109459757804871,
801
+ "learning_rate": 1.4436496514520254e-05,
802
+ "loss": 1.861,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.7789473684210526,
807
+ "grad_norm": 0.6065607666969299,
808
+ "learning_rate": 1.3616312408705689e-05,
809
+ "loss": 2.3742,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.7859649122807018,
814
+ "grad_norm": 0.7970262169837952,
815
+ "learning_rate": 1.281642769274552e-05,
816
+ "loss": 1.708,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.7929824561403509,
821
+ "grad_norm": 0.6211585998535156,
822
+ "learning_rate": 1.2037288642780576e-05,
823
+ "loss": 1.8207,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.8,
828
+ "grad_norm": 0.6198106408119202,
829
+ "learning_rate": 1.1279329960414048e-05,
830
+ "loss": 2.2564,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.8070175438596491,
835
+ "grad_norm": 0.6563048362731934,
836
+ "learning_rate": 1.0542974530180327e-05,
837
+ "loss": 2.4311,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.8140350877192982,
842
+ "grad_norm": 0.6321965456008911,
843
+ "learning_rate": 9.82863318360695e-06,
844
+ "loss": 2.2049,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.8210526315789474,
849
+ "grad_norm": 0.6662086248397827,
850
+ "learning_rate": 9.1367044700011e-06,
851
+ "loss": 2.5071,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.8280701754385965,
856
+ "grad_norm": 0.735116720199585,
857
+ "learning_rate": 8.46757443408886e-06,
858
+ "loss": 2.416,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.8350877192982457,
863
+ "grad_norm": 0.7504799962043762,
864
+ "learning_rate": 7.821616400630865e-06,
865
+ "loss": 2.5542,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.8421052631578947,
870
+ "grad_norm": 0.7176871299743652,
871
+ "learning_rate": 7.199190766135e-06,
872
+ "loss": 2.2668,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.8491228070175438,
877
+ "grad_norm": 0.6787253022193909,
878
+ "learning_rate": 6.600644797781847e-06,
879
+ "loss": 2.3853,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.856140350877193,
884
+ "grad_norm": 0.8250912427902222,
885
+ "learning_rate": 6.026312439675552e-06,
886
+ "loss": 2.5085,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.8631578947368421,
891
+ "grad_norm": 0.716204047203064,
892
+ "learning_rate": 5.476514126527771e-06,
893
+ "loss": 2.3238,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.8701754385964913,
898
+ "grad_norm": 0.7131749987602234,
899
+ "learning_rate": 4.951556604879048e-06,
900
+ "loss": 2.4683,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.8771929824561403,
905
+ "grad_norm": 0.7613798379898071,
906
+ "learning_rate": 4.4517327619569785e-06,
907
+ "loss": 2.4387,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.8842105263157894,
912
+ "grad_norm": 0.8111532926559448,
913
+ "learning_rate": 3.977321462266998e-06,
914
+ "loss": 2.5778,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.8912280701754386,
919
+ "grad_norm": 0.7677064538002014,
920
+ "learning_rate": 3.5285873920067157e-06,
921
+ "loss": 2.4661,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.8982456140350877,
926
+ "grad_norm": 1.030106782913208,
927
+ "learning_rate": 3.105780911390738e-06,
928
+ "loss": 2.8726,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.9052631578947369,
933
+ "grad_norm": 0.7944233417510986,
934
+ "learning_rate": 2.7091379149682685e-06,
935
+ "loss": 2.704,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.9122807017543859,
940
+ "grad_norm": 0.8583712577819824,
941
+ "learning_rate": 2.3388797000115427e-06,
942
+ "loss": 2.4029,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.9192982456140351,
947
+ "grad_norm": 0.9171978831291199,
948
+ "learning_rate": 1.995212843048372e-06,
949
+ "loss": 2.3883,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.9263157894736842,
954
+ "grad_norm": 0.8546057939529419,
955
+ "learning_rate": 1.6783290846078714e-06,
956
+ "loss": 2.1403,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.9333333333333333,
961
+ "grad_norm": 0.9682101607322693,
962
+ "learning_rate": 1.3884052222434718e-06,
963
+ "loss": 2.665,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.9403508771929825,
968
+ "grad_norm": 0.9316641092300415,
969
+ "learning_rate": 1.1256030118930727e-06,
970
+ "loss": 2.4537,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.9473684210526315,
975
+ "grad_norm": 1.0580928325653076,
976
+ "learning_rate": 8.900690776312281e-07,
977
+ "loss": 2.5195,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.9543859649122807,
982
+ "grad_norm": 0.92408686876297,
983
+ "learning_rate": 6.819348298638839e-07,
984
+ "loss": 2.3,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.9614035087719298,
989
+ "grad_norm": 0.9293452501296997,
990
+ "learning_rate": 5.013163920110864e-07,
991
+ "loss": 2.5365,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.968421052631579,
996
+ "grad_norm": 1.086668848991394,
997
+ "learning_rate": 3.4831453571879667e-07,
998
+ "loss": 2.2347,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.9754385964912281,
1003
+ "grad_norm": 1.0490437746047974,
1004
+ "learning_rate": 2.2301462463582557e-07,
1005
+ "loss": 1.7523,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.9824561403508771,
1010
+ "grad_norm": 1.5006375312805176,
1011
+ "learning_rate": 1.2548656678721406e-07,
1012
+ "loss": 1.843,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.9894736842105263,
1017
+ "grad_norm": 0.5156887769699097,
1018
+ "learning_rate": 5.578477557081074e-08,
1019
+ "loss": 1.8569,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.9964912280701754,
1024
+ "grad_norm": 0.731783926486969,
1025
+ "learning_rate": 1.394813939862849e-08,
1026
+ "loss": 2.3461,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.0035087719298246,
1031
+ "grad_norm": 0.9398931860923767,
1032
+ "learning_rate": 0.0,
1033
+ "loss": 2.1236,
1034
+ "step": 143
1035
  }
1036
  ],
1037
  "logging_steps": 1,
 
1055
  "should_evaluate": false,
1056
  "should_log": false,
1057
  "should_save": true,
1058
+ "should_training_stop": true
1059
  },
1060
  "attributes": {}
1061
  }
1062
  },
1063
+ "total_flos": 1.1124864152764416e+17,
1064
  "train_batch_size": 8,
1065
  "trial_name": null,
1066
  "trial_params": null