prxy5606 commited on
Commit
2d3a03a
·
verified ·
1 Parent(s): 8a0f5d8

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 sha256:85b254c61639c15a27279fbcd7d02fe27df265e7bf123be81cd803e59ab17fb9
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b306333575fc7fd7bb28f0bd22ea0b5791041a3a2f01a1616ba2ea08acfd831c
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd0f24caa0f011b726275fba39ca3ff24b0a51d222bb1ee53c66272668e5e82f
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b65dc3a521ad03594ab8f9c63b3e882b6e5cf1b3ad7ed08c81c1d620fc62d6db
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cd95e3e69ab027a17941b689751bbaaf8ac8ce15be486ff02ba929972e3a5a9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4e2483b8926df6c53297e391517b8cd7f5ba3ae446c4a91d29ee2b4c539272c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c35f928f7dd9edebe7c94dc66def3d207bbcfc6fb428fd758a6bfcafaf8bae8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bc2ced7b135c293cfea73ba311aa2c673462445da1a975d4c5be5ca782caaa5
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.16238145530223846,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.7467248908296944,
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": 33.21,
732
  "eval_steps_per_second": 8.559,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.758016755040256e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.07863566279411316,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 2.6200873362445414,
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": 33.21,
732
  "eval_steps_per_second": 8.559,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.7641921397379914,
737
+ "grad_norm": 0.9521262049674988,
738
+ "learning_rate": 4.036438697259551e-05,
739
+ "loss": 0.1226,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.7816593886462884,
744
+ "grad_norm": 0.912953794002533,
745
+ "learning_rate": 3.941480638852948e-05,
746
+ "loss": 0.1147,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.7991266375545851,
751
+ "grad_norm": 1.0413082838058472,
752
+ "learning_rate": 3.846920646287799e-05,
753
+ "loss": 0.131,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.8165938864628821,
758
+ "grad_norm": 1.115757703781128,
759
+ "learning_rate": 3.752794279710094e-05,
760
+ "loss": 0.1041,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.8340611353711789,
765
+ "grad_norm": 0.8693847060203552,
766
+ "learning_rate": 3.6591369361968124e-05,
767
+ "loss": 0.065,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.8515283842794759,
772
+ "grad_norm": 0.7901813983917236,
773
+ "learning_rate": 3.5659838364445505e-05,
774
+ "loss": 0.0864,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.8689956331877728,
779
+ "grad_norm": 1.1693010330200195,
780
+ "learning_rate": 3.473370011524435e-05,
781
+ "loss": 0.1329,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.8864628820960698,
786
+ "grad_norm": 0.6798319816589355,
787
+ "learning_rate": 3.381330289708396e-05,
788
+ "loss": 0.0583,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.9039301310043668,
793
+ "grad_norm": 0.8059512972831726,
794
+ "learning_rate": 3.289899283371657e-05,
795
+ "loss": 0.079,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.9213973799126638,
800
+ "grad_norm": 2.1519033908843994,
801
+ "learning_rate": 3.199111375976449e-05,
802
+ "loss": 0.1282,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.9388646288209608,
807
+ "grad_norm": 1.3084039688110352,
808
+ "learning_rate": 3.109000709141788e-05,
809
+ "loss": 0.1078,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.9563318777292578,
814
+ "grad_norm": 1.7590997219085693,
815
+ "learning_rate": 3.019601169804216e-05,
816
+ "loss": 0.088,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.9737991266375547,
821
+ "grad_norm": 2.152207612991333,
822
+ "learning_rate": 2.9309463774743046e-05,
823
+ "loss": 0.1825,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.9912663755458515,
828
+ "grad_norm": 1.6330548524856567,
829
+ "learning_rate": 2.8430696715937337e-05,
830
+ "loss": 0.1104,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 2.0087336244541483,
835
+ "grad_norm": 3.343381404876709,
836
+ "learning_rate": 2.7560040989976892e-05,
837
+ "loss": 0.2211,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 2.0262008733624453,
842
+ "grad_norm": 0.38313835859298706,
843
+ "learning_rate": 2.6697824014873075e-05,
844
+ "loss": 0.0646,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 2.0436681222707422,
849
+ "grad_norm": 0.9553971886634827,
850
+ "learning_rate": 2.5844370035168073e-05,
851
+ "loss": 0.064,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 2.061135371179039,
856
+ "grad_norm": 0.6309722065925598,
857
+ "learning_rate": 2.500000000000001e-05,
858
+ "loss": 0.0499,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 2.078602620087336,
863
+ "grad_norm": 0.5666458010673523,
864
+ "learning_rate": 2.4165031442406855e-05,
865
+ "loss": 0.0624,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 2.096069868995633,
870
+ "grad_norm": 0.8651885390281677,
871
+ "learning_rate": 2.333977835991545e-05,
872
+ "loss": 0.0405,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 2.11353711790393,
877
+ "grad_norm": 0.6641396880149841,
878
+ "learning_rate": 2.25245510964597e-05,
879
+ "loss": 0.0363,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 2.131004366812227,
884
+ "grad_norm": 0.7574361562728882,
885
+ "learning_rate": 2.171965622567308e-05,
886
+ "loss": 0.0423,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 2.148471615720524,
891
+ "grad_norm": 1.8589038848876953,
892
+ "learning_rate": 2.0925396435598664e-05,
893
+ "loss": 0.0724,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 2.165938864628821,
898
+ "grad_norm": 1.456919550895691,
899
+ "learning_rate": 2.0142070414860704e-05,
900
+ "loss": 0.0459,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 2.183406113537118,
905
+ "grad_norm": 0.9130675792694092,
906
+ "learning_rate": 1.936997274033986e-05,
907
+ "loss": 0.0442,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 2.2008733624454146,
912
+ "grad_norm": 1.0100352764129639,
913
+ "learning_rate": 1.8609393766395085e-05,
914
+ "loss": 0.0608,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 2.2183406113537116,
919
+ "grad_norm": 0.5539523959159851,
920
+ "learning_rate": 1.7860619515673033e-05,
921
+ "loss": 0.0303,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 2.2358078602620086,
926
+ "grad_norm": 1.8237937688827515,
927
+ "learning_rate": 1.7123931571546827e-05,
928
+ "loss": 0.0489,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 2.2532751091703056,
933
+ "grad_norm": 0.9342569708824158,
934
+ "learning_rate": 1.639960697222388e-05,
935
+ "loss": 0.0792,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 2.2707423580786026,
940
+ "grad_norm": 0.4814267158508301,
941
+ "learning_rate": 1.5687918106563326e-05,
942
+ "loss": 0.0559,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 2.2882096069868996,
947
+ "grad_norm": 0.5614648461341858,
948
+ "learning_rate": 1.4989132611641576e-05,
949
+ "loss": 0.0691,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 2.3056768558951966,
954
+ "grad_norm": 0.6089550852775574,
955
+ "learning_rate": 1.4303513272105057e-05,
956
+ "loss": 0.0603,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 2.3231441048034935,
961
+ "grad_norm": 0.39180800318717957,
962
+ "learning_rate": 1.3631317921347563e-05,
963
+ "loss": 0.0422,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 2.3406113537117905,
968
+ "grad_norm": 1.3804267644882202,
969
+ "learning_rate": 1.297279934454978e-05,
970
+ "loss": 0.044,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 2.3580786026200875,
975
+ "grad_norm": 1.0875520706176758,
976
+ "learning_rate": 1.2328205183616965e-05,
977
+ "loss": 0.0495,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 2.3755458515283845,
982
+ "grad_norm": 0.661360502243042,
983
+ "learning_rate": 1.1697777844051105e-05,
984
+ "loss": 0.043,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 2.393013100436681,
989
+ "grad_norm": 0.48929262161254883,
990
+ "learning_rate": 1.1081754403791999e-05,
991
+ "loss": 0.0203,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 2.410480349344978,
996
+ "grad_norm": 0.6960212588310242,
997
+ "learning_rate": 1.0480366524062042e-05,
998
+ "loss": 0.0266,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 2.427947598253275,
1003
+ "grad_norm": 0.7719947099685669,
1004
+ "learning_rate": 9.893840362247809e-06,
1005
+ "loss": 0.0367,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 2.445414847161572,
1010
+ "grad_norm": 0.6129599213600159,
1011
+ "learning_rate": 9.322396486851626e-06,
1012
+ "loss": 0.0358,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 2.462882096069869,
1017
+ "grad_norm": 0.8176167607307434,
1018
+ "learning_rate": 8.766249794544662e-06,
1019
+ "loss": 0.0227,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 2.480349344978166,
1024
+ "grad_norm": 1.3852804899215698,
1025
+ "learning_rate": 8.225609429353187e-06,
1026
+ "loss": 0.0755,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 2.497816593886463,
1031
+ "grad_norm": 1.7854435443878174,
1032
+ "learning_rate": 7.700678704007947e-06,
1033
+ "loss": 0.1555,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 2.51528384279476,
1038
+ "grad_norm": 0.4705410301685333,
1039
+ "learning_rate": 7.191655023486682e-06,
1040
+ "loss": 0.0344,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 2.532751091703057,
1045
+ "grad_norm": 0.40318259596824646,
1046
+ "learning_rate": 6.698729810778065e-06,
1047
+ "loss": 0.0432,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 2.5502183406113534,
1052
+ "grad_norm": 0.33191582560539246,
1053
+ "learning_rate": 6.222088434895462e-06,
1054
+ "loss": 0.0197,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 2.567685589519651,
1059
+ "grad_norm": 0.3540843725204468,
1060
+ "learning_rate": 5.7619101411671095e-06,
1061
+ "loss": 0.0366,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 2.5851528384279474,
1066
+ "grad_norm": 0.30799436569213867,
1067
+ "learning_rate": 5.318367983829392e-06,
1068
+ "loss": 0.0201,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 2.6026200873362444,
1073
+ "grad_norm": 0.7724692225456238,
1074
+ "learning_rate": 4.891628760948114e-06,
1075
+ "loss": 0.0352,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 2.6200873362445414,
1080
+ "grad_norm": 0.599810004234314,
1081
+ "learning_rate": 4.4818529516926726e-06,
1082
+ "loss": 0.0345,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 2.6200873362445414,
1087
+ "eval_loss": 0.07863566279411316,
1088
+ "eval_runtime": 2.9153,
1089
+ "eval_samples_per_second": 33.272,
1090
+ "eval_steps_per_second": 8.575,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.128095383584768e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null