lesso commited on
Commit
1178a4c
·
verified ·
1 Parent(s): 7b7dffd

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:bc4450456e428209fed6a9f910be8e2ffda4d6de663156479144261f095de5bd
3
  size 72936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ff3a93f9afafc81c90829f318608e63ed6b45fe8356425786d42bd846cbf5b1
3
  size 72936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7afcd819a48068c6c3755421597990e1b18a1d3ffc8554c56c8a64b6fc89615
3
  size 151106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:411e9ac3fe9c98184c851d57e5b1d8a628dd1caad89d3cdb3fb7ae212b866e4c
3
  size 151106
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb68b4d933f407fc169d8465a10c1ba8d22f46948e82239edb2283aaeb0a27a
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e38d9e525f7790b7e2fe0f598950624f973dbbb39aa0ad40167fc099b9d40c
3
  size 15984
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c176f023fc4bc7b64b14735744c93381ae37c2fb7d7d13ebe8235d0ed1b05f9
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9c5ee5e27f666d0042bac898d1c838b31653f183c04bbf53ecb406a784e3dd
3
  size 15984
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:826d85cca0d24c8713f1aa1300d2bb759fac390e64727beb53682cdd6d8aa6c9
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e4aa2f4acf9c089d4b3e8a1ca75ddbf88e4110c008ade5fc2cbccf30d4c72b
3
  size 15984
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0ba98a8093d8f8357b313af17ff94286d41a72aa47485b0d05efdd5d6495132
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8f8abba37b4ae938d370249f9673f8910e984b7ef4f4d9a399353a3f7bc3a3
3
  size 15984
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a20c0f89ca7f58eda7b6ab063126b28fbe8e0698e5edc060f51e51ea7d3446d
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:339e849f0ed31d48633840441bf59c6717ec4aab73f8b59923e20b88c91b0d32
3
  size 15984
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b5a9eeb3c49f2a3fc242c05cdade0cbbae6ff3e87b25cac7e94cb4ba49fd562
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7730fbadfcfbd42711011bdcf50e4246666f43355936dd5a417ab1fda26b7166
3
  size 15984
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44c4848811ec259ac5a2430c7e5b3843eb237ac5e4312cebf9c61a8346e8b76f
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:120c9b5e2753d2374e43cc710aea7ecae115d83dae9ee19e396be7cd90b4bd35
3
  size 15984
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c39eede1bbb36efb3e12c37350edee2e14e6b0a1b782f46190e15ebdea48d8a5
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f29b132d5d9d0d60a7173e09a69d22bbc193248d4743e3ed17a96ef52aaef252
3
  size 15984
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb09a39c6de2a486cc682371c416a0e1cf0414a01cda4f261ed6b472bbdffd62
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e618c561766e531a3b508498a52b6a60ed26e61c8d989456e9bc321d17c91c51
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 12.426092147827148,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.9607843137254903,
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": 866.219,
732
  "eval_steps_per_second": 27.699,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3085330022400.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 12.421979904174805,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 2.9411764705882355,
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": 866.219,
732
  "eval_steps_per_second": 27.699,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.9803921568627452,
737
+ "grad_norm": 0.12800978124141693,
738
+ "learning_rate": 3.672727272727273e-05,
739
+ "loss": 12.4221,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 2.0,
744
+ "grad_norm": 0.09714271128177643,
745
+ "learning_rate": 3.602097902097902e-05,
746
+ "loss": 12.4288,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 2.019607843137255,
751
+ "grad_norm": 0.07660553604364395,
752
+ "learning_rate": 3.531468531468531e-05,
753
+ "loss": 12.4372,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 2.0392156862745097,
758
+ "grad_norm": 0.07365182787179947,
759
+ "learning_rate": 3.460839160839161e-05,
760
+ "loss": 12.4342,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 2.0588235294117645,
765
+ "grad_norm": 0.08602866530418396,
766
+ "learning_rate": 3.39020979020979e-05,
767
+ "loss": 12.4331,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 2.0784313725490198,
772
+ "grad_norm": 0.09166587144136429,
773
+ "learning_rate": 3.319580419580419e-05,
774
+ "loss": 12.4296,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 2.0980392156862746,
779
+ "grad_norm": 0.0854063555598259,
780
+ "learning_rate": 3.2489510489510486e-05,
781
+ "loss": 12.4279,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 2.1176470588235294,
786
+ "grad_norm": 0.13535353541374207,
787
+ "learning_rate": 3.178321678321678e-05,
788
+ "loss": 12.4169,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 2.1372549019607843,
793
+ "grad_norm": 0.08088745176792145,
794
+ "learning_rate": 3.107692307692308e-05,
795
+ "loss": 12.432,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 2.156862745098039,
800
+ "grad_norm": 0.06271250545978546,
801
+ "learning_rate": 3.037062937062937e-05,
802
+ "loss": 12.4333,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 2.176470588235294,
807
+ "grad_norm": 0.07285593450069427,
808
+ "learning_rate": 2.9664335664335664e-05,
809
+ "loss": 12.4325,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 2.196078431372549,
814
+ "grad_norm": 0.06813765317201614,
815
+ "learning_rate": 2.895804195804196e-05,
816
+ "loss": 12.4286,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 2.215686274509804,
821
+ "grad_norm": 0.09649086743593216,
822
+ "learning_rate": 2.8251748251748255e-05,
823
+ "loss": 12.4253,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 2.235294117647059,
828
+ "grad_norm": 0.10359369218349457,
829
+ "learning_rate": 2.7545454545454544e-05,
830
+ "loss": 12.424,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 2.2549019607843137,
835
+ "grad_norm": 0.08479335904121399,
836
+ "learning_rate": 2.683916083916084e-05,
837
+ "loss": 12.43,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 2.2745098039215685,
842
+ "grad_norm": 0.061394382268190384,
843
+ "learning_rate": 2.6132867132867135e-05,
844
+ "loss": 12.4359,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 2.2941176470588234,
849
+ "grad_norm": 0.08093006908893585,
850
+ "learning_rate": 2.542657342657343e-05,
851
+ "loss": 12.4279,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 2.313725490196078,
856
+ "grad_norm": 0.0796235054731369,
857
+ "learning_rate": 2.4720279720279722e-05,
858
+ "loss": 12.4266,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 2.3333333333333335,
863
+ "grad_norm": 0.07345807552337646,
864
+ "learning_rate": 2.4013986013986014e-05,
865
+ "loss": 12.4301,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 2.3529411764705883,
870
+ "grad_norm": 0.08076856285333633,
871
+ "learning_rate": 2.330769230769231e-05,
872
+ "loss": 12.4252,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 2.372549019607843,
877
+ "grad_norm": 0.07977347820997238,
878
+ "learning_rate": 2.26013986013986e-05,
879
+ "loss": 12.4287,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 2.392156862745098,
884
+ "grad_norm": 0.05769919231534004,
885
+ "learning_rate": 2.1895104895104893e-05,
886
+ "loss": 12.4378,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 2.411764705882353,
891
+ "grad_norm": 0.061103228479623795,
892
+ "learning_rate": 2.118881118881119e-05,
893
+ "loss": 12.431,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 2.431372549019608,
898
+ "grad_norm": 0.07140219211578369,
899
+ "learning_rate": 2.048251748251748e-05,
900
+ "loss": 12.4293,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 2.450980392156863,
905
+ "grad_norm": 0.07010167092084885,
906
+ "learning_rate": 1.9776223776223776e-05,
907
+ "loss": 12.4295,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 2.4705882352941178,
912
+ "grad_norm": 0.07127075642347336,
913
+ "learning_rate": 1.9069930069930068e-05,
914
+ "loss": 12.4234,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 2.4901960784313726,
919
+ "grad_norm": 0.08472342044115067,
920
+ "learning_rate": 1.8363636363636364e-05,
921
+ "loss": 12.4188,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 2.5098039215686274,
926
+ "grad_norm": 0.06202932819724083,
927
+ "learning_rate": 1.7657342657342656e-05,
928
+ "loss": 12.4329,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 2.5294117647058822,
933
+ "grad_norm": 0.0649908259510994,
934
+ "learning_rate": 1.695104895104895e-05,
935
+ "loss": 12.429,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 2.549019607843137,
940
+ "grad_norm": 0.06271278858184814,
941
+ "learning_rate": 1.6244755244755243e-05,
942
+ "loss": 12.428,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 2.568627450980392,
947
+ "grad_norm": 0.06860791891813278,
948
+ "learning_rate": 1.553846153846154e-05,
949
+ "loss": 12.4257,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 2.588235294117647,
954
+ "grad_norm": 0.06407037377357483,
955
+ "learning_rate": 1.4832167832167832e-05,
956
+ "loss": 12.4273,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 2.607843137254902,
961
+ "grad_norm": 0.07560574263334274,
962
+ "learning_rate": 1.4125874125874128e-05,
963
+ "loss": 12.4194,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 2.627450980392157,
968
+ "grad_norm": 0.07092591375112534,
969
+ "learning_rate": 1.341958041958042e-05,
970
+ "loss": 12.4329,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 2.6470588235294117,
975
+ "grad_norm": 0.06500810384750366,
976
+ "learning_rate": 1.2713286713286715e-05,
977
+ "loss": 12.4296,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 2.6666666666666665,
982
+ "grad_norm": 0.05897223949432373,
983
+ "learning_rate": 1.2006993006993007e-05,
984
+ "loss": 12.4299,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 2.686274509803922,
989
+ "grad_norm": 0.06739623844623566,
990
+ "learning_rate": 1.13006993006993e-05,
991
+ "loss": 12.4266,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 2.7058823529411766,
996
+ "grad_norm": 0.06975847482681274,
997
+ "learning_rate": 1.0594405594405594e-05,
998
+ "loss": 12.4196,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 2.7254901960784315,
1003
+ "grad_norm": 0.0807594507932663,
1004
+ "learning_rate": 9.888111888111888e-06,
1005
+ "loss": 12.4253,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 2.7450980392156863,
1010
+ "grad_norm": 0.06619778275489807,
1011
+ "learning_rate": 9.181818181818182e-06,
1012
+ "loss": 12.4315,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 2.764705882352941,
1017
+ "grad_norm": 0.06023673340678215,
1018
+ "learning_rate": 8.475524475524476e-06,
1019
+ "loss": 12.4321,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 2.784313725490196,
1024
+ "grad_norm": 0.06361662596464157,
1025
+ "learning_rate": 7.76923076923077e-06,
1026
+ "loss": 12.4256,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 2.803921568627451,
1031
+ "grad_norm": 0.07309895008802414,
1032
+ "learning_rate": 7.062937062937064e-06,
1033
+ "loss": 12.4306,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 2.8235294117647056,
1038
+ "grad_norm": 0.0623571053147316,
1039
+ "learning_rate": 6.3566433566433575e-06,
1040
+ "loss": 12.4294,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 2.843137254901961,
1045
+ "grad_norm": 0.0636533796787262,
1046
+ "learning_rate": 5.65034965034965e-06,
1047
+ "loss": 12.4264,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 2.8627450980392157,
1052
+ "grad_norm": 0.08216053992509842,
1053
+ "learning_rate": 4.944055944055944e-06,
1054
+ "loss": 12.4216,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 2.8823529411764706,
1059
+ "grad_norm": 0.06114799901843071,
1060
+ "learning_rate": 4.237762237762238e-06,
1061
+ "loss": 12.4324,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 2.9019607843137254,
1066
+ "grad_norm": 0.06452635675668716,
1067
+ "learning_rate": 3.531468531468532e-06,
1068
+ "loss": 12.4265,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 2.9215686274509802,
1073
+ "grad_norm": 0.06488998979330063,
1074
+ "learning_rate": 2.825174825174825e-06,
1075
+ "loss": 12.4244,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 2.9411764705882355,
1080
+ "grad_norm": 0.06650799512863159,
1081
+ "learning_rate": 2.118881118881119e-06,
1082
+ "loss": 12.4224,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 2.9411764705882355,
1087
+ "eval_loss": 12.421979904174805,
1088
+ "eval_runtime": 0.7954,
1089
+ "eval_samples_per_second": 864.993,
1090
+ "eval_steps_per_second": 27.66,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4627995033600.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null