lesso commited on
Commit
95b54cd
·
verified ·
1 Parent(s): 6519cc9

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:e150424fba149f9feba1858803ff6ab46942ab8fec86117acbd07b4f2993fff9
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8638b7954d9c1f2fe60bede3d7a4b50cc014b85a1815d78ac5c061265f65e0f8
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d41e6f10e41d467f7a5505ba4ba5e0ad553f159b80a89b67ce9b7c1fcaa23971
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63366d7cc954d47a7b2733e2d651cf73d84dc42c4bbefb3066ea963f0db6574b
3
  size 71077780
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06dbf6779baa36433547d8aeeccc861b12f94ec17263114ec4a977eca85fd49c
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349dea0d239ae1677aa66454bd0fd4ef91728525407d36492e8250374fc2069e
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 sha256:33d7684dd513b6e5c166a4e399664b67fedcae8e60c041083572b7acbe501900
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba439ba426e7e73db788416d0cc9aeb77950dc972434443006442f97f7cd8f7
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 sha256:5d78c3829948a73746d0113a89daa425bc631ecef6fa1e6462047f5115bccf26
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aaf1f9a4ea718f13dd818771a4295f463658a2c7c8230086799fee34ada6da5
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:ec176d5d4daadfce72de71942ec2427128060e5123a85dffaadbf428b8d9bcaa
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d316aea143e5b297e6360773e7b74d2698399e9826476802cf37588cccfe102a
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 sha256:00630e67d4528bfd3be24d22917ce83226fd7d2e2969bf1a14b0aaadbf62b4e0
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbbe56f3587983b2728d27dd49143cf631b8a390e0c0d5da231dd901d54ff9f
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 sha256:5482fb9b07567aaf88e1b92ab3c7ede27144d213a846dcb766e9bf723cfbf4cc
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:182a60769f71e4caca6e4c09da81f4e4ea1aec5e0bf10e80d61da199b19acfe3
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 sha256:23b07f74839115bb41bef10206aeeeb52ce6c1c12d1a98f06304817864d5c60b
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f19d38cb3e8bfd8f312eed9561ddc5be8324423dc89e3b9982fbad5710a93eba
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 sha256:629097aec5245a39291725e580513c87359a111f42769f36e0f2648d7a958775
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a9f2caa5963767ab8f5ea757ac0f32d6a123100593bfa711b5e27b396507c7d
3
  size 15984
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6b2f615f21faa4fde4442b48613d92f84c55cd5ef4fb4d04d8e3f819305ce14
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d606eeb1aa97b417de3c30d0a970be83ac979e2c7cc0fa41135c63d459909e5
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.824101209640503,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.5502063273727648,
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": 360.291,
732
  "eval_steps_per_second": 11.337,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 5.4951036321792e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.7699949741363525,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.8253094910591472,
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": 360.291,
732
  "eval_steps_per_second": 11.337,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.5557083906464925,
737
+ "grad_norm": 0.34858810901641846,
738
+ "learning_rate": 5.262631578947368e-05,
739
+ "loss": 2.8144,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.5612104539202201,
744
+ "grad_norm": 0.3956449031829834,
745
+ "learning_rate": 5.209473684210527e-05,
746
+ "loss": 2.7376,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.5667125171939478,
751
+ "grad_norm": 0.3142583668231964,
752
+ "learning_rate": 5.1563157894736844e-05,
753
+ "loss": 2.7467,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.5722145804676754,
758
+ "grad_norm": 0.28212493658065796,
759
+ "learning_rate": 5.1031578947368426e-05,
760
+ "loss": 2.8129,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.5777166437414031,
765
+ "grad_norm": 0.3358825743198395,
766
+ "learning_rate": 5.05e-05,
767
+ "loss": 2.8636,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.5832187070151307,
772
+ "grad_norm": 0.5382664799690247,
773
+ "learning_rate": 4.9968421052631576e-05,
774
+ "loss": 2.8049,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.5887207702888583,
779
+ "grad_norm": 0.5411241054534912,
780
+ "learning_rate": 4.943684210526316e-05,
781
+ "loss": 2.7898,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.594222833562586,
786
+ "grad_norm": 0.6359642148017883,
787
+ "learning_rate": 4.890526315789474e-05,
788
+ "loss": 2.7842,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.5997248968363136,
793
+ "grad_norm": 0.4363643229007721,
794
+ "learning_rate": 4.8373684210526316e-05,
795
+ "loss": 2.7142,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.6052269601100413,
800
+ "grad_norm": 0.3082638084888458,
801
+ "learning_rate": 4.784210526315789e-05,
802
+ "loss": 2.8622,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.6107290233837689,
807
+ "grad_norm": 0.36496034264564514,
808
+ "learning_rate": 4.731052631578947e-05,
809
+ "loss": 2.8707,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.6162310866574966,
814
+ "grad_norm": 0.6148244738578796,
815
+ "learning_rate": 4.6778947368421055e-05,
816
+ "loss": 2.822,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.6217331499312242,
821
+ "grad_norm": 0.4229172170162201,
822
+ "learning_rate": 4.624736842105263e-05,
823
+ "loss": 2.9304,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.6272352132049519,
828
+ "grad_norm": 0.35635635256767273,
829
+ "learning_rate": 4.571578947368421e-05,
830
+ "loss": 2.6977,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.6327372764786795,
835
+ "grad_norm": 0.3787790834903717,
836
+ "learning_rate": 4.518421052631579e-05,
837
+ "loss": 2.7788,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.6382393397524071,
842
+ "grad_norm": 0.3218351900577545,
843
+ "learning_rate": 4.465263157894737e-05,
844
+ "loss": 2.8026,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.6437414030261348,
849
+ "grad_norm": 0.340280145406723,
850
+ "learning_rate": 4.412105263157895e-05,
851
+ "loss": 2.8456,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.6492434662998624,
856
+ "grad_norm": 0.47292360663414,
857
+ "learning_rate": 4.358947368421053e-05,
858
+ "loss": 2.8296,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.6547455295735901,
863
+ "grad_norm": 0.4561541974544525,
864
+ "learning_rate": 4.30578947368421e-05,
865
+ "loss": 2.8534,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.6602475928473177,
870
+ "grad_norm": 0.6516445875167847,
871
+ "learning_rate": 4.2526315789473685e-05,
872
+ "loss": 2.7088,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.6657496561210454,
877
+ "grad_norm": 0.6562978625297546,
878
+ "learning_rate": 4.199473684210527e-05,
879
+ "loss": 2.7653,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.671251719394773,
884
+ "grad_norm": 0.4485410451889038,
885
+ "learning_rate": 4.146315789473684e-05,
886
+ "loss": 2.7488,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.6767537826685007,
891
+ "grad_norm": 0.30714529752731323,
892
+ "learning_rate": 4.093157894736842e-05,
893
+ "loss": 2.8164,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.6822558459422283,
898
+ "grad_norm": 0.4019254148006439,
899
+ "learning_rate": 4.0400000000000006e-05,
900
+ "loss": 2.8171,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.687757909215956,
905
+ "grad_norm": 0.8390946388244629,
906
+ "learning_rate": 3.986842105263158e-05,
907
+ "loss": 2.7773,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.6932599724896836,
912
+ "grad_norm": 0.41926607489585876,
913
+ "learning_rate": 3.933684210526316e-05,
914
+ "loss": 2.7653,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.6987620357634112,
919
+ "grad_norm": 0.33970800042152405,
920
+ "learning_rate": 3.880526315789473e-05,
921
+ "loss": 2.6788,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.7042640990371389,
926
+ "grad_norm": 0.37370553612709045,
927
+ "learning_rate": 3.827368421052632e-05,
928
+ "loss": 2.7859,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.7097661623108665,
933
+ "grad_norm": 0.3301040828227997,
934
+ "learning_rate": 3.7742105263157896e-05,
935
+ "loss": 2.7552,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.7152682255845942,
940
+ "grad_norm": 0.33396825194358826,
941
+ "learning_rate": 3.721052631578947e-05,
942
+ "loss": 2.8731,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.7207702888583218,
947
+ "grad_norm": 0.5443733334541321,
948
+ "learning_rate": 3.6678947368421054e-05,
949
+ "loss": 2.834,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.7262723521320495,
954
+ "grad_norm": 0.3872360587120056,
955
+ "learning_rate": 3.6147368421052636e-05,
956
+ "loss": 2.7519,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.7317744154057771,
961
+ "grad_norm": 0.41256576776504517,
962
+ "learning_rate": 3.561578947368421e-05,
963
+ "loss": 2.6659,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.7372764786795049,
968
+ "grad_norm": 0.43341293931007385,
969
+ "learning_rate": 3.508421052631579e-05,
970
+ "loss": 2.7159,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.7427785419532325,
975
+ "grad_norm": 0.3737362325191498,
976
+ "learning_rate": 3.455263157894737e-05,
977
+ "loss": 2.8111,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.7482806052269602,
982
+ "grad_norm": 0.32392141222953796,
983
+ "learning_rate": 3.402105263157895e-05,
984
+ "loss": 2.8288,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.7537826685006878,
989
+ "grad_norm": 0.5164781212806702,
990
+ "learning_rate": 3.3489473684210526e-05,
991
+ "loss": 2.8044,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.7592847317744154,
996
+ "grad_norm": 0.37287527322769165,
997
+ "learning_rate": 3.295789473684211e-05,
998
+ "loss": 2.698,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.7647867950481431,
1003
+ "grad_norm": 0.3489149808883667,
1004
+ "learning_rate": 3.242631578947368e-05,
1005
+ "loss": 2.775,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.7702888583218707,
1010
+ "grad_norm": 0.31786078214645386,
1011
+ "learning_rate": 3.1894736842105265e-05,
1012
+ "loss": 2.6869,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.7757909215955984,
1017
+ "grad_norm": 0.29137033224105835,
1018
+ "learning_rate": 3.136315789473685e-05,
1019
+ "loss": 2.7781,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.781292984869326,
1024
+ "grad_norm": 0.38083139061927795,
1025
+ "learning_rate": 3.083157894736842e-05,
1026
+ "loss": 2.8099,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.7867950481430537,
1031
+ "grad_norm": 0.45200973749160767,
1032
+ "learning_rate": 3.0299999999999998e-05,
1033
+ "loss": 2.7964,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.7922971114167813,
1038
+ "grad_norm": 0.477425754070282,
1039
+ "learning_rate": 2.9768421052631577e-05,
1040
+ "loss": 2.8416,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.797799174690509,
1045
+ "grad_norm": 0.3879892826080322,
1046
+ "learning_rate": 2.923684210526316e-05,
1047
+ "loss": 2.65,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.8033012379642366,
1052
+ "grad_norm": 0.32230129837989807,
1053
+ "learning_rate": 2.8705263157894737e-05,
1054
+ "loss": 2.6491,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.8088033012379643,
1059
+ "grad_norm": 0.34207046031951904,
1060
+ "learning_rate": 2.8173684210526313e-05,
1061
+ "loss": 2.7093,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.8143053645116919,
1066
+ "grad_norm": 0.3115675747394562,
1067
+ "learning_rate": 2.7642105263157898e-05,
1068
+ "loss": 2.7619,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.8198074277854195,
1073
+ "grad_norm": 0.3595292270183563,
1074
+ "learning_rate": 2.7110526315789473e-05,
1075
+ "loss": 2.836,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.8253094910591472,
1080
+ "grad_norm": 0.7873729467391968,
1081
+ "learning_rate": 2.6578947368421052e-05,
1082
+ "loss": 2.8467,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.8253094910591472,
1087
+ "eval_loss": 2.7699949741363525,
1088
+ "eval_runtime": 6.5603,
1089
+ "eval_samples_per_second": 373.002,
1090
+ "eval_steps_per_second": 11.737,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 8.2426554482688e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null