lesso commited on
Commit
313f800
·
verified ·
1 Parent(s): 4340617

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 sha256:72321aef3cac08cb5691556c7f996af2e8f905bdbafb67a06522eedede54d646
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50623187d5ed0d7748c05449ab95fa89704c299b9b08334a46094e117024af0c
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acb5e0a340acfa95dd7f674bfd09566c8a3b3ea5c4ac406cbfae7cf305bec674
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:575b73ca69f449cfe67adbceda2d260fe18a97164c66bd0b17099d4771231c99
3
  size 325339796
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d032da55b0d588784f098ef9da86f8fa5038f36584c0445a8bc0862951fcdc88
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a388b1d01624e031945e9bb400e94ad30d284639d859e041d88bc9037fbd3e
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:e6a86c031cd4f806f2e61b19c2f3266d137191b016f53cc7dd4fd7983edb08b0
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7df857d6c883df0e7ab0a4d7f10d1b49fdfe185dd902b9eb9bee4d0a7a9c8c6
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:e47483786ecab0ace61acbd3053f91aceab5503c204b9afc707e2b6710f0ba68
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b09aea1a1dacf0faf58178cbbc1b67d823fa18b28ccf24853234e7d2c25c3ce0
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 sha256:29b54e328be6bb78d2b1d344c89d1e37942497b0a3297280b63b122aa4ecab79
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5a2fec68b1dcac3681fa9dc1b0747f1e0e9383db6968fcbb4f9403db80a0d5
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:c188bf65d4fa78189596f5435c5a8020b408f06e8b6736a2990a0ecc5a29fa41
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff4ffb98dec4b7d519362649a25b2a5864ce1fd3746c8b32c229ec85a571b681
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:b01480906c986e5da7e22664014a39c0998e7853e12947315bd8a1aa927aeec5
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc5c0954766a659d962137f64bbe3f7af0f6b0374e5a0bf7e9789c5eeb70498
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 sha256:8f9f7cd18871e6d127b8ee0cd744b9a3885ba38635eca8793de800fbc45aad06
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c771ff82d2ef34188026942942023ff4b332fee36fb6646b31c9c654849051
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:c5b3551a6847d353fcf167f93fcc9ecc7b94977192f89bcc6d0a84ef6e4e77ff
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce56c3b0a7357c41584cbf23c8f399a75e238712757ffc8c8295571bb56ae7c2
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": 0.9066126942634583,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.044918585064570464,
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": 144.846,
732
  "eval_steps_per_second": 4.53,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.0766140833792e+18,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8881184458732605,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.06737787759685569,
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": 144.846,
732
  "eval_steps_per_second": 4.53,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04536777091521617,
737
+ "grad_norm": 0.25195518136024475,
738
+ "learning_rate": 5.262631578947368e-05,
739
+ "loss": 0.9138,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.04581695676586187,
744
+ "grad_norm": 0.2436404973268509,
745
+ "learning_rate": 5.209473684210527e-05,
746
+ "loss": 0.9067,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.04626614261650758,
751
+ "grad_norm": 0.27484673261642456,
752
+ "learning_rate": 5.1563157894736844e-05,
753
+ "loss": 0.9343,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.04671532846715328,
758
+ "grad_norm": 0.27864891290664673,
759
+ "learning_rate": 5.1031578947368426e-05,
760
+ "loss": 0.9083,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.047164514317798986,
765
+ "grad_norm": 0.28357595205307007,
766
+ "learning_rate": 5.05e-05,
767
+ "loss": 0.8889,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.04761370016844469,
772
+ "grad_norm": 0.3293287754058838,
773
+ "learning_rate": 4.9968421052631576e-05,
774
+ "loss": 0.8996,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0480628860190904,
779
+ "grad_norm": 0.25651612877845764,
780
+ "learning_rate": 4.943684210526316e-05,
781
+ "loss": 0.9268,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.048512071869736106,
786
+ "grad_norm": 0.26456665992736816,
787
+ "learning_rate": 4.890526315789474e-05,
788
+ "loss": 0.9306,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.04896125772038181,
793
+ "grad_norm": 0.24413970112800598,
794
+ "learning_rate": 4.8373684210526316e-05,
795
+ "loss": 0.9318,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.049410443571027515,
800
+ "grad_norm": 0.24325355887413025,
801
+ "learning_rate": 4.784210526315789e-05,
802
+ "loss": 0.9073,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.04985962942167322,
807
+ "grad_norm": 0.2712045907974243,
808
+ "learning_rate": 4.731052631578947e-05,
809
+ "loss": 0.8931,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.050308815272318924,
814
+ "grad_norm": 0.3078647255897522,
815
+ "learning_rate": 4.6778947368421055e-05,
816
+ "loss": 0.8614,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.05075800112296463,
821
+ "grad_norm": 0.2627927362918854,
822
+ "learning_rate": 4.624736842105263e-05,
823
+ "loss": 0.8967,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.05120718697361033,
828
+ "grad_norm": 0.25500932335853577,
829
+ "learning_rate": 4.571578947368421e-05,
830
+ "loss": 0.9088,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.05165637282425604,
835
+ "grad_norm": 0.275991827249527,
836
+ "learning_rate": 4.518421052631579e-05,
837
+ "loss": 0.8913,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.05210555867490174,
842
+ "grad_norm": 0.2581343352794647,
843
+ "learning_rate": 4.465263157894737e-05,
844
+ "loss": 0.8865,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.052554744525547446,
849
+ "grad_norm": 0.2798708975315094,
850
+ "learning_rate": 4.412105263157895e-05,
851
+ "loss": 0.9146,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.05300393037619315,
856
+ "grad_norm": 0.3520914316177368,
857
+ "learning_rate": 4.358947368421053e-05,
858
+ "loss": 0.9002,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.053453116226838855,
863
+ "grad_norm": 0.3063805401325226,
864
+ "learning_rate": 4.30578947368421e-05,
865
+ "loss": 0.8889,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.05390230207748456,
870
+ "grad_norm": 0.268318772315979,
871
+ "learning_rate": 4.2526315789473685e-05,
872
+ "loss": 0.9306,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.054351487928130264,
877
+ "grad_norm": 0.2569490075111389,
878
+ "learning_rate": 4.199473684210527e-05,
879
+ "loss": 0.9124,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.05480067377877597,
884
+ "grad_norm": 0.24538756906986237,
885
+ "learning_rate": 4.146315789473684e-05,
886
+ "loss": 0.911,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.05524985962942167,
891
+ "grad_norm": 0.2484789937734604,
892
+ "learning_rate": 4.093157894736842e-05,
893
+ "loss": 0.9066,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.05569904548006738,
898
+ "grad_norm": 0.2707575261592865,
899
+ "learning_rate": 4.0400000000000006e-05,
900
+ "loss": 0.8681,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.05614823133071308,
905
+ "grad_norm": 0.35909488797187805,
906
+ "learning_rate": 3.986842105263158e-05,
907
+ "loss": 0.8218,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.056597417181358786,
912
+ "grad_norm": 0.23776692152023315,
913
+ "learning_rate": 3.933684210526316e-05,
914
+ "loss": 0.9211,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.05704660303200449,
919
+ "grad_norm": 0.25755029916763306,
920
+ "learning_rate": 3.880526315789473e-05,
921
+ "loss": 0.8879,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.057495788882650195,
926
+ "grad_norm": 0.2494814097881317,
927
+ "learning_rate": 3.827368421052632e-05,
928
+ "loss": 0.8906,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0579449747332959,
933
+ "grad_norm": 0.25940045714378357,
934
+ "learning_rate": 3.7742105263157896e-05,
935
+ "loss": 0.8868,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.058394160583941604,
940
+ "grad_norm": 0.2853882908821106,
941
+ "learning_rate": 3.721052631578947e-05,
942
+ "loss": 0.8775,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.05884334643458731,
947
+ "grad_norm": 0.32979917526245117,
948
+ "learning_rate": 3.6678947368421054e-05,
949
+ "loss": 0.8522,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.05929253228523301,
954
+ "grad_norm": 0.255938321352005,
955
+ "learning_rate": 3.6147368421052636e-05,
956
+ "loss": 0.9059,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.05974171813587872,
961
+ "grad_norm": 0.2526702284812927,
962
+ "learning_rate": 3.561578947368421e-05,
963
+ "loss": 0.9105,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.06019090398652442,
968
+ "grad_norm": 0.2506902813911438,
969
+ "learning_rate": 3.508421052631579e-05,
970
+ "loss": 0.8951,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.060640089837170126,
975
+ "grad_norm": 0.2672176957130432,
976
+ "learning_rate": 3.455263157894737e-05,
977
+ "loss": 0.8967,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.06108927568781583,
982
+ "grad_norm": 0.2774716913700104,
983
+ "learning_rate": 3.402105263157895e-05,
984
+ "loss": 0.8891,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.06153846153846154,
989
+ "grad_norm": 0.3068337142467499,
990
+ "learning_rate": 3.3489473684210526e-05,
991
+ "loss": 0.8719,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.061987647389107246,
996
+ "grad_norm": 0.2592477798461914,
997
+ "learning_rate": 3.295789473684211e-05,
998
+ "loss": 0.9152,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.06243683323975295,
1003
+ "grad_norm": 0.24649055302143097,
1004
+ "learning_rate": 3.242631578947368e-05,
1005
+ "loss": 0.8869,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.06288601909039865,
1010
+ "grad_norm": 0.24601422250270844,
1011
+ "learning_rate": 3.1894736842105265e-05,
1012
+ "loss": 0.9147,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.06333520494104436,
1017
+ "grad_norm": 0.2531537115573883,
1018
+ "learning_rate": 3.136315789473685e-05,
1019
+ "loss": 0.9067,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.06378439079169006,
1024
+ "grad_norm": 0.27577677369117737,
1025
+ "learning_rate": 3.083157894736842e-05,
1026
+ "loss": 0.8926,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.06423357664233577,
1031
+ "grad_norm": 0.3049788475036621,
1032
+ "learning_rate": 3.0299999999999998e-05,
1033
+ "loss": 0.8536,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.06468276249298147,
1038
+ "grad_norm": 0.26886892318725586,
1039
+ "learning_rate": 2.9768421052631577e-05,
1040
+ "loss": 0.8746,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.06513194834362718,
1045
+ "grad_norm": 0.2674404978752136,
1046
+ "learning_rate": 2.923684210526316e-05,
1047
+ "loss": 0.8991,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.06558113419427287,
1052
+ "grad_norm": 0.2553546726703644,
1053
+ "learning_rate": 2.8705263157894737e-05,
1054
+ "loss": 0.8974,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.06603032004491859,
1059
+ "grad_norm": 0.2580017149448395,
1060
+ "learning_rate": 2.8173684210526313e-05,
1061
+ "loss": 0.8854,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.06647950589556428,
1066
+ "grad_norm": 0.27426302433013916,
1067
+ "learning_rate": 2.7642105263157898e-05,
1068
+ "loss": 0.8885,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.06692869174621,
1073
+ "grad_norm": 0.3027507960796356,
1074
+ "learning_rate": 2.7110526315789473e-05,
1075
+ "loss": 0.8973,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.06737787759685569,
1080
+ "grad_norm": 0.36818036437034607,
1081
+ "learning_rate": 2.6578947368421052e-05,
1082
+ "loss": 0.8283,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.06737787759685569,
1087
+ "eval_loss": 0.8881184458732605,
1088
+ "eval_runtime": 207.2757,
1089
+ "eval_samples_per_second": 144.711,
1090
+ "eval_steps_per_second": 4.525,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.6149211250688e+18,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null