lesso commited on
Commit
0722745
·
verified ·
1 Parent(s): 82d9598

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:f865bda560e125797d4268f9da1f4ee4f03865f86806ab1c73747a4da8999c2b
3
  size 1101095848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81423449fe06f59181f60a64e49fc8d948427bd227e256237520074bdd3287a4
3
  size 1101095848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42de0be946f9884d2f784ab6f8d4b246ff51d62775d6384195aa7ee1bcc17c39
3
  size 559894228
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607da0035db4a628d1ebf1cfc067795b9fc7bf62e60d9729b80a62eb3bf2bb0e
3
  size 559894228
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8c1536bf4ad7db7edc6469539009396180ed29f84641809ff4ccbb1deaadf8c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54712af3776ec742c52b5b82aecf5c077f17d8ffaddf9711f377a52ce38f53b7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c16c2a0a7f4d1c317518a0a40a7c58dbcf9237e9297de7a3c67a0a8ebfbe5ded
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c5525f1d8420ca8a81a7fd2ec397a508131d03210dfd36c7ac5758b0e6313b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.9197953939437866,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.01710717646052519,
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": 5.199,
732
  "eval_steps_per_second": 1.301,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7.082500598582477e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.8687154054641724,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.025660764690787787,
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": 5.199,
732
  "eval_steps_per_second": 1.301,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.01727824822513044,
737
+ "grad_norm": 0.6856660842895508,
738
+ "learning_rate": 5.231368421052631e-05,
739
+ "loss": 1.8056,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.017449319989735694,
744
+ "grad_norm": 0.8271840810775757,
745
+ "learning_rate": 5.178526315789474e-05,
746
+ "loss": 1.915,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.017620391754340946,
751
+ "grad_norm": 0.7571515440940857,
752
+ "learning_rate": 5.1256842105263165e-05,
753
+ "loss": 1.9442,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0177914635189462,
758
+ "grad_norm": 0.867884635925293,
759
+ "learning_rate": 5.072842105263158e-05,
760
+ "loss": 2.145,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.01796253528355145,
765
+ "grad_norm": 0.7025319933891296,
766
+ "learning_rate": 5.02e-05,
767
+ "loss": 1.7341,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0181336070481567,
772
+ "grad_norm": 0.6765435934066772,
773
+ "learning_rate": 4.967157894736842e-05,
774
+ "loss": 2.1242,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.018304678812761953,
779
+ "grad_norm": 0.5824732184410095,
780
+ "learning_rate": 4.914315789473684e-05,
781
+ "loss": 1.9422,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.018475750577367205,
786
+ "grad_norm": 0.5176606178283691,
787
+ "learning_rate": 4.861473684210526e-05,
788
+ "loss": 2.0242,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.018646822341972458,
793
+ "grad_norm": 0.5743870139122009,
794
+ "learning_rate": 4.8086315789473686e-05,
795
+ "loss": 2.0175,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.01881789410657771,
800
+ "grad_norm": 0.5101130604743958,
801
+ "learning_rate": 4.7557894736842104e-05,
802
+ "loss": 1.8344,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.018988965871182963,
807
+ "grad_norm": 0.5062516927719116,
808
+ "learning_rate": 4.702947368421053e-05,
809
+ "loss": 1.9409,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.01916003763578821,
814
+ "grad_norm": 0.48760825395584106,
815
+ "learning_rate": 4.6501052631578946e-05,
816
+ "loss": 1.8474,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.019331109400393464,
821
+ "grad_norm": 0.492199182510376,
822
+ "learning_rate": 4.5972631578947364e-05,
823
+ "loss": 1.9067,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.019502181164998716,
828
+ "grad_norm": 0.4930146336555481,
829
+ "learning_rate": 4.544421052631579e-05,
830
+ "loss": 1.7696,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.01967325292960397,
835
+ "grad_norm": 0.5493840575218201,
836
+ "learning_rate": 4.4915789473684213e-05,
837
+ "loss": 2.0178,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.01984432469420922,
842
+ "grad_norm": 0.5961560606956482,
843
+ "learning_rate": 4.438736842105263e-05,
844
+ "loss": 1.6976,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.020015396458814474,
849
+ "grad_norm": 0.5364917516708374,
850
+ "learning_rate": 4.3858947368421056e-05,
851
+ "loss": 1.847,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.020186468223419726,
856
+ "grad_norm": 0.5656726956367493,
857
+ "learning_rate": 4.3330526315789474e-05,
858
+ "loss": 1.9252,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.020357539988024975,
863
+ "grad_norm": 0.5928261876106262,
864
+ "learning_rate": 4.280210526315789e-05,
865
+ "loss": 1.9079,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.020528611752630228,
870
+ "grad_norm": 0.5389055609703064,
871
+ "learning_rate": 4.2273684210526317e-05,
872
+ "loss": 1.7967,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.02069968351723548,
877
+ "grad_norm": 0.6076517701148987,
878
+ "learning_rate": 4.174526315789474e-05,
879
+ "loss": 1.793,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.020870755281840733,
884
+ "grad_norm": 0.6341645121574402,
885
+ "learning_rate": 4.121684210526316e-05,
886
+ "loss": 1.9671,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.021041827046445985,
891
+ "grad_norm": 0.6870526075363159,
892
+ "learning_rate": 4.068842105263158e-05,
893
+ "loss": 1.7407,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.021212898811051237,
898
+ "grad_norm": 0.6322492957115173,
899
+ "learning_rate": 4.016e-05,
900
+ "loss": 1.949,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.021383970575656486,
905
+ "grad_norm": 0.6672692894935608,
906
+ "learning_rate": 3.963157894736842e-05,
907
+ "loss": 1.9643,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.02155504234026174,
912
+ "grad_norm": 0.6229186058044434,
913
+ "learning_rate": 3.9103157894736844e-05,
914
+ "loss": 1.7221,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.02172611410486699,
919
+ "grad_norm": 0.7301349639892578,
920
+ "learning_rate": 3.857473684210526e-05,
921
+ "loss": 2.0484,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.021897185869472244,
926
+ "grad_norm": 0.7856729626655579,
927
+ "learning_rate": 3.804631578947369e-05,
928
+ "loss": 1.773,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.022068257634077496,
933
+ "grad_norm": 0.8492652177810669,
934
+ "learning_rate": 3.7517894736842105e-05,
935
+ "loss": 1.8202,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.02223932939868275,
940
+ "grad_norm": 0.7252649068832397,
941
+ "learning_rate": 3.698947368421052e-05,
942
+ "loss": 1.8962,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.022410401163287998,
947
+ "grad_norm": 0.7953678369522095,
948
+ "learning_rate": 3.646105263157895e-05,
949
+ "loss": 1.7289,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.02258147292789325,
954
+ "grad_norm": 0.728402853012085,
955
+ "learning_rate": 3.593263157894737e-05,
956
+ "loss": 1.9082,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.022752544692498503,
961
+ "grad_norm": 0.8220646381378174,
962
+ "learning_rate": 3.540421052631579e-05,
963
+ "loss": 1.9591,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.022923616457103755,
968
+ "grad_norm": 0.8018884062767029,
969
+ "learning_rate": 3.4875789473684215e-05,
970
+ "loss": 2.0895,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.023094688221709007,
975
+ "grad_norm": 0.7861109972000122,
976
+ "learning_rate": 3.434736842105263e-05,
977
+ "loss": 1.9219,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.02326575998631426,
982
+ "grad_norm": 0.8565029501914978,
983
+ "learning_rate": 3.381894736842105e-05,
984
+ "loss": 2.0818,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.023436831750919512,
989
+ "grad_norm": 0.986121416091919,
990
+ "learning_rate": 3.329052631578947e-05,
991
+ "loss": 2.0713,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.02360790351552476,
996
+ "grad_norm": 0.8753408789634705,
997
+ "learning_rate": 3.27621052631579e-05,
998
+ "loss": 1.7472,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.023778975280130014,
1003
+ "grad_norm": 1.0510600805282593,
1004
+ "learning_rate": 3.223368421052632e-05,
1005
+ "loss": 2.1363,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.023950047044735266,
1010
+ "grad_norm": 1.0964877605438232,
1011
+ "learning_rate": 3.1705263157894736e-05,
1012
+ "loss": 2.0689,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.02412111880934052,
1017
+ "grad_norm": 1.000916838645935,
1018
+ "learning_rate": 3.117684210526316e-05,
1019
+ "loss": 1.9126,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.02429219057394577,
1024
+ "grad_norm": 1.1080740690231323,
1025
+ "learning_rate": 3.064842105263158e-05,
1026
+ "loss": 2.4376,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.024463262338551024,
1031
+ "grad_norm": 1.1512094736099243,
1032
+ "learning_rate": 3.012e-05,
1033
+ "loss": 1.8156,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.024634334103156273,
1038
+ "grad_norm": 1.3569144010543823,
1039
+ "learning_rate": 2.9591578947368418e-05,
1040
+ "loss": 1.451,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.024805405867761525,
1045
+ "grad_norm": 1.311303734779358,
1046
+ "learning_rate": 2.9063157894736842e-05,
1047
+ "loss": 2.0755,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.024976477632366777,
1052
+ "grad_norm": 1.199066400527954,
1053
+ "learning_rate": 2.8534736842105264e-05,
1054
+ "loss": 1.3857,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.02514754939697203,
1059
+ "grad_norm": 1.3259034156799316,
1060
+ "learning_rate": 2.800631578947368e-05,
1061
+ "loss": 1.804,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.025318621161577282,
1066
+ "grad_norm": 1.8676377534866333,
1067
+ "learning_rate": 2.7477894736842106e-05,
1068
+ "loss": 1.8025,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.025489692926182535,
1073
+ "grad_norm": 2.550297498703003,
1074
+ "learning_rate": 2.6949473684210527e-05,
1075
+ "loss": 2.0316,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.025660764690787787,
1080
+ "grad_norm": 2.5897419452667236,
1081
+ "learning_rate": 2.6421052631578945e-05,
1082
+ "loss": 1.4353,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.025660764690787787,
1087
+ "eval_loss": 1.8687154054641724,
1088
+ "eval_runtime": 474.321,
1089
+ "eval_samples_per_second": 5.191,
1090
+ "eval_steps_per_second": 1.299,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.0588689013722317e+17,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null