prxy5607 commited on
Commit
d4bb690
·
verified ·
1 Parent(s): 704a0af

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 sha256:4f2001abb7e6ad7e392b8faad46d7a58b58213ad753d25359592f5a13c25cec0
3
  size 912336848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518cd80eb86ba89652fcc96e30df0c0ccbebf8b0454133ffe6be256512a92bd0
3
  size 912336848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5242ab24a70f7be68adda290e0cecbf0a3a5a2cf06557b5fa2b18b82c79ffb45
3
  size 463916180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb77927af4f42567e6e0469bc82c6eb8c7f26abbcf1473c7a491d66abe2b415
3
  size 463916180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee611bdc5466bea72d02aef8874550301df98279cfa2f4aeebbd0b893cf3817b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d14e54ece494c3db1349cceab1f44b92045efa8579adb811c4232f518714e0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.42568302154541,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.012904890953671441,
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": 9.182,
732
  "eval_steps_per_second": 2.296,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.3325146156630016e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.3465826511383057,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.019357336430507164,
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": 9.182,
732
  "eval_steps_per_second": 2.296,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.013033939863208156,
737
+ "grad_norm": 6.558551788330078,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 9.0319,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.01316298877274487,
744
+ "grad_norm": 6.864365577697754,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 9.3867,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.013292037682281585,
751
+ "grad_norm": 6.573170185089111,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 9.3356,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0134210865918183,
758
+ "grad_norm": 4.381434917449951,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 8.9209,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.013550135501355014,
765
+ "grad_norm": 2.770876407623291,
766
+ "learning_rate": 5e-05,
767
+ "loss": 9.1898,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.013679184410891727,
772
+ "grad_norm": 2.151318311691284,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 9.1106,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.013808233320428442,
779
+ "grad_norm": 1.8227428197860718,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 8.694,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.013937282229965157,
786
+ "grad_norm": 1.8833378553390503,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 9.3368,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.014066331139501871,
793
+ "grad_norm": 2.1978793144226074,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 9.0372,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.014195380049038586,
800
+ "grad_norm": 1.9617077112197876,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 9.1136,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.014324428958575301,
807
+ "grad_norm": 2.611269235610962,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 9.5521,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.014453477868112014,
814
+ "grad_norm": 2.0450103282928467,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 8.5825,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.014582526777648729,
821
+ "grad_norm": 2.2265167236328125,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 8.8527,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.014711575687185443,
828
+ "grad_norm": 2.497074842453003,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 9.3511,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.014840624596722158,
835
+ "grad_norm": 2.6098930835723877,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 9.1412,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.014969673506258873,
842
+ "grad_norm": 2.4353199005126953,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 8.9863,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.015098722415795587,
849
+ "grad_norm": 2.5682668685913086,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 9.1443,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0152277713253323,
856
+ "grad_norm": 2.6961557865142822,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 9.6746,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.015356820234869015,
863
+ "grad_norm": 2.621609687805176,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 9.1541,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.01548586914440573,
870
+ "grad_norm": 2.6731786727905273,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 9.0717,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.015614918053942444,
877
+ "grad_norm": 2.469315767288208,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 8.7475,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.01574396696347916,
884
+ "grad_norm": 2.711573362350464,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 9.1526,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.015873015873015872,
891
+ "grad_norm": 2.6181857585906982,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 9.2163,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.01600206478255259,
898
+ "grad_norm": 2.6454579830169678,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 8.5263,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.0161311136920893,
905
+ "grad_norm": 2.8446078300476074,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 9.2747,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.016260162601626018,
912
+ "grad_norm": 2.921170949935913,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 9.8549,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.01638921151116273,
919
+ "grad_norm": 3.0550904273986816,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 8.9324,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.016518260420699444,
926
+ "grad_norm": 2.9599196910858154,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 9.792,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.01664730933023616,
933
+ "grad_norm": 2.7958767414093018,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 8.771,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.016776358239772873,
940
+ "grad_norm": 3.115372896194458,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 9.5177,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.01690540714930959,
947
+ "grad_norm": 2.960212230682373,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 8.8467,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.017034456058846303,
954
+ "grad_norm": 3.0903122425079346,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 9.8255,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.017163504968383016,
961
+ "grad_norm": 3.277925729751587,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 9.437,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.017292553877919732,
968
+ "grad_norm": 3.2966110706329346,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 9.1051,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.017421602787456445,
975
+ "grad_norm": 3.4716148376464844,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 9.1138,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.01755065169699316,
982
+ "grad_norm": 3.7124650478363037,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 9.827,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.017679700606529875,
989
+ "grad_norm": 3.57387375831604,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 9.4026,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.01780874951606659,
996
+ "grad_norm": 3.7645928859710693,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 8.8658,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.017937798425603304,
1003
+ "grad_norm": 3.6762328147888184,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 9.0362,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.018066847335140017,
1010
+ "grad_norm": 3.9711761474609375,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 9.7462,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.018195896244676733,
1017
+ "grad_norm": 4.019091606140137,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 9.2169,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.018324945154213446,
1024
+ "grad_norm": 4.222970485687256,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 9.4692,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.018453994063750163,
1031
+ "grad_norm": 4.119962215423584,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 9.2049,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.018583042973286876,
1038
+ "grad_norm": 4.283300876617432,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 9.5706,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.01871209188282359,
1045
+ "grad_norm": 5.065773963928223,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 9.9508,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.018841140792360305,
1052
+ "grad_norm": 4.4507670402526855,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 8.9088,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.018970189701897018,
1059
+ "grad_norm": 4.944255352020264,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 10.1089,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.019099238611433735,
1066
+ "grad_norm": 4.992981433868408,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 9.816,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.019228287520970447,
1073
+ "grad_norm": 6.395650863647461,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 9.399,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.019357336430507164,
1080
+ "grad_norm": 7.018031597137451,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 9.5585,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.019357336430507164,
1087
+ "eval_loss": 2.3465826511383057,
1088
+ "eval_runtime": 1422.2973,
1089
+ "eval_samples_per_second": 9.176,
1090
+ "eval_steps_per_second": 2.294,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.4987719234945024e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null