0x1202 commited on
Commit
077d8b0
·
verified ·
1 Parent(s): 3e8a401

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:a1836ef034cdeeb7bc504e32324612eac24ed1adbf10e8d4b0dfab6ea0203517
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154c64b189522d45cf35a18b03dcba65a69af851e52c3aff505b09a3bbc84998
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:444e63d74aeb8798de0d46023a2538f4b0497ea4e296e9abe291ddc7a91cbc83
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d09ca17d98c711ccd69d54b5a7c077b4529cd2f91026c2c02c13ed435d8e40
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a4f93b131ce1afca73c97045fafa805033404de9c5494ac9eb4bf78724335d5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e34db547cf006dece3e867ecacf52dcae03c7c80d1c9b94ba6c86cd1c35e950
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": 3.9073877334594727,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.04357298474945534,
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": 14.191,
732
  "eval_steps_per_second": 3.55,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.3371612024589517e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.9679818153381348,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.06535947712418301,
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": 14.191,
732
  "eval_steps_per_second": 3.55,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04400871459694989,
737
+ "grad_norm": 4.844549655914307,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 3.0795,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.044444444444444446,
744
+ "grad_norm": 4.860598087310791,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 3.8187,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.044880174291938996,
751
+ "grad_norm": 3.8574204444885254,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 3.5216,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.04531590413943355,
758
+ "grad_norm": 2.277156352996826,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 3.6533,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0457516339869281,
765
+ "grad_norm": 1.8573322296142578,
766
+ "learning_rate": 5e-05,
767
+ "loss": 3.5722,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.04618736383442266,
772
+ "grad_norm": 1.4282306432724,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 3.1226,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.046623093681917215,
779
+ "grad_norm": 1.3700124025344849,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 3.272,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.047058823529411764,
786
+ "grad_norm": 1.1703954935073853,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 3.3815,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.04749455337690632,
793
+ "grad_norm": 1.1776833534240723,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 3.1371,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.04793028322440087,
800
+ "grad_norm": 1.345227837562561,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 3.192,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.048366013071895426,
807
+ "grad_norm": 1.2462388277053833,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.9725,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.048801742919389976,
814
+ "grad_norm": 1.332241415977478,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 3.2054,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.04923747276688453,
821
+ "grad_norm": 1.3160040378570557,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.9311,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.04967320261437908,
828
+ "grad_norm": 1.4543054103851318,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 3.26,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.05010893246187364,
835
+ "grad_norm": 1.3486131429672241,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.974,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.050544662309368195,
842
+ "grad_norm": 1.4071096181869507,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.6225,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.050980392156862744,
849
+ "grad_norm": 1.479636788368225,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.4074,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0514161220043573,
856
+ "grad_norm": 1.4064018726348877,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.1019,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.05185185185185185,
863
+ "grad_norm": 1.546591877937317,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.8507,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.05228758169934641,
870
+ "grad_norm": 1.6136044263839722,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.8392,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.052723311546840956,
877
+ "grad_norm": 1.658595085144043,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.3807,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.05315904139433551,
884
+ "grad_norm": 2.2032907009124756,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 3.2297,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.05359477124183006,
891
+ "grad_norm": 2.3491697311401367,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 3.2603,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.05403050108932462,
898
+ "grad_norm": 3.0305137634277344,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.9607,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.054466230936819175,
905
+ "grad_norm": 2.5042619705200195,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.9974,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.054901960784313725,
912
+ "grad_norm": 2.7703745365142822,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.9027,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.05533769063180828,
919
+ "grad_norm": 2.762169361114502,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.4001,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.05577342047930283,
926
+ "grad_norm": 3.0867695808410645,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.4678,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.05620915032679739,
933
+ "grad_norm": 3.359591484069824,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.6955,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.05664488017429194,
940
+ "grad_norm": 3.013075351715088,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.6053,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.05708061002178649,
947
+ "grad_norm": 3.158442497253418,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.9712,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.05751633986928104,
954
+ "grad_norm": 2.680692195892334,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.5613,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0579520697167756,
961
+ "grad_norm": 2.756537437438965,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.7349,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.058387799564270156,
968
+ "grad_norm": 2.7178499698638916,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.5581,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.058823529411764705,
975
+ "grad_norm": 2.7326412200927734,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.5431,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.05925925925925926,
982
+ "grad_norm": 2.7082595825195312,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.7033,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.05969498910675381,
989
+ "grad_norm": 2.597834825515747,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.4039,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.06013071895424837,
996
+ "grad_norm": 2.6988589763641357,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.3628,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.06056644880174292,
1003
+ "grad_norm": 2.561375856399536,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.626,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.06100217864923747,
1010
+ "grad_norm": 2.8920652866363525,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.4874,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.06143790849673202,
1017
+ "grad_norm": 2.745953321456909,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.6994,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.06187363834422658,
1024
+ "grad_norm": 2.8938546180725098,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.7683,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.062309368191721136,
1031
+ "grad_norm": 3.5593948364257812,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.0153,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.06274509803921569,
1038
+ "grad_norm": 2.6813762187957764,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.7665,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.06318082788671024,
1045
+ "grad_norm": 4.160965442657471,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.6576,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0636165577342048,
1052
+ "grad_norm": 3.5698304176330566,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.6612,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.06405228758169934,
1059
+ "grad_norm": 3.7868640422821045,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.03,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0644880174291939,
1066
+ "grad_norm": 3.7534987926483154,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.9499,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.06492374727668845,
1073
+ "grad_norm": 4.871495246887207,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.3347,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.06535947712418301,
1080
+ "grad_norm": 6.4089250564575195,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 3.6969,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.06535947712418301,
1087
+ "eval_loss": 2.9679818153381348,
1088
+ "eval_runtime": 272.5597,
1089
+ "eval_samples_per_second": 14.184,
1090
+ "eval_steps_per_second": 3.548,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.0024155320405197e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null