0x1202 commited on
Commit
62a8cbb
·
verified ·
1 Parent(s): 95a38ae

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:c752a10bc99c9a1dfe08f267e464594f4601be90e1c75551cbcfcb9737b771be
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06415142e2b020a407731da3c042383f99b5535fddc3df08907640688dbb889f
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0182583283b32db59c0dd00e395a8478fa1e3de3c9126111c668e825812b6e7d
3
  size 40177764
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ef7c62cd98d3c9378944ab01ea50dfe62a89341ee58d2e9fbf63beab2f7038
3
  size 40177764
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1cc138079aa4a51d01349f498355b76edd03778e51ca06bc87b59094a8c3f7f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f2c896a169e5d3d5d0e0f2e4b61ac59a21e1533b57d08e8e91d62bbfa12442b
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": 2.1208791732788086,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.006567281802062126,
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": 74.695,
732
  "eval_steps_per_second": 18.675,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2478356485373952.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.086007833480835,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.00985092270309319,
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": 74.695,
732
  "eval_steps_per_second": 18.675,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.006632954620082748,
737
+ "grad_norm": 0.26776552200317383,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.9213,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.006698627438103369,
744
+ "grad_norm": 0.2925421893596649,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.0808,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.00676430025612399,
751
+ "grad_norm": 0.2745435833930969,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.0522,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.006829973074144612,
758
+ "grad_norm": 0.2485833466053009,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.0857,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.006895645892165233,
765
+ "grad_norm": 0.22988854348659515,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.0713,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.006961318710185854,
772
+ "grad_norm": 0.23328274488449097,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.129,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.007026991528206476,
779
+ "grad_norm": 0.2321634739637375,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.0918,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.007092664346227097,
786
+ "grad_norm": 0.21271684765815735,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.1278,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.007158337164247718,
793
+ "grad_norm": 0.2307552695274353,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.1439,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.007224009982268339,
800
+ "grad_norm": 0.22347523272037506,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.2022,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0072896828002889606,
807
+ "grad_norm": 0.22164353728294373,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.0901,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.0073553556183095815,
814
+ "grad_norm": 0.23763644695281982,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.1446,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.0074210284363302025,
821
+ "grad_norm": 0.22384075820446014,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.0807,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.007486701254350824,
828
+ "grad_norm": 0.2535134255886078,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.0794,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.007552374072371445,
835
+ "grad_norm": 0.2027769386768341,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.086,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.007618046890392066,
842
+ "grad_norm": 0.23799559473991394,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.0019,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.007683719708412688,
849
+ "grad_norm": 0.2319781631231308,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.1162,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.007749392526433309,
856
+ "grad_norm": 0.22421769797801971,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.0987,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.00781506534445393,
863
+ "grad_norm": 0.23134103417396545,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.132,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.007880738162474551,
870
+ "grad_norm": 0.2161579728126526,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.0667,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.007946410980495174,
877
+ "grad_norm": 0.23446449637413025,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.038,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.008012083798515795,
884
+ "grad_norm": 0.23854734003543854,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.0972,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.008077756616536416,
891
+ "grad_norm": 0.226479634642601,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.1129,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.008143429434557037,
898
+ "grad_norm": 0.22427687048912048,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.0563,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.008209102252577658,
905
+ "grad_norm": 0.2315479964017868,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.0283,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.008274775070598279,
912
+ "grad_norm": 0.23581887781620026,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.0538,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0083404478886189,
919
+ "grad_norm": 0.22403451800346375,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.0729,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.008406120706639523,
926
+ "grad_norm": 0.23315103352069855,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.0769,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.008471793524660143,
933
+ "grad_norm": 0.24104753136634827,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.1748,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.008537466342680764,
940
+ "grad_norm": 0.23056164383888245,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.139,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.008603139160701385,
947
+ "grad_norm": 0.22196581959724426,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.0557,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.008668811978722006,
954
+ "grad_norm": 0.21537984907627106,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.0416,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.008734484796742627,
961
+ "grad_norm": 0.23549425601959229,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.1152,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.00880015761476325,
968
+ "grad_norm": 0.2215685397386551,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.066,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.008865830432783871,
975
+ "grad_norm": 0.23889760673046112,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.1107,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.008931503250804492,
982
+ "grad_norm": 0.23466117680072784,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.1062,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.008997176068825113,
989
+ "grad_norm": 0.2281591296195984,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.1344,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.009062848886845734,
996
+ "grad_norm": 0.2444644570350647,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.085,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.009128521704866355,
1003
+ "grad_norm": 0.23362785577774048,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.0524,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.009194194522886978,
1010
+ "grad_norm": 0.251742959022522,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.093,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.009259867340907599,
1017
+ "grad_norm": 0.27314895391464233,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.1076,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.00932554015892822,
1024
+ "grad_norm": 0.265262246131897,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.0309,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.00939121297694884,
1031
+ "grad_norm": 0.2591760456562042,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.097,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.009456885794969462,
1038
+ "grad_norm": 0.25731712579727173,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.0639,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.009522558612990083,
1045
+ "grad_norm": 0.262839138507843,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.1146,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.009588231431010705,
1052
+ "grad_norm": 0.2442999631166458,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.1524,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.009653904249031326,
1059
+ "grad_norm": 0.28426259756088257,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.1721,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.009719577067051947,
1066
+ "grad_norm": 0.26640063524246216,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.1093,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.009785249885072568,
1073
+ "grad_norm": 0.2826448082923889,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.0059,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.00985092270309319,
1080
+ "grad_norm": 0.3272068500518799,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.2535,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.00985092270309319,
1087
+ "eval_loss": 2.086007833480835,
1088
+ "eval_runtime": 345.6555,
1089
+ "eval_samples_per_second": 74.195,
1090
+ "eval_steps_per_second": 18.55,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3714444508004352.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null