0x1202 commited on
Commit
e8c73c5
·
verified ·
1 Parent(s): 594409a

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:bc6679f17a4eba4cb719d3c1c23ad9fd8766b595f7ee0a020f248abc707f4393
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15d9cb85b3c20035d6d59411d1bab34a5e2c212c867694823f1c2b60d2a146f9
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c6e65581068362858715e14bb97798f8e03fabfa411d17280c733ec3d9bc66a
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f25785c818d7197628f4a3f9cdea89a043a3aaa08e6db73084b7a8816f30ca6
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:535fdf4c0a3f71d25281edce97d7d5cb1c2b4e518dff96eeb9a6e9efb0fe9ed7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa026e0a537d7579ee130576f998e27bb91419fcac7dde96ad1ee6186d44f8e
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": 1.4839268922805786,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.1885902876001886,
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": 56.29,
732
  "eval_steps_per_second": 14.12,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7767124843954176.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4672940969467163,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.2828854314002829,
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": 56.29,
732
  "eval_steps_per_second": 14.12,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.19047619047619047,
737
+ "grad_norm": 0.7392789125442505,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.3007,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.19236209335219237,
744
+ "grad_norm": 0.8285383582115173,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.3803,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.19424799622819425,
751
+ "grad_norm": 0.7633514404296875,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.3377,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.19613389910419612,
758
+ "grad_norm": 0.7272994518280029,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.2073,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.19801980198019803,
765
+ "grad_norm": 0.7535402774810791,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.2368,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1999057048561999,
772
+ "grad_norm": 0.7271507382392883,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.426,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.20179160773220178,
779
+ "grad_norm": 0.7888609170913696,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.298,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.2036775106082037,
786
+ "grad_norm": 0.7619734406471252,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.529,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.20556341348420556,
793
+ "grad_norm": 0.7262706756591797,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.3107,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.20744931636020744,
800
+ "grad_norm": 0.7511423826217651,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.2902,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.20933521923620935,
807
+ "grad_norm": 0.7127615809440613,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.2128,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.21122112211221122,
814
+ "grad_norm": 0.7513578534126282,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.504,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.2131070249882131,
821
+ "grad_norm": 0.8162602186203003,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.4341,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.214992927864215,
828
+ "grad_norm": 0.8222413659095764,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.4536,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.21687883074021688,
835
+ "grad_norm": 0.8294031620025635,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.3297,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.21876473361621876,
842
+ "grad_norm": 0.7801927924156189,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.456,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.22065063649222066,
849
+ "grad_norm": 0.8259176015853882,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.4551,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.22253653936822254,
856
+ "grad_norm": 0.7965975999832153,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.5074,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.22442244224422442,
863
+ "grad_norm": 0.8104461431503296,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.3188,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.2263083451202263,
870
+ "grad_norm": 0.8252735137939453,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.3283,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.2281942479962282,
877
+ "grad_norm": 0.8110776543617249,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.4883,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.23008015087223008,
884
+ "grad_norm": 0.7731505632400513,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.461,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.23196605374823195,
891
+ "grad_norm": 0.7795805335044861,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.3828,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.23385195662423386,
898
+ "grad_norm": 0.8774617910385132,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.605,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.23573785950023574,
905
+ "grad_norm": 0.8436756730079651,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.4813,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.2376237623762376,
912
+ "grad_norm": 0.8913021683692932,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.4368,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.23950966525223952,
919
+ "grad_norm": 0.8260645866394043,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.5402,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.2413955681282414,
926
+ "grad_norm": 0.8445008993148804,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.4945,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.24328147100424327,
933
+ "grad_norm": 0.8457810878753662,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.4877,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.24516737388024518,
940
+ "grad_norm": 0.8343524932861328,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.4436,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.24705327675624705,
947
+ "grad_norm": 0.8800844550132751,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.4672,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.24893917963224893,
954
+ "grad_norm": 0.8727882504463196,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.5406,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.2508250825082508,
961
+ "grad_norm": 0.8764476776123047,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.5357,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.2527109853842527,
968
+ "grad_norm": 1.0033875703811646,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.548,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.2545968882602546,
975
+ "grad_norm": 0.8889184594154358,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.5711,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.2564827911362565,
982
+ "grad_norm": 0.906014621257782,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.4872,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.25836869401225837,
989
+ "grad_norm": 0.9370135068893433,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.5383,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.26025459688826025,
996
+ "grad_norm": 0.9925730228424072,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.4615,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.2621404997642621,
1003
+ "grad_norm": 0.9600664973258972,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.5633,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.264026402640264,
1010
+ "grad_norm": 0.9619641900062561,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.4668,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.26591230551626593,
1017
+ "grad_norm": 0.9631545543670654,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.5177,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.2677982083922678,
1024
+ "grad_norm": 0.9739064574241638,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.5393,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.2696841112682697,
1031
+ "grad_norm": 1.0108882188796997,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.6015,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.27157001414427157,
1038
+ "grad_norm": 1.037048578262329,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.5262,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.27345591702027344,
1045
+ "grad_norm": 1.0594589710235596,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.5892,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2753418198962753,
1052
+ "grad_norm": 1.0016132593154907,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.5237,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.27722772277227725,
1059
+ "grad_norm": 1.119092345237732,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.5041,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.27911362564827913,
1066
+ "grad_norm": 1.0873557329177856,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.7046,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.280999528524281,
1073
+ "grad_norm": 1.125348448753357,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.415,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.2828854314002829,
1080
+ "grad_norm": 1.322414517402649,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.4796,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.2828854314002829,
1087
+ "eval_loss": 1.4672940969467163,
1088
+ "eval_runtime": 15.8748,
1089
+ "eval_samples_per_second": 56.253,
1090
+ "eval_steps_per_second": 14.11,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.1650687265931264e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null