aleegis11 commited on
Commit
1276825
·
verified ·
1 Parent(s): bf42059

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:a5f989056a76a20f7b28e7372806794fd13007a937cc8cba570c1b2cba3995db
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff865c5e339894ad2a23cf86410cef5c0a8ac2298c0bde7e3b8207f0e02d60e2
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:295b128f2544aa2ad7ad248863d44d65d18e52abd5e3965608087a2a573417de
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cab5085cbbc1b6873739d643e5b6ec47f9f22828970881143da7e39c3fbf9f5
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35712a0ebc49d17156fd6a5a5206fcfc353ce2c2ec1ee245ed86b49e22c38a6a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc185a5c4957f473442c370645745139fa7ee3019b255a16d99cb2ae0cbccea
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": 0.3455173075199127,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.041097297852666186,
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": 13.517,
732
  "eval_steps_per_second": 3.38,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.430999619600384e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3154841363430023,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.06164594677899928,
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": 13.517,
732
  "eval_steps_per_second": 3.38,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04150827083119285,
737
+ "grad_norm": 5.274952411651611,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.6208,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.04191924380971951,
744
+ "grad_norm": 4.08144998550415,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.4864,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.042330216788246174,
751
+ "grad_norm": 2.737884044647217,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.443,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.04274118976677283,
758
+ "grad_norm": 2.1988816261291504,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.3324,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0431521627452995,
765
+ "grad_norm": 2.2960410118103027,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.2426,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.04356313572382616,
772
+ "grad_norm": 2.2390687465667725,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.2828,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.04397410870235282,
779
+ "grad_norm": 2.3960556983947754,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.4194,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.044385081680879485,
786
+ "grad_norm": 2.0492103099823,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.2888,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.04479605465940614,
793
+ "grad_norm": 2.0121076107025146,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.3162,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.04520702763793281,
800
+ "grad_norm": 2.2901666164398193,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.3905,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.045618000616459466,
807
+ "grad_norm": 1.9342862367630005,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.2849,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.04602897359498613,
814
+ "grad_norm": 1.832655906677246,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.203,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.04643994657351279,
821
+ "grad_norm": 1.8826347589492798,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.2088,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.046850919552039454,
828
+ "grad_norm": 1.752295732498169,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.1605,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.04726189253056612,
835
+ "grad_norm": 2.0863845348358154,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.285,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.04767286550909278,
842
+ "grad_norm": 1.8261597156524658,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.2279,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.04808383848761944,
849
+ "grad_norm": 1.960571050643921,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.2573,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0484948114661461,
856
+ "grad_norm": 2.176847219467163,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.2994,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.048905784444672765,
863
+ "grad_norm": 2.2963430881500244,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.3262,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.04931675742319942,
870
+ "grad_norm": 1.8424094915390015,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.1288,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.04972773040172609,
877
+ "grad_norm": 1.966762661933899,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.3157,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.050138703380252746,
884
+ "grad_norm": 2.4863340854644775,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.3588,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.05054967635877941,
891
+ "grad_norm": 1.7269797325134277,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.2165,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.05096064933730607,
898
+ "grad_norm": 1.803267002105713,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.2079,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.051371622315832734,
905
+ "grad_norm": 1.9960136413574219,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.3995,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.0517825952943594,
912
+ "grad_norm": 1.9701896905899048,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.3375,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.05219356827288606,
919
+ "grad_norm": 2.303657293319702,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.2451,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.05260454125141272,
926
+ "grad_norm": 1.9838213920593262,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.2861,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.05301551422993938,
933
+ "grad_norm": 1.9161285161972046,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.2781,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.053426487208466045,
940
+ "grad_norm": 1.9126702547073364,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.2527,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0538374601869927,
947
+ "grad_norm": 1.754321575164795,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.1144,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.05424843316551937,
954
+ "grad_norm": 1.589983582496643,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.1775,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.054659406144046026,
961
+ "grad_norm": 1.8121100664138794,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.2395,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.05507037912257269,
968
+ "grad_norm": 1.5348248481750488,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.0873,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.055481352101099356,
975
+ "grad_norm": 1.7048112154006958,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.2059,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.055892325079626014,
982
+ "grad_norm": 1.6508110761642456,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.1109,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.05630329805815268,
989
+ "grad_norm": 1.7701857089996338,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.1188,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.05671427103667934,
996
+ "grad_norm": 1.6648733615875244,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.1481,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.057125244015206,
1003
+ "grad_norm": 1.6659666299819946,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.0526,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.05753621699373266,
1010
+ "grad_norm": 1.4453469514846802,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.0307,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.057947189972259325,
1017
+ "grad_norm": 1.6568886041641235,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.0075,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.05835816295078598,
1024
+ "grad_norm": 1.710189700126648,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.1886,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.05876913592931265,
1031
+ "grad_norm": 1.6561558246612549,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.0218,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.05918010890783931,
1038
+ "grad_norm": 1.780678629875183,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.0088,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.05959108188636597,
1045
+ "grad_norm": 1.5461232662200928,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.9732,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.060002054864892636,
1052
+ "grad_norm": 1.5056289434432983,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.9288,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.060413027843419294,
1059
+ "grad_norm": 1.5496935844421387,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.9537,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.06082400082194596,
1066
+ "grad_norm": 1.5166020393371582,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.8448,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.06123497380047262,
1073
+ "grad_norm": 1.8695980310440063,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.9564,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.06164594677899928,
1080
+ "grad_norm": 1.3109105825424194,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.8316,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.06164594677899928,
1087
+ "eval_loss": 0.3154841363430023,
1088
+ "eval_runtime": 303.3515,
1089
+ "eval_samples_per_second": 13.512,
1090
+ "eval_steps_per_second": 3.379,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.146499429400576e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null