dimasik2987 commited on
Commit
8e7bd82
·
verified ·
1 Parent(s): 20db338

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:a6acad46c4896fcef874c1cd4dfd2827fd58b7691ea8b4a615b487306ce5ab63
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cc26509f94c6ac0af7640a204202e65d12098aeb14dace72e1db7599d6a7303
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd0308a4c7d34a7f696d4a5e77dcbdd4e2c268c4bb67c99be8360d50e0b8c260
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceaae71517f364006203a35c81e11a72acaa641c6e3cb9c07c77617b8a175273
3
  size 71077780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:502a6b74e374753f7dbf6431843ecdc0c2ba297df42b63ce53490964fe5583fa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9afeb2fcb6c83c8fe44222c176ebc30e779c1ab6f09b3f0ab9b82dfb8d834756
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c16c2a0a7f4d1c317518a0a40a7c58dbcf9237e9297de7a3c67a0a8ebfbe5ded
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c5525f1d8420ca8a81a7fd2ec397a508131d03210dfd36c7ac5758b0e6313b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.09364652633667,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.13802622498274672,
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": 42.821,
732
  "eval_steps_per_second": 10.81,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1717219885056000.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.0511386394500732,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.2070393374741201,
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": 42.821,
732
  "eval_steps_per_second": 10.81,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.13940648723257418,
737
+ "grad_norm": 1.1113362312316895,
738
+ "learning_rate": 5.231368421052631e-05,
739
+ "loss": 1.6735,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.14078674948240166,
744
+ "grad_norm": 1.1717188358306885,
745
+ "learning_rate": 5.178526315789474e-05,
746
+ "loss": 1.8926,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.14216701173222912,
751
+ "grad_norm": 1.1026091575622559,
752
+ "learning_rate": 5.1256842105263165e-05,
753
+ "loss": 2.007,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.14354727398205658,
758
+ "grad_norm": 1.0963923931121826,
759
+ "learning_rate": 5.072842105263158e-05,
760
+ "loss": 1.787,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.14492753623188406,
765
+ "grad_norm": 1.5479772090911865,
766
+ "learning_rate": 5.02e-05,
767
+ "loss": 2.1698,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.14630779848171152,
772
+ "grad_norm": 1.0915744304656982,
773
+ "learning_rate": 4.967157894736842e-05,
774
+ "loss": 2.2872,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.147688060731539,
779
+ "grad_norm": 1.1803730726242065,
780
+ "learning_rate": 4.914315789473684e-05,
781
+ "loss": 2.4359,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.14906832298136646,
786
+ "grad_norm": 1.4295563697814941,
787
+ "learning_rate": 4.861473684210526e-05,
788
+ "loss": 2.1041,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.15044858523119392,
793
+ "grad_norm": 1.0557366609573364,
794
+ "learning_rate": 4.8086315789473686e-05,
795
+ "loss": 1.9453,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.1518288474810214,
800
+ "grad_norm": 1.0212247371673584,
801
+ "learning_rate": 4.7557894736842104e-05,
802
+ "loss": 1.8541,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.15320910973084886,
807
+ "grad_norm": 1.0571060180664062,
808
+ "learning_rate": 4.702947368421053e-05,
809
+ "loss": 1.9645,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.15458937198067632,
814
+ "grad_norm": 1.12859308719635,
815
+ "learning_rate": 4.6501052631578946e-05,
816
+ "loss": 1.8444,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.1559696342305038,
821
+ "grad_norm": 1.2056413888931274,
822
+ "learning_rate": 4.5972631578947364e-05,
823
+ "loss": 1.7649,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.15734989648033126,
828
+ "grad_norm": 1.6534359455108643,
829
+ "learning_rate": 4.544421052631579e-05,
830
+ "loss": 2.2768,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.15873015873015872,
835
+ "grad_norm": 1.90774667263031,
836
+ "learning_rate": 4.4915789473684213e-05,
837
+ "loss": 2.1505,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.1601104209799862,
842
+ "grad_norm": 0.938823401927948,
843
+ "learning_rate": 4.438736842105263e-05,
844
+ "loss": 1.8724,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.16149068322981366,
849
+ "grad_norm": 1.4365911483764648,
850
+ "learning_rate": 4.3858947368421056e-05,
851
+ "loss": 1.879,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.16287094547964112,
856
+ "grad_norm": 1.195896863937378,
857
+ "learning_rate": 4.3330526315789474e-05,
858
+ "loss": 1.9316,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.1642512077294686,
863
+ "grad_norm": 1.1968637704849243,
864
+ "learning_rate": 4.280210526315789e-05,
865
+ "loss": 1.9372,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.16563146997929606,
870
+ "grad_norm": 1.14974045753479,
871
+ "learning_rate": 4.2273684210526317e-05,
872
+ "loss": 1.7375,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.16701173222912352,
877
+ "grad_norm": 1.0331716537475586,
878
+ "learning_rate": 4.174526315789474e-05,
879
+ "loss": 1.4381,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.168391994478951,
884
+ "grad_norm": 1.178269624710083,
885
+ "learning_rate": 4.121684210526316e-05,
886
+ "loss": 1.7424,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.16977225672877846,
891
+ "grad_norm": 1.0635954141616821,
892
+ "learning_rate": 4.068842105263158e-05,
893
+ "loss": 1.8893,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.17115251897860592,
898
+ "grad_norm": 1.6326851844787598,
899
+ "learning_rate": 4.016e-05,
900
+ "loss": 1.811,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1725327812284334,
905
+ "grad_norm": 1.1465870141983032,
906
+ "learning_rate": 3.963157894736842e-05,
907
+ "loss": 2.0883,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.17391304347826086,
912
+ "grad_norm": 1.2966638803482056,
913
+ "learning_rate": 3.9103157894736844e-05,
914
+ "loss": 2.1553,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.17529330572808835,
919
+ "grad_norm": 1.4659764766693115,
920
+ "learning_rate": 3.857473684210526e-05,
921
+ "loss": 1.6968,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.1766735679779158,
926
+ "grad_norm": 1.5177134275436401,
927
+ "learning_rate": 3.804631578947369e-05,
928
+ "loss": 2.3954,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.17805383022774326,
933
+ "grad_norm": 1.3623806238174438,
934
+ "learning_rate": 3.7517894736842105e-05,
935
+ "loss": 1.9746,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.17943409247757075,
940
+ "grad_norm": 2.719251871109009,
941
+ "learning_rate": 3.698947368421052e-05,
942
+ "loss": 2.2148,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1808143547273982,
947
+ "grad_norm": 1.3998181819915771,
948
+ "learning_rate": 3.646105263157895e-05,
949
+ "loss": 1.9759,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.18219461697722567,
954
+ "grad_norm": 1.0175858736038208,
955
+ "learning_rate": 3.593263157894737e-05,
956
+ "loss": 1.7491,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.18357487922705315,
961
+ "grad_norm": 1.354689121246338,
962
+ "learning_rate": 3.540421052631579e-05,
963
+ "loss": 2.3992,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1849551414768806,
968
+ "grad_norm": 1.246686577796936,
969
+ "learning_rate": 3.4875789473684215e-05,
970
+ "loss": 1.6956,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.18633540372670807,
975
+ "grad_norm": 1.4282056093215942,
976
+ "learning_rate": 3.434736842105263e-05,
977
+ "loss": 1.8083,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.18771566597653555,
982
+ "grad_norm": 1.2194526195526123,
983
+ "learning_rate": 3.381894736842105e-05,
984
+ "loss": 1.5603,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.189095928226363,
989
+ "grad_norm": 1.3371927738189697,
990
+ "learning_rate": 3.329052631578947e-05,
991
+ "loss": 1.8759,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.19047619047619047,
996
+ "grad_norm": 1.5761876106262207,
997
+ "learning_rate": 3.27621052631579e-05,
998
+ "loss": 1.8185,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.19185645272601795,
1003
+ "grad_norm": 1.40762197971344,
1004
+ "learning_rate": 3.223368421052632e-05,
1005
+ "loss": 2.1374,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.1932367149758454,
1010
+ "grad_norm": 1.4383774995803833,
1011
+ "learning_rate": 3.1705263157894736e-05,
1012
+ "loss": 2.0446,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.19461697722567287,
1017
+ "grad_norm": 1.4140267372131348,
1018
+ "learning_rate": 3.117684210526316e-05,
1019
+ "loss": 2.1209,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.19599723947550035,
1024
+ "grad_norm": 1.440808892250061,
1025
+ "learning_rate": 3.064842105263158e-05,
1026
+ "loss": 1.8894,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.1973775017253278,
1031
+ "grad_norm": 1.4002034664154053,
1032
+ "learning_rate": 3.012e-05,
1033
+ "loss": 1.5099,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.19875776397515527,
1038
+ "grad_norm": 1.9405709505081177,
1039
+ "learning_rate": 2.9591578947368418e-05,
1040
+ "loss": 2.3698,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.20013802622498275,
1045
+ "grad_norm": 1.799262285232544,
1046
+ "learning_rate": 2.9063157894736842e-05,
1047
+ "loss": 2.4062,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2015182884748102,
1052
+ "grad_norm": 1.4573534727096558,
1053
+ "learning_rate": 2.8534736842105264e-05,
1054
+ "loss": 1.9666,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2028985507246377,
1059
+ "grad_norm": 1.7938553094863892,
1060
+ "learning_rate": 2.800631578947368e-05,
1061
+ "loss": 1.9005,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.20427881297446515,
1066
+ "grad_norm": 1.662430763244629,
1067
+ "learning_rate": 2.7477894736842106e-05,
1068
+ "loss": 1.8399,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.2056590752242926,
1073
+ "grad_norm": 2.1903955936431885,
1074
+ "learning_rate": 2.6949473684210527e-05,
1075
+ "loss": 2.2387,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.2070393374741201,
1080
+ "grad_norm": 2.4292702674865723,
1081
+ "learning_rate": 2.6421052631578945e-05,
1082
+ "loss": 1.8656,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.2070393374741201,
1087
+ "eval_loss": 2.0511386394500732,
1088
+ "eval_runtime": 7.5598,
1089
+ "eval_samples_per_second": 40.345,
1090
+ "eval_steps_per_second": 10.185,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2575829827584000.0,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null