prxy5605 commited on
Commit
dcf7bf8
·
verified ·
1 Parent(s): 3eb5e20

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 sha256:8c9c369232afcf88c994171f38016074d01563b66b24e5c97ff565499dfcb572
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76979180be189ec990e3459eaecb2de0ec8a8c8eadea7bbb74a45d0a114eeee9
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f7195a86d976834a21a0ae42718d7a0210b77cd590463fa28ded8ea39f251bc
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e647b2f1952c410a0e6ee55d88b4621fa553b7dfcfa9a173e5a37fc06f2618c
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:720beb628244d3e7e52a4ee594799e93166f635e750e5ed19a3aa03970c87a85
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd0e731c78489e8462c7659fcf89c8118a0d5ea09b14fbed00701025d69a1e8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1823816299438477,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.08547008547008547,
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": 12.303,
732
  "eval_steps_per_second": 6.155,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0974299907684326,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.1282051282051282,
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": 12.303,
732
  "eval_steps_per_second": 6.155,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.08632478632478632,
737
+ "grad_norm": 1.4788637161254883,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 1.3518,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.08717948717948718,
744
+ "grad_norm": 1.335060954093933,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 1.3276,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.08803418803418804,
751
+ "grad_norm": 1.2039484977722168,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 1.2607,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.08888888888888889,
758
+ "grad_norm": 1.0319693088531494,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 1.1666,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.08974358974358974,
765
+ "grad_norm": 0.9345054030418396,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 1.1578,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0905982905982906,
772
+ "grad_norm": 1.000648021697998,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 1.1824,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.09145299145299145,
779
+ "grad_norm": 1.0595582723617554,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 1.1541,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.09230769230769231,
786
+ "grad_norm": 1.059521198272705,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 1.1684,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.09316239316239316,
793
+ "grad_norm": 1.0103936195373535,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.1032,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.09401709401709402,
800
+ "grad_norm": 0.906261682510376,
801
+ "learning_rate": 5e-05,
802
+ "loss": 1.092,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.09487179487179487,
807
+ "grad_norm": 0.9363418817520142,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.1439,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.09572649572649573,
814
+ "grad_norm": 0.8963008522987366,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 1.134,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.09658119658119659,
821
+ "grad_norm": 0.932476282119751,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 1.0302,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.09743589743589744,
828
+ "grad_norm": 0.97416752576828,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 1.0884,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.09829059829059829,
835
+ "grad_norm": 0.9831287860870361,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.1182,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09914529914529914,
842
+ "grad_norm": 0.9273348450660706,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.1024,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.1,
849
+ "grad_norm": 0.9426711201667786,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 1.0477,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.10085470085470086,
856
+ "grad_norm": 0.9395505785942078,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.0258,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.10170940170940171,
863
+ "grad_norm": 0.9015635848045349,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 1.0528,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.10256410256410256,
870
+ "grad_norm": 0.9608397483825684,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 1.0525,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.10341880341880341,
877
+ "grad_norm": 0.8854332566261292,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 1.0047,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.10427350427350428,
884
+ "grad_norm": 0.9256286025047302,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.0357,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.10512820512820513,
891
+ "grad_norm": 0.9587220549583435,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.072,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.10598290598290598,
898
+ "grad_norm": 0.8476926684379578,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 0.9156,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.10683760683760683,
905
+ "grad_norm": 1.0829159021377563,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 1.0192,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1076923076923077,
912
+ "grad_norm": 1.1867055892944336,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 1.209,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.10854700854700855,
919
+ "grad_norm": 1.2425880432128906,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 1.1204,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.1094017094017094,
926
+ "grad_norm": 1.2878048419952393,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 1.1409,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.11025641025641025,
933
+ "grad_norm": 1.1198961734771729,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.1092,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1111111111111111,
940
+ "grad_norm": 1.176654577255249,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 1.2354,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.11196581196581197,
947
+ "grad_norm": 1.188136339187622,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 1.1406,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.11282051282051282,
954
+ "grad_norm": 1.10467529296875,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 1.0738,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.11367521367521367,
961
+ "grad_norm": 1.2116912603378296,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 1.1281,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.11452991452991453,
968
+ "grad_norm": 1.1236222982406616,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 1.0202,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.11538461538461539,
975
+ "grad_norm": 1.1949799060821533,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.0866,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.11623931623931624,
982
+ "grad_norm": 1.192546010017395,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.0747,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1170940170940171,
989
+ "grad_norm": 1.2602277994155884,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 1.203,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.11794871794871795,
996
+ "grad_norm": 1.1787879467010498,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 1.0729,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.1188034188034188,
1003
+ "grad_norm": 1.6451057195663452,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 1.1883,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.11965811965811966,
1010
+ "grad_norm": 1.201676368713379,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 1.0824,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.12051282051282051,
1017
+ "grad_norm": 1.1939303874969482,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 1.1034,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.12136752136752137,
1024
+ "grad_norm": 1.3140331506729126,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 1.221,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.12222222222222222,
1031
+ "grad_norm": 1.427099347114563,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 1.2256,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.12307692307692308,
1038
+ "grad_norm": 1.2661031484603882,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 1.2103,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.12393162393162394,
1045
+ "grad_norm": 1.2099844217300415,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 1.0893,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.12478632478632479,
1052
+ "grad_norm": 1.1992117166519165,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 0.9973,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.12564102564102564,
1059
+ "grad_norm": 1.2342702150344849,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 1.1072,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.1264957264957265,
1066
+ "grad_norm": 1.3184571266174316,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 1.0684,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.12735042735042734,
1073
+ "grad_norm": 1.321618676185608,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 1.0538,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.1282051282051282,
1080
+ "grad_norm": 1.1892586946487427,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 0.9054,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.1282051282051282,
1087
+ "eval_loss": 1.0974299907684326,
1088
+ "eval_runtime": 160.2081,
1089
+ "eval_samples_per_second": 12.303,
1090
+ "eval_steps_per_second": 6.154,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.262770368118784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null