aleegis09 commited on
Commit
8d4cc6a
·
verified ·
1 Parent(s): 6183739

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 sha256:543cabfc6d5bc954b47dcdde6571ec3d5ce0243b46b60f1fe4a8ea9865e952f5
3
  size 479005064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f53dd43b2abea6bb22908267f76f436b117145ab9368a98260a9c542d933798f
3
  size 479005064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ee2148d3d1fa3fa092d0f526567ff9407d7e80527157565c20ac7e4b8758c26
3
  size 958299770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af465da49c4bfda42091a2ea385b02ec734fcef5f84bb8660e46e95c9f5af07a
3
  size 958299770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c624552f1c961b604c5438d23262731c2c34ed397e3dcfcfd955324544844da
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c77a731a0272264625bc90759d3435f5f1af8a50c530c44fa549c1dd7e63a9d
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": 0.08056939393281937,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.043318171973142736,
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": 18.943,
732
  "eval_steps_per_second": 9.472,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 5.719288523312333e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.05704093724489212,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.0649772579597141,
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": 18.943,
732
  "eval_steps_per_second": 9.472,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04375135369287416,
737
+ "grad_norm": 0.9752314686775208,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 0.1654,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.044184535412605586,
744
+ "grad_norm": 0.903446614742279,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 0.1832,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.04461771713233702,
751
+ "grad_norm": 0.6539014577865601,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 0.1592,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.04505089885206844,
758
+ "grad_norm": 0.4455128014087677,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 0.1276,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.04548408057179987,
765
+ "grad_norm": 0.5171334743499756,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 0.1779,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0459172622915313,
772
+ "grad_norm": 0.6053957343101501,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 0.1559,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.046350444011262724,
779
+ "grad_norm": 0.5147733092308044,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 0.1247,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.04678362573099415,
786
+ "grad_norm": 0.6188340783119202,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 0.1215,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.04721680745072558,
793
+ "grad_norm": 0.4769625663757324,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 0.1144,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.047649989170457006,
800
+ "grad_norm": 0.5022192597389221,
801
+ "learning_rate": 5e-05,
802
+ "loss": 0.1214,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.04808317089018843,
807
+ "grad_norm": 0.3280904293060303,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 0.0796,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.04851635260991986,
814
+ "grad_norm": 0.5279192328453064,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 0.1151,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.04894953432965129,
821
+ "grad_norm": 0.47400593757629395,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 0.1186,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.04938271604938271,
828
+ "grad_norm": 0.6582249999046326,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 0.0961,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.049815897769114145,
835
+ "grad_norm": 0.40480566024780273,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 0.0765,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.05024907948884557,
842
+ "grad_norm": 0.3763730823993683,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 0.0739,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.050682261208576995,
849
+ "grad_norm": 0.40720927715301514,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 0.0798,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.05111544292830843,
856
+ "grad_norm": 0.7141808271408081,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 0.0874,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.05154862464803985,
863
+ "grad_norm": 0.5295721888542175,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 0.0861,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.05198180636777128,
870
+ "grad_norm": 0.3550686240196228,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 0.0749,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.05241498808750271,
877
+ "grad_norm": 0.5598456859588623,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 0.139,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.052848169807234134,
884
+ "grad_norm": 0.3951553702354431,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 0.0669,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.05328135152696556,
891
+ "grad_norm": 0.5975047945976257,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 0.1032,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.05371453324669699,
898
+ "grad_norm": 0.49492087960243225,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 0.0682,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.054147714966428416,
905
+ "grad_norm": 0.540847897529602,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 0.0871,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.05458089668615984,
912
+ "grad_norm": 0.44237419962882996,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 0.0571,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.05501407840589127,
919
+ "grad_norm": 0.5057970881462097,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 0.0885,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0554472601256227,
926
+ "grad_norm": 0.3728044629096985,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 0.0395,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.05588044184535412,
933
+ "grad_norm": 0.39620381593704224,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 0.048,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.056313623565085555,
940
+ "grad_norm": 0.5850706696510315,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 0.0673,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.05674680528481698,
947
+ "grad_norm": 0.4705985486507416,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 0.0457,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.057179987004548405,
954
+ "grad_norm": 0.39884859323501587,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 0.0609,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.05761316872427984,
961
+ "grad_norm": 0.34650862216949463,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 0.0439,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.05804635044401126,
968
+ "grad_norm": 0.5266785621643066,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 0.0665,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.05847953216374269,
975
+ "grad_norm": 0.23444664478302002,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 0.0308,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.05891271388347412,
982
+ "grad_norm": 0.25425028800964355,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 0.0171,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.059345895603205544,
989
+ "grad_norm": 0.40159934759140015,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 0.0369,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.05977907732293697,
996
+ "grad_norm": 0.32667964696884155,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 0.0294,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.0602122590426684,
1003
+ "grad_norm": 0.40988171100616455,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 0.039,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.060645440762399826,
1010
+ "grad_norm": 0.23806576430797577,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 0.0233,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.06107862248213125,
1017
+ "grad_norm": 0.8812161087989807,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 0.043,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.06151180420186268,
1024
+ "grad_norm": 0.38497522473335266,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 0.0168,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.06194498592159411,
1031
+ "grad_norm": 0.2601085901260376,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 0.0048,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.06237816764132553,
1038
+ "grad_norm": 0.2766932249069214,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 0.0226,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.06281134936105696,
1045
+ "grad_norm": 0.09686120599508286,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 0.0024,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0632445310807884,
1052
+ "grad_norm": 0.08909226208925247,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 0.0031,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.06367771280051981,
1059
+ "grad_norm": 0.2203822135925293,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 0.0149,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.06411089452025125,
1066
+ "grad_norm": 0.12339666485786438,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 0.0041,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.06454407623998268,
1073
+ "grad_norm": 0.2815093696117401,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 0.0132,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.0649772579597141,
1080
+ "grad_norm": 0.0794215053319931,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 0.0021,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.0649772579597141,
1087
+ "eval_loss": 0.05704093724489212,
1088
+ "eval_runtime": 204.8642,
1089
+ "eval_samples_per_second": 18.978,
1090
+ "eval_steps_per_second": 9.489,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 8.564705699089613e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null