prxy5605 commited on
Commit
edfc3b1
·
verified ·
1 Parent(s): e1f81f7

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 sha256:00eaadf807d93761ef5e07139c8dddbb275e835a415337718c887545d74e7ba7
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82645c9fe11ec7c0f62f872f36cf328e10bf47eb8ffaae8b79e8280971a05352
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59c49c3f7d0592475f5a3b291ddc60e64ea767a49fdbecfaa24782fe4b88e25b
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf865d3895b08fe49e302c4c30226d962b97e15ab75c9b2cdf298096b64826d
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49e687ee3597cc2458951fb9af2b7ff6d3ff128adb033f60830e063504287484
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2454fca9dcb56b67560d9129d69cdaedcbff5c09ff4e39ece5be8576c03eb0f8
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": 1.2480071783065796,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0307243259850987,
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": 12.355,
732
  "eval_steps_per_second": 6.177,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.434577118649385e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0585381984710693,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.046086488977648055,
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": 12.355,
732
  "eval_steps_per_second": 6.177,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.031031569244949687,
737
+ "grad_norm": 10.580477714538574,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 5.5392,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.031338812504800674,
744
+ "grad_norm": 9.869646072387695,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 5.5595,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.03164605576465166,
751
+ "grad_norm": 9.99475383758545,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 4.8398,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.03195329902450265,
758
+ "grad_norm": 6.947811126708984,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 4.2438,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.032260542284353634,
765
+ "grad_norm": 6.170292377471924,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 4.6814,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.03256778554420462,
772
+ "grad_norm": 6.3110246658325195,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 4.4389,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.032875028804055614,
779
+ "grad_norm": 6.087858200073242,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 4.1039,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0331822720639066,
786
+ "grad_norm": 6.2835211753845215,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 4.0166,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03348951532375759,
793
+ "grad_norm": 6.776898384094238,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 4.2686,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.033796758583608574,
800
+ "grad_norm": 6.588527202606201,
801
+ "learning_rate": 5e-05,
802
+ "loss": 3.7269,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03410400184345956,
807
+ "grad_norm": 7.68696403503418,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 3.9392,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.03441124510331055,
814
+ "grad_norm": 5.877866744995117,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 3.5263,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.034718488363161534,
821
+ "grad_norm": 7.236352920532227,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 3.7052,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.03502573162301252,
828
+ "grad_norm": 6.501185894012451,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 2.9949,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03533297488286351,
835
+ "grad_norm": 6.9282941818237305,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 3.5694,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.035640218142714494,
842
+ "grad_norm": 7.355767250061035,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 3.9165,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.03594746140256548,
849
+ "grad_norm": 7.192873954772949,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 3.1828,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.03625470466241647,
856
+ "grad_norm": 6.482280254364014,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 3.2275,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.036561947922267454,
863
+ "grad_norm": 6.704769611358643,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 3.1593,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.03686919118211844,
870
+ "grad_norm": 6.919817924499512,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 3.0843,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.03717643444196943,
877
+ "grad_norm": 7.4176506996154785,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 3.4191,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.037483677701820414,
884
+ "grad_norm": 7.300436496734619,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 3.7824,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.0377909209616714,
891
+ "grad_norm": 6.638614177703857,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 3.3756,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.03809816422152239,
898
+ "grad_norm": 6.030972957611084,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 3.3504,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.038405407481373374,
905
+ "grad_norm": 7.475324630737305,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 3.5805,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.03871265074122437,
912
+ "grad_norm": 7.8704609870910645,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 3.6184,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.039019894001075354,
919
+ "grad_norm": 7.465869426727295,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 4.1467,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.03932713726092634,
926
+ "grad_norm": 7.257153511047363,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 4.2342,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.03963438052077733,
933
+ "grad_norm": 7.452193260192871,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 4.3429,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.039941623780628314,
940
+ "grad_norm": 7.880541801452637,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 4.3863,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0402488670404793,
947
+ "grad_norm": 8.45700740814209,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 4.8662,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.04055611030033029,
954
+ "grad_norm": 8.435225486755371,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 4.2266,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.040863353560181274,
961
+ "grad_norm": 9.154268264770508,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 4.2599,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.04117059682003226,
968
+ "grad_norm": 7.695627212524414,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 4.0229,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.04147784007988325,
975
+ "grad_norm": 9.314230918884277,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 4.8999,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.041785083339734234,
982
+ "grad_norm": 9.278669357299805,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 4.6078,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.04209232659958522,
989
+ "grad_norm": 10.638617515563965,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 4.6089,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.04239956985943621,
996
+ "grad_norm": 8.870823860168457,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 4.3292,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.042706813119287194,
1003
+ "grad_norm": 9.005095481872559,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 4.5548,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.04301405637913818,
1010
+ "grad_norm": 10.735925674438477,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 4.8442,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.04332129963898917,
1017
+ "grad_norm": 9.419788360595703,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 4.926,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.043628542898840154,
1024
+ "grad_norm": 9.60610580444336,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 4.2713,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.04393578615869114,
1031
+ "grad_norm": 8.531740188598633,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 4.0917,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.04424302941854213,
1038
+ "grad_norm": 9.785737037658691,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 4.6779,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.044550272678393114,
1045
+ "grad_norm": 10.093374252319336,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 4.713,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.04485751593824411,
1052
+ "grad_norm": 11.576554298400879,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 5.0362,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.045164759198095095,
1059
+ "grad_norm": 12.363187789916992,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 5.3881,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.04547200245794608,
1066
+ "grad_norm": 11.872509956359863,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 4.8039,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.04577924571779707,
1073
+ "grad_norm": 13.223235130310059,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 5.4591,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.046086488977648055,
1080
+ "grad_norm": 13.729710578918457,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 5.6227,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.046086488977648055,
1087
+ "eval_loss": 1.0585381984710693,
1088
+ "eval_runtime": 443.8526,
1089
+ "eval_samples_per_second": 12.351,
1090
+ "eval_steps_per_second": 6.175,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.150076928449577e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null