prxy5608 commited on
Commit
6fef251
·
verified ·
1 Parent(s): 47a0c58

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 sha256:6764e321a6b576dcd0c276e14433412d16a99d76219a6a6858603806d79dc6ab
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee0efc73b7434ff2a78294aaebc6be66aeec24a26458daffba6a33b5333e56a7
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc8515e295f88a0ce9dbc2017cdd7f1686a13161da9cd4724799fe1c9aeba116
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:041ebf9cade094f0b6aa9cc3617c591ca6ed68e8164973b0965a27127845e1fb
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a998a50f97e3f478aab2ceec4259aa3539418f1a85a44db802c0e9f0030526b6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a22ff951079e4e8135cc1cc953b25b1ecb8f85b88cab9503221c3be2cfe76c65
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": 0.3120051324367523,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.00946924861512239,
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": 12.921,
732
  "eval_steps_per_second": 6.461,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.330495774261248e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3101840913295746,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.014203872922683585,
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": 12.921,
732
  "eval_steps_per_second": 6.461,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.009563941101273614,
737
+ "grad_norm": 0.4451744258403778,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 0.2185,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.009658633587424838,
744
+ "grad_norm": 0.393392950296402,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 0.2326,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.009753326073576062,
751
+ "grad_norm": 0.3935139775276184,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 0.2376,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.009848018559727285,
758
+ "grad_norm": 0.49239593744277954,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 0.3127,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.00994271104587851,
765
+ "grad_norm": 0.5239997506141663,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 0.4293,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.010037403532029733,
772
+ "grad_norm": 0.4456406831741333,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 0.3016,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.010132096018180957,
779
+ "grad_norm": 0.40427473187446594,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 0.186,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01022678850433218,
786
+ "grad_norm": 0.32894396781921387,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 0.2442,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.010321480990483405,
793
+ "grad_norm": 0.4474416971206665,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 0.2203,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.010416173476634628,
800
+ "grad_norm": 0.4535369873046875,
801
+ "learning_rate": 5e-05,
802
+ "loss": 0.329,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.010510865962785852,
807
+ "grad_norm": 0.566321074962616,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 0.3164,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.010605558448937076,
814
+ "grad_norm": 0.33763089776039124,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 0.2745,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.0107002509350883,
821
+ "grad_norm": 0.37318381667137146,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 0.2406,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.010794943421239525,
828
+ "grad_norm": 0.35014447569847107,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 0.2285,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.01088963590739075,
835
+ "grad_norm": 0.3987157642841339,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 0.2837,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.010984328393541973,
842
+ "grad_norm": 0.36429470777511597,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 0.2372,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.011079020879693197,
849
+ "grad_norm": 0.4331720769405365,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 0.3545,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.01117371336584442,
856
+ "grad_norm": 0.32597437500953674,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 0.2248,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.011268405851995645,
863
+ "grad_norm": 0.32949554920196533,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 0.2144,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.011363098338146868,
870
+ "grad_norm": 0.5105450749397278,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 0.4314,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.011457790824298092,
877
+ "grad_norm": 0.37223193049430847,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 0.2877,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.011552483310449316,
884
+ "grad_norm": 0.33164238929748535,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 0.2723,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.01164717579660054,
891
+ "grad_norm": 0.37629207968711853,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 0.2631,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.011741868282751764,
898
+ "grad_norm": 0.4204508364200592,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 0.2915,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.011836560768902988,
905
+ "grad_norm": 0.49447402358055115,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 0.3062,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.011931253255054211,
912
+ "grad_norm": 0.38985031843185425,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 0.3535,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.012025945741205435,
919
+ "grad_norm": 0.393546462059021,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 0.3109,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.012120638227356659,
926
+ "grad_norm": 0.4812166690826416,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 0.2909,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.012215330713507883,
933
+ "grad_norm": 0.4680134952068329,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 0.3586,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.012310023199659107,
940
+ "grad_norm": 0.30080264806747437,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 0.2044,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.01240471568581033,
947
+ "grad_norm": 0.3511880338191986,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 0.2577,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.012499408171961554,
954
+ "grad_norm": 0.482510507106781,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 0.3746,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.012594100658112778,
961
+ "grad_norm": 0.4897306263446808,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 0.2549,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.012688793144264002,
968
+ "grad_norm": 0.48270678520202637,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 0.2571,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.012783485630415226,
975
+ "grad_norm": 0.7660849094390869,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 0.3252,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.01287817811656645,
982
+ "grad_norm": 0.34716224670410156,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 0.2741,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.012972870602717674,
989
+ "grad_norm": 0.41306325793266296,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 0.2623,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.013067563088868897,
996
+ "grad_norm": 0.47318580746650696,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 0.309,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.013162255575020123,
1003
+ "grad_norm": 0.537813663482666,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 0.3915,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.013256948061171347,
1010
+ "grad_norm": 0.5747792720794678,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 0.3346,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.01335164054732257,
1017
+ "grad_norm": 0.5642172694206238,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 0.3576,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.013446333033473794,
1024
+ "grad_norm": 0.725172758102417,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 0.4239,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.013541025519625018,
1031
+ "grad_norm": 0.6283183097839355,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 0.3412,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.013635718005776242,
1038
+ "grad_norm": 0.5846209526062012,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 0.3374,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.013730410491927466,
1045
+ "grad_norm": 0.7421755194664001,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 0.3344,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.01382510297807869,
1052
+ "grad_norm": 0.5736775994300842,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 0.215,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.013919795464229914,
1059
+ "grad_norm": 0.5754392743110657,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 0.2971,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.014014487950381137,
1066
+ "grad_norm": 0.5859729051589966,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 0.3441,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.014109180436532361,
1073
+ "grad_norm": 0.6326302886009216,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 0.3143,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.014203872922683585,
1080
+ "grad_norm": 0.47283610701560974,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 0.3032,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.014203872922683585,
1087
+ "eval_loss": 0.3101840913295746,
1088
+ "eval_runtime": 1378.4955,
1089
+ "eval_samples_per_second": 12.903,
1090
+ "eval_steps_per_second": 6.452,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.995743661391872e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null