0x1202 commited on
Commit
d83a4f8
·
verified ·
1 Parent(s): 8d15e42

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 sha256:4944a96e3f8b1d0df3a20867cb1d55cbce82fcb349c9f1170b2bb02da35e2b90
3
  size 912336848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88eadfdb27fb0993fe2b57c68f109f9c723a9645085d211322f31b1315be42fc
3
  size 912336848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7094ac9468e5f1bb1f2905ecd4a8d6be707d55f0b908d253a063661bb90bff0e
3
  size 1824995682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d835a2a8f7ebefe958ea59d078258e2be375553e98ae2f1f7f7b9aad20a53c31
3
  size 1824995682
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f439dbdc7cab89b851bc5b1a439599eb4bcd2c82aa8600ce280b751cbc8aab5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:987e07c9c7bcd8e15d96b84448a7f4c3b1b4c179f5adfa392649dc25d7e2b2cc
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": 0.3840712308883667,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.016717515777155516,
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": 8.532,
732
  "eval_steps_per_second": 4.267,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.3267123404996608e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.33944934606552124,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.025076273665733274,
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": 8.532,
732
  "eval_steps_per_second": 4.267,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.01688469093492707,
737
+ "grad_norm": 8.497836112976074,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 1.1939,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.017051866092698625,
744
+ "grad_norm": 7.477349758148193,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 2.0787,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01721904125047018,
751
+ "grad_norm": 7.172429084777832,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 1.6864,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.017386216408241735,
758
+ "grad_norm": 8.384211540222168,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 1.8249,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.01755339156601329,
765
+ "grad_norm": 5.726856231689453,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 1.5703,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.017720566723784845,
772
+ "grad_norm": 6.198292255401611,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 2.1273,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0178877418815564,
779
+ "grad_norm": 4.357252597808838,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 1.1151,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.018054917039327954,
786
+ "grad_norm": 4.520287036895752,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 1.7011,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.018222092197099513,
793
+ "grad_norm": 3.671816349029541,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.0517,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.018389267354871067,
800
+ "grad_norm": 5.582248687744141,
801
+ "learning_rate": 5e-05,
802
+ "loss": 1.6454,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.018556442512642622,
807
+ "grad_norm": 4.559932708740234,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.6997,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.018723617670414177,
814
+ "grad_norm": 4.87907600402832,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 1.6121,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.018890792828185732,
821
+ "grad_norm": 5.985311508178711,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 1.894,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.019057967985957287,
828
+ "grad_norm": 5.563694477081299,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 1.4096,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.01922514314372884,
835
+ "grad_norm": 4.012616157531738,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.1671,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.019392318301500396,
842
+ "grad_norm": 5.445400238037109,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.1218,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.01955949345927195,
849
+ "grad_norm": 4.193072319030762,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 1.1577,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.019726668617043506,
856
+ "grad_norm": 4.184262752532959,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.3176,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.019893843774815064,
863
+ "grad_norm": 3.5578956604003906,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 1.0705,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.02006101893258662,
870
+ "grad_norm": 4.154637336730957,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 1.6145,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.020228194090358174,
877
+ "grad_norm": 8.214539527893066,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 1.3255,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.02039536924812973,
884
+ "grad_norm": 3.9702048301696777,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.3089,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.020562544405901283,
891
+ "grad_norm": 4.168085098266602,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.2921,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.020729719563672838,
898
+ "grad_norm": 4.158751487731934,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 1.1961,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.020896894721444393,
905
+ "grad_norm": 3.0978500843048096,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 1.027,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.021064069879215948,
912
+ "grad_norm": 4.032132625579834,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 1.1975,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.021231245036987503,
919
+ "grad_norm": 3.2967450618743896,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 1.1724,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.021398420194759057,
926
+ "grad_norm": 4.184244632720947,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 1.0997,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.021565595352530612,
933
+ "grad_norm": 3.61553955078125,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.2168,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.02173277051030217,
940
+ "grad_norm": 2.7184441089630127,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 0.9683,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.021899945668073725,
947
+ "grad_norm": 2.7383294105529785,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 0.7704,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.02206712082584528,
954
+ "grad_norm": 3.5409862995147705,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 0.9742,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.022234295983616835,
961
+ "grad_norm": 2.9273834228515625,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 1.0346,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.02240147114138839,
968
+ "grad_norm": 3.1921045780181885,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 1.1151,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.022568646299159945,
975
+ "grad_norm": 3.4800987243652344,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.0467,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0227358214569315,
982
+ "grad_norm": 3.3189215660095215,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.1769,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.022902996614703054,
989
+ "grad_norm": 3.6555469036102295,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 1.1048,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.02307017177247461,
996
+ "grad_norm": 3.6582908630371094,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 1.1974,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.023237346930246164,
1003
+ "grad_norm": 2.606125593185425,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 0.7513,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.023404522088017722,
1010
+ "grad_norm": 3.5903327465057373,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 1.2009,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.023571697245789277,
1017
+ "grad_norm": 4.257547855377197,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 1.7713,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.02373887240356083,
1024
+ "grad_norm": 3.8268728256225586,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 1.3315,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.023906047561332387,
1031
+ "grad_norm": 3.9802815914154053,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 1.531,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.02407322271910394,
1038
+ "grad_norm": 3.5218703746795654,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 0.9738,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.024240397876875496,
1045
+ "grad_norm": 3.5325393676757812,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 1.1883,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.02440757303464705,
1052
+ "grad_norm": 2.8327746391296387,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 1.1112,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.024574748192418606,
1059
+ "grad_norm": 3.83736252784729,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 1.6377,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.02474192335019016,
1066
+ "grad_norm": 3.671001672744751,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 1.3769,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.024909098507961715,
1073
+ "grad_norm": 5.089761257171631,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 2.1632,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.025076273665733274,
1080
+ "grad_norm": 11.317509651184082,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 1.8115,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.025076273665733274,
1087
+ "eval_loss": 0.33944934606552124,
1088
+ "eval_runtime": 1179.9193,
1089
+ "eval_samples_per_second": 8.539,
1090
+ "eval_steps_per_second": 4.27,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.4929696483311616e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null