0x1202 commited on
Commit
5e97ae5
·
verified ·
1 Parent(s): 55f3df4

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:b7b13319842c308ca7c9e7b3be72f196865baccdeba453ce8daa90facf0a8813
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c439bba88a9bd3b36c0b1ad6af94e363b240968e6c2de0de346e595b95064982
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5cea42f5ecd80d6163cc2ff7029407d2bef933122e0e121b8d0c75298fc58ee
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7459678fa1667c148f82c1354f8b3eb4868b128ca6bcfceac9ae7c02d018515
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41ce16549c5ce648bc4cd70eabfbfffcac03ae175cbb67d6f132b32b27e35e91
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5340866a960d0fc52b38f1b47e1935683c371307df793bae14bfaa4a5aa47fa3
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": 1.5086487531661987,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.059127864005912786,
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": 11.833,
732
  "eval_steps_per_second": 5.919,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5273960904065024e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4425833225250244,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.08869179600886919,
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": 11.833,
732
  "eval_steps_per_second": 5.919,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.05971914264597192,
737
+ "grad_norm": 0.6345250010490417,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 1.2306,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.06031042128603104,
744
+ "grad_norm": 0.661770761013031,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 1.1069,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.06090169992609017,
751
+ "grad_norm": 0.6401956081390381,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 1.1062,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0614929785661493,
758
+ "grad_norm": 0.5216076374053955,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 1.1759,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06208425720620843,
765
+ "grad_norm": 0.508010745048523,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 1.1372,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06267553584626756,
772
+ "grad_norm": 0.43060287833213806,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 0.9952,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06326681448632668,
779
+ "grad_norm": 0.42570412158966064,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 1.038,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.06385809312638581,
786
+ "grad_norm": 0.398336261510849,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 1.0446,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.06444937176644494,
793
+ "grad_norm": 0.42458900809288025,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.04,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.06504065040650407,
800
+ "grad_norm": 0.4676673114299774,
801
+ "learning_rate": 5e-05,
802
+ "loss": 1.1186,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.06563192904656319,
807
+ "grad_norm": 0.4919835031032562,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.2161,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.06622320768662232,
814
+ "grad_norm": 0.45064666867256165,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 1.15,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.06681448632668145,
821
+ "grad_norm": 0.4385722875595093,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 0.9469,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.06740576496674058,
828
+ "grad_norm": 0.4354681074619293,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 1.1776,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.0679970436067997,
835
+ "grad_norm": 0.44736358523368835,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.1351,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.06858832224685883,
842
+ "grad_norm": 0.4752048850059509,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.0846,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.06917960088691796,
849
+ "grad_norm": 0.4718168377876282,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 1.1177,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0697708795269771,
856
+ "grad_norm": 0.47653982043266296,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.2877,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.07036215816703621,
863
+ "grad_norm": 0.4798600673675537,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 1.2453,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.07095343680709534,
870
+ "grad_norm": 0.4777057468891144,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 1.2573,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07154471544715447,
877
+ "grad_norm": 0.5245465040206909,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 1.2607,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0721359940872136,
884
+ "grad_norm": 0.6541303992271423,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.3967,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.07272727272727272,
891
+ "grad_norm": 0.4983082115650177,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.1609,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.07331855136733186,
898
+ "grad_norm": 0.5334490537643433,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 1.4802,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.07390983000739099,
905
+ "grad_norm": 0.5178830623626709,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 1.2526,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.07450110864745012,
912
+ "grad_norm": 0.6008628606796265,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 1.5288,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.07509238728750924,
919
+ "grad_norm": 0.5870925188064575,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 1.3033,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.07568366592756837,
926
+ "grad_norm": 0.6223778128623962,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 1.4781,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0762749445676275,
933
+ "grad_norm": 0.6285609006881714,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.4295,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.07686622320768663,
940
+ "grad_norm": 0.6036990880966187,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 1.3522,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.07745750184774575,
947
+ "grad_norm": 0.64960116147995,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 1.6885,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.07804878048780488,
954
+ "grad_norm": 0.7212278246879578,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 1.7423,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.07864005912786401,
961
+ "grad_norm": 0.7196757197380066,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 1.641,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.07923133776792314,
968
+ "grad_norm": 0.7324296832084656,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 1.7138,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.07982261640798226,
975
+ "grad_norm": 0.8470680713653564,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.7422,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.08041389504804139,
982
+ "grad_norm": 0.8423807621002197,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.9454,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.08100517368810052,
989
+ "grad_norm": 0.7693266272544861,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 1.6584,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.08159645232815965,
996
+ "grad_norm": 0.7691271901130676,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 1.7034,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.08218773096821877,
1003
+ "grad_norm": 0.8926898241043091,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 1.9296,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0827790096082779,
1010
+ "grad_norm": 1.0026094913482666,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 2.0774,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.08337028824833703,
1017
+ "grad_norm": 0.9475246667861938,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 1.8612,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.08396156688839616,
1024
+ "grad_norm": 1.0189855098724365,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 2.0114,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.08455284552845528,
1031
+ "grad_norm": 0.9443454742431641,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 1.9034,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.08514412416851441,
1038
+ "grad_norm": 1.159962773323059,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 1.9818,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.08573540280857354,
1045
+ "grad_norm": 1.0357986688613892,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 1.971,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.08632668144863268,
1052
+ "grad_norm": 1.1854385137557983,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 2.0195,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.08691796008869179,
1059
+ "grad_norm": 1.549296498298645,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 2.3472,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.08750923872875092,
1066
+ "grad_norm": 1.5036619901657104,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 2.3668,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.08810051736881006,
1073
+ "grad_norm": 1.41562819480896,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 2.1436,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.08869179600886919,
1080
+ "grad_norm": 1.4566277265548706,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 2.0975,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.08869179600886919,
1087
+ "eval_loss": 1.4425833225250244,
1088
+ "eval_runtime": 240.4675,
1089
+ "eval_samples_per_second": 11.848,
1090
+ "eval_steps_per_second": 5.926,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2892084614240666e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null