Training in progress, step 150, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 37965300
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c176d54ad21da2583d0c1b8a23b42d5d4f5d087533579337f01ee622178a9065
|
| 3 |
size 37965300
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a39d244929ff4d03b82e59d530f09311a95ad8bbc413f0e1a16b9f12428b3e0
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:285055c203c0e51e433ff14d6fa6e0c364698ec978202e506a844a8372901f4a
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 38,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -837,6 +837,258 @@
|
|
| 837 |
"eval_samples_per_second": 9.685,
|
| 838 |
"eval_steps_per_second": 4.842,
|
| 839 |
"step": 114
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 840 |
}
|
| 841 |
],
|
| 842 |
"logging_steps": 1,
|
|
@@ -851,12 +1103,12 @@
|
|
| 851 |
"should_evaluate": false,
|
| 852 |
"should_log": false,
|
| 853 |
"should_save": true,
|
| 854 |
-
"should_training_stop":
|
| 855 |
},
|
| 856 |
"attributes": {}
|
| 857 |
}
|
| 858 |
},
|
| 859 |
-
"total_flos":
|
| 860 |
"train_batch_size": 2,
|
| 861 |
"trial_name": null,
|
| 862 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2660753880266075,
|
| 5 |
"eval_steps": 38,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 837 |
"eval_samples_per_second": 9.685,
|
| 838 |
"eval_steps_per_second": 4.842,
|
| 839 |
"step": 114
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.2039911308203991,
|
| 843 |
+
"grad_norm": NaN,
|
| 844 |
+
"learning_rate": 5.857864376269051e-05,
|
| 845 |
+
"loss": 0.0,
|
| 846 |
+
"step": 115
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.2057649667405765,
|
| 850 |
+
"grad_norm": NaN,
|
| 851 |
+
"learning_rate": 5.544102723452171e-05,
|
| 852 |
+
"loss": 0.0,
|
| 853 |
+
"step": 116
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.2075388026607539,
|
| 857 |
+
"grad_norm": NaN,
|
| 858 |
+
"learning_rate": 5.237620050253189e-05,
|
| 859 |
+
"loss": 0.0,
|
| 860 |
+
"step": 117
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.20931263858093127,
|
| 864 |
+
"grad_norm": NaN,
|
| 865 |
+
"learning_rate": 4.938570679927783e-05,
|
| 866 |
+
"loss": 0.0,
|
| 867 |
+
"step": 118
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.21108647450110865,
|
| 871 |
+
"grad_norm": NaN,
|
| 872 |
+
"learning_rate": 4.647105192839778e-05,
|
| 873 |
+
"loss": 0.0,
|
| 874 |
+
"step": 119
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.21286031042128603,
|
| 878 |
+
"grad_norm": NaN,
|
| 879 |
+
"learning_rate": 4.363370350639404e-05,
|
| 880 |
+
"loss": 0.0,
|
| 881 |
+
"step": 120
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.2146341463414634,
|
| 885 |
+
"grad_norm": NaN,
|
| 886 |
+
"learning_rate": 4.087509022364382e-05,
|
| 887 |
+
"loss": 0.0,
|
| 888 |
+
"step": 121
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 0.2164079822616408,
|
| 892 |
+
"grad_norm": NaN,
|
| 893 |
+
"learning_rate": 3.819660112501053e-05,
|
| 894 |
+
"loss": 0.0,
|
| 895 |
+
"step": 122
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 0.21818181818181817,
|
| 899 |
+
"grad_norm": NaN,
|
| 900 |
+
"learning_rate": 3.5599584910418035e-05,
|
| 901 |
+
"loss": 0.0,
|
| 902 |
+
"step": 123
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.21995565410199558,
|
| 906 |
+
"grad_norm": NaN,
|
| 907 |
+
"learning_rate": 3.3085349255739474e-05,
|
| 908 |
+
"loss": 0.0,
|
| 909 |
+
"step": 124
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.22172949002217296,
|
| 913 |
+
"grad_norm": NaN,
|
| 914 |
+
"learning_rate": 3.0655160154343174e-05,
|
| 915 |
+
"loss": 0.0,
|
| 916 |
+
"step": 125
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.22350332594235034,
|
| 920 |
+
"grad_norm": NaN,
|
| 921 |
+
"learning_rate": 2.831024127962678e-05,
|
| 922 |
+
"loss": 0.0,
|
| 923 |
+
"step": 126
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.22527716186252772,
|
| 927 |
+
"grad_norm": NaN,
|
| 928 |
+
"learning_rate": 2.6051773368860934e-05,
|
| 929 |
+
"loss": 0.0,
|
| 930 |
+
"step": 127
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.2270509977827051,
|
| 934 |
+
"grad_norm": NaN,
|
| 935 |
+
"learning_rate": 2.38808936286524e-05,
|
| 936 |
+
"loss": 0.0,
|
| 937 |
+
"step": 128
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.22882483370288248,
|
| 941 |
+
"grad_norm": NaN,
|
| 942 |
+
"learning_rate": 2.1798695162326442e-05,
|
| 943 |
+
"loss": 0.0,
|
| 944 |
+
"step": 129
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.23059866962305986,
|
| 948 |
+
"grad_norm": NaN,
|
| 949 |
+
"learning_rate": 1.9806226419516192e-05,
|
| 950 |
+
"loss": 0.0,
|
| 951 |
+
"step": 130
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.23237250554323724,
|
| 955 |
+
"grad_norm": NaN,
|
| 956 |
+
"learning_rate": 1.790449066823683e-05,
|
| 957 |
+
"loss": 0.0,
|
| 958 |
+
"step": 131
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 0.23414634146341465,
|
| 962 |
+
"grad_norm": NaN,
|
| 963 |
+
"learning_rate": 1.6094445489709885e-05,
|
| 964 |
+
"loss": 0.0,
|
| 965 |
+
"step": 132
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 0.23592017738359203,
|
| 969 |
+
"grad_norm": NaN,
|
| 970 |
+
"learning_rate": 1.4377002296192233e-05,
|
| 971 |
+
"loss": 0.0,
|
| 972 |
+
"step": 133
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 0.2376940133037694,
|
| 976 |
+
"grad_norm": NaN,
|
| 977 |
+
"learning_rate": 1.275302587205256e-05,
|
| 978 |
+
"loss": 0.0,
|
| 979 |
+
"step": 134
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 0.2394678492239468,
|
| 983 |
+
"grad_norm": NaN,
|
| 984 |
+
"learning_rate": 1.1223333938326485e-05,
|
| 985 |
+
"loss": 0.0,
|
| 986 |
+
"step": 135
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.24124168514412417,
|
| 990 |
+
"grad_norm": NaN,
|
| 991 |
+
"learning_rate": 9.788696740969295e-06,
|
| 992 |
+
"loss": 0.0,
|
| 993 |
+
"step": 136
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.24301552106430155,
|
| 997 |
+
"grad_norm": NaN,
|
| 998 |
+
"learning_rate": 8.44983666301391e-06,
|
| 999 |
+
"loss": 0.0,
|
| 1000 |
+
"step": 137
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.24478935698447893,
|
| 1004 |
+
"grad_norm": NaN,
|
| 1005 |
+
"learning_rate": 7.2074278608293525e-06,
|
| 1006 |
+
"loss": 0.0,
|
| 1007 |
+
"step": 138
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.2465631929046563,
|
| 1011 |
+
"grad_norm": NaN,
|
| 1012 |
+
"learning_rate": 6.062095924662625e-06,
|
| 1013 |
+
"loss": 0.0,
|
| 1014 |
+
"step": 139
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.24833702882483372,
|
| 1018 |
+
"grad_norm": NaN,
|
| 1019 |
+
"learning_rate": 5.0144175636352765e-06,
|
| 1020 |
+
"loss": 0.0,
|
| 1021 |
+
"step": 140
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.2501108647450111,
|
| 1025 |
+
"grad_norm": NaN,
|
| 1026 |
+
"learning_rate": 4.064920315352904e-06,
|
| 1027 |
+
"loss": 0.0,
|
| 1028 |
+
"step": 141
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.2518847006651885,
|
| 1032 |
+
"grad_norm": NaN,
|
| 1033 |
+
"learning_rate": 3.2140822802740668e-06,
|
| 1034 |
+
"loss": 0.0,
|
| 1035 |
+
"step": 142
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.25365853658536586,
|
| 1039 |
+
"grad_norm": NaN,
|
| 1040 |
+
"learning_rate": 2.462331880972468e-06,
|
| 1041 |
+
"loss": 0.0,
|
| 1042 |
+
"step": 143
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.25543237250554324,
|
| 1046 |
+
"grad_norm": NaN,
|
| 1047 |
+
"learning_rate": 1.81004764641306e-06,
|
| 1048 |
+
"loss": 0.0,
|
| 1049 |
+
"step": 144
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.2572062084257206,
|
| 1053 |
+
"grad_norm": NaN,
|
| 1054 |
+
"learning_rate": 1.2575580213514792e-06,
|
| 1055 |
+
"loss": 0.0,
|
| 1056 |
+
"step": 145
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.258980044345898,
|
| 1060 |
+
"grad_norm": NaN,
|
| 1061 |
+
"learning_rate": 8.051412009521864e-07,
|
| 1062 |
+
"loss": 0.0,
|
| 1063 |
+
"step": 146
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.2607538802660754,
|
| 1067 |
+
"grad_norm": NaN,
|
| 1068 |
+
"learning_rate": 4.530249907087836e-07,
|
| 1069 |
+
"loss": 0.0,
|
| 1070 |
+
"step": 147
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.26252771618625276,
|
| 1074 |
+
"grad_norm": NaN,
|
| 1075 |
+
"learning_rate": 2.0138669173708213e-07,
|
| 1076 |
+
"loss": 0.0,
|
| 1077 |
+
"step": 148
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.26430155210643014,
|
| 1081 |
+
"grad_norm": NaN,
|
| 1082 |
+
"learning_rate": 5.035301149869387e-08,
|
| 1083 |
+
"loss": 0.0,
|
| 1084 |
+
"step": 149
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.2660753880266075,
|
| 1088 |
+
"grad_norm": NaN,
|
| 1089 |
+
"learning_rate": 0.0,
|
| 1090 |
+
"loss": 0.0,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1103 |
"should_evaluate": false,
|
| 1104 |
"should_log": false,
|
| 1105 |
"should_save": true,
|
| 1106 |
+
"should_training_stop": true
|
| 1107 |
},
|
| 1108 |
"attributes": {}
|
| 1109 |
}
|
| 1110 |
},
|
| 1111 |
+
"total_flos": 4898508138086400.0,
|
| 1112 |
"train_batch_size": 2,
|
| 1113 |
"trial_name": null,
|
| 1114 |
"trial_params": null
|