Training in progress, step 165, 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 70667778
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39806d510b9ab24c764ffd908298907c327f0384acbaeda1da48e73cbb9e8ff6
|
| 3 |
size 70667778
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:257e290e23f3600edd1a568035aeb836a5aa20ce6d4cb3d5d8a1e69ff580b547
|
| 3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d1e404665d992b110eddd34e0b6a2f6f7b0fb1ba998e4738f1e997e398233ee
|
| 3 |
size 14512
|
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 sha256:79db7aed3a9923aa682703f13ca01a142bd6b5bf7acc8d720a4162bff9c52329
|
| 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": 55,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -801,6 +801,399 @@
|
|
| 801 |
"eval_samples_per_second": 22.024,
|
| 802 |
"eval_steps_per_second": 5.506,
|
| 803 |
"step": 110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 804 |
}
|
| 805 |
],
|
| 806 |
"logging_steps": 1,
|
|
@@ -820,7 +1213,7 @@
|
|
| 820 |
"attributes": {}
|
| 821 |
}
|
| 822 |
},
|
| 823 |
-
"total_flos":
|
| 824 |
"train_batch_size": 2,
|
| 825 |
"trial_name": null,
|
| 826 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7474518686296716,
|
| 5 |
"eval_steps": 55,
|
| 6 |
+
"global_step": 165,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 801 |
"eval_samples_per_second": 22.024,
|
| 802 |
"eval_steps_per_second": 5.506,
|
| 803 |
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.5028312570781427,
|
| 807 |
+
"grad_norm": NaN,
|
| 808 |
+
"learning_rate": 7.145603043863045e-05,
|
| 809 |
+
"loss": 0.0,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.507361268403171,
|
| 814 |
+
"grad_norm": NaN,
|
| 815 |
+
"learning_rate": 7.061781587369519e-05,
|
| 816 |
+
"loss": 0.0,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.5118912797281994,
|
| 821 |
+
"grad_norm": NaN,
|
| 822 |
+
"learning_rate": 6.977256034352712e-05,
|
| 823 |
+
"loss": 0.0,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.5164212910532276,
|
| 828 |
+
"grad_norm": NaN,
|
| 829 |
+
"learning_rate": 6.892055250211552e-05,
|
| 830 |
+
"loss": 0.0,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.5209513023782559,
|
| 835 |
+
"grad_norm": NaN,
|
| 836 |
+
"learning_rate": 6.806208330935766e-05,
|
| 837 |
+
"loss": 0.0,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.5254813137032842,
|
| 842 |
+
"grad_norm": NaN,
|
| 843 |
+
"learning_rate": 6.719744593169641e-05,
|
| 844 |
+
"loss": 0.0,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.5300113250283126,
|
| 849 |
+
"grad_norm": NaN,
|
| 850 |
+
"learning_rate": 6.632693564200416e-05,
|
| 851 |
+
"loss": 0.0,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.5345413363533409,
|
| 856 |
+
"grad_norm": NaN,
|
| 857 |
+
"learning_rate": 6.545084971874738e-05,
|
| 858 |
+
"loss": 0.0,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.5390713476783692,
|
| 863 |
+
"grad_norm": NaN,
|
| 864 |
+
"learning_rate": 6.456948734446624e-05,
|
| 865 |
+
"loss": 0.0,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.5436013590033975,
|
| 870 |
+
"grad_norm": NaN,
|
| 871 |
+
"learning_rate": 6.368314950360415e-05,
|
| 872 |
+
"loss": 0.0,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.5481313703284258,
|
| 877 |
+
"grad_norm": NaN,
|
| 878 |
+
"learning_rate": 6.279213887972179e-05,
|
| 879 |
+
"loss": 0.0,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.5526613816534541,
|
| 884 |
+
"grad_norm": NaN,
|
| 885 |
+
"learning_rate": 6.189675975213094e-05,
|
| 886 |
+
"loss": 0.0,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.5571913929784824,
|
| 891 |
+
"grad_norm": NaN,
|
| 892 |
+
"learning_rate": 6.099731789198344e-05,
|
| 893 |
+
"loss": 0.0,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.5617214043035108,
|
| 898 |
+
"grad_norm": NaN,
|
| 899 |
+
"learning_rate": 6.009412045785051e-05,
|
| 900 |
+
"loss": 0.0,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.5662514156285391,
|
| 905 |
+
"grad_norm": NaN,
|
| 906 |
+
"learning_rate": 5.918747589082853e-05,
|
| 907 |
+
"loss": 0.0,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.5707814269535674,
|
| 912 |
+
"grad_norm": NaN,
|
| 913 |
+
"learning_rate": 5.82776938092065e-05,
|
| 914 |
+
"loss": 0.0,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.5753114382785957,
|
| 919 |
+
"grad_norm": NaN,
|
| 920 |
+
"learning_rate": 5.736508490273188e-05,
|
| 921 |
+
"loss": 0.0,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.579841449603624,
|
| 926 |
+
"grad_norm": NaN,
|
| 927 |
+
"learning_rate": 5.644996082651017e-05,
|
| 928 |
+
"loss": 0.0,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.5843714609286523,
|
| 933 |
+
"grad_norm": NaN,
|
| 934 |
+
"learning_rate": 5.553263409457504e-05,
|
| 935 |
+
"loss": 0.0,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.5889014722536806,
|
| 940 |
+
"grad_norm": NaN,
|
| 941 |
+
"learning_rate": 5.4613417973165106e-05,
|
| 942 |
+
"loss": 0.0,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.5934314835787089,
|
| 947 |
+
"grad_norm": NaN,
|
| 948 |
+
"learning_rate": 5.3692626373743706e-05,
|
| 949 |
+
"loss": 0.0,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.5979614949037373,
|
| 954 |
+
"grad_norm": NaN,
|
| 955 |
+
"learning_rate": 5.27705737457985e-05,
|
| 956 |
+
"loss": 0.0,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.6024915062287656,
|
| 961 |
+
"grad_norm": NaN,
|
| 962 |
+
"learning_rate": 5.184757496945726e-05,
|
| 963 |
+
"loss": 0.0,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.6070215175537939,
|
| 968 |
+
"grad_norm": NaN,
|
| 969 |
+
"learning_rate": 5.092394524795649e-05,
|
| 970 |
+
"loss": 0.0,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.6115515288788222,
|
| 975 |
+
"grad_norm": NaN,
|
| 976 |
+
"learning_rate": 5e-05,
|
| 977 |
+
"loss": 0.0,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.6160815402038505,
|
| 982 |
+
"grad_norm": NaN,
|
| 983 |
+
"learning_rate": 4.907605475204352e-05,
|
| 984 |
+
"loss": 0.0,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.6206115515288788,
|
| 989 |
+
"grad_norm": NaN,
|
| 990 |
+
"learning_rate": 4.8152425030542766e-05,
|
| 991 |
+
"loss": 0.0,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.6251415628539071,
|
| 996 |
+
"grad_norm": NaN,
|
| 997 |
+
"learning_rate": 4.72294262542015e-05,
|
| 998 |
+
"loss": 0.0,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.6296715741789355,
|
| 1003 |
+
"grad_norm": NaN,
|
| 1004 |
+
"learning_rate": 4.6307373626256306e-05,
|
| 1005 |
+
"loss": 0.0,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.6342015855039638,
|
| 1010 |
+
"grad_norm": NaN,
|
| 1011 |
+
"learning_rate": 4.5386582026834906e-05,
|
| 1012 |
+
"loss": 0.0,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.638731596828992,
|
| 1017 |
+
"grad_norm": NaN,
|
| 1018 |
+
"learning_rate": 4.446736590542497e-05,
|
| 1019 |
+
"loss": 0.0,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.6432616081540203,
|
| 1024 |
+
"grad_norm": NaN,
|
| 1025 |
+
"learning_rate": 4.3550039173489845e-05,
|
| 1026 |
+
"loss": 0.0,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.6477916194790487,
|
| 1031 |
+
"grad_norm": NaN,
|
| 1032 |
+
"learning_rate": 4.2634915097268115e-05,
|
| 1033 |
+
"loss": 0.0,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.652321630804077,
|
| 1038 |
+
"grad_norm": NaN,
|
| 1039 |
+
"learning_rate": 4.1722306190793495e-05,
|
| 1040 |
+
"loss": 0.0,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.6568516421291053,
|
| 1045 |
+
"grad_norm": NaN,
|
| 1046 |
+
"learning_rate": 4.0812524109171476e-05,
|
| 1047 |
+
"loss": 0.0,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.6613816534541337,
|
| 1052 |
+
"grad_norm": NaN,
|
| 1053 |
+
"learning_rate": 3.99058795421495e-05,
|
| 1054 |
+
"loss": 0.0,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.665911664779162,
|
| 1059 |
+
"grad_norm": NaN,
|
| 1060 |
+
"learning_rate": 3.9002682108016585e-05,
|
| 1061 |
+
"loss": 0.0,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.6704416761041903,
|
| 1066 |
+
"grad_norm": NaN,
|
| 1067 |
+
"learning_rate": 3.8103240247869075e-05,
|
| 1068 |
+
"loss": 0.0,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.6749716874292185,
|
| 1073 |
+
"grad_norm": NaN,
|
| 1074 |
+
"learning_rate": 3.720786112027822e-05,
|
| 1075 |
+
"loss": 0.0,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.6795016987542469,
|
| 1080 |
+
"grad_norm": NaN,
|
| 1081 |
+
"learning_rate": 3.631685049639586e-05,
|
| 1082 |
+
"loss": 0.0,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.6840317100792752,
|
| 1087 |
+
"grad_norm": NaN,
|
| 1088 |
+
"learning_rate": 3.543051265553377e-05,
|
| 1089 |
+
"loss": 0.0,
|
| 1090 |
+
"step": 151
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.6885617214043035,
|
| 1094 |
+
"grad_norm": NaN,
|
| 1095 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 1096 |
+
"loss": 0.0,
|
| 1097 |
+
"step": 152
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.6930917327293318,
|
| 1101 |
+
"grad_norm": NaN,
|
| 1102 |
+
"learning_rate": 3.367306435799584e-05,
|
| 1103 |
+
"loss": 0.0,
|
| 1104 |
+
"step": 153
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.6976217440543602,
|
| 1108 |
+
"grad_norm": NaN,
|
| 1109 |
+
"learning_rate": 3.2802554068303596e-05,
|
| 1110 |
+
"loss": 0.0,
|
| 1111 |
+
"step": 154
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.7021517553793885,
|
| 1115 |
+
"grad_norm": NaN,
|
| 1116 |
+
"learning_rate": 3.1937916690642356e-05,
|
| 1117 |
+
"loss": 0.0,
|
| 1118 |
+
"step": 155
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.7066817667044167,
|
| 1122 |
+
"grad_norm": NaN,
|
| 1123 |
+
"learning_rate": 3.107944749788449e-05,
|
| 1124 |
+
"loss": 0.0,
|
| 1125 |
+
"step": 156
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.711211778029445,
|
| 1129 |
+
"grad_norm": NaN,
|
| 1130 |
+
"learning_rate": 3.0227439656472877e-05,
|
| 1131 |
+
"loss": 0.0,
|
| 1132 |
+
"step": 157
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.7157417893544734,
|
| 1136 |
+
"grad_norm": NaN,
|
| 1137 |
+
"learning_rate": 2.9382184126304834e-05,
|
| 1138 |
+
"loss": 0.0,
|
| 1139 |
+
"step": 158
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.7202718006795017,
|
| 1143 |
+
"grad_norm": NaN,
|
| 1144 |
+
"learning_rate": 2.8543969561369556e-05,
|
| 1145 |
+
"loss": 0.0,
|
| 1146 |
+
"step": 159
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.72480181200453,
|
| 1150 |
+
"grad_norm": NaN,
|
| 1151 |
+
"learning_rate": 2.771308221117309e-05,
|
| 1152 |
+
"loss": 0.0,
|
| 1153 |
+
"step": 160
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.7293318233295584,
|
| 1157 |
+
"grad_norm": NaN,
|
| 1158 |
+
"learning_rate": 2.688980582298435e-05,
|
| 1159 |
+
"loss": 0.0,
|
| 1160 |
+
"step": 161
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.7338618346545867,
|
| 1164 |
+
"grad_norm": NaN,
|
| 1165 |
+
"learning_rate": 2.607442154493568e-05,
|
| 1166 |
+
"loss": 0.0,
|
| 1167 |
+
"step": 162
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.7383918459796149,
|
| 1171 |
+
"grad_norm": NaN,
|
| 1172 |
+
"learning_rate": 2.5267207830011068e-05,
|
| 1173 |
+
"loss": 0.0,
|
| 1174 |
+
"step": 163
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.7429218573046432,
|
| 1178 |
+
"grad_norm": NaN,
|
| 1179 |
+
"learning_rate": 2.446844034095466e-05,
|
| 1180 |
+
"loss": 0.0,
|
| 1181 |
+
"step": 164
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.7474518686296716,
|
| 1185 |
+
"grad_norm": NaN,
|
| 1186 |
+
"learning_rate": 2.3678391856132204e-05,
|
| 1187 |
+
"loss": 0.0,
|
| 1188 |
+
"step": 165
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.7474518686296716,
|
| 1192 |
+
"eval_loss": NaN,
|
| 1193 |
+
"eval_runtime": 16.7388,
|
| 1194 |
+
"eval_samples_per_second": 22.224,
|
| 1195 |
+
"eval_steps_per_second": 5.556,
|
| 1196 |
+
"step": 165
|
| 1197 |
}
|
| 1198 |
],
|
| 1199 |
"logging_steps": 1,
|
|
|
|
| 1213 |
"attributes": {}
|
| 1214 |
}
|
| 1215 |
},
|
| 1216 |
+
"total_flos": 2.37914919272448e+16,
|
| 1217 |
"train_batch_size": 2,
|
| 1218 |
"trial_name": null,
|
| 1219 |
"trial_params": null
|