zharry29
/

order_benchmark_gpt

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

system HF staff commited on Sep 20, 2020

Commit

c73918c

•

1 Parent(s): ee5c1c4

Update is_test_false_eval_results.txt

Files changed (1) hide show

is_test_false_eval_results.txt +3 -3

is_test_false_eval_results.txt CHANGED Viewed

@@ -1,7 +1,7 @@
 model           =gpt2
 total batch size=40
-train num epochs=30
 fp16            =True
 max seq length  =40
-eval_acc = 0.8064516129032258
-eval_loss = 1.131058534210728

 model           =gpt2
 total batch size=40
+train num epochs=3
 fp16            =True
 max seq length  =40
+eval_acc = 0.7935483870967742
+eval_loss = 0.5006362595865803