wip

convlab/policy/ppo/emoTUS-BertNLU-RuleDST-PPOPolicy.json

@@ -3,12 +3,12 @@
         "load_path": "convlab/policy/ppo/pretrained_models/mle",
         "pretrained_load_path": "",
         "use_pretrained_initialisation": false,
-        "batchsz": 2,
+        "batchsz": 200,
         "seed": 0,
         "epoch": 100,
         "eval_frequency": 5,
         "process_num": 1,
-        "num_eval_dialogues": 2,
+        "num_eval_dialogues": 200,
         "sys_semantic_to_usr": false
     },
     "vectorizer_sys": {