Update config.json

config.json

@@ -1,16 +1,16 @@
 {
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
+  "activation_dropout": 0.1,
   "activation_function": "gelu",
+  "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "BartModel",
-    "BartForMaskedLM",
+    "BartForConditionalGeneration",
     "BartForSequenceClassification"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
+  "classif_dropout": 0.1,
   "d_model": 1024,
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
@@ -18,6 +18,7 @@
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
+  "early_stopping": true,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
@@ -39,18 +40,28 @@
   "model_type": "bart",
   "normalize_before": false,
   "num_hidden_layers": 12,
-  "output_past": false,
   "pad_token_id": 1,
-  "prefix": " ",
   "scale_embedding": false,
+  "num_beams": 4,
+  "no_repeat_ngram_size": 3,
   "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
+  	"summarization": {
+   	  "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {      
       "length_penalty": 2.0,
       "max_length": 142,
       "min_length": 56,
-      "no_repeat_ngram_size": 3,
       "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
     }
   },
   "vocab_size": 50265