Fix errors of RTE Fine Tune predictions

DeFacto · Jul 22, 2018 · 142a49e · 142a49e
1 parent df14bb1
commit 142a49e
Show file tree

Hide file tree

Showing 3 changed files with 82 additions and 2 deletions.
diff --git a/rte/fever_output/config.json b/rte/fever_output/config.json
@@ -15,6 +15,44 @@
     },
     "train_data_path": "fever_data/train_fever_snliFormat.jsonl",
     "validation_data_path": "fever_data/dev_fever_snliFormat.jsonl",
+    "model": {
+    "type": "decomposable_attention",
+    "text_field_embedder": {
+      "tokens": {
+        "type": "embedding",
+        "projection_dim": 200,
+        "pretrained_file": "https://s3-us-west-2.amazonaws.com/allennlp/datasets/glove/glove.6B.300d.txt.gz",
+        "embedding_dim": 300,
+        "trainable": false
+      }
+    },
+    "attend_feedforward": {
+      "input_dim": 200,
+      "num_layers": 2,
+      "hidden_dims": 200,
+      "activations": "relu",
+      "dropout": 0.2
+    },
+    "similarity_function": {"type": "dot_product"},
+    "compare_feedforward": {
+      "input_dim": 400,
+      "num_layers": 2,
+      "hidden_dims": 200,
+      "activations": "relu",
+      "dropout": 0.2
+    },
+    "aggregate_feedforward": {
+      "input_dim": 400,
+      "num_layers": 2,
+      "hidden_dims": [200, 3],
+      "activations": ["relu", "linear"],
+      "dropout": [0.2, 0.0]
+    },
+     "initializer": [
+      [".*linear_layers.*weight", {"type": "xavier_normal"}],
+      [".*token_embedder_tokens\._projection.*weight", {"type": "xavier_normal"}]
+     ]
+    },
     "iterator": {
         "type": "bucket",
         "sorting_keys": [
@@ -39,4 +77,4 @@
             "type": "adagrad"
         }
     }
-}
+}
diff --git a/rte/fever_output/model.tar.gz b/rte/fever_output/model.tar.gz
diff --git a/rte/fineTuning_config/decomposable_attention_fineTuning.json b/rte/fineTuning_config/decomposable_attention_fineTuning.json
@@ -11,14 +11,56 @@
       "end_tokens": ["@@NULL@@"]
     }
   },
+
   "train_data_path": "fever_data/train_fever_snliFormat.jsonl",
+
   "validation_data_path": "fever_data/dev_fever_snliFormat.jsonl",
+
+  "model": {
+    "type": "decomposable_attention",
+    "text_field_embedder": {
+      "tokens": {
+        "type": "embedding",
+        "projection_dim": 200,
+        "pretrained_file": "https://s3-us-west-2.amazonaws.com/allennlp/datasets/glove/glove.6B.300d.txt.gz",
+        "embedding_dim": 300,
+        "trainable": false
+      }
+    },
+    "attend_feedforward": {
+      "input_dim": 200,
+      "num_layers": 2,
+      "hidden_dims": 200,
+      "activations": "relu",
+      "dropout": 0.2
+    },
+    "similarity_function": {"type": "dot_product"},
+    "compare_feedforward": {
+      "input_dim": 400,
+      "num_layers": 2,
+      "hidden_dims": 200,
+      "activations": "relu",
+      "dropout": 0.2
+    },
+    "aggregate_feedforward": {
+      "input_dim": 400,
+      "num_layers": 2,
+      "hidden_dims": [200, 3],
+      "activations": ["relu", "linear"],
+      "dropout": [0.2, 0.0]
+    },
+     "initializer": [
+      [".*linear_layers.*weight", {"type": "xavier_normal"}],
+      [".*token_embedder_tokens\._projection.*weight", {"type": "xavier_normal"}]
+     ]
+   },
+
   "iterator": {
     "type": "bucket",
     "sorting_keys": [["premise", "num_tokens"], ["hypothesis", "num_tokens"]],
     "batch_size": 64
   },
-
+  
   "trainer": {
     "num_epochs": 140,
     "patience": 20,