Update repository

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.th filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,6 @@
+---
+tags:
+- allennlp
+---
+
+# TODO: Fill this model card

config.json

@@ -0,0 +1,120 @@
+{
+    "dataset_reader": {
+        "type": "squad",
+        "token_indexers": {
+            "elmo": {
+                "type": "elmo_characters"
+            },
+            "token_characters": {
+                "type": "characters",
+                "character_tokenizer": {
+                    "byte_encoding": "utf-8",
+                    "end_tokens": [
+                        260
+                    ],
+                    "start_tokens": [
+                        259
+                    ]
+                },
+                "min_padding_length": 5
+            },
+            "tokens": {
+                "type": "single_id",
+                "lowercase_tokens": true
+            }
+        }
+    },
+    "model": {
+        "type": "bidaf",
+        "dropout": 0.2,
+        "matrix_attention": {
+            "type": "linear",
+            "combination": "x,y,x*y",
+            "tensor_1_dim": 200,
+            "tensor_2_dim": 200
+        },
+        "modeling_layer": {
+            "type": "lstm",
+            "bidirectional": true,
+            "dropout": 0.2,
+            "hidden_size": 100,
+            "input_size": 800,
+            "num_layers": 2
+        },
+        "num_highway_layers": 2,
+        "phrase_layer": {
+            "type": "lstm",
+            "bidirectional": true,
+            "hidden_size": 100,
+            "input_size": 1224,
+            "num_layers": 1
+        },
+        "span_end_encoder": {
+            "type": "lstm",
+            "bidirectional": true,
+            "hidden_size": 100,
+            "input_size": 1400,
+            "num_layers": 1
+        },
+        "text_field_embedder": {
+            "token_embedders": {
+                "elmo": {
+                    "type": "elmo_token_embedder",
+                    "do_layer_norm": false,
+                    "dropout": 0,
+                    "options_file": "https://allennlp.s3.amazonaws.com/models/elmo/2x4096_512_2048cnn_2xhighway/elmo_2x4096_512_2048cnn_2xhighway_options.json",
+                    "weight_file": "https://allennlp.s3.amazonaws.com/models/elmo/2x4096_512_2048cnn_2xhighway/elmo_2x4096_512_2048cnn_2xhighway_weights.hdf5"
+                },
+                "token_characters": {
+                    "type": "character_encoding",
+                    "dropout": 0.2,
+                    "embedding": {
+                        "embedding_dim": 16,
+                        "num_embeddings": 262
+                    },
+                    "encoder": {
+                        "type": "cnn",
+                        "embedding_dim": 16,
+                        "ngram_filter_sizes": [
+                            5
+                        ],
+                        "num_filters": 100
+                    }
+                },
+                "tokens": {
+                    "type": "embedding",
+                    "embedding_dim": 100,
+                    "pretrained_file": "https://allennlp.s3.amazonaws.com/datasets/glove/glove.6B.100d.txt.gz",
+                    "trainable": false
+                }
+            }
+        }
+    },
+    "train_data_path": "https://allennlp.s3.amazonaws.com/datasets/squad/squad-train-v1.1.json",
+    "validation_data_path": "https://allennlp.s3.amazonaws.com/datasets/squad/squad-dev-v1.1.json",
+    "trainer": {
+        "grad_norm": 5,
+        "learning_rate_scheduler": {
+            "type": "reduce_on_plateau",
+            "factor": 0.5,
+            "mode": "max",
+            "patience": 2
+        },
+        "num_epochs": 20,
+        "optimizer": {
+            "type": "adam",
+            "betas": [
+                0.9,
+                0.9
+            ]
+        },
+        "patience": 10,
+        "validation_metric": "+em"
+    },
+    "data_loader": {
+        "batch_sampler": {
+            "type": "bucket",
+            "batch_size": 40
+        }
+    }
+}

metrics.json

@@ -0,0 +1,27 @@
+{
+  "best_epoch": 4,
+  "peak_worker_0_memory_MB": 39697.6484375,
+  "peak_gpu_0_memory_MB": 7284.326171875,
+  "training_duration": "4:33:51.728517",
+  "epoch": 14,
+  "training_start_acc": 0.9632758364821516,
+  "training_end_acc": 0.9648968595531913,
+  "training_span_acc": 0.9375221178323954,
+  "training_em": 0.9490519298165504,
+  "training_f1": 0.9746247710065422,
+  "training_loss": 0.21539007184950457,
+  "training_worker_0_memory_MB": 39697.6484375,
+  "training_gpu_0_memory_MB": 7283.4765625,
+  "validation_start_acc": 0.6205298013245033,
+  "validation_end_acc": 0.6693472090823084,
+  "validation_span_acc": 0.5271523178807948,
+  "validation_em": 0.6779564806054872,
+  "validation_f1": 0.786469085303725,
+  "validation_loss": 4.7776187914722374,
+  "best_validation_start_acc": 0.6631031220435194,
+  "best_validation_end_acc": 0.6990539262062441,
+  "best_validation_span_acc": 0.5754020813623463,
+  "best_validation_em": 0.7165562913907285,
+  "best_validation_f1": 0.8039716876069539,
+  "best_validation_loss": 2.22837360759951
+}

model.th

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c6ab78b861d00865e4ea3973d9be71677c2f08a7ed72607b1dfd6a2a9d827c
+size 450055351

vocabulary/non_padded_namespaces.txt

@@ -0,0 +1,2 @@
+*labels
+*tags