Update from ddemszky

command_args.json

@@ -0,0 +1 @@
+{"dataset_path": "data/switchboard_question_detection.json", "model_name": "bert-base-uncased", "checkpoint": "bert-base-uncased", "max_history": 0, "train_batch_size": 32, "valid_batch_size": 16, "gradient_accumulation_steps": 1, "max_length": 300, "lr": 6.25e-05, "max_norm": 1.0, "n_epochs": 3, "eval_before_start": true, "min_prev_length": 0, "final_speaker": -1, "fp16": "O2", "local_rank": -1, "head_attr": {"is_question": {"size": 2}}, "distributed": false}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "MultiHeadModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

model_training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce47d22031b2427148e0a9be0d6a67f64f758f4517c931ab4f2a83bb882ab6f6
+size 703

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057f3bb15adf44a4383c6fb4b010c10d8ede269773be8e33d4ae017904d3126c
+size 437989727

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}

val_results.txt

@@ -0,0 +1,12 @@
+{'average_accuracy': 0.6614378054548321,
+ 'is_question_accuracy': 0.6614378054548321,
+ 'is_question_loss': 0.6052431167722518}
+{'average_accuracy': 0.9674444269273215,
+ 'is_question_accuracy': 0.9674444269273215,
+ 'is_question_loss': 0.09393756604431444}
+{'average_accuracy': 0.9680750433548794,
+ 'is_question_accuracy': 0.9680750433548794,
+ 'is_question_loss': 0.09026440343758332}
+{'average_accuracy': 0.9682326974617689,
+ 'is_question_accuracy': 0.9682326974617689,
+ 'is_question_loss': 0.10944933036552813}