add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,70 @@
+---
+language:
+- en
+license: cc-by-4.0
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+- mit_restaurant
+model_index:
+- name: bert-large-uncased-whole-word-masking-squad2-with-ner-mit-restaurant-with-neg-with-repeat
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: squad_v2
+      type: squad_v2
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: mit_restaurant
+      type: mit_restaurant
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bert-large-uncased-whole-word-masking-squad2-with-ner-mit-restaurant-with-neg-with-repeat
+
+This model is a fine-tuned version of [deepset/bert-large-uncased-whole-word-masking-squad2](https://huggingface.co/deepset/bert-large-uncased-whole-word-masking-squad2) on the squad_v2 and the mit_restaurant datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.8.2
+- Pytorch 1.8.1+cu111
+- Datasets 1.8.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.19971155819849962,
+    "train_runtime": 81086.0351,
+    "train_samples": 37331,
+    "train_samples_per_second": 2.302,
+    "train_steps_per_second": 0.144
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "deepset/bert-large-uncased-whole-word-masking-squad2",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "squad2",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "language": "english",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "name": "Bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.8.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

log.log

@@ -0,0 +1,6 @@
+Training dataset length: 
+37331
+Validation dataset length: 
+4059
+Test dataset length: 
+8171

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef50ffd97da2f7f916e19c4821c1d4987ca5d282730e39675dc86591e4ba1c68
+size 1336547639

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, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/ec2-user/.cache/huggingface/transformers/ef9bc2ba6867b86932babe745cbccc9822ae43e5c873d03088aee4251bd45fff.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "deepset/bert-large-uncased-whole-word-masking-squad2", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.19971155819849962,
+    "train_runtime": 81086.0351,
+    "train_samples": 37331,
+    "train_samples_per_second": 2.302,
+    "train_steps_per_second": 0.144
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c6d706ead39a7034ef21839ba2daa280a6261483fdc8237f99d6ce56fec93d
+size 2927