add model

.gitignore

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

README.md

@@ -0,0 +1,67 @@
+---
+language:
+- en
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+- mit_restaurant
+model_index:
+- name: distilbert-base-uncased-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. -->
+
+# distilbert-base-uncased-squad2-with-ner-mit-restaurant-with-neg-with-repeat
+
+This model is a fine-tuned version of [twmkn9/distilbert-base-uncased-squad2](https://huggingface.co/twmkn9/distilbert-base-uncased-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: 16
+- eval_batch_size: 16
+- seed: 42
+- 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": 0.2209618340421152,
+    "train_runtime": 2411.0385,
+    "train_samples": 37331,
+    "train_samples_per_second": 77.417,
+    "train_steps_per_second": 4.84
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "twmkn9/distilbert-base-uncased-squad2",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "eos_token_ids": null,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.8.2",
+  "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 sha256:3a9f174ae02852e64e95f4768d4d2aeda8de4453ec43fe382212337e887ec889
+size 265500101

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, "max_len": 512, "special_tokens_map_file": "/home/ec2-user/.cache/huggingface/transformers/1ca0b152f7e9e7bd279fded5ffd0930ddafcdc395cbebe37fee225d756a796d3.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "twmkn9/distilbert-base-uncased-squad2", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "DistilBertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.2209618340421152,
+    "train_runtime": 2411.0385,
+    "train_samples": 37331,
+    "train_samples_per_second": 77.417,
+    "train_steps_per_second": 4.84
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424c6d94ce6bb0410fb3634bebdaa8898bf42f4ff7fcb3d966af6076068688e3
+size 2863