add model

README.md

@@ -0,0 +1,66 @@
+---
+datasets:
+- squad_v2
+model_index:
+- name: sapbert-from-pubmedbert-squad2
+  results:
+  - task:
+      name: Question Answering
+      type: question-answering
+    dataset:
+      name: squad_v2
+      type: squad_v2
+      args: squad_v2
+---
+
+<!-- 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. -->
+
+# sapbert-from-pubmedbert-squad2
+
+This model is a fine-tuned version of [cambridgeltl/SapBERT-from-PubMedBERT-fulltext](https://huggingface.co/cambridgeltl/SapBERT-from-PubMedBERT-fulltext) on the squad_v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2582
+
+## 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
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.035         | 1.0   | 8298  | 0.9545          |
+| 0.8053        | 2.0   | 16596 | 0.9988          |
+| 0.5949        | 3.0   | 24894 | 0.9909          |
+| 0.4878        | 4.0   | 33192 | 1.1428          |
+| 0.3932        | 5.0   | 41490 | 1.2582          |
+
+
+### Framework versions
+
+- Transformers 4.7.0
+- Pytorch 1.8.0
+- Datasets 1.4.1
+- Tokenizers 0.10.2

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "cambridgeltl/SapBERT-from-PubMedBERT-fulltext",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.7.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a04701018b13498d468fcd99178996f4628376b85ab47a7dd21ee5c226619f95
+size 435660911

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": null, "full_tokenizer_file": null, "name_or_path": "cambridgeltl/SapBERT-from-PubMedBERT-fulltext", "do_basic_tokenize": true, "never_split": null}