bert-cased

README.md

@@ -0,0 +1,80 @@
+---
+license: cc-by-4.0
+base_model: hung200504/bert-covidqa-3
+tags:
+- generated_from_trainer
+datasets:
+- covid_qa_deepset
+model-index:
+- name: bert-covidqa-4
+  results: []
+---
+
+<!-- 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-covidqa-4
+
+This model is a fine-tuned version of [hung200504/bert-covidqa-3](https://huggingface.co/hung200504/bert-covidqa-3) on the covid_qa_deepset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4380
+
+## 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: 3e-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: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.4937        | 0.04  | 5    | 0.4384          |
+| 0.2678        | 0.09  | 10   | 0.4334          |
+| 0.4938        | 0.13  | 15   | 0.4269          |
+| 0.2227        | 0.18  | 20   | 0.4598          |
+| 0.1708        | 0.22  | 25   | 0.4827          |
+| 0.1605        | 0.26  | 30   | 0.5107          |
+| 0.4913        | 0.31  | 35   | 0.5024          |
+| 0.3042        | 0.35  | 40   | 0.4838          |
+| 0.6595        | 0.39  | 45   | 0.4559          |
+| 0.4116        | 0.44  | 50   | 0.4385          |
+| 0.1758        | 0.48  | 55   | 0.4387          |
+| 0.4278        | 0.53  | 60   | 0.4403          |
+| 0.3984        | 0.57  | 65   | 0.4300          |
+| 0.3893        | 0.61  | 70   | 0.4201          |
+| 0.2478        | 0.66  | 75   | 0.4241          |
+| 0.2724        | 0.7   | 80   | 0.4258          |
+| 0.2483        | 0.75  | 85   | 0.4236          |
+| 0.1039        | 0.79  | 90   | 0.4286          |
+| 0.2723        | 0.83  | 95   | 0.4344          |
+| 0.3411        | 0.88  | 100  | 0.4367          |
+| 0.1883        | 0.92  | 105  | 0.4375          |
+| 0.5123        | 0.96  | 110  | 0.4380          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "hung200504/bert-covidqa-3",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "language": "english",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "name": "Bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "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 sha256:24e76d049441f64d16633a8242b85812c2601bb923224d6a490050ea8b874aad
+size 435640934

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 384,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29908e306c91b13a94e2bbc26a877c89b228a7f77cf6787a56b7f389365e46f7
+size 4536