bert-squad

README.md

@@ -0,0 +1,92 @@
+---
+license: mit
+base_model: hung200504/bert-squadv2
+tags:
+- generated_from_trainer
+datasets:
+- covid_qa_deepset
+model-index:
+- name: bert-squad-covidqa
+  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-squad-covidqa
+
+This model is a fine-tuned version of [hung200504/bert-squadv2](https://huggingface.co/hung200504/bert-squadv2) on the covid_qa_deepset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5141
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.1636        | 0.09  | 5    | 1.4553          |
+| 0.8433        | 0.18  | 10   | 0.6359          |
+| 0.8245        | 0.26  | 15   | 0.5610          |
+| 0.5916        | 0.35  | 20   | 0.5416          |
+| 0.5899        | 0.44  | 25   | 0.5148          |
+| 0.4838        | 0.53  | 30   | 0.4996          |
+| 0.4501        | 0.61  | 35   | 0.4929          |
+| 0.7377        | 0.7   | 40   | 0.4610          |
+| 0.455         | 0.79  | 45   | 0.4645          |
+| 0.478         | 0.88  | 50   | 0.4745          |
+| 0.3672        | 0.96  | 55   | 0.4803          |
+| 0.6509        | 1.05  | 60   | 0.4875          |
+| 0.3094        | 1.14  | 65   | 0.5089          |
+| 0.3203        | 1.23  | 70   | 0.5751          |
+| 0.3955        | 1.32  | 75   | 0.5416          |
+| 0.6197        | 1.4   | 80   | 0.4848          |
+| 0.455         | 1.49  | 85   | 0.4716          |
+| 0.4086        | 1.58  | 90   | 0.4738          |
+| 0.5028        | 1.67  | 95   | 0.4818          |
+| 0.4953        | 1.75  | 100  | 0.4867          |
+| 0.557         | 1.84  | 105  | 0.4826          |
+| 0.3139        | 1.93  | 110  | 0.4832          |
+| 0.3217        | 2.02  | 115  | 0.4921          |
+| 0.4175        | 2.11  | 120  | 0.5056          |
+| 0.3471        | 2.19  | 125  | 0.5204          |
+| 0.209         | 2.28  | 130  | 0.5321          |
+| 0.5151        | 2.37  | 135  | 0.5285          |
+| 0.441         | 2.46  | 140  | 0.5141          |
+| 0.3022        | 2.54  | 145  | 0.5031          |
+| 0.3789        | 2.63  | 150  | 0.5002          |
+| 0.2917        | 2.72  | 155  | 0.5041          |
+| 0.372         | 2.81  | 160  | 0.5097          |
+| 0.4001        | 2.89  | 165  | 0.5105          |
+| 0.1803        | 2.98  | 170  | 0.5141          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "hung200504/bert-squadv2",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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",
+  "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 sha256:7732e5e98ea5b2591a32bfb2c324b479bcea7f8949755f47e308ef68bb631e1c
+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 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 384,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "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:c7a7e784eb63e144eb9a8d78661b0537d0ac76917663ed952e757bfd5896f34d
+size 4536