bert-squad

README.md

@@ -0,0 +1,91 @@
+---
+license: mit
+base_model: hung200504/bert-squadv2
+tags:
+- generated_from_trainer
+model-index:
+- name: bert-covid-21
+ 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-covid-21
+
+This model is a fine-tuned version of [hung200504/bert-squadv2](https://huggingface.co/hung200504/bert-squadv2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6103
+
+## 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: 8
+- eval_batch_size: 8
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.2561 | 0.03 | 5 | 1.1801 |
+| 1.1175 | 0.06 | 10 | 0.9406 |
+| 1.2258 | 0.08 | 15 | 0.7456 |
+| 0.8306 | 0.11 | 20 | 0.5948 |
+| 0.5743 | 0.14 | 25 | 0.5835 |
+| 0.4958 | 0.17 | 30 | 0.7125 |
+| 0.4448 | 0.2 | 35 | 0.6664 |
+| 0.8538 | 0.22 | 40 | 0.7098 |
+| 0.8115 | 0.25 | 45 | 0.6869 |
+| 0.9364 | 0.28 | 50 | 0.5814 |
+| 1.0413 | 0.31 | 55 | 0.5434 |
+| 0.7219 | 0.34 | 60 | 0.5274 |
+| 0.6852 | 0.37 | 65 | 0.5764 |
+| 0.4603 | 0.39 | 70 | 0.6586 |
+| 0.8428 | 0.42 | 75 | 0.7742 |
+| 0.3679 | 0.45 | 80 | 0.7430 |
+| 1.0074 | 0.48 | 85 | 0.6630 |
+| 0.8531 | 0.51 | 90 | 0.5403 |
+| 0.4513 | 0.53 | 95 | 0.5452 |
+| 0.3039 | 0.56 | 100 | 0.6193 |
+| 1.7221 | 0.59 | 105 | 0.6734 |
+| 0.8286 | 0.62 | 110 | 0.5892 |
+| 0.6836 | 0.65 | 115 | 0.5413 |
+| 0.2059 | 0.67 | 120 | 0.5407 |
+| 0.8272 | 0.7 | 125 | 0.5446 |
+| 0.3456 | 0.73 | 130 | 0.5652 |
+| 1.1423 | 0.76 | 135 | 0.5697 |
+| 0.2456 | 0.79 | 140 | 0.5737 |
+| 0.7639 | 0.81 | 145 | 0.5767 |
+| 0.5946 | 0.84 | 150 | 0.5565 |
+| 0.0976 | 0.87 | 155 | 0.5857 |
+| 0.3246 | 0.9 | 160 | 0.6162 |
+| 1.039 | 0.93 | 165 | 0.6297 |
+| 0.6297 | 0.96 | 170 | 0.6217 |
+| 1.1724 | 0.98 | 175 | 0.6103 |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- 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 sha256:0862481a53c07636d5d78c7edc7f0d81f8388000aabc4b76924ab9b657804d09
+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 sha256:174a711d5c39302b7a40ed673b70c0e4b345c84962066656bc8d38bf3031d324
+size 4536