bert-cased

README.md

@@ -0,0 +1,80 @@
+---
+license: cc-by-4.0
+base_model: deepset/bert-base-cased-squad2
+tags:
+- generated_from_trainer
+datasets:
+- covid_qa_deepset
+model-index:
+- name: bert-covidqa-1
+  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-1
+
+This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on the covid_qa_deepset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4528
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0353        | 0.04  | 5    | 0.7327          |
+| 1.1116        | 0.09  | 10   | 0.5674          |
+| 0.8086        | 0.13  | 15   | 0.5025          |
+| 0.814         | 0.18  | 20   | 0.5620          |
+| 0.4168        | 0.22  | 25   | 0.6628          |
+| 0.7069        | 0.26  | 30   | 0.5637          |
+| 0.4168        | 0.31  | 35   | 0.4855          |
+| 0.5636        | 0.35  | 40   | 0.4708          |
+| 0.398         | 0.39  | 45   | 0.4712          |
+| 0.4681        | 0.44  | 50   | 0.5235          |
+| 0.34          | 0.48  | 55   | 0.5863          |
+| 0.2484        | 0.53  | 60   | 0.6422          |
+| 0.4526        | 0.57  | 65   | 0.6614          |
+| 0.2941        | 0.61  | 70   | 0.6210          |
+| 0.7383        | 0.66  | 75   | 0.5334          |
+| 0.7337        | 0.7   | 80   | 0.4612          |
+| 0.4082        | 0.75  | 85   | 0.4447          |
+| 0.3517        | 0.79  | 90   | 0.4429          |
+| 0.341         | 0.83  | 95   | 0.4446          |
+| 0.2751        | 0.88  | 100  | 0.4536          |
+| 0.4916        | 0.92  | 105  | 0.4566          |
+| 0.4895        | 0.96  | 110  | 0.4528          |
+
+
+### 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": "deepset/bert-base-cased-squad2",
+  "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,
+  "language": "english",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "name": "Bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "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": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d1b50a725249eff5982d518f9922bc012c1be79380aec2cd9eec792179c17d
+size 430953062

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ceb195ce20b408c3f534fee2c04b0b18d73a633b570814b73d8f9d496b9877
+size 4536