bert-cased

README.md

@@ -0,0 +1,89 @@
+---
+license: cc-by-4.0
+base_model: deepset/bert-base-cased-squad2
+tags:
+- generated_from_trainer
+model-index:
+- name: bert-17
+  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-17
+
+This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.7381
+
+## 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: 0.0005
+- 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 11.0352       | 0.09  | 5    | 11.3392         |
+| 10.0155       | 0.18  | 10   | 10.1330         |
+| 8.6139        | 0.27  | 15   | 9.0228          |
+| 7.7654        | 0.36  | 20   | 8.0477          |
+| 7.1161        | 0.45  | 25   | 7.2438          |
+| 6.486         | 0.55  | 30   | 6.6691          |
+| 5.9793        | 0.64  | 35   | 6.3524          |
+| 5.8845        | 0.73  | 40   | 6.2251          |
+| 5.8619        | 0.82  | 45   | 6.1625          |
+| 5.7536        | 0.91  | 50   | 6.1058          |
+| 5.6831        | 1.0   | 55   | 6.0479          |
+| 5.5525        | 1.09  | 60   | 5.9939          |
+| 5.4714        | 1.18  | 65   | 5.9510          |
+| 5.4384        | 1.27  | 70   | 5.9123          |
+| 5.4539        | 1.36  | 75   | 5.8817          |
+| 5.4073        | 1.45  | 80   | 5.8593          |
+| 5.4048        | 1.55  | 85   | 5.8395          |
+| 5.2997        | 1.64  | 90   | 5.8225          |
+| 5.2388        | 1.73  | 95   | 5.8099          |
+| 5.2564        | 1.82  | 100  | 5.7986          |
+| 5.1758        | 1.91  | 105  | 5.7872          |
+| 5.1926        | 2.0   | 110  | 5.7800          |
+| 4.9244        | 2.09  | 115  | 5.7747          |
+| 5.0897        | 2.18  | 120  | 5.7689          |
+| 5.2493        | 2.27  | 125  | 5.7610          |
+| 5.0594        | 2.36  | 130  | 5.7541          |
+| 5.0792        | 2.45  | 135  | 5.7485          |
+| 4.9952        | 2.55  | 140  | 5.7455          |
+| 4.8796        | 2.64  | 145  | 5.7436          |
+| 4.9344        | 2.73  | 150  | 5.7418          |
+| 5.2387        | 2.82  | 155  | 5.7402          |
+| 5.0734        | 2.91  | 160  | 5.7385          |
+| 5.0227        | 3.0   | 165  | 5.7381          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+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 sha256:60f32e6fe193f09179ab0b1908342029a3bed52cb329c3a8478501221c2c434e
+size 430952617

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 sha256:5f8eb5e0e33a4e5ea6f40099a1d041f369fb3990e2397020854abbe69e49ff8f
+size 4027