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-23
+  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-23
+
+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: 5.9468
+
+## 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: 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 10.9511       | 0.09  | 5    | 10.5588         |
+| 8.6122        | 0.18  | 10   | 8.0465          |
+| 6.3959        | 0.27  | 15   | 6.5185          |
+| 5.5714        | 0.36  | 20   | 5.9355          |
+| 5.2088        | 0.45  | 25   | 5.8452          |
+| 5.0174        | 0.55  | 30   | 5.9581          |
+| 4.3863        | 0.64  | 35   | 6.1063          |
+| 4.2079        | 0.73  | 40   | 6.1976          |
+| 4.5909        | 0.82  | 45   | 5.8724          |
+| 4.2584        | 0.91  | 50   | 5.5712          |
+| 4.2042        | 1.0   | 55   | 5.4376          |
+| 3.7625        | 1.09  | 60   | 5.4613          |
+| 3.5759        | 1.18  | 65   | 5.5305          |
+| 3.6831        | 1.27  | 70   | 5.5329          |
+| 3.7596        | 1.36  | 75   | 5.5254          |
+| 3.6216        | 1.45  | 80   | 5.5825          |
+| 3.769         | 1.55  | 85   | 5.6090          |
+| 3.5107        | 1.64  | 90   | 5.6351          |
+| 3.3485        | 1.73  | 95   | 5.6501          |
+| 3.4216        | 1.82  | 100  | 5.6611          |
+| 3.3527        | 1.91  | 105  | 5.7240          |
+| 3.2204        | 2.0   | 110  | 5.8332          |
+| 2.9853        | 2.09  | 115  | 5.8772          |
+| 3.207         | 2.18  | 120  | 5.8846          |
+| 3.4566        | 2.27  | 125  | 5.8788          |
+| 3.1248        | 2.36  | 130  | 5.8898          |
+| 3.0917        | 2.45  | 135  | 5.9108          |
+| 3.1331        | 2.55  | 140  | 5.9545          |
+| 2.9234        | 2.64  | 145  | 5.9664          |
+| 3.0005        | 2.73  | 150  | 5.9582          |
+| 3.4196        | 2.82  | 155  | 5.9526          |
+| 3.2783        | 2.91  | 160  | 5.9486          |
+| 3.1719        | 3.0   | 165  | 5.9468          |
+
+
+### 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 sha256:916161a93bc90f187c46a2b179e4ca0ffb0e33d28005d37757d06806929c4d60
+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 sha256:83cb5fe135587e8214fb0eaf890ce14f452f8881408121d32955331ed9c2a410
+size 4027