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-11
+  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-11
+
+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: 6.8857
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 10.1921       | 0.09  | 5    | 7.0754          |
+| 5.8664        | 0.18  | 10   | 5.7086          |
+| 5.1625        | 0.27  | 15   | 5.4529          |
+| 4.5385        | 0.36  | 20   | 5.3727          |
+| 3.897         | 0.45  | 25   | 5.5354          |
+| 3.6878        | 0.55  | 30   | 5.3682          |
+| 2.9641        | 0.64  | 35   | 5.1507          |
+| 2.7122        | 0.73  | 40   | 5.3411          |
+| 2.741         | 0.82  | 45   | 5.5691          |
+| 2.4612        | 0.91  | 50   | 5.7809          |
+| 2.1667        | 1.0   | 55   | 6.0948          |
+| 1.9087        | 1.09  | 60   | 6.2781          |
+| 1.6097        | 1.18  | 65   | 6.4563          |
+| 1.6726        | 1.27  | 70   | 6.5659          |
+| 1.4427        | 1.36  | 75   | 6.5445          |
+| 1.359         | 1.45  | 80   | 6.5064          |
+| 1.3626        | 1.55  | 85   | 6.6096          |
+| 1.0693        | 1.64  | 90   | 6.6934          |
+| 1.1223        | 1.73  | 95   | 6.7681          |
+| 1.0488        | 1.82  | 100  | 6.7284          |
+| 0.8296        | 1.91  | 105  | 6.6706          |
+| 0.9246        | 2.0   | 110  | 6.7214          |
+| 0.7915        | 2.09  | 115  | 6.7793          |
+| 0.5945        | 2.18  | 120  | 6.8051          |
+| 0.6342        | 2.27  | 125  | 6.7852          |
+| 0.513         | 2.36  | 130  | 6.8174          |
+| 0.5309        | 2.45  | 135  | 6.8690          |
+| 0.5658        | 2.55  | 140  | 6.8917          |
+| 0.5028        | 2.64  | 145  | 6.8958          |
+| 0.5523        | 2.73  | 150  | 6.9080          |
+| 0.4203        | 2.82  | 155  | 6.9098          |
+| 0.4735        | 2.91  | 160  | 6.8899          |
+| 0.4147        | 3.0   | 165  | 6.8857          |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

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": "4.34.0",
+  "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:fd48b5d6af73b84e2490741c2bfd47d0ccf007db7b17aee9f2fd57f43a5050d4
+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 +1,59 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "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:b443edc4c50f75ec62a97b0d4b74796002915af76b336339c9ecc00ebf45e4ef
+size 4027