bert-cased

README.md

@@ -0,0 +1,88 @@
+---
+base_model: phiyodr/bert-base-finetuned-squad2
+tags:
+- generated_from_trainer
+model-index:
+- name: test-bert-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. -->
+
+# test-bert-1
+
+This model is a fine-tuned version of [phiyodr/bert-base-finetuned-squad2](https://huggingface.co/phiyodr/bert-base-finetuned-squad2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 8.3972
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 8.3538        | 0.09  | 5    | 9.3652          |
+| 8.271         | 0.18  | 10   | 9.3025          |
+| 8.2794        | 0.27  | 15   | 9.2420          |
+| 8.0966        | 0.36  | 20   | 9.1837          |
+| 8.1925        | 0.45  | 25   | 9.1277          |
+| 8.1126        | 0.55  | 30   | 9.0740          |
+| 7.711         | 0.64  | 35   | 9.0230          |
+| 7.5978        | 0.73  | 40   | 8.9749          |
+| 8.0276        | 0.82  | 45   | 8.9287          |
+| 7.7477        | 0.91  | 50   | 8.8839          |
+| 7.5803        | 1.0   | 55   | 8.8422          |
+| 7.6439        | 1.09  | 60   | 8.8022          |
+| 7.4937        | 1.18  | 65   | 8.7649          |
+| 7.6905        | 1.27  | 70   | 8.7294          |
+| 7.7922        | 1.36  | 75   | 8.6950          |
+| 7.7377        | 1.45  | 80   | 8.6623          |
+| 7.8642        | 1.55  | 85   | 8.6316          |
+| 7.5909        | 1.64  | 90   | 8.6025          |
+| 7.4629        | 1.73  | 95   | 8.5758          |
+| 7.5195        | 1.82  | 100  | 8.5512          |
+| 7.664         | 1.91  | 105  | 8.5282          |
+| 7.3092        | 2.0   | 110  | 8.5074          |
+| 7.015         | 2.09  | 115  | 8.4889          |
+| 7.4112        | 2.18  | 120  | 8.4719          |
+| 7.6664        | 2.27  | 125  | 8.4563          |
+| 7.5634        | 2.36  | 130  | 8.4430          |
+| 7.4502        | 2.45  | 135  | 8.4314          |
+| 7.3085        | 2.55  | 140  | 8.4212          |
+| 7.2558        | 2.64  | 145  | 8.4128          |
+| 7.4077        | 2.73  | 150  | 8.4066          |
+| 7.6318        | 2.82  | 155  | 8.4017          |
+| 7.3355        | 2.91  | 160  | 8.3988          |
+| 7.4367        | 3.0   | 165  | 8.3972          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "phiyodr/bert-base-finetuned-squad2",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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 sha256:9e40ee1e778de93a15011ebcf422ff4777fa695f101ce08a3c393d438c3384cb
+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 +1,65 @@
+{
+  "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,
+  "max_length": 384,
+  "model_max_length": 512,
+  "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 sha256:57c6b3910ac3438e624af6a8692d18ee66bc9828877b803be819366d15417774
+size 4536