update

README.md

@@ -0,0 +1,56 @@
+---
+base_model: NlpHUST/electra-base-vn
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: electra-vbpl_cls
+  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. -->
+
+# electra-vbpl_cls
+
+This model is a fine-tuned version of [NlpHUST/electra-base-vn](https://huggingface.co/NlpHUST/electra-base-vn) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0125
+- Accuracy: 0.9972
+
+## 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: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9971590909090909,
+    "eval_loss": 0.012539840303361416,
+    "eval_runtime": 6.4144,
+    "eval_samples": 704,
+    "eval_samples_per_second": 109.753,
+    "eval_steps_per_second": 13.719,
+    "train_loss": 0.14407250677997416,
+    "train_runtime": 1327.6934,
+    "train_samples": 11263,
+    "train_samples_per_second": 42.416,
+    "train_steps_per_second": 1.326
+}

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "NlpHUST/electra-base-vn",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B\u00e1o c\u00e1o",
+    "1": "Ch\u1ec9 th\u1ecb",
+    "2": "C\u00f4ng \u0111i\u1ec7n",
+    "3": "H\u01b0\u1edbng d\u1eabn",
+    "4": "K\u1ebf ho\u1ea1ch",
+    "5": "Lu\u1eadt",
+    "6": "Ngh\u1ecb quy\u1ebft",
+    "7": "Ngh\u1ecb \u0111\u1ecbnh",
+    "8": "Quy ch\u1ebf",
+    "9": "Quy \u0111\u1ecbnh",
+    "10": "Quy\u1ebft \u0111\u1ecbnh",
+    "11": "Th\u00f4ng b\u00e1o",
+    "12": "Th\u00f4ng t\u01b0",
+    "13": "Th\u00f4ng t\u01b0 li\u00ean t\u1ecbch",
+    "14": "V\u0103n b\u1ea3n kh\u00e1c",
+    "15": "\u0110i\u1ec1u \u01b0\u1edbc qu\u1ed1c t\u1ebf"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B\u00e1o c\u00e1o": 0,
+    "Ch\u1ec9 th\u1ecb": 1,
+    "C\u00f4ng \u0111i\u1ec7n": 2,
+    "H\u01b0\u1edbng d\u1eabn": 3,
+    "K\u1ebf ho\u1ea1ch": 4,
+    "Lu\u1eadt": 5,
+    "Ngh\u1ecb quy\u1ebft": 6,
+    "Ngh\u1ecb \u0111\u1ecbnh": 7,
+    "Quy ch\u1ebf": 8,
+    "Quy \u0111\u1ecbnh": 9,
+    "Quy\u1ebft \u0111\u1ecbnh": 10,
+    "Th\u00f4ng b\u00e1o": 11,
+    "Th\u00f4ng t\u01b0": 12,
+    "Th\u00f4ng t\u01b0 li\u00ean t\u1ecbch": 13,
+    "V\u0103n b\u1ea3n kh\u00e1c": 14,
+    "\u0110i\u1ec1u \u01b0\u1edbc qu\u1ed1c t\u1ebf": 15
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 62000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9971590909090909,
+    "eval_loss": 0.012539840303361416,
+    "eval_runtime": 6.4144,
+    "eval_samples": 704,
+    "eval_samples_per_second": 109.753,
+    "eval_steps_per_second": 13.719
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01faa9e19d8b7dc11a3ba7d17425ee3646e7d0c57a88b4624a13ad906d2f1380
+size 534702736

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.14407250677997416,
+    "train_runtime": 1327.6934,
+    "train_samples": 11263,
+    "train_samples_per_second": 42.416,
+    "train_steps_per_second": 1.326
+}