--- base_model: NlpHUST/ner-vietnamese-electra-base tags: - generated_from_trainer model-index: - name: my_awesome_ner-token_classification_v1.0.7-7 results: [] --- # my_awesome_ner-token_classification_v1.0.7-7 This model is a fine-tuned version of [NlpHUST/ner-vietnamese-electra-base](https://huggingface.co/NlpHUST/ner-vietnamese-electra-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3324 - Age: {'precision': 0.8854961832061069, 'recall': 0.8656716417910447, 'f1': 0.8754716981132075, 'number': 134} - Datetime: {'precision': 0.6675774134790529, 'recall': 0.7426545086119554, 'f1': 0.7031175059952038, 'number': 987} - Disease: {'precision': 0.6914893617021277, 'recall': 0.7442748091603053, 'f1': 0.7169117647058824, 'number': 262} - Event: {'precision': 0.3287671232876712, 'recall': 0.34285714285714286, 'f1': 0.3356643356643356, 'number': 280} - Gender: {'precision': 0.7529411764705882, 'recall': 0.735632183908046, 'f1': 0.7441860465116279, 'number': 87} - Law: {'precision': 0.5590062111801242, 'recall': 0.7058823529411765, 'f1': 0.6239168110918544, 'number': 255} - Location: {'precision': 0.6794407042982911, 'recall': 0.7309192200557103, 'f1': 0.7042404723564144, 'number': 1795} - Organization: {'precision': 0.6267441860465116, 'recall': 0.712491738268341, 'f1': 0.6668728734921126, 'number': 1513} - Person: {'precision': 0.6789052069425902, 'recall': 0.7316546762589928, 'f1': 0.7042936288088643, 'number': 1390} - Quantity: {'precision': 0.522273425499232, 'recall': 0.6007067137809188, 'f1': 0.5587510271158588, 'number': 566} - Role: {'precision': 0.46021840873634945, 'recall': 0.5393053016453382, 'f1': 0.49663299663299665, 'number': 547} - Transportation: {'precision': 0.49645390070921985, 'recall': 0.6086956521739131, 'f1': 0.5468749999999999, 'number': 115} - Overall Precision: 0.6251 - Overall Recall: 0.6930 - Overall F1: 0.6573 - Overall Accuracy: 0.8992 ## 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: cosine - num_epochs: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | Age | Datetime | Disease | Event | Gender | Law | Location | Organization | Person | Quantity | Role | Transportation | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |:-------------:|:------:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| | 0.3138 | 1.9991 | 2313 | 0.3302 | {'precision': 0.8721804511278195, 'recall': 0.8656716417910447, 'f1': 0.8689138576779025, 'number': 134} | {'precision': 0.6596715328467153, 'recall': 0.7325227963525835, 'f1': 0.6941910705712914, 'number': 987} | {'precision': 0.6421725239616614, 'recall': 0.767175572519084, 'f1': 0.6991304347826088, 'number': 262} | {'precision': 0.34297520661157027, 'recall': 0.29642857142857143, 'f1': 0.31800766283524906, 'number': 280} | {'precision': 0.84, 'recall': 0.7241379310344828, 'f1': 0.7777777777777777, 'number': 87} | {'precision': 0.5373134328358209, 'recall': 0.7058823529411765, 'f1': 0.6101694915254238, 'number': 255} | {'precision': 0.6927312775330396, 'recall': 0.7008356545961003, 'f1': 0.6967599003046248, 'number': 1795} | {'precision': 0.6132789749563191, 'recall': 0.6959682749504296, 'f1': 0.6520123839009287, 'number': 1513} | {'precision': 0.704323570432357, 'recall': 0.7266187050359713, 'f1': 0.7152974504249292, 'number': 1390} | {'precision': 0.5159817351598174, 'recall': 0.598939929328622, 'f1': 0.55437448896157, 'number': 566} | {'precision': 0.4633333333333333, 'recall': 0.5082266910420475, 'f1': 0.4847428073234525, 'number': 547} | {'precision': 0.49206349206349204, 'recall': 0.5391304347826087, 'f1': 0.5145228215767634, 'number': 115} | 0.6280 | 0.6766 | 0.6514 | 0.9015 | | 0.2556 | 3.9983 | 4626 | 0.3324 | {'precision': 0.8854961832061069, 'recall': 0.8656716417910447, 'f1': 0.8754716981132075, 'number': 134} | {'precision': 0.6675774134790529, 'recall': 0.7426545086119554, 'f1': 0.7031175059952038, 'number': 987} | {'precision': 0.6914893617021277, 'recall': 0.7442748091603053, 'f1': 0.7169117647058824, 'number': 262} | {'precision': 0.3287671232876712, 'recall': 0.34285714285714286, 'f1': 0.3356643356643356, 'number': 280} | {'precision': 0.7529411764705882, 'recall': 0.735632183908046, 'f1': 0.7441860465116279, 'number': 87} | {'precision': 0.5590062111801242, 'recall': 0.7058823529411765, 'f1': 0.6239168110918544, 'number': 255} | {'precision': 0.6794407042982911, 'recall': 0.7309192200557103, 'f1': 0.7042404723564144, 'number': 1795} | {'precision': 0.6267441860465116, 'recall': 0.712491738268341, 'f1': 0.6668728734921126, 'number': 1513} | {'precision': 0.6789052069425902, 'recall': 0.7316546762589928, 'f1': 0.7042936288088643, 'number': 1390} | {'precision': 0.522273425499232, 'recall': 0.6007067137809188, 'f1': 0.5587510271158588, 'number': 566} | {'precision': 0.46021840873634945, 'recall': 0.5393053016453382, 'f1': 0.49663299663299665, 'number': 547} | {'precision': 0.49645390070921985, 'recall': 0.6086956521739131, 'f1': 0.5468749999999999, 'number': 115} | 0.6251 | 0.6930 | 0.6573 | 0.8992 | ### Framework versions - Transformers 4.41.2 - Pytorch 2.1.2 - Datasets 2.19.2 - Tokenizers 0.19.1