lengocquangLAB/Palate-classifier

1---2license: apache-2.03base_model: google-bert/bert-base-uncased4tags:5- generated_from_trainer6metrics:7- accuracy8model-index:9- name: Palate-classifier10  results: []11---12 13<!-- This model card has been generated automatically according to the information the Trainer had access to. You14should probably proofread and complete it, then remove this comment. -->15 16# Palate-classifier17 18This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.19It achieves the following results on the evaluation set:20- Loss: 0.582421- Accuracy: 0.861222 23## Model description24 25More information needed26 27## Intended uses & limitations28 29More information needed30 31## Training and evaluation data32 33More information needed34 35## Training procedure36 37### Training hyperparameters38 39The following hyperparameters were used during training:40- learning_rate: 5e-0541- train_batch_size: 842- eval_batch_size: 843- seed: 4244- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0845- lr_scheduler_type: linear46- num_epochs: 3.047 48### Training results49 50| Training Loss | Epoch | Step | Validation Loss | Accuracy |51|:-------------:|:-----:|:----:|:---------------:|:--------:|52| 0.3797        | 1.0   | 2500 | 0.4659          | 0.8379   |53| 0.318         | 2.0   | 5000 | 0.4107          | 0.8621   |54| 0.2048        | 3.0   | 7500 | 0.5824          | 0.8612   |55 56 57### Framework versions58 59- Transformers 4.38.260- Pytorch 2.1.261- Datasets 2.1.062- Tokenizers 0.15.263