| license: mit | |
| tags: | |
| - generated_from_trainer | |
| metrics: | |
| - accuracy | |
| - f1 | |
| - precision | |
| - recall | |
| model-index: | |
| - name: outputs | |
| 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. --> | |
| # outputs | |
| This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 1.5411 | |
| - Accuracy: 0.5226 | |
| - F1: 0.4181 | |
| - Precision: 0.4320 | |
| - Recall: 0.4102 | |
| ## 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 | Accuracy | F1 | Precision | Recall | | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| | |
| | 1.5774 | 1.0 | 638 | 1.3539 | 0.5329 | 0.3936 | 0.4611 | 0.4001 | | |
| | 1.0496 | 2.0 | 1276 | 1.4186 | 0.5226 | 0.3943 | 0.4234 | 0.3883 | | |
| | 0.7299 | 3.0 | 1914 | 1.5411 | 0.5226 | 0.4181 | 0.4320 | 0.4102 | | |
| ### Framework versions | |
| - Transformers 4.25.1 | |
| - Pytorch 1.13.1+cu116 | |
| - Datasets 2.8.0 | |
| - Tokenizers 0.13.2 | |