--- library_name: transformers license: mit base_model: roberta-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: fincausal-task1-roberta-base results: [] --- # fincausal-task1-roberta-base 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: 0.1272 - Accuracy: 0.9581 - Macro F1: 0.8478 - Micro F1: 0.9581 ## 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: 64 - eval_batch_size: 32 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Micro F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| | No log | 1.0 | 235 | 0.1046 | 0.9496 | 0.8220 | 0.9496 | | No log | 2.0 | 470 | 0.1089 | 0.9528 | 0.8394 | 0.9528 | | 0.1394 | 3.0 | 705 | 0.1272 | 0.9581 | 0.8478 | 0.9581 | ### Framework versions - Transformers 4.50.3 - Pytorch 2.11.0+cu130 - Datasets 3.6.0 - Tokenizers 0.21.4