--- library_name: transformers license: mit base_model: microsoft/deberta-v3-large tags: - generated_from_trainer metrics: - accuracy model-index: - name: biotech-sentiment-A-deberta-large-focal-clean results: [] --- # biotech-sentiment-A-deberta-large-focal-clean This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4881 - F1 Macro: 0.1184 - F1 Weighted: 0.0767 - Accuracy: 0.2159 - F1 Neg: 0.0 - F1 Neu: 0.0 - F1 Pos: 0.3551 ## 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: 1e-05 - train_batch_size: 8 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 0.1 - num_epochs: 15 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy | F1 Neg | F1 Neu | F1 Pos | |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:------:|:------:|:------:| | 4.8571 | 1.0 | 85 | 1.0855 | 0.1207 | 0.0800 | 0.2211 | 0.3621 | 0.0 | 0.0 | | 2.2902 | 2.0 | 170 | 0.4893 | 0.1184 | 0.0767 | 0.2159 | 0.0 | 0.0 | 0.3551 | | 1.9634 | 3.0 | 255 | 0.4977 | 0.1207 | 0.0800 | 0.2211 | 0.3621 | 0.0 | 0.0 | | 1.9550 | 4.0 | 340 | 0.4888 | 0.1184 | 0.0767 | 0.2159 | 0.0 | 0.0 | 0.3551 | | 1.9236 | 5.0 | 425 | 0.4881 | 0.1184 | 0.0767 | 0.2159 | 0.0 | 0.0 | 0.3551 | ### Framework versions - Transformers 5.3.0 - Pytorch 2.10.0+cu128 - Datasets 4.8.2 - Tokenizers 0.22.2