| language: en | |
| license: apache-2.0 | |
| base_model: roberta-base | |
| tags: | |
| - text-classification | |
| - sentiment | |
| datasets: | |
| - surrey-nlp/BESSTIE-CW-26 | |
| metrics: | |
| - f1 | |
| - accuracy | |
| # roberta-base-sentiment | |
| Fine-tuned [`roberta-base`](https://huggingface.co/roberta-base) on the | |
| [BESSTIE-CW-26](https://huggingface.co/datasets/surrey-nlp/BESSTIE-CW-26) | |
| dataset for binary sentiment classification. | |
| ## Training | |
| - Base model: `roberta-base` | |
| - Task: `sentiment` (binary) | |
| - Epochs: 2 | |
| - Batch size: 4 | |
| - Learning rate: 2e-5 | |
| - Weight decay: 0.01 | |
| - Max sequence length: 64 | |
| - Seed: 65 (best of {42, 65, 131}) | |
| - Optimizer: AdamW (Trainer default) | |
| ## Test results | |
| - macro-F1: **0.8932** | |
| ## Usage | |
| ```python | |
| from transformers import AutoModelForSequenceClassification, AutoTokenizer | |
| model = AutoModelForSequenceClassification.from_pretrained("vyshnav112233/roberta-base-sentiment") | |
| tokenizer = AutoTokenizer.from_pretrained("vyshnav112233/roberta-base-sentiment") | |
| inputs = tokenizer("your sentence here", return_tensors="pt", truncation=True, max_length=64) | |
| logits = model(**inputs).logits | |
| ``` | |