| license: apache-2.0 | |
| library_name: transformers | |
| # BestCheckpoint Demo | |
| This model checkpoint was selected from a hyperparameter sweep as the best-performing run. | |
| ## Evaluation Metrics | |
| | Metric | Value | | |
| |---|---| | |
| | Validation Accuracy | 0.861 | | |
| | Validation Loss | 0.412 | | |
| | Validation F1 | 0.855 | | |
| ## Training Configuration | |
| The best run used the following hyperparameters: | |
| | Hyperparameter | Value | | |
| |---|---| | |
| | Learning Rate | 3e-05 | | |
| | Weight Decay | 0.1 | | |
| | Epochs | 10 | | |
| | Batch Size | 32 | | |
| ## How to Use | |
| ```python | |
| from transformers import AutoModelForSequenceClassification, AutoTokenizer | |
| model = AutoModelForSequenceClassification.from_pretrained("BestCheckpoint-Demo") | |
| tokenizer = AutoTokenizer.from_pretrained("BestCheckpoint-Demo") | |
| ``` | |
| ## License | |
| This model is released under the Apache 2.0 license. | |