This model is a fine-tuned version of distilbert-base-uncased on the mit_restaurant dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 431 | 0.4575 | 0.6220 | 0.6856 | 0.6523 | 0.8650 |
| 1.1705 | 2.0 | 862 | 0.3183 | 0.7747 | 0.7953 | 0.7848 | 0.9071 |
| 0.3254 | 3.0 | 1293 | 0.3163 | 0.7668 | 0.8021 | 0.7841 | 0.9058 |
| 0.2287 | 4.0 | 1724 | 0.3097 | 0.7874 | 0.8104 | 0.7988 | 0.9119 |
pytorch_model.bin 266 MBtraining_args.bin 2.8 kB