This model is a fine-tuned version of microsoft/xtremedistil-l6-h256-uncased on the Turkish squad 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 |
|---|---|---|---|
| No log | 1.0 | 350 | 3.8389 |
| 4.4474 | 2.0 | 700 | 3.3748 |
| 3.512 | 3.0 | 1050 | 3.0657 |
| 3.512 | 4.0 | 1400 | 2.9219 |
| 3.1526 | 5.0 | 1750 | 2.8517 |
| 2.9972 | 6.0 | 2100 | 2.8135 |
pytorch_model.bin 51 MBtraining_args.bin 3.2 kB