metadata
license: mit
tags:
- generated_from_trainer
datasets:
- squad_v2
model-index:
- name: qwerty
results: []
xtremedistil-l6-h384-uncased-changed
This model is a fine-tuned version of microsoft/xtremedistil-l6-h384-uncased on the squad_v2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.5931
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6372 | 1.0 | 8235 | 1.6719 |
| 1.4847 | 2.0 | 16470 | 1.5866 |
| 1.4038 | 3.0 | 24705 | 1.5931 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2