metadata
base_model: mrm8488/mobilebert-uncased-finetuned-squadv1
tags:
- generated_from_trainer
model-index:
- name: mobilebert-uncased-finetuned-squadv1-231123
results: []
mobilebert-uncased-finetuned-squadv1-231123
This model is a fine-tuned version of mrm8488/mobilebert-uncased-finetuned-squadv1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9911
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 261 | 2.3054 |
| 2.2403 | 2.0 | 522 | 2.1807 |
| 2.2403 | 3.0 | 783 | 2.9374 |
| 1.7505 | 4.0 | 1044 | 2.2380 |
| 1.7505 | 5.0 | 1305 | 2.4475 |
| 1.3342 | 6.0 | 1566 | 2.4172 |
| 1.3342 | 7.0 | 1827 | 2.6019 |
| 1.1435 | 8.0 | 2088 | 2.7694 |
| 1.1435 | 9.0 | 2349 | 2.9024 |
| 0.968 | 10.0 | 2610 | 2.9911 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0