metadata
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
model-index:
- name: baseroberta-finetuned_squadcovid
results: []
baseroberta-finetuned_squadcovid
This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8426
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6662 | 0.21 | 1000 | 1.0762 |
| 0.7148 | 0.42 | 2000 | 0.9627 |
| 0.6548 | 0.64 | 3000 | 0.8933 |
| 0.601 | 0.85 | 4000 | 0.8712 |
| 0.5623 | 1.06 | 5000 | 0.8938 |
| 0.4915 | 1.27 | 6000 | 0.8678 |
| 0.4772 | 1.49 | 7000 | 0.8568 |
| 0.4709 | 1.7 | 8000 | 0.8479 |
| 0.4616 | 1.91 | 9000 | 0.8426 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2