metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: test_trainer
results: []
test_trainer
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6445
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
---|---|---|---|
0.7754 | 0.5 | 500 | 0.7388 |
0.7724 | 1.0 | 1000 | 0.6889 |
0.693 | 1.5 | 1500 | 0.6731 |
0.6487 | 2.0 | 2000 | 0.6217 |
0.5377 | 2.5 | 2500 | 0.6684 |
0.5239 | 3.0 | 3000 | 0.6445 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3