metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: roberta-base-finetuned-wls-whisper-8ep
results: []
roberta-base-finetuned-wls-whisper-8ep
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0840
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.461 | 1.0 | 26 | 1.2521 |
| 1.231 | 2.0 | 52 | 1.2105 |
| 1.1867 | 3.0 | 78 | 1.1645 |
| 1.1347 | 4.0 | 104 | 1.1235 |
| 1.0661 | 5.0 | 130 | 1.1472 |
| 1.089 | 6.0 | 156 | 1.0720 |
| 1.0168 | 7.0 | 182 | 1.1341 |
| 1.03 | 8.0 | 208 | 1.0483 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.11.0+cu113
- Datasets 2.14.4
- Tokenizers 0.13.3