metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: roberta-base-finetuned-wls-manual-10ep
results: []
roberta-base-finetuned-wls-manual-10ep
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0599
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8201 | 0.93 | 7 | 1.5286 |
| 1.4462 | 2.0 | 15 | 1.3480 |
| 1.3032 | 2.93 | 22 | 1.3377 |
| 1.2564 | 4.0 | 30 | 1.1907 |
| 1.246 | 4.93 | 37 | 1.1702 |
| 1.1777 | 6.0 | 45 | 1.1549 |
| 1.118 | 6.93 | 52 | 1.0611 |
| 1.1339 | 8.0 | 60 | 1.1084 |
| 1.1158 | 8.93 | 67 | 1.1376 |
| 1.0143 | 9.33 | 70 | 1.1225 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.11.0+cu113
- Datasets 2.14.4
- Tokenizers 0.13.3