metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: roberta-base
model-index:
- name: Roberta_peft_model
results: []
Roberta_peft_model
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2995
- Accuracy: 0.9392
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: 0.00037260644859873676
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2468 | 1.0 | 8419 | 0.2589 | 0.9289 |
| 0.2273 | 2.0 | 16838 | 0.2549 | 0.9392 |
| 0.1927 | 3.0 | 25257 | 0.2752 | 0.9358 |
| 0.1615 | 4.0 | 33676 | 0.2995 | 0.9392 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2