metadata
license: mit
base_model: roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-large-lora-2.63M-snli-model2
results: []
roberta-large-lora-2.63M-snli-model2
This model is a fine-tuned version of roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6398
- Accuracy: 0.785
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: 256
- eval_batch_size: 256
- seed: 84
- 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 | Accuracy |
|---|---|---|---|---|
| 0.3568 | 1.0 | 2146 | 0.2681 | 0.9052 |
| 0.3292 | 2.0 | 4292 | 0.2502 | 0.9097 |
| 0.3252 | 3.0 | 6438 | 0.2459 | 0.9102 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0