metadata
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fine_tuned_2e-5
results: []
fine_tuned_2e-5
This model is a fine-tuned version of FacebookAI/roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0598
- Accuracy: 0.99
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: 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 | Accuracy |
|---|---|---|---|---|
| 0.393 | 0.15 | 100 | 0.1670 | 0.97 |
| 0.2681 | 0.3 | 200 | 0.2389 | 0.9583 |
| 0.1241 | 0.44 | 300 | 0.0751 | 0.9883 |
| 0.1371 | 0.59 | 400 | 0.0506 | 0.9867 |
| 0.0888 | 0.74 | 500 | 0.0598 | 0.99 |
| 0.1169 | 0.89 | 600 | 0.0633 | 0.9917 |
| 0.0501 | 1.04 | 700 | 0.0804 | 0.9883 |
| 0.0452 | 1.19 | 800 | 0.1110 | 0.9833 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.1+cu118
- Datasets 2.16.0
- Tokenizers 0.15.0