metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: Bart_classifier
results: []
Bart_classifier
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5262
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2135 | 1.0 | 219 | 0.1489 |
| 0.197 | 2.0 | 438 | 0.2690 |
| 0.1443 | 3.0 | 657 | 0.1525 |
| 0.1655 | 4.0 | 876 | 0.1819 |
| 0.0984 | 5.0 | 1095 | 0.1819 |
| 0.0854 | 6.0 | 1314 | 0.2220 |
| 0.0622 | 7.0 | 1533 | 0.2892 |
| 0.0446 | 8.0 | 1752 | 0.3801 |
| 0.0171 | 9.0 | 1971 | 0.4832 |
| 0.0108 | 10.0 | 2190 | 0.5262 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1