metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: Bart-base-v1
results: []
Bart-base-v1
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0391
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0951 | 0.32 | 250 | 0.0443 |
| 0.051 | 0.64 | 500 | 0.0424 |
| 0.0493 | 0.96 | 750 | 0.0409 |
| 0.0441 | 1.28 | 1000 | 0.0401 |
| 0.0428 | 1.61 | 1250 | 0.0399 |
| 0.0426 | 1.93 | 1500 | 0.0393 |
| 0.0394 | 2.25 | 1750 | 0.0397 |
| 0.0382 | 2.57 | 2000 | 0.0390 |
| 0.038 | 2.89 | 2250 | 0.0389 |
| 0.0356 | 3.21 | 2500 | 0.0393 |
| 0.0347 | 3.53 | 2750 | 0.0392 |
| 0.0343 | 3.85 | 3000 | 0.0390 |
| 0.0331 | 4.17 | 3250 | 0.0392 |
| 0.0313 | 4.49 | 3500 | 0.0393 |
| 0.0319 | 4.82 | 3750 | 0.0390 |
| 0.0307 | 5.14 | 4000 | 0.0392 |
| 0.0296 | 5.46 | 4250 | 0.0394 |
| 0.0297 | 5.78 | 4500 | 0.0391 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.15.2