metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: 04-07-06-08-35
results: []
04-07-06-08-35
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: 0.6641
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: 0.0002
- train_batch_size: 4
- 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 |
|---|---|---|---|
| 0.6434 | 0.21 | 10 | 0.6758 |
| 0.619 | 0.42 | 20 | 0.6846 |
| 0.6186 | 0.62 | 30 | 0.6807 |
| 0.7283 | 0.83 | 40 | 0.6655 |
| 0.6407 | 1.04 | 50 | 0.6577 |
| 0.7037 | 1.25 | 60 | 0.6553 |
| 0.6299 | 1.46 | 70 | 0.6504 |
| 0.6685 | 1.67 | 80 | 0.6455 |
| 0.6158 | 1.88 | 90 | 0.6450 |
| 0.6166 | 2.08 | 100 | 0.6567 |
| 0.6191 | 2.29 | 110 | 0.6685 |
| 0.7038 | 2.5 | 120 | 0.6660 |
| 0.6003 | 2.71 | 130 | 0.6650 |
| 0.6293 | 2.92 | 140 | 0.6641 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.13.3