metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
model-index:
- name: bart-finetuned-lyrlen-128-tokens
results: []
bart-finetuned-lyrlen-128-tokens
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9008
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2981 | 0.33 | 500 | 3.0587 |
| 3.0335 | 0.67 | 1000 | 2.9762 |
| 2.9525 | 1.0 | 1500 | 2.9432 |
| 2.9021 | 1.33 | 2000 | 2.9562 |
| 2.8671 | 1.67 | 2500 | 2.9502 |
| 2.8037 | 2.0 | 3000 | 2.9134 |
| 2.7389 | 2.33 | 3500 | 2.9058 |
| 2.7305 | 2.67 | 4000 | 2.9016 |
| 2.7196 | 3.0 | 4500 | 2.8960 |
| 2.7217 | 3.33 | 5000 | 2.9097 |
| 2.6659 | 3.67 | 5500 | 2.9045 |
| 2.6616 | 4.0 | 6000 | 2.9008 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2