metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: emnlp_5clusters
results: []
emnlp_5clusters
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: 0.4399
- Bleu: 65.7826
- Gen Len: 10.7768
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: 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.8878 | 1.0 | 4678 | 0.6679 | 51.7004 | 10.7623 |
| 0.6265 | 2.0 | 9356 | 0.5087 | 61.1439 | 10.7779 |
| 0.5037 | 3.0 | 14034 | 0.4596 | 64.4875 | 10.7615 |
| 0.4408 | 4.0 | 18712 | 0.4399 | 65.7826 | 10.7768 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1