metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: emnlp_test_9clusters_combined_bart_large_200k
results: []
emnlp_test_9clusters_combined_bart_large_200k
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: 0.4843
- Bleu: 86.9507
- Gen Len: 10.8804
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.5265 | 1.0 | 5605 | 0.6332 | 79.0951 | 10.8681 |
| 0.3437 | 2.0 | 11210 | 0.4387 | 83.6164 | 10.9593 |
| 0.2586 | 3.0 | 16815 | 0.4504 | 85.3036 | 10.8776 |
| 0.2168 | 4.0 | 22420 | 0.3906 | 86.0988 | 10.97 |
| 0.1835 | 5.0 | 28025 | 0.4560 | 86.677 | 10.893 |
| 0.1665 | 6.0 | 33630 | 0.4843 | 86.9507 | 10.8804 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1