metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: emnlp_test_9clusters_bart_large_sati
results: []
emnlp_test_9clusters_bart_large_sati
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: 0.5178
- Bleu: 83.1112
- Gen Len: 10.6083
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.1866 | 2.3303 | 15000 | 0.5819 | 80.4332 | 11.3463 |
| 0.1127 | 4.6606 | 30000 | 0.5120 | 82.2508 | 10.6137 |
| 0.0774 | 6.9908 | 45000 | 0.4587 | 82.8524 | 10.6968 |
| 0.0574 | 9.3211 | 60000 | 0.5178 | 83.1112 | 10.6083 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1