metadata
library_name: transformers
license: mit
base_model: facebook/mbart-large-50
tags:
- generated_from_trainer
model-index:
- name: mbart-sci-tr
results: []
mbart-sci-tr
This model is a fine-tuned version of facebook/mbart-large-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5785
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2766 | 1.0 | 697 | 2.7514 |
| 2.7113 | 2.0 | 1394 | 2.6414 |
| 2.4987 | 3.0 | 2091 | 2.5912 |
| 2.3388 | 4.0 | 2788 | 2.5784 |
| 2.2795 | 5.0 | 3485 | 2.5751 |
| 2.1717 | 6.0 | 4182 | 2.5785 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.3.1.post300
- Datasets 2.19.1
- Tokenizers 0.19.1