metadata
license: mit
base_model: facebook/mbart-large-50
tags:
- generated_from_trainer
model-index:
- name: mscocoownbart
results: []
mscocoownbart
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: 0.2140
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- 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 |
|---|---|---|---|
| 0.2732 | 1.0 | 1600 | 0.2376 |
| 0.269 | 2.0 | 3200 | 0.2166 |
| 0.1508 | 3.0 | 4800 | 0.2101 |
| 0.1283 | 4.0 | 6400 | 0.2140 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1