metadata
license: apache-2.0
base_model: dumitrescustefan/mt5-base-romanian
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: ROAI_proba_2
results: []
ROAI_proba_2
This model is a fine-tuned version of dumitrescustefan/mt5-base-romanian on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4289
- Bleu: 0.6870
- Meteor: 0.8509
- Rouge-l: 0.8753
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Meteor | Rouge-l |
|---|---|---|---|---|---|---|
| 0.6694 | 1.0 | 1207 | 0.5275 | 0.6257 | 0.8122 | 0.8390 |
| 0.8264 | 2.0 | 2414 | 0.4472 | 0.6727 | 0.8430 | 0.8671 |
| 0.5424 | 3.0 | 3621 | 0.4289 | 0.6870 | 0.8509 | 0.8753 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1