metadata
base_model: UBC-NLP/AraT5v2-base-1024
library_name: peft
metrics:
- bleu
- rouge
tags:
- generated_from_trainer
model-index:
- name: finetune-t5-base-on-opus100-Ar2En-with-lora
results: []
finetune-t5-base-on-opus100-Ar2En-with-lora
This model is a fine-tuned version of UBC-NLP/AraT5v2-base-1024 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7552
- Bleu: 4.3018
- Rouge: 0.2386
- Gen Len: 10.572
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge | Gen Len |
|---|---|---|---|---|---|---|
| 6.6745 | 1.0 | 700 | 4.6813 | 3.2487 | 0.2249 | 10.726 |
| 6.1243 | 2.0 | 1400 | 4.0666 | 3.3995 | 0.2273 | 10.0245 |
| 5.3863 | 3.0 | 2100 | 3.9208 | 3.8728 | 0.2335 | 10.3965 |
| 5.1275 | 4.0 | 2800 | 3.8485 | 3.9535 | 0.2331 | 10.5655 |
| 4.975 | 5.0 | 3500 | 3.7971 | 3.9941 | 0.2318 | 10.572 |
| 4.8991 | 6.0 | 4200 | 3.7639 | 4.0786 | 0.2349 | 10.6005 |
| 4.857 | 7.0 | 4900 | 3.7552 | 4.3018 | 0.2386 | 10.572 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1