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: 3.6399
- Bleu: 4.8897
- Rouge: 0.2479
- Gen Len: 10.622
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge | Gen Len |
|---|---|---|---|---|---|---|
| 15.1403 | 1.0 | 700 | 5.2590 | 1.1467 | 0.1085 | 11.17 |
| 6.6309 | 2.0 | 1400 | 4.6547 | 3.1579 | 0.2258 | 10.297 |
| 5.9949 | 3.0 | 2100 | 4.0112 | 3.4311 | 0.2226 | 10.095 |
| 5.2808 | 4.0 | 2800 | 3.8936 | 3.7676 | 0.2331 | 10.5535 |
| 5.0299 | 5.0 | 3500 | 3.8082 | 3.8261 | 0.2272 | 10.4065 |
| 4.893 | 6.0 | 4200 | 3.7392 | 4.2894 | 0.235 | 10.426 |
| 4.7854 | 7.0 | 4900 | 3.6929 | 4.8132 | 0.2422 | 10.4765 |
| 4.7114 | 8.0 | 5600 | 3.6592 | 4.9749 | 0.2477 | 10.6395 |
| 4.6835 | 9.0 | 6300 | 3.6455 | 4.9315 | 0.2475 | 10.584 |
| 4.6606 | 10.0 | 7000 | 3.6399 | 4.8897 | 0.2479 | 10.622 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1