metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: t5-base-finetuned-English-to-Dagaare
results: []
t5-base-finetuned-English-to-Dagaare
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1439
- Bleu: 0.0
- Gen Len: 6.0454
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 484 | 0.1642 | 0.0 | 4.9104 |
| 0.7996 | 2.0 | 968 | 0.1519 | 0.0 | 5.5891 |
| 0.1548 | 3.0 | 1452 | 0.1470 | 0.0 | 5.7218 |
| 0.1469 | 4.0 | 1936 | 0.1447 | 0.0 | 5.7835 |
| 0.1444 | 5.0 | 2420 | 0.1439 | 0.0 | 6.0454 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1