metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: my_awesome_opus_books_model
results: []
my_awesome_opus_books_model
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2384
- Bleu: 0.4736
- Gen Len: 18.0826
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 |
|---|---|---|---|---|---|
| 2.9148 | 1.0 | 4674 | 2.5719 | 0.2155 | 18.2619 |
| 2.7067 | 2.0 | 9348 | 2.3872 | 0.3419 | 18.1173 |
| 2.5969 | 3.0 | 14022 | 2.2973 | 0.4065 | 18.101 |
| 2.5413 | 4.0 | 18696 | 2.2518 | 0.4603 | 18.0815 |
| 2.5223 | 5.0 | 23370 | 2.2384 | 0.4736 | 18.0826 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.15.0