metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- opus_books
metrics:
- bleu
model-index:
- name: test_t5_small_example_3
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: opus_books
type: opus_books
config: en-fr
split: train
args: en-fr
metrics:
- name: Bleu
type: bleu
value: 6.2099
test_t5_small_example_3
This model is a fine-tuned version of t5-small on the opus_books dataset. It achieves the following results on the evaluation set:
- Loss: 1.5333
- Bleu: 6.2099
- Gen Len: 17.5692
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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.7061 | 1.0 | 6355 | 1.5458 | 6.1194 | 17.5769 |
| 1.7168 | 2.0 | 12710 | 1.5333 | 6.2099 | 17.5692 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3