metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wmt16
metrics:
- bleu
model-index:
- name: wnt116
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: wmt16
type: wmt16
config: de-en
split: validation
args: de-en
metrics:
- name: Bleu
type: bleu
value: 0.7374
wnt116
This model is a fine-tuned version of t5-small on the wmt16 dataset. It achieves the following results on the evaluation set:
- Loss: 2.5838
- Bleu: 0.7374
- Gen Len: 18.1222
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 |
---|---|---|---|---|---|
No log | 1.0 | 32 | 2.6201 | 0.7588 | 18.0821 |
No log | 2.0 | 64 | 2.5838 | 0.7374 | 18.1222 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.2