my_awesome_opus_books_model
This model is a fine-tuned version of google-t5/t5-small on the kde4 dataset. It achieves the following results on the evaluation set:
- Loss: 1.8499
- Bleu: 5.8314
- Gen Len: 13.8817
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 |
|---|---|---|---|---|---|
| 2.1658 | 1.0 | 9040 | 1.9233 | 5.6749 | 13.6234 |
| 2.0639 | 2.0 | 18080 | 1.8499 | 5.8314 | 13.8817 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu118
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for SouthMemphis/my_awesome_opus_books_model
Base model
google-t5/t5-smallDataset used to train SouthMemphis/my_awesome_opus_books_model
Evaluation results
- Bleu on kde4self-reported5.831
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("SouthMemphis/my_awesome_opus_books_model") model = AutoModelForSeq2SeqLM.from_pretrained("SouthMemphis/my_awesome_opus_books_model", device_map="auto")