Instructions to use livles/csb-sent-25perc-byte with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use livles/csb-sent-25perc-byte with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("livles/csb-sent-25perc-byte") model = AutoModelForSeq2SeqLM.from_pretrained("livles/csb-sent-25perc-byte", device_map="auto") - Notebooks
- Google Colab
- Kaggle
csb-sent-25perc-byte
This model is a fine-tuned version of google/byt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1702
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.2481 | 1.0 | 563 | 2.2139 |
| 2.1906 | 2.0 | 1126 | 1.7570 |
| 1.9140 | 3.0 | 1689 | 1.6125 |
| 1.7785 | 4.0 | 2252 | 1.4032 |
| 1.6386 | 5.0 | 2815 | 1.3365 |
| 1.5470 | 6.0 | 3378 | 1.2607 |
| 1.4803 | 7.0 | 3941 | 1.2251 |
| 1.4017 | 8.0 | 4504 | 1.2045 |
| 1.3709 | 9.0 | 5067 | 1.1899 |
| 1.3522 | 10.0 | 5630 | 1.1788 |
| 1.3407 | 11.0 | 6193 | 1.1722 |
| 1.3288 | 12.0 | 6756 | 1.1702 |
Framework versions
- Transformers 5.6.2
- Pytorch 2.9.1+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support