| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: google/flan-t5-small |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: flan-t5-small-gigatrue-layercut-D5 |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # flan-t5-small-gigatrue-layercut-D5 |
|
|
| This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 2.1698 |
|
|
| ## 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: 0.0003 |
| - train_batch_size: 256 |
| - eval_batch_size: 256 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 3 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:------:|:-----:|:---------------:| |
| | 2.6416 | 0.2030 | 3000 | 2.2210 | |
| | 2.5493 | 0.4059 | 6000 | 2.1990 | |
| | 2.5262 | 0.6089 | 9000 | 2.1853 | |
| | 2.5175 | 0.8119 | 12000 | 2.1791 | |
| | 2.5115 | 1.0148 | 15000 | 2.1753 | |
| | 2.5073 | 1.2178 | 18000 | 2.1723 | |
| | 2.505 | 1.4207 | 21000 | 2.1716 | |
| | 2.5018 | 1.6237 | 24000 | 2.1730 | |
| | 2.5013 | 1.8267 | 27000 | 2.1698 | |
| | 2.5016 | 2.0296 | 30000 | 2.1704 | |
| | 2.4996 | 2.2326 | 33000 | 2.1705 | |
| | 2.5016 | 2.4356 | 36000 | 2.1701 | |
| | 2.5006 | 2.6385 | 39000 | 2.1697 | |
| | 2.5013 | 2.8415 | 42000 | 2.1698 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.45.2 |
| - Pytorch 2.5.1 |
| - Datasets 3.2.0 |
| - Tokenizers 0.20.3 |
|
|
