metadata
base_model: t5-small
library_name: transformers
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: en-af-sql-training-1727527893
results: []
en-af-sql-training-1727527893
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0210
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: 0.005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0573 | 0.1348 | 500 | 0.0452 |
| 0.0424 | 0.2695 | 1000 | 0.0364 |
| 0.037 | 0.4043 | 1500 | 0.0323 |
| 0.0356 | 0.5391 | 2000 | 0.0287 |
| 0.0328 | 0.6739 | 2500 | 0.0269 |
| 0.0281 | 0.8086 | 3000 | 0.0255 |
| 0.0286 | 0.9434 | 3500 | 0.0238 |
| 0.0269 | 1.0782 | 4000 | 0.0233 |
| 0.0247 | 1.2129 | 4500 | 0.0225 |
| 0.0245 | 1.3477 | 5000 | 0.0217 |
| 0.0226 | 1.4825 | 5500 | 0.0214 |
| 0.0245 | 1.6173 | 6000 | 0.0211 |
| 0.024 | 1.7520 | 6500 | 0.0210 |
| 0.0249 | 1.8868 | 7000 | 0.0210 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 3.0.0
- Tokenizers 0.19.1