flan-t5-base
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7809
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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 7 | 3.7457 |
| 4.2412 | 2.0 | 14 | 3.1903 |
| 3.4905 | 3.0 | 21 | 1.9625 |
| 3.4905 | 4.0 | 28 | 1.4156 |
| 2.5997 | 5.0 | 35 | 1.2528 |
| 2.0712 | 6.0 | 42 | 0.9727 |
| 2.0712 | 7.0 | 49 | 0.9482 |
| 1.7497 | 8.0 | 56 | 0.8107 |
| 1.5059 | 9.0 | 63 | 0.7856 |
| 1.4235 | 10.0 | 70 | 0.7809 |
Framework versions
- PEFT 0.14.0
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.0
- Tokenizers 0.21.0
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Vaishnavi2207/flan-t5-base
Base model
google/flan-t5-base