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: 2.1012
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 7 | 26.2662 |
| 31.9106 | 2.0 | 14 | 17.8852 |
| 17.7251 | 3.0 | 21 | 7.9461 |
| 17.7251 | 4.0 | 28 | 4.9229 |
| 6.9954 | 5.0 | 35 | 4.5398 |
| 4.9995 | 6.0 | 42 | 4.3391 |
| 4.9995 | 7.0 | 49 | 4.1412 |
| 4.4866 | 8.0 | 56 | 3.9415 |
| 4.244 | 9.0 | 63 | 3.7367 |
| 3.9481 | 10.0 | 70 | 3.5045 |
| 3.9481 | 11.0 | 77 | 3.1543 |
| 3.6009 | 12.0 | 84 | 2.7014 |
| 3.2636 | 13.0 | 91 | 2.3692 |
| 3.2636 | 14.0 | 98 | 2.1540 |
| 3.0238 | 15.0 | 105 | 2.1012 |
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
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Srikar9106/flan-t5-base
Base model
google/flan-t5-base