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: 81.9123
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: 0.1
- 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 | 33.1369 |
| 20.7016 | 2.0 | 14 | 12.1900 |
| 25.2412 | 3.0 | 21 | 32.0566 |
| 25.2412 | 4.0 | 28 | 79.4659 |
| 56.202 | 5.0 | 35 | 73.7778 |
| 78.0759 | 6.0 | 42 | 73.1364 |
| 78.0759 | 7.0 | 49 | 78.5961 |
| 83.1807 | 8.0 | 56 | 101.5425 |
| 88.3209 | 9.0 | 63 | 80.0633 |
| 80.4304 | 10.0 | 70 | 81.9123 |
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
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for hasinibangale/flan-t5-base
Base model
google/flan-t5-base