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: 0.3073
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 |
|---|---|---|---|
| 31.3334 | 1.0 | 18 | 10.1799 |
| 5.945 | 2.0 | 36 | 4.4270 |
| 4.1975 | 3.0 | 54 | 3.4159 |
| 2.7355 | 4.0 | 72 | 1.4944 |
| 1.5343 | 5.0 | 90 | 0.6784 |
| 1.175 | 6.0 | 108 | 0.4871 |
| 0.903 | 7.0 | 126 | 0.3941 |
| 0.7155 | 8.0 | 144 | 0.3448 |
| 0.6221 | 9.0 | 162 | 0.3126 |
| 0.6374 | 10.0 | 180 | 0.3073 |
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 kushal1208/flan-t5-base
Base model
google/flan-t5-base