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: 7.1660
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 |
|---|---|---|---|
| 9.2953 | 1.0 | 10 | 7.5640 |
| 9.0145 | 2.0 | 20 | 7.3709 |
| 8.9068 | 3.0 | 30 | 7.2321 |
| 8.5713 | 4.0 | 40 | 7.1978 |
| 8.2664 | 5.0 | 50 | 7.1871 |
| 8.2607 | 6.0 | 60 | 7.1742 |
| 8.9269 | 7.0 | 70 | 7.1636 |
| 8.6234 | 8.0 | 80 | 7.1596 |
| 8.3256 | 9.0 | 90 | 7.1630 |
| 8.2742 | 10.0 | 100 | 7.1660 |
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 kampallipallavi1/flan-t5-base
Base model
google/flan-t5-base