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: 0.5110
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 |
|---|---|---|---|
| 32.2849 | 1.0 | 18 | 11.8491 |
| 6.3129 | 2.0 | 36 | 4.4540 |
| 4.3164 | 3.0 | 54 | 3.7053 |
| 3.1888 | 4.0 | 72 | 1.7085 |
| 1.8738 | 5.0 | 90 | 0.9427 |
| 1.4921 | 6.0 | 108 | 0.6772 |
| 1.1213 | 7.0 | 126 | 0.6060 |
| 0.962 | 8.0 | 144 | 0.5443 |
| 0.8762 | 9.0 | 162 | 0.5207 |
| 0.8776 | 10.0 | 180 | 0.5110 |
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 saitejabingi/flan-t5-base
Base model
google/flan-t5-base