best-Date-model
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: 0.0416
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: 0.0004
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1885 | 0.7921 | 200 | 0.0803 |
| 0.1378 | 1.5822 | 400 | 0.0663 |
| 0.0717 | 2.3723 | 600 | 0.0491 |
| 0.0664 | 3.1624 | 800 | 0.0425 |
| 0.03 | 3.9545 | 1000 | 0.0424 |
| 0.0456 | 4.7446 | 1200 | 0.0425 |
| 0.0295 | 5.5347 | 1400 | 0.0416 |
Framework versions
- PEFT 0.17.1
- Transformers 4.56.2
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Downloads last month
- 33
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for aminLo/best-date-model
Base model
google/flan-t5-base