best-grade-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: 0.1721
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 8
- 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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4312 | 0.8649 | 200 | 0.2963 |
| 0.2898 | 1.7265 | 400 | 0.2353 |
| 0.2282 | 2.5881 | 600 | 0.2004 |
| 0.1997 | 3.4497 | 800 | 0.1907 |
| 0.175 | 4.3114 | 1000 | 0.1886 |
| 0.149 | 5.1730 | 1200 | 0.1806 |
| 0.1538 | 6.0346 | 1400 | 0.1743 |
| 0.148 | 6.8995 | 1600 | 0.1741 |
| 0.1319 | 7.7611 | 1800 | 0.1721 |
Framework versions
- PEFT 0.17.1
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for aminLo/best-grade-model
Base model
google/flan-t5-base