flan-t5-base-skill-extraction-lora-ver2-10epoch
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: 1.1738
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_8BIT 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: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8033 | 0.5051 | 300 | 1.4502 |
| 1.5222 | 1.0101 | 600 | 1.3232 |
| 1.4343 | 1.5152 | 900 | 1.2480 |
| 1.4092 | 2.0202 | 1200 | 1.2256 |
| 1.3916 | 2.5253 | 1500 | 1.2051 |
| 1.3404 | 3.0303 | 1800 | 1.1885 |
| 1.3295 | 3.5354 | 2100 | 1.1738 |
| 1.3158 | 4.0404 | 2400 | 1.1748 |
| 1.3312 | 4.5455 | 2700 | 1.1738 |
Framework versions
- PEFT 0.10.0
- Transformers 4.49.0
- Pytorch 2.4.1+cu118
- Datasets 4.1.1
- Tokenizers 0.21.0
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for nguyen10001/flan-t5-base-skill-extraction-lora-ver2-10epoch
Base model
google/flan-t5-base