metadata
library_name: peft
license: mit
base_model: VietAI/vit5-base
tags:
- base_model:adapter:VietAI/vit5-base
- lora
- transformers
model-index:
- name: vit5-base-skill-extraction-lora
results: []
vit5-base-skill-extraction-lora
This model is a fine-tuned version of VietAI/vit5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1861
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: 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1176 | 0.5051 | 300 | 1.8360 |
| 1.733 | 1.0101 | 600 | 1.5659 |
| 1.5552 | 1.5152 | 900 | 1.4389 |
| 1.4686 | 2.0202 | 1200 | 1.3778 |
| 1.3579 | 2.5253 | 1500 | 1.3089 |
| 1.2818 | 3.0303 | 1800 | 1.2438 |
| 1.2286 | 3.5354 | 2100 | 1.2269 |
| 1.1603 | 4.0404 | 2400 | 1.1947 |
| 1.1482 | 4.5455 | 2700 | 1.1861 |
Framework versions
- PEFT 0.17.1
- Transformers 4.57.0
- Pytorch 2.8.0+cu126
- Datasets 4.1.1
- Tokenizers 0.22.1