metadata
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: TWON-Agent-OSN-debug
results: []
TWON-Agent-OSN-debug
This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 2.8582
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use 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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.4066 | 1.0 | 5 | 3.2770 |
| 3.2678 | 2.0 | 10 | 3.1435 |
| 3.1418 | 3.0 | 15 | 3.0416 |
| 3.0482 | 4.0 | 20 | 2.9683 |
| 2.9771 | 5.0 | 25 | 2.9152 |
| 2.9285 | 6.0 | 30 | 2.8812 |
| 2.8971 | 7.0 | 35 | 2.8638 |
| 2.884 | 8.0 | 40 | 2.8582 |
Framework versions
- PEFT 0.12.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0