| --- |
| base_model: hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode |
| tags: |
| - trl |
| - sft |
| - generated_from_trainer |
| model-index: |
| - name: Meta-Llama-3-8B-Instruct-function-calling-json-mode-VisitorRequests |
| results: [] |
| library_name: peft |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # Meta-Llama-3-8B-Instruct-function-calling-json-mode-VisitorRequests |
|
|
| This model is a fine-tuned version of [hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode](https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.7458 |
|
|
| ## 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: 1 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - gradient_accumulation_steps: 8 |
| - total_train_batch_size: 8 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: constant |
| - num_epochs: 2 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:------:|:----:|:---------------:| |
| | 2.0583 | 0.0630 | 1 | 3.3171 | |
| | 3.2898 | 0.1260 | 2 | 1.8112 | |
| | 1.7495 | 0.1890 | 3 | 1.3350 | |
| | 1.3176 | 0.2520 | 4 | 5.6302 | |
| | 5.9627 | 0.3150 | 5 | 2.1688 | |
| | 2.1926 | 0.3780 | 6 | 1.4297 | |
| | 1.3724 | 0.4409 | 7 | 1.2279 | |
| | 1.2125 | 0.5039 | 8 | 0.9445 | |
| | 0.9749 | 0.5669 | 9 | 1.1901 | |
| | 1.2164 | 0.6299 | 10 | 0.9843 | |
| | 0.9808 | 0.6929 | 11 | 0.9213 | |
| | 0.8698 | 0.7559 | 12 | 0.8721 | |
| | 0.8668 | 0.8189 | 13 | 0.9308 | |
| | 0.8635 | 0.8819 | 14 | 0.8319 | |
| | 0.7789 | 0.9449 | 15 | 0.8164 | |
| | 0.7402 | 1.0079 | 16 | 0.8220 | |
| | 0.7312 | 1.0709 | 17 | 0.8305 | |
| | 0.7561 | 1.1339 | 18 | 0.9768 | |
| | 0.9879 | 1.1969 | 19 | 0.8437 | |
| | 0.7647 | 1.2598 | 20 | 0.8364 | |
| | 0.7093 | 1.3228 | 21 | 0.8028 | |
| | 0.7358 | 1.3858 | 22 | 0.8184 | |
| | 0.7301 | 1.4488 | 23 | 0.8050 | |
| | 0.7607 | 1.5118 | 24 | 0.7652 | |
| | 0.6892 | 1.5748 | 25 | 0.7317 | |
| | 0.7158 | 1.6378 | 26 | 0.7236 | |
| | 0.6701 | 1.7008 | 27 | 0.7130 | |
| | 0.6905 | 1.7638 | 28 | 0.7529 | |
| | 0.6791 | 1.8268 | 29 | 0.7813 | |
| | 0.7093 | 1.8898 | 30 | 0.7458 | |
| |
| |
| ### Framework versions |
| |
| - PEFT 0.5.0 |
| - Transformers 4.44.0 |
| - Pytorch 2.1.0+cu118 |
| - Datasets 2.16.0 |
| - Tokenizers 0.19.1 |
| |
