|
--- |
|
license: llama3.1 |
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: Meta-Llama-3.1-8B-Instruct-function-calling-json-mode-VisitorRequests_Lora |
|
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-3.1-8B-Instruct-function-calling-json-mode-VisitorRequests_Lora |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6890 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.2123 | 0.0630 | 1 | 2.0355 | |
|
| 2.031 | 0.1260 | 2 | 1.8189 | |
|
| 1.8617 | 0.1890 | 3 | 1.2382 | |
|
| 1.2165 | 0.2520 | 4 | 1.2213 | |
|
| 1.2384 | 0.3150 | 5 | 1.3884 | |
|
| 1.2876 | 0.3780 | 6 | 1.3734 | |
|
| 1.3752 | 0.4409 | 7 | 1.0046 | |
|
| 0.9925 | 0.5039 | 8 | 1.1719 | |
|
| 1.1438 | 0.5669 | 9 | 0.9010 | |
|
| 0.9124 | 0.6299 | 10 | 0.8452 | |
|
| 0.8283 | 0.6929 | 11 | 0.7755 | |
|
| 0.762 | 0.7559 | 12 | 0.7758 | |
|
| 0.7601 | 0.8189 | 13 | 0.8326 | |
|
| 0.7841 | 0.8819 | 14 | 0.7731 | |
|
| 0.697 | 0.9449 | 15 | 0.7534 | |
|
| 0.7392 | 1.0079 | 16 | 0.7244 | |
|
| 0.6977 | 1.0709 | 17 | 0.7054 | |
|
| 0.6216 | 1.1339 | 18 | 0.6978 | |
|
| 0.9607 | 1.1969 | 19 | 0.7370 | |
|
| 0.693 | 1.2598 | 20 | 0.8337 | |
|
| 0.8311 | 1.3228 | 21 | 0.9197 | |
|
| 0.8475 | 1.3858 | 22 | 0.8201 | |
|
| 0.7663 | 1.4488 | 23 | 0.7467 | |
|
| 0.6859 | 1.5118 | 24 | 0.7316 | |
|
| 0.6419 | 1.5748 | 25 | 0.7193 | |
|
| 0.6363 | 1.6378 | 26 | 0.7011 | |
|
| 0.6569 | 1.7008 | 27 | 0.7019 | |
|
| 0.6467 | 1.7638 | 28 | 0.6921 | |
|
| 0.6779 | 1.8268 | 29 | 0.6918 | |
|
| 0.6638 | 1.8898 | 30 | 0.6890 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.5.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.19.1 |
|
|
