|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- unsloth |
|
- generated_from_trainer |
|
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit |
|
model-index: |
|
- name: llama3-chat_QA-test |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# llama3-chat_QA-test |
|
|
|
This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0283 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 3407 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 5 |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.0046 | 0.2928 | 100 | 1.8727 | |
|
| 1.7686 | 0.5857 | 200 | 1.8637 | |
|
| 1.6753 | 0.8785 | 300 | 1.8871 | |
|
| 1.5211 | 1.1713 | 400 | 1.9180 | |
|
| 1.4003 | 1.4641 | 500 | 1.9352 | |
|
| 1.3533 | 1.7570 | 600 | 1.9609 | |
|
| 1.2794 | 2.0498 | 700 | 2.0143 | |
|
| 1.1736 | 2.3426 | 800 | 2.0222 | |
|
| 1.1609 | 2.6354 | 900 | 2.0301 | |
|
| 1.1577 | 2.9283 | 1000 | 2.0283 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
