|
--- |
|
library_name: peft |
|
tags: |
|
- llama-factory |
|
- lora |
|
- generated_from_trainer |
|
base_model: meta-llama/Meta-Llama-3-8B |
|
model-index: |
|
- name: Llama3_AAID_mixed_train_final |
|
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_AAID_mixed_train_final |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the AAID_mixed dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8113 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.0078 | 0.0109 | 10 | 0.9146 | |
|
| 0.5077 | 0.0219 | 20 | 0.8363 | |
|
| 0.4613 | 0.0328 | 30 | 0.8338 | |
|
| 0.4794 | 0.0438 | 40 | 0.8337 | |
|
| 0.4624 | 0.0547 | 50 | 0.8181 | |
|
| 0.4366 | 0.0656 | 60 | 0.8187 | |
|
| 0.4323 | 0.0766 | 70 | 0.8172 | |
|
| 0.433 | 0.0875 | 80 | 0.8255 | |
|
| 0.4401 | 0.0984 | 90 | 0.8300 | |
|
| 0.4019 | 0.1094 | 100 | 0.8479 | |
|
| 0.4112 | 0.1203 | 110 | 0.8113 | |
|
| 0.4009 | 0.1313 | 120 | 0.8454 | |
|
| 0.4023 | 0.1422 | 130 | 0.8435 | |
|
| 0.3924 | 0.1531 | 140 | 0.8308 | |
|
| 0.4079 | 0.1641 | 150 | 0.8372 | |
|
| 0.3898 | 0.1750 | 160 | 0.8542 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |