|
--- |
|
base_model: meta-llama/Llama-3.2-1B |
|
library_name: peft |
|
license: llama3.2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Llama-3.2-1B_v2 |
|
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. --> |
|
|
|
# Llama-3.2-1B_v2 |
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2671 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 30 |
|
- training_steps: 1000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.452 | 0.1 | 100 | 0.3832 | |
|
| 0.3539 | 0.2 | 200 | 0.3223 | |
|
| 0.2994 | 0.3 | 300 | 0.3045 | |
|
| 0.2855 | 0.4 | 400 | 0.2919 | |
|
| 0.2334 | 0.5 | 500 | 0.2832 | |
|
| 0.2435 | 0.6 | 600 | 0.2761 | |
|
| 0.3055 | 0.7 | 700 | 0.2716 | |
|
| 0.2668 | 0.8 | 800 | 0.2687 | |
|
| 0.2443 | 0.9 | 900 | 0.2674 | |
|
| 0.2245 | 1.0 | 1000 | 0.2671 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.0 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
