|
--- |
|
library_name: peft |
|
license: other |
|
base_model: unsloth/Llama-3.2-3B-Instruct |
|
tags: |
|
- llama-factory |
|
- lora |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: llm3br256 |
|
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. --> |
|
|
|
# llm3br256 |
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the mini_akash_unifo_757 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0029 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 36 |
|
- eval_batch_size: 36 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 288 |
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 25.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-------:|:----:|:---------------:| |
|
| 0.0145 | 4.4444 | 5 | 0.0093 | |
|
| 0.0052 | 8.8889 | 10 | 0.0057 | |
|
| 0.0042 | 13.3333 | 15 | 0.0036 | |
|
| 0.0029 | 17.7778 | 20 | 0.0030 | |
|
| 0.0069 | 22.2222 | 25 | 0.0029 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.46.1 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
