|
--- |
|
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 akoul_whitehorseliquidity_25c dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0008 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 32 |
|
- 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.0078 | 0.0808 | 25 | 0.0079 | |
|
| 0.0119 | 0.1616 | 50 | 0.0051 | |
|
| 0.0036 | 0.2424 | 75 | 0.0032 | |
|
| 0.004 | 0.3232 | 100 | 0.0025 | |
|
| 0.0019 | 0.4040 | 125 | 0.0020 | |
|
| 0.0021 | 0.4848 | 150 | 0.0018 | |
|
| 0.0016 | 0.5657 | 175 | 0.0016 | |
|
| 0.0013 | 0.6465 | 200 | 0.0015 | |
|
| 0.0017 | 0.7273 | 225 | 0.0015 | |
|
| 0.0015 | 0.8081 | 250 | 0.0014 | |
|
| 0.0023 | 0.8889 | 275 | 0.0013 | |
|
| 0.0012 | 0.9697 | 300 | 0.0013 | |
|
| 0.0011 | 1.0505 | 325 | 0.0013 | |
|
| 0.0011 | 1.1313 | 350 | 0.0013 | |
|
| 0.0009 | 1.2121 | 375 | 0.0012 | |
|
| 0.0015 | 1.2929 | 400 | 0.0011 | |
|
| 0.0025 | 1.3737 | 425 | 0.0011 | |
|
| 0.0016 | 1.4545 | 450 | 0.0011 | |
|
| 0.001 | 1.5354 | 475 | 0.0011 | |
|
| 0.0007 | 1.6162 | 500 | 0.0011 | |
|
| 0.0008 | 1.6970 | 525 | 0.0011 | |
|
| 0.001 | 1.7778 | 550 | 0.0010 | |
|
| 0.0007 | 1.8586 | 575 | 0.0010 | |
|
| 0.0013 | 1.9394 | 600 | 0.0009 | |
|
| 0.0007 | 2.0202 | 625 | 0.0010 | |
|
| 0.0006 | 2.1010 | 650 | 0.0009 | |
|
| 0.0007 | 2.1818 | 675 | 0.0009 | |
|
| 0.001 | 2.2626 | 700 | 0.0009 | |
|
| 0.0015 | 2.3434 | 725 | 0.0009 | |
|
| 0.0012 | 2.4242 | 750 | 0.0010 | |
|
| 0.0012 | 2.5051 | 775 | 0.0009 | |
|
| 0.0015 | 2.5859 | 800 | 0.0010 | |
|
| 0.0011 | 2.6667 | 825 | 0.0009 | |
|
| 0.0007 | 2.7475 | 850 | 0.0009 | |
|
| 0.0009 | 2.8283 | 875 | 0.0009 | |
|
| 0.0009 | 2.9091 | 900 | 0.0008 | |
|
| 0.001 | 2.9899 | 925 | 0.0009 | |
|
| 0.0006 | 3.0707 | 950 | 0.0009 | |
|
| 0.0006 | 3.1515 | 975 | 0.0009 | |
|
| 0.0007 | 3.2323 | 1000 | 0.0009 | |
|
| 0.0004 | 3.3131 | 1025 | 0.0009 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.46.1 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
