|
--- |
|
license: llama2 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: meta-llama/Llama-2-7b-chat-hf |
|
model-index: |
|
- name: Llama-2-code-python |
|
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-2-code-python |
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0589 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 6 |
|
- eval_batch_size: 6 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 24 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.612 | 0.3183 | 30 | 1.6686 | |
|
| 1.4094 | 0.6366 | 60 | 1.4388 | |
|
| 1.2172 | 0.9549 | 90 | 1.2583 | |
|
| 1.0647 | 1.2732 | 120 | 1.1357 | |
|
| 1.0144 | 1.5915 | 150 | 1.0771 | |
|
| 1.0622 | 1.9098 | 180 | 1.0643 | |
|
| 1.045 | 2.2281 | 210 | 1.0599 | |
|
| 1.0739 | 2.5464 | 240 | 1.0588 | |
|
| 1.0306 | 2.8647 | 270 | 1.0589 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
