|
--- |
|
license: llama2 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: codellama/CodeLlama-13b-Instruct-hf |
|
model-index: |
|
- name: lora-out |
|
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. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
# lora-out |
|
|
|
This model is a fine-tuned version of [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4198 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 16 |
|
- total_eval_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.6555 | 0.01 | 1 | 0.6550 | |
|
| 0.6532 | 0.05 | 7 | 0.6035 | |
|
| 0.5278 | 0.1 | 14 | 0.4977 | |
|
| 0.5466 | 0.15 | 21 | 0.4736 | |
|
| 0.4832 | 0.2 | 28 | 0.4637 | |
|
| 0.5069 | 0.25 | 35 | 0.4492 | |
|
| 0.4864 | 0.3 | 42 | 0.4436 | |
|
| 0.4625 | 0.35 | 49 | 0.4379 | |
|
| 0.4792 | 0.4 | 56 | 0.4336 | |
|
| 0.4608 | 0.45 | 63 | 0.4302 | |
|
| 0.4738 | 0.5 | 70 | 0.4266 | |
|
| 0.4839 | 0.55 | 77 | 0.4245 | |
|
| 0.4791 | 0.6 | 84 | 0.4227 | |
|
| 0.4701 | 0.65 | 91 | 0.4233 | |
|
| 0.4612 | 0.7 | 98 | 0.4225 | |
|
| 0.4419 | 0.75 | 105 | 0.4212 | |
|
| 0.4705 | 0.8 | 112 | 0.4199 | |
|
| 0.4422 | 0.85 | 119 | 0.4198 | |
|
| 0.4889 | 0.9 | 126 | 0.4198 | |
|
| 0.4914 | 0.95 | 133 | 0.4195 | |
|
| 0.4799 | 1.0 | 140 | 0.4198 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
## Training procedure |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.6.0 |
|
|
