| --- |
| base_model: |
| - elinas/Llama-3-13B-Instruct |
| library_name: transformers |
| tags: |
| - mergekit |
| - merge |
| datasets: |
| - Chat-Error/Pure-dove-sharegpt |
| license: llama3 |
| --- |
| # Llama-3-13B-Instruct-ft |
|
|
| This is a QLoRA **finetune** of a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
| The model is based on my passthrough merge of [Llama-3-13B-Instruct](https://huggingface.co/elinas/Llama-3-13B-Instruct) |
|
|
| This was primarily an experiment to see how a passthrough merge will respond to further finetuning, though this was done on a small dataset. |
|
|
| The goal was to make a "mid" sized model like Meta has released in the past and the merge method was inspired by [mlabonne's Llama-3-120B](https://huggingface.co/mlabonne/Meta-Llama-3-120B-Instruct). |
|
|
| The model was finetuned on **8192 context length** and is likely reliable using RoPE up to 32k. |
|
|
| It still cannot do math reliably; neither can Llama-3-8B, and in my tests only Llama-3-70B passes basic arithmetic, but it is a better storywriter/RP than Llama-3-8B from some side by side testing I conducted. |
|
|
| Further finetuning this model or finetuning the [base model](https://huggingface.co/elinas/Llama-3-13B-Instruct) on more samples is encouraged. |
|
|
| ## Datasets |
|
|
| * [Chat-Error/Pure-dove-sharegpt](https://huggingface.co/datasets/Chat-Error/Pure-dove-sharegpt) |
|
|
| A small dataset was used to see how it affects performance. Originally I planned to do a larger dataset (196k samples), but wanted to start with a smaller one first to see how much the model improved with some additional finetuning. |
|
|
| Next steps would be finetuning on a larger dataset if through further testing, performance improvements are noticed. |
|
|
| ## Finetuning details |
| This is a QLoRA model and all modules were targeted. |
| ```yaml |
| lora_target_modules: |
| - gate_proj |
| - down_proj |
| - up_proj |
| - q_proj |
| - v_proj |
| - k_proj |
| - o_proj |
| lora_modules_to_save: |
| - embed_tokens |
| - lm_head |
| ``` |
|
|
| ```yaml |
| The following hyperparameters were used during training: |
| - learning_rate: 1e-05 |
| - train_batch_size: 1 |
| - eval_batch_size: 1 |
| - seed: 42 |
| - distributed_type: multi-GPU |
| - num_devices: 3 |
| - total_train_batch_size: 3 |
| - total_eval_batch_size: 3 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 25 |
| - num_epochs: 1 |
| ``` |
|
|
| Optimizer `paged_adamw_8bit` and Deepspeed ZeRO 3 was used at a LR of `1e-5` using the cosine scheduler for 1 epoch on 3x3090s taking 4h 12m 13s total. |
|
|
| Sample packing and padding was disabled to reduce VRAM consumption significantly at the cost of speed. |
|
|
| W&B Run Summary |
| ``` |
| wandb: Run summary: |
| wandb: eval/loss 1.00774 |
| wandb: eval/runtime 535.3847 |
| wandb: eval/samples_per_second 0.721 |
| wandb: eval/steps_per_second 0.241 |
| wandb: total_flos 4167452590080.0 |
| wandb: train/epoch 1.0 |
| wandb: train/global_step 1157 |
| wandb: train/grad_norm 4.50846 |
| wandb: train/learning_rate 0.0 |
| wandb: train/loss 1.4115 |
| wandb: train_loss 1.00352 |
| wandb: train_runtime 14921.1227 |
| wandb: train_samples_per_second 0.233 |
| wandb: train_steps_per_second 0.078 |
| ``` |
|
|
| ### Framework versions |
|
|
| - PEFT 0.10.0 |
| - Transformers 4.40.0.dev0 |
| - Pytorch 2.3.0+cu121 |
| - Datasets 2.15.0 |
| - Tokenizers 0.15.0 |
|
|
| ## Model Evaluation |
|
|
| TBD - submitted |
|
|
| If you have any questions or comments on the model, feel free to open a discussion in the community tab. |
|
|
| [<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) |
