|
--- |
|
base_model: |
|
- elinas/Llama-3-15B-Instruct-zeroed |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- finetune |
|
datasets: |
|
- Chat-Error/Pure-dove-sharegpt |
|
license: llama3 |
|
--- |
|
# Llama-3-15B-Instruct-zeroed-ft-v2 |
|
|
|
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 a "zeroed" passthrough merge of [Llama-3-15B-Instruct-zeroed](https://huggingface.co/elinas/Llama-3-15B-Instruct-zeroed) |
|
|
|
This was primarily an experiment to see how a passthrough merge will respond to further finetuning of all LoRA modules. |
|
|
|
The model was finetuned on **8192 context length** and it can possibly be extended using RoPE up to 32k. |
|
|
|
**v3 of the model will contain significantly more data, primarily human focused, aimed to excel at writing as well as maintaining logic, coherency, and continuity.** |
|
|
|
**[GGUF Quants provided by @gelukuMLG](https://huggingface.co/gelukuMLG/Llama-3-15B-Instruct-ft-v2-GGUF)** |
|
|
|
## Datasets |
|
|
|
* [Chat-Error/Pure-dove-sharegpt](https://huggingface.co/datasets/Chat-Error/Pure-dove-sharegpt) |
|
|
|
A small, high quality, curated dataset was used as a PoC / validation on stabilizing the model after the original passthrough merge. |
|
|
|
## Finetuning details |
|
This is a QLoRA model and all of the LoRA modules were targeted this time to ensure sufficient training before moving on to larger datasets. |
|
the first version of this model only targeted **o_proj** and **up_proj** |
|
```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 |
|
``` |
|
|
|
The model is coherent even with training the "zeroed" layers plus the additional layers, as this was the recommendation from [Charles Goddard](https://huggingface.co/chargoddard) (mergekit developer) - thank you for sharing the method of merging as well as Toasty |
|
Pigeon for bringing it to my attention! |
|
|
|
```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 4 hours total. |
|
|
|
**Unsloth** was used for speed and memory savings. |
|
|
|
Sample packing and padding was disabled to reduce VRAM consumption significantly at the cost of speed. |
|
|
|
W&B Run Summary |
|
``` |
|
wandb: eval/loss 0.90895 |
|
wandb: eval/runtime 463.4688 |
|
wandb: eval/samples_per_second 0.833 |
|
wandb: eval/steps_per_second 0.278 |
|
wandb: total_flos 8270790524928.0 |
|
wandb: train/epoch 1.0 |
|
wandb: train/global_step 1157 |
|
wandb: train/grad_norm 7.3847 |
|
wandb: train/learning_rate 0.0 |
|
wandb: train/loss 0.8702 |
|
wandb: train_loss 0.87814 |
|
wandb: train_runtime 16425.2713 |
|
wandb: train_samples_per_second 0.211 |
|
wandb: train_steps_per_second 0.07 |
|
``` |
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
|
## Model Evaluation |
|
|
|
TBD |
|
|
|
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) |
