|
|
--- |
|
|
base_model: mistralai/Mistral-7B-Instruct-v0.1 |
|
|
library_name: peft |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- trl |
|
|
- sft |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: Mistral-QLoRA |
|
|
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/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/dhanishetty-personaluse/huggingface/runs/pjjtau6u) |
|
|
# Mistral-QLoRA |
|
|
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.7712 |
|
|
|
|
|
## 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: 5e-05 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 16 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: inverse_sqrt |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 1.0043 | 0.2022 | 100 | 1.0068 | |
|
|
| 0.8452 | 0.4044 | 200 | 0.8355 | |
|
|
| 0.7876 | 0.6067 | 300 | 0.8093 | |
|
|
| 0.8128 | 0.8089 | 400 | 0.7969 | |
|
|
| 0.747 | 1.0111 | 500 | 0.7895 | |
|
|
| 0.744 | 1.2133 | 600 | 0.7853 | |
|
|
| 0.7757 | 1.4156 | 700 | 0.7797 | |
|
|
| 0.7342 | 1.6178 | 800 | 0.7763 | |
|
|
| 0.7338 | 1.8200 | 900 | 0.7736 | |
|
|
| 0.707 | 2.0222 | 1000 | 0.7737 | |
|
|
| 0.7021 | 2.2245 | 1100 | 0.7756 | |
|
|
| 0.7102 | 2.4267 | 1200 | 0.7742 | |
|
|
| 0.697 | 2.6289 | 1300 | 0.7735 | |
|
|
| 0.7155 | 2.8311 | 1400 | 0.7712 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.11.1 |
|
|
- Transformers 4.42.4 |
|
|
- Pytorch 2.3.0+cu121 |
|
|
- Datasets 2.20.0 |
|
|
- Tokenizers 0.19.1 |
