|
|
--- |
|
|
base_model: mistralai/Mistral-7B-v0.1 |
|
|
tags: |
|
|
- alignment-handbook |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- maxidl/instruct-en-de |
|
|
model-index: |
|
|
- name: Mistral-7B-v0.1-Instruct-sft-en-de |
|
|
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. --> |
|
|
|
|
|
# Mistral-7B-v0.1-Instruct-sft-en-de |
|
|
|
|
|
A full finetune of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) using a mix of English and German instruction data. |
|
|
|
|
|
|
|
|
## Dataset |
|
|
|
|
|
|source|#examples| |
|
|
|---|---| |
|
|
teknium/OpenHermes-2.5 |1001551 |
|
|
maxidl/OpenOrca-gpt4-de |119559 |
|
|
maxidl/MathInstruct-de |56793 |
|
|
maxidl/Capybara-de |15991 |
|
|
maxidl/math-prm-800k-de |12298 |
|
|
maxidl/wikihow-de |10103 |
|
|
maxidl/no_robots-de |9500 |
|
|
maxidl/lima-de |1030 |
|
|
|
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 1e-05 |
|
|
- train_batch_size: 4 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 32 |
|
|
- total_train_batch_size: 128 |
|
|
- total_eval_batch_size: 256 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 50 |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.39.3 |
|
|
- Pytorch 2.1.2 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
