metadata
base_model: mistral-community/Mixtral-8x22B-v0.1
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- maxidl/instruct-en-de
- teknium/OpenHermes-2.5
model-index:
- name: Mixtral-8x22B-v0.1-Instruct-sft-en-de
results: []
license: apache-2.0
language:
- en
- de
Mixtral-8x22B-v0.1-Instruct-sft-en-de
A full SFT of mistral-community/Mixtral-8x22B-v0.1 using a mix of English and German instruction data.
There is also an ORPO-trained version: maxidl/Mixtral-8x22B-v0.1-capybara-orpo-en-de
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: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 64
- total_train_batch_size: 64
- total_eval_batch_size: 512
- 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