metadata
base_model: orpo-explorers/kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-1epoch
tags:
- alignment-handbook
- trl
- orpo
- generated_from_trainer
- trl
- orpo
- generated_from_trainer
datasets:
- argilla/Capybara-Preferences
model-index:
- name: kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-1epoch-capybara-2epoch
results: []
kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-1epoch-capybara-2epoch
This model is a fine-tuned version of orpo-explorers/kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-1epoch on the argilla/Capybara-Preferences dataset.
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2
Training results
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2.post303
- Datasets 2.18.0
- Tokenizers 0.15.2