metadata
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
library_name: peft
license: other
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: mixtral2
results: []
mixtral2
This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the data_data 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-05
- train_batch_size: 10
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 80
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 80.0
Training results
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.1
- Datasets 2.21.0
- Tokenizers 0.19.1