metadata
license: other
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
model-index:
- name: sft_trained_woaqa_mixtral
results: []
sft_trained_woaqa_mixtral
This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the sft_wo_aqa_mistral dataset. It achieves the following results on the evaluation set:
- Loss: 0.8062
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: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 4.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8668 | 0.63 | 100 | 0.8571 |
| 0.7837 | 1.26 | 200 | 0.8230 |
| 0.7824 | 1.9 | 300 | 0.8058 |
| 0.7401 | 2.53 | 400 | 0.8059 |
| 0.7101 | 3.16 | 500 | 0.8072 |
| 0.7037 | 3.79 | 600 | 0.8062 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2