metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
model-index:
- name: mixtral-nek-finetune_0.3_all_data_4_lines
results: []
mixtral-nek-finetune_0.3_all_data_4_lines
This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8051
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- num_epochs: 1.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8456 | 0.09 | 1000 | 0.8573 |
| 0.838 | 0.18 | 2000 | 0.8426 |
| 0.8373 | 0.27 | 3000 | 0.8341 |
| 0.8168 | 0.36 | 4000 | 0.8274 |
| 0.8163 | 0.44 | 5000 | 0.8222 |
| 0.8079 | 0.53 | 6000 | 0.8181 |
| 0.8089 | 0.62 | 7000 | 0.8140 |
| 0.8119 | 0.71 | 8000 | 0.8108 |
| 0.8007 | 0.8 | 9000 | 0.8082 |
| 0.809 | 0.89 | 10000 | 0.8062 |
| 0.8084 | 0.98 | 11000 | 0.8051 |
Framework versions
- PEFT 0.8.2.dev0
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1