metadata
library_name: peft
license: other
base_model: mistralai/Mistral-7B-Instruct-v0.3
tags:
- llama-factory
- lora
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: factory_mistral_results
results: []
factory_mistral_results
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the train dataset. It achieves the following results on the evaluation set:
- Loss: 0.2260
- Accuracy: 0.9587
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 9.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3179 | 1.0 | 32 | 0.3321 | 0.9217 |
| 0.206 | 2.0 | 64 | 0.2425 | 0.9408 |
| 0.1447 | 3.0 | 96 | 0.2109 | 0.9489 |
| 0.1067 | 4.0 | 128 | 0.2062 | 0.9527 |
| 0.0612 | 5.0 | 160 | 0.2128 | 0.9539 |
| 0.0491 | 6.0 | 192 | 0.2169 | 0.9549 |
| 0.0378 | 7.0 | 224 | 0.2166 | 0.9584 |
| 0.0294 | 8.0 | 256 | 0.2224 | 0.9588 |
| 0.0215 | 9.0 | 288 | 0.2260 | 0.9587 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.7.0
- Datasets 3.6.0
- Tokenizers 0.21.1