Hugging Face's logo

nqtruong
/
LLaVA-Mistral-finetuned

PEFT
Safetensors
Generated from Trainer
Model card Files Community
1
LLaVA-Mistral-finetuned / README.md
nqtruong's picture
nqtruong
End of training
93d9436 verified
preview code
|
raw
history blame
1.52 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: liuhaotian/llava-v1.6-mistral-7b
model-index:
  - name: LLaVA-Mistral-finetuned
    results: []

LLaVA-Mistral-finetuned

This model is a fine-tuned version of liuhaotian/llava-v1.6-mistral-7b on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6291

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: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 25
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.7239 0.0 10 0.6832
0.7502 0.01 20 0.6291

Framework versions

  • PEFT 0.9.0
  • Transformers 4.38.1
  • Pytorch 2.1.2
  • Datasets 2.1.0
  • Tokenizers 0.15.2