emendes3's picture
End of training
d782af6 verified
metadata
library_name: peft
tags:
  - generated_from_trainer
base_model: liuhaotian/llava-v1.5-13b
model-index:
  - name: llava_13b_neighborhood
    results: []

llava_13b_neighborhood

This model is a fine-tuned version of liuhaotian/llava-v1.5-13b on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4711

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: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • total_train_batch_size: 32
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 10.0

Training results

Training Loss Epoch Step Validation Loss
0.896 1.0 9 1.0162
0.2277 2.0 18 1.1135
0.0717 3.0 27 1.1909
0.0271 4.0 36 1.4078
0.0083 5.0 45 1.4837
0.0087 6.0 54 1.5063
0.0087 7.0 63 1.4929
0.0011 8.0 72 1.5387
0.0008 9.0 81 1.5352
0.0032 10.0 90 1.4711

Framework versions

  • PEFT 0.10.0
  • Transformers 4.37.2
  • Pytorch 2.1.2+cu121
  • Tokenizers 0.15.1