llava_13b_country

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: 1.6820

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
0.8996	1.0	9	1.0150
0.2338	2.0	18	1.1114
0.0743	3.0	27	1.1836
0.0278	4.0	36	1.4034
0.0122	5.0	45	1.4664
0.0129	6.0	54	1.4691
0.0062	7.0	63	1.4761
0.0026	8.0	72	1.4731
0.0018	9.0	81	1.6151
0.0012	10.0	90	1.6820

Framework versions

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