BITAMIN_PET_FINAL

This model is a fine-tuned version of ddobokki/vision-encoder-decoder-vit-gpt2-coco-ko on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0670
• Rouge1: 5.1373
• Rouge2: 3.2797
• Rougel: 5.1561
• Rougelsum: 5.1999
• Gen Len: 100.0

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Gen Len	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.1753	1.0	5963	100.0	0.1586	0.0	0.0	0.0	0.0
0.1066	2.0	11926	0.1091	0.2155	0.1961	0.2155	0.2305	100.0
0.0659	3.0	17889	0.0834	1.8169	1.2573	1.8423	1.8571	100.0
0.0417	4.0	23852	0.0712	2.9034	1.9182	2.9223	2.9168	100.0
0.0319	5.0	29815	0.0670	5.1373	3.2797	5.1561	5.1999	100.0

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1