IC_ver3a_coco_swin_gpt2_

This model is a fine-tuned version of on the coco dataset. It achieves the following results on the evaluation set:

• Loss: 1.0156
• Rouge1: 33.8659
• Rouge2: 10.1039
• Rougel: 31.4861
• Rougelsum: 31.4905
• Bleu: 5.7396
• Gen Len: 11.2887

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: 96
• eval_batch_size: 96
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu	Gen Len
1.4761	0.34	100	1.1047	28.2757	6.0267	26.4732	26.5071	2.7859	11.2887
1.1238	0.68	200	1.0406	32.0448	8.6347	29.6117	29.6193	4.4174	11.2887

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3