IC_ver2_coco_swin_gpt2_5pc_1e

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

• Loss: 0.9972
• Rouge1: 34.8608
• Rouge2: 10.9857
• Rougel: 32.1905
• Rougelsum: 32.1794
• Bleu: 6.1162
• 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: 64
• eval_batch_size: 64
• 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
1.4995	0.23	100	1.1227	28.4179	5.9026	26.5601	26.5682	3.0237	11.2887
1.136	0.45	200	1.0506	31.4866	8.9504	29.1403	29.0996	4.2965	11.2887
1.0899	0.68	300	1.0203	33.9899	10.3576	31.6646	31.6435	5.5456	11.2887
1.057	0.9	400	0.9972	34.8608	10.9857	32.1905	32.1794	6.1162	11.2887

Framework versions

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