IC_ver6M_coco_swin_gpt2_50A_1e

This model is a fine-tuned version of VK246/IC_ver6L_coco_swin_gpt2_50B_1e on the coco dataset. It achieves the following results on the evaluation set:

• Loss: 0.8502
• Cider: 74.2614
• Rouge1: 41.2346
• Rouge2: 15.6726
• Rougel: 37.3373
• Rougelsum: 37.3448
• Bleu-1: 42.1725
• Bleu-2: 24.0988
• Bleu-3: 15.0597
• Bleu-4: 9.8745
• Gen Len: 11.2806

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	Cider	Rouge1	Rouge2	Rougel	Rougelsum	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Gen Len
0.4052	0.34	1000	0.9934	68.6639	39.9165	14.5681	36.2437	36.2466	41.4603	23.2118	14.2892	9.3187	11.2806
0.5281	0.68	2000	0.8502	74.2614	41.2346	15.6726	37.3373	37.3448	42.1725	24.0988	15.0597	9.8745	11.2806

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3