IC_ver5a_coco_swin_gpt2_05pc_1e

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

• Loss: 1.2245
• Rouge1: 22.0956
• Rouge2: 2.7707
• Rougel: 20.6806
• Rougelsum: 20.6915
• Bleu: 1.2101
• Gen Len: 11.1124

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
2.1625	0.42	25	1.2744	22.7707	2.4514	20.6431	20.6829	0.0	11.1124
1.3438	0.85	50	1.2374	21.3271	2.4116	19.7122	19.7385	0.7474	11.1124

Framework versions

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