IC_ver1_coco_swin_gpt2_5pc_2e

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

• Loss: 0.9700
• Rouge1: 36.317
• Rouge2: 12.0175
• Rougel: 33.7883
• Rougelsum: 33.7342
• Bleu: 6.5392
• 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: 100
• eval_batch_size: 100
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu	Gen Len
1.29	0.71	200	1.0273	33.6256	10.3076	31.0868	31.0562	5.5088	11.2887
1.0193	1.41	400	0.9700	36.317	12.0175	33.7883	33.7342	6.5392	11.2887

Framework versions

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