image-captioning-output

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

• Loss: 0.3319
• Rouge1: 21.9307
• Rouge2: 4.1909
• Rougel: 20.068
• Rougelsum: 19.9653
• Gen Len: 12.0625

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	20	0.3359	18.236	0.5556	18.2694	18.255	7.0
No log	2.0	40	0.3315	19.2924	3.6258	18.3375	18.3568	14.1875
No log	3.0	60	0.3319	21.9307	4.1909	20.068	19.9653	12.0625

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0