This model is a fine-tuned version of VK246/IC_ver6d_coco_swin_gpt2_50Bpc_1e on the coco dataset.
It achieves the following results on the evaluation set:
Loss: 0.8113
Cider: 43.6787
Rouge1: 41.4057
Rouge2: 16.177
Rougel: 38.9636
Rougelsum: 38.8335
Bleu-1: 43.1153
Bleu-2: 24.9997
Bleu-3: 15.7558
Bleu-4: 10.4674
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
