IC_ver6H_coco_swin_gpt2_50B_1e

This model is a fine-tuned version of VK246/IC_ver6G_coco_swin_gpt2_50A_1e on the coco dataset. It achieves the following results on the evaluation set:

• Loss: 0.7969
• Cider: 7.3588
• Rouge1: 41.9295
• Rouge2: 16.3455
• Rougel: 37.9811
• Rougelsum: 37.9766
• Bleu-1: 42.8743
• Bleu-2: 24.7756
• Bleu-3: 15.6692
• Bleu-4: 10.4429
• Gen Len: 11.3063

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
0.6159	0.34	1000	0.8323	6.7172	41.0274	15.5809	37.2211	37.2045	42.2207	24.0365	15.0562	9.9118	11.3063
0.6802	0.68	2000	0.7969	7.3588	41.9295	16.3455	37.9811	37.9766	42.8743	24.7756	15.6692	10.4429	11.3063

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3