--- license: apache-2.0 tags: - generated_from_trainer base_model: nlpconnect/vit-gpt2-image-captioning metrics: - rouge model-index: - name: Vit-GPT2-COCO2017Flickr-40k-05 results: [] --- # Vit-GPT2-COCO2017Flickr-40k-05 This model is a fine-tuned version of [nlpconnect/vit-gpt2-image-captioning](https://huggingface.co/nlpconnect/vit-gpt2-image-captioning) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.5528 - Rouge1: 44.1624 - Rouge2: 19.6736 - Rougel: 40.3898 - Rougelsum: 40.4029 - Gen Len: 12.263 ## 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 | |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| | 0.1497 | 0.1 | 500 | 0.5462 | 40.1774 | 14.6199 | 36.3335 | 36.3518 | 12.5965 | | 0.1604 | 0.2 | 1000 | 0.5302 | 41.4714 | 16.0237 | 37.5992 | 37.5915 | 11.914 | | 0.1631 | 0.3 | 1500 | 0.5436 | 40.3816 | 14.6958 | 36.6109 | 36.6027 | 12.3295 | | 0.1634 | 0.4 | 2000 | 0.5266 | 40.9484 | 15.9068 | 37.5194 | 37.5088 | 12.033 | | 0.1576 | 0.5 | 2500 | 0.5544 | 40.373 | 15.012 | 36.5218 | 36.5141 | 12.3345 | | 0.1599 | 0.6 | 3000 | 0.5425 | 40.7552 | 15.2754 | 37.1059 | 37.1299 | 12.191 | | 0.291 | 0.7 | 3500 | 0.4545 | 41.5934 | 16.251 | 37.7291 | 37.7113 | 12.0295 | | 0.2825 | 0.8 | 4000 | 0.4558 | 42.6728 | 17.1703 | 38.8692 | 38.8841 | 12.246 | | 0.2737 | 0.9 | 4500 | 0.4565 | 43.0036 | 16.8421 | 39.1761 | 39.1693 | 11.7975 | | 0.2683 | 1.0 | 5000 | 0.4576 | 42.1341 | 16.7973 | 38.2881 | 38.3083 | 11.8655 | | 0.1687 | 1.1 | 5500 | 0.4996 | 41.7152 | 16.4042 | 37.7724 | 37.7629 | 12.384 | | 0.168 | 1.2 | 6000 | 0.5046 | 41.6521 | 16.6159 | 37.7915 | 37.7778 | 12.661 | | 0.1688 | 1.3 | 6500 | 0.5020 | 42.3292 | 17.1408 | 38.5407 | 38.5282 | 11.846 | | 0.1682 | 1.4 | 7000 | 0.5045 | 42.848 | 17.6905 | 38.9854 | 38.9896 | 12.025 | | 0.1703 | 1.5 | 7500 | 0.5103 | 42.1175 | 16.7765 | 38.3023 | 38.3199 | 12.4315 | | 0.1618 | 1.6 | 8000 | 0.5019 | 43.207 | 17.8145 | 39.3822 | 39.3884 | 12.3485 | | 0.1657 | 1.7 | 8500 | 0.4945 | 42.8399 | 17.8975 | 39.1618 | 39.1951 | 11.8575 | | 0.1643 | 1.8 | 9000 | 0.5064 | 43.0186 | 17.8969 | 39.2518 | 39.2735 | 12.0095 | | 0.1654 | 1.9 | 9500 | 0.5011 | 43.2785 | 18.2603 | 39.4479 | 39.4437 | 12.2305 | | 0.158 | 2.0 | 10000 | 0.4945 | 43.3824 | 18.3183 | 39.3471 | 39.3334 | 12.1495 | | 0.1096 | 2.1 | 10500 | 0.5520 | 43.5068 | 18.4313 | 39.7084 | 39.7205 | 12.112 | | 0.1037 | 2.2 | 11000 | 0.5510 | 43.1909 | 18.1204 | 39.1945 | 39.2052 | 12.349 | | 0.1045 | 2.3 | 11500 | 0.5453 | 42.9965 | 18.4064 | 39.0931 | 39.0868 | 12.1825 | | 0.1027 | 2.4 | 12000 | 0.5473 | 43.4973 | 18.8697 | 39.944 | 39.9407 | 12.447 | | 0.1034 | 2.5 | 12500 | 0.5512 | 43.9534 | 19.327 | 40.0946 | 40.0724 | 12.2395 | | 0.1018 | 2.6 | 13000 | 0.5527 | 43.7136 | 19.1214 | 39.9218 | 39.9274 | 12.3245 | | 0.0986 | 2.7 | 13500 | 0.5557 | 44.0502 | 19.3213 | 40.0291 | 40.0286 | 12.3345 | | 0.0953 | 2.8 | 14000 | 0.5510 | 44.0001 | 19.4482 | 40.1204 | 40.1175 | 12.1255 | | 0.098 | 2.9 | 14500 | 0.5534 | 43.9554 | 19.4673 | 40.1401 | 40.1521 | 12.2395 | | 0.0947 | 3.0 | 15000 | 0.5528 | 44.1624 | 19.6736 | 40.3898 | 40.4029 | 12.263 | ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2