This model is a fine-tuned version of NourFakih/Vit-GPT2-COCO2017Flickr-115k-nlpconnect on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Gen Len | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|---|
| 0.4218 | 0.2783 | 2000 | 11.7001 | 0.4402 | 40.8374 | 15.0971 | 36.9258 | 36.9122 |
| 0.4071 | 0.5565 | 4000 | 11.2742 | 0.4353 | 41.1785 | 15.7543 | 37.5183 | 37.5112 |
| 0.3914 | 0.8348 | 6000 | 11.7367 | 0.4345 | 41.4425 | 15.991 | 37.5387 | 37.5422 |
| 0.3367 | 1.1130 | 8000 | 11.8434 | 0.4481 | 41.0677 | 15.8609 | 37.3991 | 37.3749 |
| 0.3265 | 1.3913 | 10000 | 11.6695 | 0.4518 | 41.3243 | 16.1077 | 37.5478 | 37.5367 |
| 0.3158 | 1.6696 | 12000 | 11.7170 | 0.4556 | 41.3022 | 15.9154 | 37.3943 | 37.3924 |
| 0.3094 | 1.9479 | 14000 | 11.5969 | 0.4602 | 41.411 | 16.1338 | 37.6313 | 37.6262 |
| 0.2639 | 2.2262 | 16000 | 11.8349 | 0.4871 | 40.8402 | 15.4182 | 36.9302 | 36.9355 |
| 0.2515 | 2.5045 | 18000 | 0.4940 | 41.0116 | 15.4407 | 37.0026 | 37.0188 | 11.8727 |
| 0.253 | 2.7827 | 20000 | 0.4978 | 40.7656 | 15.3367 | 36.9775 | 36.9808 | 11.8545 |
checkpoint-10000/optimizer.pt 1.9 GBcheckpoint-12000/optimizer.pt 1.9 GBcheckpoint-14000/optimizer.pt 1.9 GBcheckpoint-16000/optimizer.pt 1.9 GBcheckpoint-18000/optimizer.pt 1.9 GBcheckpoint-2000/optimizer.pt 1.9 GBcheckpoint-20000/optimizer.pt 1.9 GBcheckpoint-21561/optimizer.pt 1.9 GBcheckpoint-4000/optimizer.pt 1.9 GBcheckpoint-6000/optimizer.pt 1.9 GBcheckpoint-8000/optimizer.pt 1.9 GBcheckpoint-10000/model.safetensors 957 MBcheckpoint-12000/model.safetensors 957 MBcheckpoint-14000/model.safetensors 957 MBcheckpoint-16000/model.safetensors 957 MBcheckpoint-18000/model.safetensors 957 MBcheckpoint-2000/model.safetensors 957 MBcheckpoint-20000/model.safetensors 957 MBcheckpoint-21561/model.safetensors 957 MBcheckpoint-4000/model.safetensors 957 MBcheckpoint-6000/model.safetensors 957 MBcheckpoint-8000/model.safetensors 957 MBmodel.safetensors 957 MBcheckpoint-10000/rng_state.pth 14.2 kBcheckpoint-12000/rng_state.pth 14.2 kBcheckpoint-14000/rng_state.pth 14.2 kBcheckpoint-16000/rng_state.pth 14.2 kBcheckpoint-18000/rng_state.pth 14.2 kBcheckpoint-2000/rng_state.pth 14.2 kBcheckpoint-20000/rng_state.pth 14.2 kBcheckpoint-21561/rng_state.pth 14.2 kBcheckpoint-4000/rng_state.pth 14.2 kBcheckpoint-6000/rng_state.pth 14.2 kBcheckpoint-8000/rng_state.pth 14.2 kBcheckpoint-10000/training_args.bin 5.3 kBcheckpoint-12000/training_args.bin 5.3 kBcheckpoint-14000/training_args.bin 5.3 kBcheckpoint-16000/training_args.bin 5.3 kBcheckpoint-18000/training_args.bin 5.3 kBcheckpoint-2000/training_args.bin 5.3 kBcheckpoint-20000/training_args.bin 5.3 kBcheckpoint-21561/training_args.bin 5.3 kBcheckpoint-4000/training_args.bin 5.3 kBcheckpoint-6000/training_args.bin 5.3 kBcheckpoint-8000/training_args.bin 5.3 kBtraining_args.bin 5.3 kBcheckpoint-10000/scheduler.pt 1.1 kBcheckpoint-12000/scheduler.pt 1.1 kBcheckpoint-14000/scheduler.pt 1.1 kBcheckpoint-16000/scheduler.pt 1.1 kBcheckpoint-18000/scheduler.pt 1.1 kBcheckpoint-2000/scheduler.pt 1.1 kBcheckpoint-20000/scheduler.pt 1.1 kBcheckpoint-21561/scheduler.pt 1.1 kBcheckpoint-4000/scheduler.pt 1.1 kBcheckpoint-6000/scheduler.pt 1.1 kBcheckpoint-8000/scheduler.pt 1.1 kBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo Image-Captioning-ML/Vit-GPT2-COCO2017Flickr-115k-nlpconnect ./model-folderImage-Captioning-ML/Vit-GPT2-COCO2017Flickr-115k-nlpconnect