--- tags: - generated_from_trainer model-index: - name: clip-hugging-face-finetuned results: [] --- # clip-hugging-face-finetuned This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.4228 ## 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: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 1.8261 | 0.0625 | 1 | 1.7808 | | 1.7935 | 0.125 | 2 | 1.6237 | | 2.2498 | 0.1875 | 3 | 1.7418 | | 1.9536 | 0.25 | 4 | 1.7778 | | 2.1207 | 0.3125 | 5 | 1.7882 | | 2.1623 | 0.375 | 6 | 1.8578 | | 2.0764 | 0.4375 | 7 | 1.8868 | | 2.206 | 0.5 | 8 | 1.8571 | | 2.2791 | 0.5625 | 9 | 1.8134 | | 2.2276 | 0.625 | 10 | 1.7591 | | 1.826 | 0.6875 | 11 | 1.6688 | | 1.668 | 0.75 | 12 | 1.5710 | | 1.8039 | 0.8125 | 13 | 1.5271 | | 1.7761 | 0.875 | 14 | 1.4974 | | 1.5512 | 0.9375 | 15 | 1.4799 | | 1.0115 | 1.0 | 16 | 1.4686 | | 0.4346 | 1.0625 | 17 | 1.4616 | | 0.3421 | 1.125 | 18 | 1.4560 | | 0.3134 | 1.1875 | 19 | 1.4582 | | 0.2237 | 1.25 | 20 | 1.4679 | | 0.6518 | 1.3125 | 21 | 1.4689 | | 0.3559 | 1.375 | 22 | 1.4730 | | 0.38 | 1.4375 | 23 | 1.4652 | | 0.3887 | 1.5 | 24 | 1.4595 | | 0.3202 | 1.5625 | 25 | 1.4468 | | 0.2525 | 1.625 | 26 | 1.4385 | | 0.5361 | 1.6875 | 27 | 1.4364 | | 0.3427 | 1.75 | 28 | 1.4358 | | 0.2529 | 1.8125 | 29 | 1.4346 | | 0.1857 | 1.875 | 30 | 1.4301 | | 0.3143 | 1.9375 | 31 | 1.4248 | | 0.1912 | 2.0 | 32 | 1.4228 | ### Framework versions - Transformers 4.41.0.dev0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1