--- license: apache-2.0 base_model: dandelin/vilt-b32-mlm tags: - generated_from_trainer model-index: - name: vilt_finetuned_100000 results: [] --- # vilt_finetuned_100000 This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.2049 ## 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: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 148.4684 | 0.04 | 250 | 5.6972 | | 5.0473 | 0.08 | 500 | 4.5986 | | 4.4685 | 0.12 | 750 | 4.2115 | | 4.0423 | 0.16 | 1000 | 3.8991 | | 3.8019 | 0.2 | 1250 | 3.7080 | | 3.6731 | 0.24 | 1500 | 3.5319 | | 3.5226 | 0.28 | 1750 | 3.4277 | | 3.3556 | 0.32 | 2000 | 3.3546 | | 3.279 | 0.36 | 2250 | 3.2592 | | 3.2406 | 0.4 | 2500 | 3.1792 | | 3.1275 | 0.44 | 2750 | 3.1014 | | 3.0569 | 0.48 | 3000 | 3.0938 | | 3.0484 | 0.52 | 3250 | 2.9939 | | 2.9883 | 0.56 | 3500 | 2.9230 | | 2.9351 | 0.6 | 3750 | 2.8902 | | 2.8526 | 0.64 | 4000 | 2.8242 | | 2.8469 | 0.68 | 4250 | 2.8069 | | 2.7228 | 0.72 | 4500 | 2.7304 | | 2.6549 | 0.76 | 4750 | 2.6875 | | 2.6304 | 0.8 | 5000 | 2.6461 | | 2.6239 | 0.84 | 5250 | 2.6117 | | 2.6334 | 0.88 | 5500 | 2.5914 | | 2.622 | 0.92 | 5750 | 2.5320 | | 2.5581 | 0.96 | 6000 | 2.5028 | | 2.536 | 1.0 | 6250 | 2.5663 | | 2.3565 | 1.04 | 6500 | 2.4770 | | 2.2907 | 1.08 | 6750 | 2.4965 | | 2.3328 | 1.12 | 7000 | 2.4514 | | 2.2924 | 1.16 | 7250 | 2.4503 | | 2.2799 | 1.2 | 7500 | 2.4083 | | 2.2477 | 1.24 | 7750 | 2.4246 | | 2.2662 | 1.28 | 8000 | 2.3792 | | 2.2656 | 1.32 | 8250 | 2.3568 | | 2.1932 | 1.36 | 8500 | 2.3682 | | 2.1821 | 1.4 | 8750 | 2.3241 | | 2.1663 | 1.44 | 9000 | 2.3182 | | 2.1017 | 1.48 | 9250 | 2.3225 | | 2.1884 | 1.52 | 9500 | 2.3069 | | 2.1873 | 1.56 | 9750 | 2.2613 | | 2.1094 | 1.6 | 10000 | 2.2730 | | 2.0764 | 1.64 | 10250 | 2.2694 | | 2.1051 | 1.68 | 10500 | 2.2537 | | 2.1283 | 1.72 | 10750 | 2.2434 | | 2.1212 | 1.76 | 11000 | 2.2164 | | 2.0978 | 1.8 | 11250 | 2.2168 | | 1.9994 | 1.84 | 11500 | 2.2015 | | 2.0101 | 1.88 | 11750 | 2.1916 | | 2.0156 | 1.92 | 12000 | 2.1699 | | 2.014 | 1.96 | 12250 | 2.1821 | | 1.9576 | 2.0 | 12500 | 2.1739 | | 1.6838 | 2.04 | 12750 | 2.2527 | | 1.6692 | 2.08 | 13000 | 2.2432 | | 1.6237 | 2.12 | 13250 | 2.2824 | | 1.5776 | 2.16 | 13500 | 2.2619 | | 1.6468 | 2.2 | 13750 | 2.2499 | | 1.6279 | 2.24 | 14000 | 2.2454 | | 1.6277 | 2.28 | 14250 | 2.2624 | | 1.6293 | 2.32 | 14500 | 2.2283 | | 1.6217 | 2.36 | 14750 | 2.2720 | | 1.5921 | 2.4 | 15000 | 2.2643 | | 1.578 | 2.44 | 15250 | 2.2336 | | 1.5559 | 2.48 | 15500 | 2.2311 | | 1.5932 | 2.52 | 15750 | 2.2063 | | 1.5532 | 2.56 | 16000 | 2.2205 | | 1.5736 | 2.6 | 16250 | 2.2141 | | 1.5931 | 2.64 | 16500 | 2.2399 | | 1.5735 | 2.68 | 16750 | 2.2106 | | 1.5161 | 2.72 | 17000 | 2.1973 | | 1.5388 | 2.76 | 17250 | 2.2009 | | 1.5139 | 2.8 | 17500 | 2.2083 | | 1.5298 | 2.84 | 17750 | 2.2030 | | 1.5339 | 2.88 | 18000 | 2.2031 | | 1.4774 | 2.92 | 18250 | 2.2050 | | 1.5067 | 2.96 | 18500 | 2.2074 | | 1.4847 | 3.0 | 18750 | 2.2049 | ### Framework versions - Transformers 4.34.1 - Pytorch 2.1.0+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1