--- license: mit base_model: indolem/indobert-base-uncased tags: - generated_from_trainer model-index: - name: QA_using_indoBERT_LORA_qv2 results: [] --- # QA_using_indoBERT_LORA_qv2 This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co./indolem/indobert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.9435 ## 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: 0.0001 - train_batch_size: 4 - 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 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 5.7426 | 0.02 | 500 | 6.2378 | | 5.1601 | 0.03 | 1000 | 4.0267 | | 3.466 | 0.05 | 1500 | 3.0399 | | 2.9304 | 0.06 | 2000 | 2.8011 | | 2.7403 | 0.08 | 2500 | 2.7113 | | 2.599 | 0.09 | 3000 | 2.6337 | | 2.4993 | 0.11 | 3500 | 2.4798 | | 2.4454 | 0.12 | 4000 | 2.4486 | | 2.3938 | 0.14 | 4500 | 2.3848 | | 2.3124 | 0.15 | 5000 | 2.3729 | | 2.2595 | 0.17 | 5500 | 2.4021 | | 2.241 | 0.18 | 6000 | 2.3487 | | 2.3296 | 0.2 | 6500 | 2.2819 | | 2.21 | 0.21 | 7000 | 2.2588 | | 2.2386 | 0.23 | 7500 | 2.3498 | | 2.164 | 0.25 | 8000 | 2.2315 | | 2.2535 | 0.26 | 8500 | 2.2315 | | 2.2621 | 0.28 | 9000 | 2.3788 | | 2.364 | 0.29 | 9500 | 2.8077 | | 2.2345 | 0.31 | 10000 | 2.2495 | | 2.1571 | 0.32 | 10500 | 2.2306 | | 2.0452 | 0.34 | 11000 | 2.2417 | | 2.1279 | 0.35 | 11500 | 2.1814 | | 2.1482 | 0.37 | 12000 | 2.1762 | | 2.1064 | 0.38 | 12500 | 2.1931 | | 1.9992 | 0.4 | 13000 | 2.1902 | | 2.1265 | 0.41 | 13500 | 2.1558 | | 2.0659 | 0.43 | 14000 | 2.2007 | | 2.0314 | 0.44 | 14500 | 2.1326 | | 2.0086 | 0.46 | 15000 | 2.1282 | | 2.0168 | 0.48 | 15500 | 2.1372 | | 2.024 | 0.49 | 16000 | 2.1111 | | 2.0636 | 0.51 | 16500 | 2.0926 | | 1.9673 | 0.52 | 17000 | 2.1200 | | 2.0207 | 0.54 | 17500 | 2.1710 | | 2.0857 | 0.55 | 18000 | 2.1886 | | 2.1617 | 0.57 | 18500 | 2.1123 | | 1.9912 | 0.58 | 19000 | 2.0999 | | 2.1166 | 0.6 | 19500 | 2.0940 | | 2.0312 | 0.61 | 20000 | 2.1436 | | 2.1124 | 0.63 | 20500 | 2.1743 | | 2.0399 | 0.64 | 21000 | 2.0801 | | 1.9246 | 0.66 | 21500 | 2.0535 | | 1.9792 | 0.67 | 22000 | 2.0926 | | 1.9713 | 0.69 | 22500 | 2.0666 | | 1.9285 | 0.71 | 23000 | 2.0699 | | 1.9454 | 0.72 | 23500 | 2.0873 | | 1.9255 | 0.74 | 24000 | 2.0515 | | 1.9428 | 0.75 | 24500 | 2.0771 | | 1.9093 | 0.77 | 25000 | 2.0538 | | 1.933 | 0.78 | 25500 | 2.0308 | | 1.8628 | 0.8 | 26000 | 2.0554 | | 1.906 | 0.81 | 26500 | 2.0581 | | 1.9255 | 0.83 | 27000 | 2.0167 | | 1.8795 | 0.84 | 27500 | 2.0423 | | 1.8987 | 0.86 | 28000 | 2.0300 | | 1.8464 | 0.87 | 28500 | 2.0540 | | 1.9619 | 0.89 | 29000 | 2.0068 | | 1.9475 | 0.9 | 29500 | 2.0079 | | 1.9399 | 0.92 | 30000 | 1.9889 | | 1.8473 | 0.94 | 30500 | 2.0135 | | 1.8775 | 0.95 | 31000 | 2.0096 | | 1.8049 | 0.97 | 31500 | 2.0289 | | 1.8029 | 0.98 | 32000 | 2.0561 | | 1.9167 | 1.0 | 32500 | 2.0199 | | 1.873 | 1.01 | 33000 | 2.0081 | | 1.7915 | 1.03 | 33500 | 2.0418 | | 1.8741 | 1.04 | 34000 | 2.0087 | | 1.8528 | 1.06 | 34500 | 2.0023 | | 1.8255 | 1.07 | 35000 | 2.0275 | | 1.8667 | 1.09 | 35500 | 2.0227 | | 1.7821 | 1.1 | 36000 | 1.9990 | | 1.7809 | 1.12 | 36500 | 2.0067 | | 1.8287 | 1.13 | 37000 | 1.9984 | | 1.8026 | 1.15 | 37500 | 2.0272 | | 1.8299 | 1.16 | 38000 | 2.0259 | | 1.7972 | 1.18 | 38500 | 2.0382 | | 1.8505 | 1.2 | 39000 | 1.9803 | | 1.8319 | 1.21 | 39500 | 1.9699 | | 1.8171 | 1.23 | 40000 | 1.9931 | | 1.7986 | 1.24 | 40500 | 1.9933 | | 1.8228 | 1.26 | 41000 | 1.9807 | | 1.8793 | 1.27 | 41500 | 1.9999 | | 1.7724 | 1.29 | 42000 | 1.9779 | | 1.7328 | 1.3 | 42500 | 1.9725 | | 1.8083 | 1.32 | 43000 | 1.9603 | | 1.7829 | 1.33 | 43500 | 1.9790 | | 1.7823 | 1.35 | 44000 | 1.9777 | | 1.7715 | 1.36 | 44500 | 1.9831 | | 1.8368 | 1.38 | 45000 | 1.9531 | | 1.7688 | 1.39 | 45500 | 1.9666 | | 1.7946 | 1.41 | 46000 | 1.9662 | | 1.8104 | 1.43 | 46500 | 1.9799 | | 1.758 | 1.44 | 47000 | 1.9697 | | 1.802 | 1.46 | 47500 | 1.9617 | | 1.7628 | 1.47 | 48000 | 1.9645 | | 1.8014 | 1.49 | 48500 | 1.9642 | | 1.8153 | 1.5 | 49000 | 1.9449 | | 1.7997 | 1.52 | 49500 | 1.9682 | | 1.8021 | 1.53 | 50000 | 1.9567 | | 1.766 | 1.55 | 50500 | 1.9740 | | 1.7886 | 1.56 | 51000 | 1.9513 | | 1.7865 | 1.58 | 51500 | 1.9411 | | 1.8403 | 1.59 | 52000 | 1.9396 | | 1.7257 | 1.61 | 52500 | 1.9590 | | 1.7743 | 1.62 | 53000 | 1.9408 | | 1.7903 | 1.64 | 53500 | 1.9469 | | 1.8302 | 1.66 | 54000 | 1.9370 | | 1.7979 | 1.67 | 54500 | 1.9394 | | 1.8109 | 1.69 | 55000 | 1.9440 | | 1.7397 | 1.7 | 55500 | 1.9579 | | 1.7374 | 1.72 | 56000 | 1.9501 | | 1.7373 | 1.73 | 56500 | 1.9518 | | 1.7273 | 1.75 | 57000 | 1.9474 | | 1.8064 | 1.76 | 57500 | 1.9368 | | 1.7913 | 1.78 | 58000 | 1.9426 | | 1.8166 | 1.79 | 58500 | 1.9331 | | 1.8238 | 1.81 | 59000 | 1.9341 | | 1.8049 | 1.82 | 59500 | 1.9464 | | 1.8735 | 1.84 | 60000 | 1.9397 | | 1.8169 | 1.85 | 60500 | 1.9388 | | 1.7689 | 1.87 | 61000 | 1.9393 | | 1.7612 | 1.89 | 61500 | 1.9433 | | 1.7768 | 1.9 | 62000 | 1.9402 | | 1.6952 | 1.92 | 62500 | 1.9478 | | 1.7951 | 1.93 | 63000 | 1.9395 | | 1.764 | 1.95 | 63500 | 1.9381 | | 1.7895 | 1.96 | 64000 | 1.9362 | | 1.6671 | 1.98 | 64500 | 1.9428 | | 1.7535 | 1.99 | 65000 | 1.9435 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0