--- language: - bm base_model: oza75/bambara-vqvae tags: - generated_from_trainer model-index: - name: bambara-vqvae results: [] --- # bambara-vqvae This model is a fine-tuned version of [oza75/bambara-vqvae](https://huggingface.co/oza75/bambara-vqvae) on the oza75/bambara-tts dataset. It achieves the following results on the evaluation set: - Loss: 0.2141 - Mse: 0.0388 - Snr: 21.6232 ## Model description This model is a VQ-VAE model for encoding bambara speech into discrete latents codes. Model paper [https://arxiv.org/pdf/1711.00937](https://arxiv.org/pdf/1711.00937) ## 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: 128 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training 1 Results | Training Loss | Epoch | Step | Validation Loss | Mse | Snr | |:-------------:|:-------:|:-----:|:---------------:|:------:|:-------:| | 4.8671 | 0.4630 | 100 | 4.7616 | 0.0956 | 17.7057 | | 4.5386 | 0.9259 | 200 | 4.5686 | 0.0972 | 17.6335 | | 4.3309 | 1.3889 | 300 | 5.1175 | 0.0859 | 18.1749 | | 3.9055 | 1.8519 | 400 | 3.6748 | 0.0930 | 17.8268 | | 3.5462 | 2.3148 | 500 | 3.9152 | 0.0950 | 17.7360 | | 3.363 | 2.7778 | 600 | 2.7866 | 0.0905 | 17.9436 | | 3.2075 | 3.2407 | 700 | 3.7970 | 0.0883 | 18.0506 | | 3.1522 | 3.7037 | 800 | 3.0179 | 0.0886 | 18.0392 | | 2.9735 | 4.1667 | 900 | 4.4034 | 0.0810 | 18.4270 | | 2.9057 | 4.6296 | 1000 | 2.4479 | 0.0832 | 18.3087 | | 2.9167 | 5.0926 | 1100 | 2.3498 | 0.0879 | 18.0715 | | 2.6331 | 5.5556 | 1200 | 2.4513 | 0.0878 | 18.0789 | | 2.6169 | 6.0185 | 1300 | 2.0518 | 0.0843 | 18.2525 | | 2.5604 | 6.4815 | 1400 | 2.1794 | 0.0771 | 18.6442 | | 2.3571 | 6.9444 | 1500 | 2.1198 | 0.0755 | 18.7310 | | 2.1271 | 7.4074 | 1600 | 2.5908 | 0.0789 | 18.5391 | | 2.1477 | 7.8704 | 1700 | 2.5674 | 0.0746 | 18.7879 | | 2.0593 | 8.3333 | 1800 | 2.3501 | 0.0746 | 18.7838 | | 1.9987 | 8.7963 | 1900 | 2.0077 | 0.0645 | 19.4190 | | 2.0554 | 9.2593 | 2000 | 1.8095 | 0.0760 | 18.7045 | | 1.9182 | 9.7222 | 2100 | 1.8944 | 0.0640 | 19.4540 | | 1.8437 | 10.1852 | 2200 | 1.6660 | 0.0592 | 19.7857 | | 1.8262 | 10.6481 | 2300 | 2.0191 | 0.0614 | 19.6274 | | 1.9519 | 11.1111 | 2400 | 1.6278 | 0.0652 | 19.3679 | | 2.0337 | 11.5741 | 2500 | 2.1123 | 0.0613 | 19.6387 | | 2.1823 | 12.0370 | 2600 | 1.9423 | 0.0627 | 19.5405 | | 2.3532 | 12.5 | 2700 | 2.3935 | 0.0650 | 19.3812 | | 2.4301 | 12.9630 | 2800 | 2.3374 | 0.0712 | 18.9884 | | 2.5901 | 13.4259 | 2900 | 2.5515 | 0.0650 | 19.3858 | | 2.5238 | 13.8889 | 3000 | 2.8894 | 0.0626 | 19.5469 | | 2.4095 | 14.3519 | 3100 | 2.5859 | 0.0620 | 19.5864 | | 2.3416 | 14.8148 | 3200 | 2.6629 | 0.0639 | 19.4582 | | 2.2236 | 15.2778 | 3300 | 2.2810 | 0.0628 | 19.5334 | | 2.2794 | 15.7407 | 3400 | 2.3351 | 0.0629 | 19.5267 | | 2.283 | 16.2037 | 3500 | 1.9756 | 0.0684 | 19.1625 | | 2.3028 | 16.6667 | 3600 | 2.0231 | 0.0646 | 19.4107 | | 2.2763 | 17.1296 | 3700 | 2.3012 | 0.0654 | 19.3539 | | 2.0332 | 17.5926 | 3800 | 2.1426 | 0.0594 | 19.7712 | | 1.9263 | 18.0556 | 3900 | 1.9053 | 0.0630 | 19.5177 | | 2.0636 | 18.5185 | 4000 | 1.8481 | 0.0640 | 19.4531 | | 1.8676 | 18.9815 | 4100 | 1.8974 | 0.0590 | 19.8004 | | 1.8779 | 19.4444 | 4200 | 2.2541 | 0.0549 | 20.1192 | | 1.8702 | 19.9074 | 4300 | 2.1981 | 0.0582 | 19.8627 | | 1.8691 | 20.3704 | 4400 | 1.9649 | 0.0604 | 19.7007 | | 1.8502 | 20.8333 | 4500 | 1.7129 | 0.0608 | 19.6731 | | 1.5922 | 21.2963 | 4600 | 1.5730 | 0.0581 | 19.8731 | | 1.549 | 21.7593 | 4700 | 1.4156 | 0.0633 | 19.5011 | | 1.5809 | 22.2222 | 4800 | 1.4624 | 0.0622 | 19.5714 | | 1.4754 | 22.6852 | 4900 | 1.3217 | 0.0596 | 19.7625 | | 1.4417 | 23.1481 | 5000 | 1.6220 | 0.0587 | 19.8262 | | 1.5053 | 23.6111 | 5100 | 1.6476 | 0.0550 | 20.1102 | | 1.4686 | 24.0741 | 5200 | 1.4523 | 0.0595 | 19.7643 | | 1.3764 | 24.5370 | 5300 | 1.7580 | 0.0544 | 20.1585 | | 1.3844 | 25.0 | 5400 | 1.3904 | 0.0571 | 19.9453 | | 1.3781 | 25.4630 | 5500 | 1.2143 | 0.0604 | 19.7001 | | 1.2932 | 25.9259 | 5600 | 1.4524 | 0.0595 | 19.7648 | | 1.3513 | 26.3889 | 5700 | 1.3591 | 0.0567 | 19.9765 | | 1.2994 | 26.8519 | 5800 | 1.1925 | 0.0554 | 20.0771 | | 1.2484 | 27.3148 | 5900 | 1.2242 | 0.0588 | 19.8152 | | 1.197 | 27.7778 | 6000 | 1.2605 | 0.0528 | 20.2832 | | 1.2305 | 28.2407 | 6100 | 1.1420 | 0.0559 | 20.0395 | | 1.1684 | 28.7037 | 6200 | 1.1063 | 0.0597 | 19.7491 | | 1.1854 | 29.1667 | 6300 | 1.2520 | 0.0560 | 20.0334 | | 1.2 | 29.6296 | 6400 | 1.1011 | 0.0540 | 20.1849 | | 1.176 | 30.0926 | 6500 | 1.0271 | 0.0567 | 19.9757 | | 1.1101 | 30.5556 | 6600 | 1.1846 | 0.0563 | 20.0074 | | 1.1426 | 31.0185 | 6700 | 1.0993 | 0.0570 | 19.9544 | | 1.103 | 31.4815 | 6800 | 1.0927 | 0.0570 | 19.9572 | | 1.0376 | 31.9444 | 6900 | 1.1137 | 0.0566 | 19.9874 | | 1.0489 | 32.4074 | 7000 | 1.1397 | 0.0569 | 19.9585 | | 1.0923 | 32.8704 | 7100 | 0.9335 | 0.0554 | 20.0784 | | 1.0614 | 33.3333 | 7200 | 1.2029 | 0.0551 | 20.0982 | | 1.0185 | 33.7963 | 7300 | 1.1350 | 0.0565 | 19.9945 | | 1.0401 | 34.2593 | 7400 | 1.1784 | 0.0565 | 19.9957 | | 1.0318 | 34.7222 | 7500 | 0.9407 | 0.0570 | 19.9527 | | 1.0171 | 35.1852 | 7600 | 0.9488 | 0.0569 | 19.9638 | | 1.0752 | 35.6481 | 7700 | 0.9837 | 0.0559 | 20.0420 | | 1.0916 | 36.1111 | 7800 | 1.1981 | 0.0561 | 20.0249 | | 1.1146 | 36.5741 | 7900 | 1.0566 | 0.0559 | 20.0370 | | 1.1023 | 37.0370 | 8000 | 1.0555 | 0.0553 | 20.0849 | | 1.1288 | 37.5 | 8100 | 1.1477 | 0.0559 | 20.0360 | | 1.1209 | 37.9630 | 8200 | 1.1293 | 0.0576 | 19.9067 | | 1.1332 | 38.4259 | 8300 | 1.2328 | 0.0542 | 20.1711 | | 1.1516 | 38.8889 | 8400 | 1.1648 | 0.0547 | 20.1290 | | 1.1606 | 39.3519 | 8500 | 1.1606 | 0.0564 | 19.9969 | | 1.1642 | 39.8148 | 8600 | 1.2534 | 0.0553 | 20.0878 | | 1.1356 | 40.2778 | 8700 | 1.1032 | 0.0564 | 19.9972 | | 1.1859 | 40.7407 | 8800 | 1.2939 | 0.0554 | 20.0791 | | 1.13 | 41.2037 | 8900 | 1.1200 | 0.0556 | 20.0620 | | 1.1486 | 41.6667 | 9000 | 1.1004 | 0.0557 | 20.0569 | | 1.0811 | 42.1296 | 9100 | 1.0300 | 0.0528 | 20.2869 | | 1.0941 | 42.5926 | 9200 | 1.1182 | 0.0530 | 20.2731 | | 1.0818 | 43.0556 | 9300 | 1.1210 | 0.0541 | 20.1829 | | 1.0588 | 43.5185 | 9400 | 1.2151 | 0.0524 | 20.3231 | | 1.0702 | 43.9815 | 9500 | 1.1523 | 0.0539 | 20.1985 | | 1.0094 | 44.4444 | 9600 | 1.0473 | 0.0530 | 20.2713 | | 1.0314 | 44.9074 | 9700 | 0.9793 | 0.0531 | 20.2655 | | 1.0258 | 45.3704 | 9800 | 1.0890 | 0.0513 | 20.4112 | | 1.0282 | 45.8333 | 9900 | 0.9711 | 0.0520 | 20.3517 | | 0.9859 | 46.2963 | 10000 | 0.9357 | 0.0509 | 20.4481 | | 0.9495 | 46.7593 | 10100 | 1.0113 | 0.0524 | 20.3229 | | 0.9553 | 47.2222 | 10200 | 0.9366 | 0.0517 | 20.3766 | | 0.9829 | 47.6852 | 10300 | 1.0695 | 0.0508 | 20.4506 | | 0.9316 | 48.1481 | 10400 | 0.8101 | 0.0534 | 20.2348 | | 0.9645 | 48.6111 | 10500 | 0.9829 | 0.0503 | 20.5004 | | 0.9223 | 49.0741 | 10600 | 0.9013 | 0.0517 | 20.3745 | | 0.9247 | 49.5370 | 10700 | 0.8640 | 0.0520 | 20.3559 | | 0.9265 | 50.0 | 10800 | 0.9571 | 0.0508 | 20.4535 | | 0.9149 | 50.4630 | 10900 | 0.8377 | 0.0493 | 20.5842 | | 0.9087 | 50.9259 | 11000 | 0.8752 | 0.0486 | 20.6452 | | 0.8582 | 51.3889 | 11100 | 0.8580 | 0.0520 | 20.3545 | | 0.8732 | 51.8519 | 11200 | 0.9128 | 0.0487 | 20.6348 | | 0.8973 | 52.3148 | 11300 | 0.8384 | 0.0505 | 20.4767 | | 0.853 | 52.7778 | 11400 | 0.8849 | 0.0490 | 20.6070 | | 0.8422 | 53.2407 | 11500 | 0.8829 | 0.0478 | 20.7160 | | 0.8353 | 53.7037 | 11600 | 0.9033 | 0.0500 | 20.5217 | | 0.8281 | 54.1667 | 11700 | 0.8503 | 0.0491 | 20.6028 | | 0.8437 | 54.6296 | 11800 | 0.8617 | 0.0514 | 20.4034 | | 0.8529 | 55.0926 | 11900 | 0.8649 | 0.0500 | 20.5240 | | 0.832 | 55.5556 | 12000 | 0.8541 | 0.0492 | 20.5944 | | 0.8331 | 56.0185 | 12100 | 0.7907 | 0.0485 | 20.6559 | | 0.8279 | 56.4815 | 12200 | 0.8512 | 0.0478 | 20.7184 | | 0.7912 | 56.9444 | 12300 | 0.8266 | 0.0481 | 20.6883 | | 0.8058 | 57.4074 | 12400 | 0.8213 | 0.0490 | 20.6134 | | 0.7863 | 57.8704 | 12500 | 0.8091 | 0.0474 | 20.7526 | | 0.7759 | 58.3333 | 12600 | 0.7051 | 0.0460 | 20.8827 | | 0.766 | 58.7963 | 12700 | 0.8549 | 0.0476 | 20.7343 | | 0.773 | 59.2593 | 12800 | 0.7508 | 0.0468 | 20.8111 | | 0.7683 | 59.7222 | 12900 | 0.7186 | 0.0477 | 20.7255 | | 0.7684 | 60.1852 | 13000 | 0.7521 | 0.0455 | 20.9347 | | 0.7289 | 60.6481 | 13100 | 0.7606 | 0.0467 | 20.8210 | | 0.727 | 61.1111 | 13200 | 0.7770 | 0.0485 | 20.6545 | | 0.74 | 61.5741 | 13300 | 0.6966 | 0.0482 | 20.6852 | | 0.741 | 62.0370 | 13400 | 0.7099 | 0.0473 | 20.7609 | | 0.7321 | 62.5 | 13500 | 0.7439 | 0.0470 | 20.7887 | | 0.7313 | 62.9630 | 13600 | 0.7171 | 0.0468 | 20.8111 | | 0.7257 | 63.4259 | 13700 | 0.7233 | 0.0468 | 20.8060 | | 0.7016 | 63.8889 | 13800 | 0.7619 | 0.0463 | 20.8533 | | 0.6963 | 64.3519 | 13900 | 0.7370 | 0.0466 | 20.8295 | | 0.7218 | 64.8148 | 14000 | 0.7081 | 0.0468 | 20.8096 | | 0.691 | 65.2778 | 14100 | 0.6877 | 0.0463 | 20.8571 | | 0.6883 | 65.7407 | 14200 | 0.6769 | 0.0457 | 20.9102 | | 0.6903 | 66.2037 | 14300 | 0.7429 | 0.0481 | 20.6951 | | 0.6916 | 66.6667 | 14400 | 0.7208 | 0.0456 | 20.9191 | | 0.6867 | 67.1296 | 14500 | 0.7134 | 0.0462 | 20.8635 | | 0.6508 | 67.5926 | 14600 | 0.6630 | 0.0464 | 20.8489 | | 0.6528 | 68.0556 | 14700 | 0.6637 | 0.0461 | 20.8780 | | 0.6573 | 68.5185 | 14800 | 0.6419 | 0.0456 | 20.9207 | | 0.659 | 68.9815 | 14900 | 0.6901 | 0.0460 | 20.8864 | | 0.6279 | 69.4444 | 15000 | 0.6815 | 0.0452 | 20.9613 | | 0.6409 | 69.9074 | 15100 | 0.6239 | 0.0462 | 20.8657 | | 0.6391 | 70.3704 | 15200 | 0.6703 | 0.0451 | 20.9689 | | 0.6559 | 70.8333 | 15300 | 0.6870 | 0.0450 | 20.9783 | | 0.6417 | 71.2963 | 15400 | 0.6202 | 0.0459 | 20.8984 | | 0.6364 | 71.7593 | 15500 | 0.6792 | 0.0460 | 20.8857 | | 0.6197 | 72.2222 | 15600 | 0.6580 | 0.0463 | 20.8582 | | 0.6415 | 72.6852 | 15700 | 0.6028 | 0.0456 | 20.9194 | | 0.6312 | 73.1481 | 15800 | 0.6408 | 0.0451 | 20.9713 | | 0.628 | 73.6111 | 15900 | 0.6099 | 0.0443 | 21.0436 | | 0.6471 | 74.0741 | 16000 | 0.6503 | 0.0458 | 20.9028 | | 0.6005 | 74.5370 | 16100 | 0.6151 | 0.0455 | 20.9343 | | 0.5998 | 75.0 | 16200 | 0.6550 | 0.0453 | 20.9517 | | 0.6076 | 75.4630 | 16300 | 0.6203 | 0.0456 | 20.9209 | | 0.612 | 75.9259 | 16400 | 0.6461 | 0.0448 | 21.0018 | | 0.6088 | 76.3889 | 16500 | 0.6396 | 0.0454 | 20.9440 | | 0.607 | 76.8519 | 16600 | 0.6423 | 0.0451 | 20.9665 | | 0.613 | 77.3148 | 16700 | 0.5506 | 0.0452 | 20.9617 | | 0.6216 | 77.7778 | 16800 | 0.6033 | 0.0451 | 20.9713 | | 0.5965 | 78.2407 | 16900 | 0.5685 | 0.0452 | 20.9654 | | 0.6057 | 78.7037 | 17000 | 0.5780 | 0.0442 | 21.0586 | | 0.6066 | 79.1667 | 17100 | 0.5873 | 0.0448 | 21.0039 | | 0.592 | 79.6296 | 17200 | 0.6609 | 0.0450 | 20.9780 | | 0.5918 | 80.0926 | 17300 | 0.6346 | 0.0459 | 20.8910 | | 0.5894 | 80.5556 | 17400 | 0.5987 | 0.0455 | 20.9292 | | 0.5788 | 81.0185 | 17500 | 0.6360 | 0.0447 | 21.0109 | | 0.5813 | 81.4815 | 17600 | 0.6108 | 0.0446 | 21.0205 | | 0.5965 | 81.9444 | 17700 | 0.5828 | 0.0447 | 21.0046 | | 0.5848 | 82.4074 | 17800 | 0.5959 | 0.0451 | 20.9723 | | 0.5851 | 82.8704 | 17900 | 0.5986 | 0.0443 | 21.0487 | | 0.5964 | 83.3333 | 18000 | 0.5758 | 0.0454 | 20.9396 | | 0.5723 | 83.7963 | 18100 | 0.6167 | 0.0446 | 21.0190 | | 0.5766 | 84.2593 | 18200 | 0.6056 | 0.0446 | 21.0172 | | 0.5828 | 84.7222 | 18300 | 0.5831 | 0.0442 | 21.0598 | | 0.5747 | 85.1852 | 18400 | 0.5841 | 0.0444 | 21.0353 | | 0.59 | 85.6481 | 18500 | 0.5907 | 0.0445 | 21.0262 | | 0.5689 | 86.1111 | 18600 | 0.5549 | 0.0446 | 21.0194 | | 0.6038 | 86.5741 | 18700 | 0.5776 | 0.0448 | 21.0044 | | 0.5745 | 87.0370 | 18800 | 0.5802 | 0.0451 | 20.9694 | | 0.573 | 87.5 | 18900 | 0.5801 | 0.0442 | 21.0588 | | 0.5665 | 87.9630 | 19000 | 0.6071 | 0.0454 | 20.9416 | | 0.5489 | 88.4259 | 19100 | 0.5778 | 0.0444 | 21.0404 | | 0.56 | 88.8889 | 19200 | 0.6000 | 0.0443 | 21.0468 | | 0.5578 | 89.3519 | 19300 | 0.5696 | 0.0444 | 21.0400 | | 0.5536 | 89.8148 | 19400 | 0.5665 | 0.0440 | 21.0786 | | 0.5721 | 90.2778 | 19500 | 0.5666 | 0.0443 | 21.0495 | | 0.5719 | 90.7407 | 19600 | 0.5694 | 0.0443 | 21.0505 | | 0.5767 | 91.2037 | 19700 | 0.5783 | 0.0446 | 21.0216 | | 0.5699 | 91.6667 | 19800 | 0.5687 | 0.0442 | 21.0589 | | 0.5622 | 92.1296 | 19900 | 0.5692 | 0.0444 | 21.0370 | | 0.5718 | 92.5926 | 20000 | 0.5753 | 0.0439 | 21.0847 | | 0.5638 | 93.0556 | 20100 | 0.5667 | 0.0439 | 21.0862 | | 0.5802 | 93.5185 | 20200 | 0.5550 | 0.0444 | 21.0415 | | 0.5687 | 93.9815 | 20300 | 0.5851 | 0.0443 | 21.0440 | | 0.5718 | 94.4444 | 20400 | 0.5577 | 0.0442 | 21.0627 | | 0.5548 | 94.9074 | 20500 | 0.5573 | 0.0443 | 21.0511 | | 0.5569 | 95.3704 | 20600 | 0.5648 | 0.0438 | 21.0929 | | 0.5607 | 95.8333 | 20700 | 0.5621 | 0.0442 | 21.0554 | | 0.5666 | 96.2963 | 20800 | 0.5657 | 0.0444 | 21.0404 | | 0.5727 | 96.7593 | 20900 | 0.5649 | 0.0441 | 21.0633 | | 0.5796 | 97.2222 | 21000 | 0.5673 | 0.0442 | 21.0560 | | 0.554 | 97.6852 | 21100 | 0.5575 | 0.0440 | 21.0743 | | 0.5653 | 98.1481 | 21200 | 0.5647 | 0.0443 | 21.0512 | | 0.5707 | 98.6111 | 21300 | 0.5649 | 0.0443 | 21.0504 | | 0.5518 | 99.0741 | 21400 | 0.5614 | 0.0442 | 21.0580 | | 0.5662 | 99.5370 | 21500 | 0.5577 | 0.0441 | 21.0645 | | 0.5648 | 100.0 | 21600 | 0.5621 | 0.0441 | 21.0636 | ### Training 2 results | Training Loss | Epoch | Step | Validation Loss | Mse | Snr | |:-------------:|:-------:|:-----:|:---------------:|:------:|:-------:| | 0.5677 | 0.4630 | 100 | 0.6122 | 0.0440 | 21.0825 | | 0.5558 | 0.9259 | 200 | 0.5925 | 0.0444 | 21.0412 | | 0.5579 | 1.3889 | 300 | 0.6126 | 0.0445 | 21.0335 | | 0.5711 | 1.8519 | 400 | 0.6078 | 0.0430 | 21.1782 | | 0.5698 | 2.3148 | 500 | 0.5475 | 0.0447 | 21.0131 | | 0.5427 | 2.7778 | 600 | 0.5879 | 0.0440 | 21.0778 | | 0.4864 | 3.2407 | 700 | 0.5822 | 0.0459 | 20.8911 | | 0.5086 | 3.7037 | 800 | 0.4969 | 0.0450 | 20.9817 | | 0.5224 | 4.1667 | 900 | 0.5290 | 0.0441 | 21.0634 | | 0.5091 | 4.6296 | 1000 | 0.5169 | 0.0434 | 21.1327 | | 0.5162 | 5.0926 | 1100 | 0.4908 | 0.0474 | 20.7552 | | 0.4982 | 5.5556 | 1200 | 0.4993 | 0.0428 | 21.1959 | | 0.4894 | 6.0185 | 1300 | 0.4267 | 0.0428 | 21.1945 | | 0.4727 | 6.4815 | 1400 | 0.5009 | 0.0435 | 21.1285 | | 0.4879 | 6.9444 | 1500 | 0.5038 | 0.0455 | 20.9315 | | 0.467 | 7.4074 | 1600 | 0.4557 | 0.0450 | 20.9773 | | 0.483 | 7.8704 | 1700 | 0.5395 | 0.0425 | 21.2259 | | 0.4668 | 8.3333 | 1800 | 0.4553 | 0.0442 | 21.0575 | | 0.4824 | 8.7963 | 1900 | 0.4558 | 0.0434 | 21.1353 | | 0.4797 | 9.2593 | 2000 | 0.4364 | 0.0448 | 20.9965 | | 0.4618 | 9.7222 | 2100 | 0.4926 | 0.0451 | 20.9719 | | 0.4408 | 10.1852 | 2200 | 0.4168 | 0.0433 | 21.1472 | | 0.4493 | 10.6481 | 2300 | 0.4842 | 0.0447 | 21.0089 | | 0.4456 | 11.1111 | 2400 | 0.4067 | 0.0438 | 21.1018 | | 0.4347 | 11.5741 | 2500 | 0.4760 | 0.0419 | 21.2927 | | 0.4337 | 12.0370 | 2600 | 0.3838 | 0.0442 | 21.0568 | | 0.4383 | 12.5 | 2700 | 0.4358 | 0.0457 | 20.9107 | | 0.4156 | 12.9630 | 2800 | 0.4855 | 0.0438 | 21.0949 | | 0.415 | 13.4259 | 2900 | 0.4486 | 0.0443 | 21.0527 | | 0.4311 | 13.8889 | 3000 | 0.4502 | 0.0430 | 21.1770 | | 0.412 | 14.3519 | 3100 | 0.4045 | 0.0438 | 21.0983 | | 0.4229 | 14.8148 | 3200 | 0.4118 | 0.0454 | 20.9410 | | 0.3895 | 15.2778 | 3300 | 0.3951 | 0.0434 | 21.1407 | | 0.404 | 15.7407 | 3400 | 0.3730 | 0.0456 | 20.9207 | | 0.4044 | 16.2037 | 3500 | 0.4251 | 0.0442 | 21.0600 | | 0.3991 | 16.6667 | 3600 | 0.4125 | 0.0431 | 21.1651 | | 0.3822 | 17.1296 | 3700 | 0.4440 | 0.0443 | 21.0530 | | 0.3808 | 17.5926 | 3800 | 0.3842 | 0.0429 | 21.1915 | | 0.3753 | 18.0556 | 3900 | 0.3789 | 0.0439 | 21.0840 | | 0.3896 | 18.5185 | 4000 | 0.3899 | 0.0444 | 21.0411 | | 0.3648 | 18.9815 | 4100 | 0.3431 | 0.0428 | 21.2004 | | 0.3742 | 19.4444 | 4200 | 0.3637 | 0.0441 | 21.0636 | | 0.3748 | 19.9074 | 4300 | 0.3774 | 0.0437 | 21.1046 | | 0.3645 | 20.3704 | 4400 | 0.3855 | 0.0451 | 20.9709 | | 0.3651 | 20.8333 | 4500 | 0.3881 | 0.0438 | 21.0954 | | 0.35 | 21.2963 | 4600 | 0.3600 | 0.0425 | 21.2300 | | 0.3541 | 21.7593 | 4700 | 0.3662 | 0.0452 | 20.9625 | | 0.3552 | 22.2222 | 4800 | 0.3795 | 0.0422 | 21.2598 | | 0.3434 | 22.6852 | 4900 | 0.3424 | 0.0433 | 21.1513 | | 0.3426 | 23.1481 | 5000 | 0.3621 | 0.0416 | 21.3237 | | 0.3508 | 23.6111 | 5100 | 0.3624 | 0.0426 | 21.2155 | | 0.3333 | 24.0741 | 5200 | 0.3563 | 0.0439 | 21.0870 | | 0.3403 | 24.5370 | 5300 | 0.3678 | 0.0425 | 21.2243 | | 0.3459 | 25.0 | 5400 | 0.3455 | 0.0433 | 21.1425 | | 0.3335 | 25.4630 | 5500 | 0.3450 | 0.0424 | 21.2427 | | 0.3395 | 25.9259 | 5600 | 0.3615 | 0.0439 | 21.0848 | | 0.3358 | 26.3889 | 5700 | 0.3193 | 0.0438 | 21.0945 | | 0.3264 | 26.8519 | 5800 | 0.3410 | 0.0435 | 21.1323 | | 0.3298 | 27.3148 | 5900 | 0.3294 | 0.0443 | 21.0527 | | 0.3189 | 27.7778 | 6000 | 0.3193 | 0.0435 | 21.1289 | | 0.3309 | 28.2407 | 6100 | 0.3255 | 0.0424 | 21.2416 | | 0.3137 | 28.7037 | 6200 | 0.3374 | 0.0445 | 21.0272 | | 0.3158 | 29.1667 | 6300 | 0.3200 | 0.0445 | 21.0245 | | 0.3176 | 29.6296 | 6400 | 0.3351 | 0.0427 | 21.2113 | | 0.3166 | 30.0926 | 6500 | 0.2949 | 0.0420 | 21.2784 | | 0.3095 | 30.5556 | 6600 | 0.3173 | 0.0422 | 21.2565 | | 0.3202 | 31.0185 | 6700 | 0.3052 | 0.0424 | 21.2393 | | 0.315 | 31.4815 | 6800 | 0.3197 | 0.0428 | 21.1954 | | 0.3118 | 31.9444 | 6900 | 0.3006 | 0.0434 | 21.1332 | | 0.3002 | 32.4074 | 7000 | 0.3322 | 0.0433 | 21.1481 | | 0.3143 | 32.8704 | 7100 | 0.2918 | 0.0410 | 21.3850 | | 0.3057 | 33.3333 | 7200 | 0.3166 | 0.0403 | 21.4642 | | 0.2924 | 33.7963 | 7300 | 0.3248 | 0.0417 | 21.3092 | | 0.3006 | 34.2593 | 7400 | 0.3126 | 0.0431 | 21.1718 | | 0.2967 | 34.7222 | 7500 | 0.2866 | 0.0398 | 21.5149 | | 0.2848 | 35.1852 | 7600 | 0.2854 | 0.0415 | 21.3295 | | 0.3027 | 35.6481 | 7700 | 0.2809 | 0.0427 | 21.2067 | | 0.2888 | 36.1111 | 7800 | 0.2841 | 0.0426 | 21.2207 | | 0.2858 | 36.5741 | 7900 | 0.2796 | 0.0428 | 21.1980 | | 0.2897 | 37.0370 | 8000 | 0.2703 | 0.0414 | 21.3461 | | 0.2924 | 37.5 | 8100 | 0.2895 | 0.0426 | 21.2142 | | 0.2796 | 37.9630 | 8200 | 0.2977 | 0.0430 | 21.1760 | | 0.2751 | 38.4259 | 8300 | 0.2916 | 0.0416 | 21.3194 | | 0.2808 | 38.8889 | 8400 | 0.2970 | 0.0421 | 21.2747 | | 0.2784 | 39.3519 | 8500 | 0.2800 | 0.0427 | 21.2095 | | 0.2821 | 39.8148 | 8600 | 0.2929 | 0.0412 | 21.3627 | | 0.2774 | 40.2778 | 8700 | 0.2743 | 0.0414 | 21.3445 | | 0.2843 | 40.7407 | 8800 | 0.3020 | 0.0415 | 21.3325 | | 0.2724 | 41.2037 | 8900 | 0.2810 | 0.0421 | 21.2651 | | 0.2739 | 41.6667 | 9000 | 0.2781 | 0.0421 | 21.2719 | | 0.2672 | 42.1296 | 9100 | 0.2675 | 0.0411 | 21.3770 | | 0.2722 | 42.5926 | 9200 | 0.2751 | 0.0422 | 21.2586 | | 0.2719 | 43.0556 | 9300 | 0.2752 | 0.0418 | 21.2978 | | 0.2659 | 43.5185 | 9400 | 0.2788 | 0.0413 | 21.3577 | | 0.2698 | 43.9815 | 9500 | 0.2866 | 0.0410 | 21.3812 | | 0.263 | 44.4444 | 9600 | 0.2839 | 0.0415 | 21.3324 | | 0.2659 | 44.9074 | 9700 | 0.2675 | 0.0410 | 21.3832 | | 0.2616 | 45.3704 | 9800 | 0.2753 | 0.0406 | 21.4219 | | 0.2663 | 45.8333 | 9900 | 0.2597 | 0.0421 | 21.2660 | | 0.2637 | 46.2963 | 10000 | 0.2565 | 0.0408 | 21.4025 | | 0.2588 | 46.7593 | 10100 | 0.2651 | 0.0411 | 21.3746 | | 0.2541 | 47.2222 | 10200 | 0.2614 | 0.0417 | 21.3115 | | 0.2615 | 47.6852 | 10300 | 0.2843 | 0.0421 | 21.2659 | | 0.251 | 48.1481 | 10400 | 0.2354 | 0.0414 | 21.3444 | | 0.2567 | 48.6111 | 10500 | 0.2662 | 0.0407 | 21.4188 | | 0.2537 | 49.0741 | 10600 | 0.2670 | 0.0413 | 21.3502 | | 0.2556 | 49.5370 | 10700 | 0.2425 | 0.0408 | 21.4062 | | 0.2526 | 50.0 | 10800 | 0.2658 | 0.0414 | 21.3399 | | 0.2545 | 50.4630 | 10900 | 0.2506 | 0.0407 | 21.4211 | | 0.2551 | 50.9259 | 11000 | 0.2530 | 0.0418 | 21.3017 | | 0.247 | 51.3889 | 11100 | 0.2532 | 0.0426 | 21.2180 | | 0.2501 | 51.8519 | 11200 | 0.2638 | 0.0410 | 21.3860 | | 0.2469 | 52.3148 | 11300 | 0.2457 | 0.0417 | 21.3151 | | 0.245 | 52.7778 | 11400 | 0.2527 | 0.0405 | 21.4325 | | 0.2425 | 53.2407 | 11500 | 0.2599 | 0.0411 | 21.3752 | | 0.2437 | 53.7037 | 11600 | 0.2586 | 0.0409 | 21.3962 | | 0.2456 | 54.1667 | 11700 | 0.2496 | 0.0420 | 21.2753 | | 0.2469 | 54.6296 | 11800 | 0.2473 | 0.0401 | 21.4771 | | 0.2493 | 55.0926 | 11900 | 0.2473 | 0.0407 | 21.4180 | | 0.2454 | 55.5556 | 12000 | 0.2513 | 0.0414 | 21.3473 | | 0.2418 | 56.0185 | 12100 | 0.2440 | 0.0410 | 21.3820 | | 0.245 | 56.4815 | 12200 | 0.2472 | 0.0404 | 21.4448 | | 0.2413 | 56.9444 | 12300 | 0.2430 | 0.0407 | 21.4160 | | 0.2402 | 57.4074 | 12400 | 0.2421 | 0.0415 | 21.3321 | | 0.2383 | 57.8704 | 12500 | 0.2464 | 0.0398 | 21.5081 | | 0.2398 | 58.3333 | 12600 | 0.2301 | 0.0415 | 21.3292 | | 0.2386 | 58.7963 | 12700 | 0.2586 | 0.0406 | 21.4287 | | 0.2355 | 59.2593 | 12800 | 0.2364 | 0.0407 | 21.4137 | | 0.2381 | 59.7222 | 12900 | 0.2384 | 0.0416 | 21.3241 | | 0.2363 | 60.1852 | 13000 | 0.2400 | 0.0398 | 21.5170 | | 0.2312 | 60.6481 | 13100 | 0.2390 | 0.0411 | 21.3759 | | 0.2284 | 61.1111 | 13200 | 0.2502 | 0.0410 | 21.3851 | | 0.233 | 61.5741 | 13300 | 0.2240 | 0.0400 | 21.4947 | | 0.2359 | 62.0370 | 13400 | 0.2356 | 0.0402 | 21.4751 | | 0.231 | 62.5 | 13500 | 0.2389 | 0.0404 | 21.4448 | | 0.2308 | 62.9630 | 13600 | 0.2338 | 0.0406 | 21.4281 | | 0.2305 | 63.4259 | 13700 | 0.2371 | 0.0403 | 21.4601 | | 0.227 | 63.8889 | 13800 | 0.2455 | 0.0403 | 21.4540 | | 0.231 | 64.3519 | 13900 | 0.2442 | 0.0399 | 21.5027 | | 0.2317 | 64.8148 | 14000 | 0.2345 | 0.0404 | 21.4498 | | 0.2266 | 65.2778 | 14100 | 0.2347 | 0.0402 | 21.4754 | | 0.2301 | 65.7407 | 14200 | 0.2238 | 0.0403 | 21.4640 | | 0.2324 | 66.2037 | 14300 | 0.2400 | 0.0400 | 21.4867 | | 0.2289 | 66.6667 | 14400 | 0.2342 | 0.0398 | 21.5156 | | 0.2286 | 67.1296 | 14500 | 0.2391 | 0.0405 | 21.4362 | | 0.2234 | 67.5926 | 14600 | 0.2335 | 0.0400 | 21.4898 | | 0.2203 | 68.0556 | 14700 | 0.2336 | 0.0404 | 21.4517 | | 0.2271 | 68.5185 | 14800 | 0.2267 | 0.0405 | 21.4390 | | 0.2279 | 68.9815 | 14900 | 0.2380 | 0.0407 | 21.4177 | | 0.2171 | 69.4444 | 15000 | 0.2306 | 0.0390 | 21.5992 | | 0.225 | 69.9074 | 15100 | 0.2250 | 0.0394 | 21.5567 | | 0.2245 | 70.3704 | 15200 | 0.2351 | 0.0399 | 21.5079 | | 0.2236 | 70.8333 | 15300 | 0.2331 | 0.0396 | 21.5340 | | 0.2262 | 71.2963 | 15400 | 0.2295 | 0.0403 | 21.4613 | | 0.223 | 71.7593 | 15500 | 0.2324 | 0.0394 | 21.5539 | | 0.2154 | 72.2222 | 15600 | 0.2328 | 0.0396 | 21.5315 | | 0.2248 | 72.6852 | 15700 | 0.2198 | 0.0396 | 21.5363 | | 0.2168 | 73.1481 | 15800 | 0.2250 | 0.0398 | 21.5182 | | 0.2222 | 73.6111 | 15900 | 0.2250 | 0.0389 | 21.6151 | | 0.2279 | 74.0741 | 16000 | 0.2286 | 0.0399 | 21.4977 | | 0.2141 | 74.5370 | 16100 | 0.2199 | 0.0395 | 21.5449 | | 0.2162 | 75.0 | 16200 | 0.2320 | 0.0397 | 21.5226 | | 0.217 | 75.4630 | 16300 | 0.2314 | 0.0396 | 21.5307 | | 0.2186 | 75.9259 | 16400 | 0.2230 | 0.0402 | 21.4689 | | 0.2169 | 76.3889 | 16500 | 0.2285 | 0.0392 | 21.5767 | | 0.2168 | 76.8519 | 16600 | 0.2272 | 0.0390 | 21.6016 | | 0.2201 | 77.3148 | 16700 | 0.2123 | 0.0405 | 21.4343 | | 0.2227 | 77.7778 | 16800 | 0.2242 | 0.0403 | 21.4561 | | 0.2142 | 78.2407 | 16900 | 0.2145 | 0.0395 | 21.5514 | | 0.2175 | 78.7037 | 17000 | 0.2179 | 0.0389 | 21.6143 | | 0.2154 | 79.1667 | 17100 | 0.2159 | 0.0396 | 21.5385 | | 0.2171 | 79.6296 | 17200 | 0.2298 | 0.0394 | 21.5541 | | 0.2155 | 80.0926 | 17300 | 0.2270 | 0.0396 | 21.5338 | | 0.2149 | 80.5556 | 17400 | 0.2239 | 0.0393 | 21.5645 | | 0.2116 | 81.0185 | 17500 | 0.2237 | 0.0393 | 21.5681 | | 0.212 | 81.4815 | 17600 | 0.2264 | 0.0394 | 21.5598 | | 0.2184 | 81.9444 | 17700 | 0.2141 | 0.0393 | 21.5686 | | 0.21 | 82.4074 | 17800 | 0.2199 | 0.0393 | 21.5683 | | 0.211 | 82.8704 | 17900 | 0.2262 | 0.0385 | 21.6539 | | 0.2181 | 83.3333 | 18000 | 0.2167 | 0.0398 | 21.5153 | | 0.2111 | 83.7963 | 18100 | 0.2228 | 0.0390 | 21.5982 | | 0.2113 | 84.2593 | 18200 | 0.2233 | 0.0389 | 21.6100 | | 0.213 | 84.7222 | 18300 | 0.2261 | 0.0392 | 21.5813 | | 0.2123 | 85.1852 | 18400 | 0.2200 | 0.0392 | 21.5826 | | 0.214 | 85.6481 | 18500 | 0.2216 | 0.0394 | 21.5544 | | 0.2125 | 86.1111 | 18600 | 0.2156 | 0.0390 | 21.6009 | | 0.2139 | 86.5741 | 18700 | 0.2151 | 0.0390 | 21.5976 | | 0.2124 | 87.0370 | 18800 | 0.2175 | 0.0389 | 21.6161 | | 0.21 | 87.5 | 18900 | 0.2181 | 0.0387 | 21.6363 | | 0.2098 | 87.9630 | 19000 | 0.2215 | 0.0389 | 21.6166 | | 0.2074 | 88.4259 | 19100 | 0.2116 | 0.0388 | 21.6255 | | 0.2096 | 88.8889 | 19200 | 0.2203 | 0.0388 | 21.6220 | | 0.2076 | 89.3519 | 19300 | 0.2134 | 0.0386 | 21.6458 | | 0.2058 | 89.8148 | 19400 | 0.2168 | 0.0390 | 21.6004 | | 0.2118 | 90.2778 | 19500 | 0.2133 | 0.0390 | 21.6052 | | 0.2098 | 90.7407 | 19600 | 0.2206 | 0.0385 | 21.6544 | | 0.2131 | 91.2037 | 19700 | 0.2187 | 0.0389 | 21.6142 | | 0.2106 | 91.6667 | 19800 | 0.2154 | 0.0386 | 21.6431 | | 0.2085 | 92.1296 | 19900 | 0.2153 | 0.0394 | 21.5610 | | 0.2112 | 92.5926 | 20000 | 0.2134 | 0.0390 | 21.5981 | | 0.2121 | 93.0556 | 20100 | 0.2161 | 0.0390 | 21.6019 | | 0.215 | 93.5185 | 20200 | 0.2132 | 0.0391 | 21.5935 | | 0.2092 | 93.9815 | 20300 | 0.2167 | 0.0388 | 21.6249 | | 0.2135 | 94.4444 | 20400 | 0.2120 | 0.0387 | 21.6370 | | 0.2076 | 94.9074 | 20500 | 0.2132 | 0.0388 | 21.6225 | | 0.2087 | 95.3704 | 20600 | 0.2145 | 0.0388 | 21.6221 | | 0.207 | 95.8333 | 20700 | 0.2147 | 0.0388 | 21.6195 | | 0.2107 | 96.2963 | 20800 | 0.2150 | 0.0391 | 21.5929 | | 0.2118 | 96.7593 | 20900 | 0.2148 | 0.0389 | 21.6133 | | 0.2136 | 97.2222 | 21000 | 0.2164 | 0.0387 | 21.6379 | | 0.2082 | 97.6852 | 21100 | 0.2146 | 0.0388 | 21.6265 | | 0.2102 | 98.1481 | 21200 | 0.2151 | 0.0389 | 21.6096 | | 0.2106 | 98.6111 | 21300 | 0.2144 | 0.0388 | 21.6295 | | 0.2056 | 99.0741 | 21400 | 0.2141 | 0.0387 | 21.6313 | | 0.2104 | 99.5370 | 21500 | 0.2131 | 0.0388 | 21.6204 | | 0.2106 | 100.0 | 21600 | 0.2141 | 0.0388 | 21.6232 | ### Framework versions - Transformers 4.41.1 - Pytorch 2.2.0+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1