--- library_name: transformers tags: - generated_from_trainer model-index: - name: clip-roberta-finetuned results: [] --- # clip-roberta-finetuned This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.7885 ## 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-06 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 1000.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:--------:|:-----:|:---------------:| | No log | 1.3333 | 100 | 1.3757 | | No log | 2.6667 | 200 | 1.6360 | | No log | 4.0 | 300 | 1.3093 | | No log | 5.3333 | 400 | 1.6471 | | 1.2974 | 6.6667 | 500 | 1.4341 | | 1.2974 | 8.0 | 600 | 1.2909 | | 1.2974 | 9.3333 | 700 | 1.5774 | | 1.2974 | 10.6667 | 800 | 1.5693 | | 1.2974 | 12.0 | 900 | 1.3354 | | 1.0923 | 13.3333 | 1000 | 1.5447 | | 1.0923 | 14.6667 | 1100 | 1.6669 | | 1.0923 | 16.0 | 1200 | 1.6088 | | 1.0923 | 17.3333 | 1300 | 1.7851 | | 1.0923 | 18.6667 | 1400 | 1.7353 | | 1.0658 | 20.0 | 1500 | 1.7231 | | 1.0658 | 21.3333 | 1600 | 1.9703 | | 1.0658 | 22.6667 | 1700 | 1.8358 | | 1.0658 | 24.0 | 1800 | 1.7885 | | 1.0658 | 25.3333 | 1900 | 1.7439 | | 1.0656 | 26.6667 | 2000 | 1.8050 | | 1.0656 | 28.0 | 2100 | 1.5398 | | 1.0656 | 29.3333 | 2200 | 1.5121 | | 1.0656 | 30.6667 | 2300 | 1.5402 | | 1.0656 | 32.0 | 2400 | 1.7192 | | 1.0312 | 33.3333 | 2500 | 1.7869 | | 1.0312 | 34.6667 | 2600 | 1.7577 | | 1.0312 | 36.0 | 2700 | 1.7128 | | 1.0312 | 37.3333 | 2800 | 1.7279 | | 1.0312 | 38.6667 | 2900 | 1.8015 | | 1.0194 | 40.0 | 3000 | 1.7510 | | 1.0194 | 41.3333 | 3100 | 1.7213 | | 1.0194 | 42.6667 | 3200 | 1.6871 | | 1.0194 | 44.0 | 3300 | 1.7161 | | 1.0194 | 45.3333 | 3400 | 1.7033 | | 1.0267 | 46.6667 | 3500 | 1.6090 | | 1.0267 | 48.0 | 3600 | 1.6582 | | 1.0267 | 49.3333 | 3700 | 1.8187 | | 1.0267 | 50.6667 | 3800 | 1.7960 | | 1.0267 | 52.0 | 3900 | 1.7181 | | 1.0336 | 53.3333 | 4000 | 1.7711 | | 1.0336 | 54.6667 | 4100 | 1.8512 | | 1.0336 | 56.0 | 4200 | 1.6164 | | 1.0336 | 57.3333 | 4300 | 1.7198 | | 1.0336 | 58.6667 | 4400 | 1.9392 | | 1.0152 | 60.0 | 4500 | 1.7398 | | 1.0152 | 61.3333 | 4600 | 1.7675 | | 1.0152 | 62.6667 | 4700 | 1.7337 | | 1.0152 | 64.0 | 4800 | 1.9170 | | 1.0152 | 65.3333 | 4900 | 1.9818 | | 1.0139 | 66.6667 | 5000 | 1.7038 | | 1.0139 | 68.0 | 5100 | 1.8328 | | 1.0139 | 69.3333 | 5200 | 1.6285 | | 1.0139 | 70.6667 | 5300 | 1.8206 | | 1.0139 | 72.0 | 5400 | 1.8342 | | 1.0068 | 73.3333 | 5500 | 1.8048 | | 1.0068 | 74.6667 | 5600 | 1.7320 | | 1.0068 | 76.0 | 5700 | 1.7143 | | 1.0068 | 77.3333 | 5800 | 2.0508 | | 1.0068 | 78.6667 | 5900 | 1.7538 | | 1.0056 | 80.0 | 6000 | 1.7577 | | 1.0056 | 81.3333 | 6100 | 1.7149 | | 1.0056 | 82.6667 | 6200 | 1.6160 | | 1.0056 | 84.0 | 6300 | 1.6220 | | 1.0056 | 85.3333 | 6400 | 1.8385 | | 1.0003 | 86.6667 | 6500 | 1.6388 | | 1.0003 | 88.0 | 6600 | 1.7860 | | 1.0003 | 89.3333 | 6700 | 1.8467 | | 1.0003 | 90.6667 | 6800 | 1.8202 | | 1.0003 | 92.0 | 6900 | 1.7831 | | 0.9939 | 93.3333 | 7000 | 1.5784 | | 0.9939 | 94.6667 | 7100 | 1.8027 | | 0.9939 | 96.0 | 7200 | 1.7966 | | 0.9939 | 97.3333 | 7300 | 1.6956 | | 0.9939 | 98.6667 | 7400 | 1.8204 | | 1.0131 | 100.0 | 7500 | 1.7424 | | 1.0131 | 101.3333 | 7600 | 1.5216 | | 1.0131 | 102.6667 | 7700 | 1.6042 | | 1.0131 | 104.0 | 7800 | 1.7261 | | 1.0131 | 105.3333 | 7900 | 1.6648 | | 1.0327 | 106.6667 | 8000 | 1.6512 | | 1.0327 | 108.0 | 8100 | 1.7187 | | 1.0327 | 109.3333 | 8200 | 1.7838 | | 1.0327 | 110.6667 | 8300 | 1.6908 | | 1.0327 | 112.0 | 8400 | 1.5459 | | 1.004 | 113.3333 | 8500 | 1.8061 | | 1.004 | 114.6667 | 8600 | 1.8637 | | 1.004 | 116.0 | 8700 | 1.6184 | | 1.004 | 117.3333 | 8800 | 1.6870 | | 1.004 | 118.6667 | 8900 | 1.7125 | | 0.9897 | 120.0 | 9000 | 1.6457 | | 0.9897 | 121.3333 | 9100 | 1.6648 | | 0.9897 | 122.6667 | 9200 | 1.6011 | | 0.9897 | 124.0 | 9300 | 1.6195 | | 0.9897 | 125.3333 | 9400 | 1.7013 | | 0.9933 | 126.6667 | 9500 | 1.7618 | | 0.9933 | 128.0 | 9600 | 1.6934 | | 0.9933 | 129.3333 | 9700 | 1.7036 | | 0.9933 | 130.6667 | 9800 | 1.6653 | | 0.9933 | 132.0 | 9900 | 1.6666 | | 0.9757 | 133.3333 | 10000 | 1.7314 | | 0.9757 | 134.6667 | 10100 | 1.7937 | | 0.9757 | 136.0 | 10200 | 1.6462 | | 0.9757 | 137.3333 | 10300 | 1.5436 | | 0.9757 | 138.6667 | 10400 | 2.0111 | | 0.9935 | 140.0 | 10500 | 1.7568 | | 0.9935 | 141.3333 | 10600 | 1.7115 | | 0.9935 | 142.6667 | 10700 | 1.7389 | | 0.9935 | 144.0 | 10800 | 1.7510 | | 0.9935 | 145.3333 | 10900 | 1.9284 | | 0.9858 | 146.6667 | 11000 | 1.8227 | | 0.9858 | 148.0 | 11100 | 1.5214 | | 0.9858 | 149.3333 | 11200 | 1.7092 | | 0.9858 | 150.6667 | 11300 | 1.8388 | | 0.9858 | 152.0 | 11400 | 1.6451 | | 1.0067 | 153.3333 | 11500 | 1.7067 | | 1.0067 | 154.6667 | 11600 | 1.6046 | | 1.0067 | 156.0 | 11700 | 1.6563 | | 1.0067 | 157.3333 | 11800 | 1.6087 | | 1.0067 | 158.6667 | 11900 | 1.6843 | | 0.9771 | 160.0 | 12000 | 1.7212 | | 0.9771 | 161.3333 | 12100 | 1.7619 | | 0.9771 | 162.6667 | 12200 | 1.7759 | | 0.9771 | 164.0 | 12300 | 1.8585 | | 0.9771 | 165.3333 | 12400 | 1.8833 | | 1.0029 | 166.6667 | 12500 | 1.5845 | | 1.0029 | 168.0 | 12600 | 1.7250 | | 1.0029 | 169.3333 | 12700 | 1.6341 | | 1.0029 | 170.6667 | 12800 | 1.6908 | | 1.0029 | 172.0 | 12900 | 1.7291 | | 1.0056 | 173.3333 | 13000 | 1.7934 | | 1.0056 | 174.6667 | 13100 | 1.6862 | | 1.0056 | 176.0 | 13200 | 1.6645 | | 1.0056 | 177.3333 | 13300 | 1.6266 | | 1.0056 | 178.6667 | 13400 | 1.4598 | | 0.9797 | 180.0 | 13500 | 1.5745 | | 0.9797 | 181.3333 | 13600 | 1.4517 | | 0.9797 | 182.6667 | 13700 | 1.7140 | | 0.9797 | 184.0 | 13800 | 1.7389 | | 0.9797 | 185.3333 | 13900 | 1.7348 | | 0.9865 | 186.6667 | 14000 | 1.5544 | | 0.9865 | 188.0 | 14100 | 1.8664 | | 0.9865 | 189.3333 | 14200 | 1.5657 | | 0.9865 | 190.6667 | 14300 | 1.7390 | | 0.9865 | 192.0 | 14400 | 2.0766 | | 0.9972 | 193.3333 | 14500 | 1.7838 | | 0.9972 | 194.6667 | 14600 | 1.7653 | | 0.9972 | 196.0 | 14700 | 1.6500 | | 0.9972 | 197.3333 | 14800 | 1.6214 | | 0.9972 | 198.6667 | 14900 | 1.6204 | | 0.9843 | 200.0 | 15000 | 1.8807 | | 0.9843 | 201.3333 | 15100 | 1.7443 | | 0.9843 | 202.6667 | 15200 | 1.6455 | | 0.9843 | 204.0 | 15300 | 1.7236 | | 0.9843 | 205.3333 | 15400 | 1.6652 | | 0.9878 | 206.6667 | 15500 | 1.8002 | | 0.9878 | 208.0 | 15600 | 1.8208 | | 0.9878 | 209.3333 | 15700 | 1.6777 | | 0.9878 | 210.6667 | 15800 | 2.0752 | | 0.9878 | 212.0 | 15900 | 1.7015 | | 0.9926 | 213.3333 | 16000 | 1.6571 | | 0.9926 | 214.6667 | 16100 | 1.7757 | | 0.9926 | 216.0 | 16200 | 1.7986 | | 0.9926 | 217.3333 | 16300 | 1.6360 | | 0.9926 | 218.6667 | 16400 | 1.7862 | | 0.9993 | 220.0 | 16500 | 1.8996 | | 0.9993 | 221.3333 | 16600 | 1.6890 | | 0.9993 | 222.6667 | 16700 | 2.0968 | | 0.9993 | 224.0 | 16800 | 1.6648 | | 0.9993 | 225.3333 | 16900 | 1.5713 | | 0.9925 | 226.6667 | 17000 | 1.8458 | | 0.9925 | 228.0 | 17100 | 1.7706 | | 0.9925 | 229.3333 | 17200 | 1.9783 | | 0.9925 | 230.6667 | 17300 | 1.9077 | | 0.9925 | 232.0 | 17400 | 1.4450 | | 0.9964 | 233.3333 | 17500 | 1.6719 | | 0.9964 | 234.6667 | 17600 | 2.0009 | | 0.9964 | 236.0 | 17700 | 1.8131 | | 0.9964 | 237.3333 | 17800 | 1.9490 | | 0.9964 | 238.6667 | 17900 | 1.9603 | | 1.0044 | 240.0 | 18000 | 1.9288 | | 1.0044 | 241.3333 | 18100 | 1.5704 | | 1.0044 | 242.6667 | 18200 | 1.6068 | | 1.0044 | 244.0 | 18300 | 1.5850 | | 1.0044 | 245.3333 | 18400 | 2.0470 | | 0.9872 | 246.6667 | 18500 | 1.7222 | | 0.9872 | 248.0 | 18600 | 1.8908 | | 0.9872 | 249.3333 | 18700 | 1.9146 | | 0.9872 | 250.6667 | 18800 | 1.5986 | | 0.9872 | 252.0 | 18900 | 1.6979 | | 0.9792 | 253.3333 | 19000 | 1.6714 | | 0.9792 | 254.6667 | 19100 | 1.8374 | | 0.9792 | 256.0 | 19200 | 1.6442 | | 0.9792 | 257.3333 | 19300 | 1.7039 | | 0.9792 | 258.6667 | 19400 | 1.8681 | | 0.9874 | 260.0 | 19500 | 1.9041 | | 0.9874 | 261.3333 | 19600 | 2.0812 | | 0.9874 | 262.6667 | 19700 | 2.1596 | | 0.9874 | 264.0 | 19800 | 1.8892 | | 0.9874 | 265.3333 | 19900 | 2.0073 | | 0.9658 | 266.6667 | 20000 | 2.1017 | | 0.9658 | 268.0 | 20100 | 1.9788 | | 0.9658 | 269.3333 | 20200 | 1.9469 | | 0.9658 | 270.6667 | 20300 | 1.7930 | | 0.9658 | 272.0 | 20400 | 2.0478 | | 0.9922 | 273.3333 | 20500 | 1.8702 | | 0.9922 | 274.6667 | 20600 | 1.7105 | | 0.9922 | 276.0 | 20700 | 1.7072 | | 0.9922 | 277.3333 | 20800 | 1.6417 | | 0.9922 | 278.6667 | 20900 | 1.7585 | | 0.9838 | 280.0 | 21000 | 1.7428 | | 0.9838 | 281.3333 | 21100 | 1.7915 | | 0.9838 | 282.6667 | 21200 | 1.7450 | | 0.9838 | 284.0 | 21300 | 1.8440 | | 0.9838 | 285.3333 | 21400 | 1.8164 | | 0.9815 | 286.6667 | 21500 | 1.7036 | | 0.9815 | 288.0 | 21600 | 1.8327 | | 0.9815 | 289.3333 | 21700 | 1.6627 | | 0.9815 | 290.6667 | 21800 | 1.6603 | | 0.9815 | 292.0 | 21900 | 1.6701 | | 0.9836 | 293.3333 | 22000 | 1.7467 | | 0.9836 | 294.6667 | 22100 | 1.8039 | | 0.9836 | 296.0 | 22200 | 1.6190 | | 0.9836 | 297.3333 | 22300 | 1.6194 | | 0.9836 | 298.6667 | 22400 | 1.5753 | | 0.9888 | 300.0 | 22500 | 1.4923 | | 0.9888 | 301.3333 | 22600 | 1.5361 | | 0.9888 | 302.6667 | 22700 | 1.8874 | | 0.9888 | 304.0 | 22800 | 1.8453 | | 0.9888 | 305.3333 | 22900 | 1.6728 | | 0.9797 | 306.6667 | 23000 | 1.8922 | | 0.9797 | 308.0 | 23100 | 1.8606 | | 0.9797 | 309.3333 | 23200 | 1.9504 | | 0.9797 | 310.6667 | 23300 | 1.6589 | | 0.9797 | 312.0 | 23400 | 1.5259 | | 0.9917 | 313.3333 | 23500 | 1.5227 | | 0.9917 | 314.6667 | 23600 | 1.6790 | | 0.9917 | 316.0 | 23700 | 1.7229 | | 0.9917 | 317.3333 | 23800 | 1.6771 | | 0.9917 | 318.6667 | 23900 | 1.6257 | | 0.9926 | 320.0 | 24000 | 1.9988 | | 0.9926 | 321.3333 | 24100 | 1.5780 | | 0.9926 | 322.6667 | 24200 | 1.6264 | | 0.9926 | 324.0 | 24300 | 1.8260 | | 0.9926 | 325.3333 | 24400 | 1.8611 | | 0.9907 | 326.6667 | 24500 | 1.8523 | | 0.9907 | 328.0 | 24600 | 1.6932 | | 0.9907 | 329.3333 | 24700 | 1.7654 | | 0.9907 | 330.6667 | 24800 | 1.7335 | | 0.9907 | 332.0 | 24900 | 1.7039 | | 0.9724 | 333.3333 | 25000 | 1.6618 | | 0.9724 | 334.6667 | 25100 | 1.9623 | | 0.9724 | 336.0 | 25200 | 1.9368 | | 0.9724 | 337.3333 | 25300 | 1.7732 | | 0.9724 | 338.6667 | 25400 | 1.9566 | | 0.9798 | 340.0 | 25500 | 1.8827 | | 0.9798 | 341.3333 | 25600 | 1.7523 | | 0.9798 | 342.6667 | 25700 | 1.7631 | | 0.9798 | 344.0 | 25800 | 1.8616 | | 0.9798 | 345.3333 | 25900 | 1.6152 | | 1.0 | 346.6667 | 26000 | 1.7113 | | 1.0 | 348.0 | 26100 | 1.7063 | | 1.0 | 349.3333 | 26200 | 1.5869 | | 1.0 | 350.6667 | 26300 | 1.6878 | | 1.0 | 352.0 | 26400 | 1.5915 | | 0.9816 | 353.3333 | 26500 | 1.5613 | | 0.9816 | 354.6667 | 26600 | 1.7842 | | 0.9816 | 356.0 | 26700 | 1.6814 | | 0.9816 | 357.3333 | 26800 | 1.7293 | | 0.9816 | 358.6667 | 26900 | 1.8886 | | 0.9845 | 360.0 | 27000 | 1.9464 | | 0.9845 | 361.3333 | 27100 | 1.7940 | | 0.9845 | 362.6667 | 27200 | 1.7593 | | 0.9845 | 364.0 | 27300 | 1.6187 | | 0.9845 | 365.3333 | 27400 | 1.6948 | | 0.9705 | 366.6667 | 27500 | 1.7642 | | 0.9705 | 368.0 | 27600 | 1.6308 | | 0.9705 | 369.3333 | 27700 | 1.5529 | | 0.9705 | 370.6667 | 27800 | 1.6417 | | 0.9705 | 372.0 | 27900 | 1.6802 | | 0.975 | 373.3333 | 28000 | 1.7856 | | 0.975 | 374.6667 | 28100 | 1.5541 | | 0.975 | 376.0 | 28200 | 1.6259 | | 0.975 | 377.3333 | 28300 | 1.7255 | | 0.975 | 378.6667 | 28400 | 1.7840 | | 0.99 | 380.0 | 28500 | 1.6973 | | 0.99 | 381.3333 | 28600 | 1.7193 | | 0.99 | 382.6667 | 28700 | 1.6016 | | 0.99 | 384.0 | 28800 | 1.8773 | | 0.99 | 385.3333 | 28900 | 1.6752 | | 0.9784 | 386.6667 | 29000 | 1.6632 | | 0.9784 | 388.0 | 29100 | 1.5473 | | 0.9784 | 389.3333 | 29200 | 1.5605 | | 0.9784 | 390.6667 | 29300 | 1.6580 | | 0.9784 | 392.0 | 29400 | 1.7756 | | 0.9945 | 393.3333 | 29500 | 1.6096 | | 0.9945 | 394.6667 | 29600 | 1.7556 | | 0.9945 | 396.0 | 29700 | 2.0568 | | 0.9945 | 397.3333 | 29800 | 1.6420 | | 0.9945 | 398.6667 | 29900 | 1.7073 | | 0.9859 | 400.0 | 30000 | 1.5981 | | 0.9859 | 401.3333 | 30100 | 1.5672 | | 0.9859 | 402.6667 | 30200 | 1.5390 | | 0.9859 | 404.0 | 30300 | 1.5045 | | 0.9859 | 405.3333 | 30400 | 1.6327 | | 0.987 | 406.6667 | 30500 | 1.4833 | | 0.987 | 408.0 | 30600 | 1.7449 | | 0.987 | 409.3333 | 30700 | 1.7675 | | 0.987 | 410.6667 | 30800 | 1.7203 | | 0.987 | 412.0 | 30900 | 1.6196 | | 0.9725 | 413.3333 | 31000 | 1.6557 | | 0.9725 | 414.6667 | 31100 | 1.7799 | | 0.9725 | 416.0 | 31200 | 1.9889 | | 0.9725 | 417.3333 | 31300 | 1.7929 | | 0.9725 | 418.6667 | 31400 | 1.7601 | | 0.9783 | 420.0 | 31500 | 1.7172 | | 0.9783 | 421.3333 | 31600 | 1.8756 | | 0.9783 | 422.6667 | 31700 | 1.7748 | | 0.9783 | 424.0 | 31800 | 1.7909 | | 0.9783 | 425.3333 | 31900 | 1.8520 | | 0.9849 | 426.6667 | 32000 | 1.4917 | | 0.9849 | 428.0 | 32100 | 1.5645 | | 0.9849 | 429.3333 | 32200 | 1.5803 | | 0.9849 | 430.6667 | 32300 | 1.6522 | | 0.9849 | 432.0 | 32400 | 1.9999 | | 0.9772 | 433.3333 | 32500 | 1.6718 | | 0.9772 | 434.6667 | 32600 | 1.6779 | | 0.9772 | 436.0 | 32700 | 1.5872 | | 0.9772 | 437.3333 | 32800 | 1.7565 | | 0.9772 | 438.6667 | 32900 | 1.7727 | | 0.9756 | 440.0 | 33000 | 1.7910 | | 0.9756 | 441.3333 | 33100 | 1.7867 | | 0.9756 | 442.6667 | 33200 | 1.7775 | | 0.9756 | 444.0 | 33300 | 1.7976 | | 0.9756 | 445.3333 | 33400 | 1.5831 | | 0.9806 | 446.6667 | 33500 | 1.7222 | | 0.9806 | 448.0 | 33600 | 1.7587 | | 0.9806 | 449.3333 | 33700 | 1.7713 | | 0.9806 | 450.6667 | 33800 | 1.7805 | | 0.9806 | 452.0 | 33900 | 1.7822 | | 0.9821 | 453.3333 | 34000 | 1.7681 | | 0.9821 | 454.6667 | 34100 | 1.8012 | | 0.9821 | 456.0 | 34200 | 1.7847 | | 0.9821 | 457.3333 | 34300 | 1.7784 | | 0.9821 | 458.6667 | 34400 | 1.7340 | | 0.9786 | 460.0 | 34500 | 1.7655 | | 0.9786 | 461.3333 | 34600 | 1.7261 | | 0.9786 | 462.6667 | 34700 | 1.7453 | | 0.9786 | 464.0 | 34800 | 1.6568 | | 0.9786 | 465.3333 | 34900 | 1.6578 | | 0.972 | 466.6667 | 35000 | 1.6702 | | 0.972 | 468.0 | 35100 | 1.6752 | | 0.972 | 469.3333 | 35200 | 1.9994 | | 0.972 | 470.6667 | 35300 | 1.6725 | | 0.972 | 472.0 | 35400 | 1.6621 | | 0.9736 | 473.3333 | 35500 | 1.7036 | | 0.9736 | 474.6667 | 35600 | 1.6911 | | 0.9736 | 476.0 | 35700 | 1.6890 | | 0.9736 | 477.3333 | 35800 | 1.7306 | | 0.9736 | 478.6667 | 35900 | 1.7283 | | 0.9742 | 480.0 | 36000 | 1.4974 | | 0.9742 | 481.3333 | 36100 | 1.7059 | | 0.9742 | 482.6667 | 36200 | 1.7060 | | 0.9742 | 484.0 | 36300 | 1.7079 | | 0.9742 | 485.3333 | 36400 | 1.7405 | | 0.9902 | 486.6667 | 36500 | 1.7769 | | 0.9902 | 488.0 | 36600 | 1.6518 | | 0.9902 | 489.3333 | 36700 | 1.7669 | | 0.9902 | 490.6667 | 36800 | 1.8105 | | 0.9902 | 492.0 | 36900 | 1.6839 | | 0.9767 | 493.3333 | 37000 | 1.8279 | | 0.9767 | 494.6667 | 37100 | 1.7739 | | 0.9767 | 496.0 | 37200 | 1.6554 | | 0.9767 | 497.3333 | 37300 | 1.6143 | | 0.9767 | 498.6667 | 37400 | 1.9613 | | 0.9845 | 500.0 | 37500 | 1.7611 | | 0.9845 | 501.3333 | 37600 | 1.7701 | | 0.9845 | 502.6667 | 37700 | 1.8048 | | 0.9845 | 504.0 | 37800 | 1.7465 | | 0.9845 | 505.3333 | 37900 | 2.0235 | | 0.9934 | 506.6667 | 38000 | 1.6972 | | 0.9934 | 508.0 | 38100 | 1.7221 | | 0.9934 | 509.3333 | 38200 | 1.6900 | | 0.9934 | 510.6667 | 38300 | 1.6905 | | 0.9934 | 512.0 | 38400 | 1.7762 | | 0.9837 | 513.3333 | 38500 | 1.7382 | | 0.9837 | 514.6667 | 38600 | 1.7435 | | 0.9837 | 516.0 | 38700 | 1.7328 | | 0.9837 | 517.3333 | 38800 | 1.7523 | | 0.9837 | 518.6667 | 38900 | 1.7747 | | 0.9842 | 520.0 | 39000 | 1.8172 | | 0.9842 | 521.3333 | 39100 | 1.7908 | | 0.9842 | 522.6667 | 39200 | 1.7846 | | 0.9842 | 524.0 | 39300 | 1.7873 | | 0.9842 | 525.3333 | 39400 | 1.7076 | | 0.9665 | 526.6667 | 39500 | 1.6820 | | 0.9665 | 528.0 | 39600 | 1.7303 | | 0.9665 | 529.3333 | 39700 | 1.7036 | | 0.9665 | 530.6667 | 39800 | 1.7116 | | 0.9665 | 532.0 | 39900 | 1.7333 | | 0.9951 | 533.3333 | 40000 | 1.7403 | | 0.9951 | 534.6667 | 40100 | 1.6699 | | 0.9951 | 536.0 | 40200 | 1.6887 | | 0.9951 | 537.3333 | 40300 | 1.6864 | | 0.9951 | 538.6667 | 40400 | 1.6653 | | 0.9753 | 540.0 | 40500 | 1.6738 | | 0.9753 | 541.3333 | 40600 | 1.6469 | | 0.9753 | 542.6667 | 40700 | 1.8662 | | 0.9753 | 544.0 | 40800 | 2.1967 | | 0.9753 | 545.3333 | 40900 | 1.7643 | | 0.9893 | 546.6667 | 41000 | 1.7935 | | 0.9893 | 548.0 | 41100 | 1.8633 | | 0.9893 | 549.3333 | 41200 | 1.8706 | | 0.9893 | 550.6667 | 41300 | 1.8712 | | 0.9893 | 552.0 | 41400 | 1.8823 | | 0.9922 | 553.3333 | 41500 | 1.8661 | | 0.9922 | 554.6667 | 41600 | 1.8561 | | 0.9922 | 556.0 | 41700 | 1.8344 | | 0.9922 | 557.3333 | 41800 | 1.8317 | | 0.9922 | 558.6667 | 41900 | 1.8053 | | 0.969 | 560.0 | 42000 | 1.7482 | | 0.969 | 561.3333 | 42100 | 1.7675 | | 0.969 | 562.6667 | 42200 | 1.7875 | | 0.969 | 564.0 | 42300 | 1.8815 | | 0.969 | 565.3333 | 42400 | 1.7954 | | 0.9774 | 566.6667 | 42500 | 1.8543 | | 0.9774 | 568.0 | 42600 | 1.8677 | | 0.9774 | 569.3333 | 42700 | 1.8582 | | 0.9774 | 570.6667 | 42800 | 1.7222 | | 0.9774 | 572.0 | 42900 | 1.8004 | | 0.9801 | 573.3333 | 43000 | 1.7880 | | 0.9801 | 574.6667 | 43100 | 1.8814 | | 0.9801 | 576.0 | 43200 | 1.8421 | | 0.9801 | 577.3333 | 43300 | 1.8552 | | 0.9801 | 578.6667 | 43400 | 2.1513 | | 0.9812 | 580.0 | 43500 | 2.1082 | | 0.9812 | 581.3333 | 43600 | 2.1574 | | 0.9812 | 582.6667 | 43700 | 2.1666 | | 0.9812 | 584.0 | 43800 | 1.9117 | | 0.9812 | 585.3333 | 43900 | 1.8374 | | 0.979 | 586.6667 | 44000 | 2.0417 | | 0.979 | 588.0 | 44100 | 2.0315 | | 0.979 | 589.3333 | 44200 | 1.9731 | | 0.979 | 590.6667 | 44300 | 1.8571 | | 0.979 | 592.0 | 44400 | 2.0701 | | 0.9794 | 593.3333 | 44500 | 2.0199 | | 0.9794 | 594.6667 | 44600 | 2.0371 | | 0.9794 | 596.0 | 44700 | 2.0721 | | 0.9794 | 597.3333 | 44800 | 1.8099 | | 0.9794 | 598.6667 | 44900 | 1.8730 | | 0.9798 | 600.0 | 45000 | 1.8337 | | 0.9798 | 601.3333 | 45100 | 1.7989 | | 0.9798 | 602.6667 | 45200 | 1.8385 | | 0.9798 | 604.0 | 45300 | 1.8556 | | 0.9798 | 605.3333 | 45400 | 1.8457 | | 0.9685 | 606.6667 | 45500 | 1.8226 | | 0.9685 | 608.0 | 45600 | 1.8561 | | 0.9685 | 609.3333 | 45700 | 1.8446 | | 0.9685 | 610.6667 | 45800 | 1.8914 | | 0.9685 | 612.0 | 45900 | 1.9163 | | 0.9883 | 613.3333 | 46000 | 2.0725 | | 0.9883 | 614.6667 | 46100 | 1.8508 | | 0.9883 | 616.0 | 46200 | 1.7464 | | 0.9883 | 617.3333 | 46300 | 1.7489 | | 0.9883 | 618.6667 | 46400 | 1.8174 | | 0.9681 | 620.0 | 46500 | 1.8431 | | 0.9681 | 621.3333 | 46600 | 1.8340 | | 0.9681 | 622.6667 | 46700 | 1.8259 | | 0.9681 | 624.0 | 46800 | 1.7972 | | 0.9681 | 625.3333 | 46900 | 1.7690 | | 0.9857 | 626.6667 | 47000 | 1.6657 | | 0.9857 | 628.0 | 47100 | 1.6629 | | 0.9857 | 629.3333 | 47200 | 1.6513 | | 0.9857 | 630.6667 | 47300 | 1.7079 | | 0.9857 | 632.0 | 47400 | 1.7471 | | 0.9682 | 633.3333 | 47500 | 1.7287 | | 0.9682 | 634.6667 | 47600 | 1.7276 | | 0.9682 | 636.0 | 47700 | 1.7201 | | 0.9682 | 637.3333 | 47800 | 1.7354 | | 0.9682 | 638.6667 | 47900 | 1.7249 | | 0.9808 | 640.0 | 48000 | 1.7139 | | 0.9808 | 641.3333 | 48100 | 1.7039 | | 0.9808 | 642.6667 | 48200 | 1.7000 | | 0.9808 | 644.0 | 48300 | 1.7216 | | 0.9808 | 645.3333 | 48400 | 1.7227 | | 0.9715 | 646.6667 | 48500 | 1.7268 | | 0.9715 | 648.0 | 48600 | 1.7103 | | 0.9715 | 649.3333 | 48700 | 1.7828 | | 0.9715 | 650.6667 | 48800 | 1.7630 | | 0.9715 | 652.0 | 48900 | 1.7744 | | 0.9787 | 653.3333 | 49000 | 1.6837 | | 0.9787 | 654.6667 | 49100 | 1.6776 | | 0.9787 | 656.0 | 49200 | 1.6682 | | 0.9787 | 657.3333 | 49300 | 1.6667 | | 0.9787 | 658.6667 | 49400 | 1.6990 | | 0.9841 | 660.0 | 49500 | 1.7288 | | 0.9841 | 661.3333 | 49600 | 1.7429 | | 0.9841 | 662.6667 | 49700 | 1.8161 | | 0.9841 | 664.0 | 49800 | 1.7449 | | 0.9841 | 665.3333 | 49900 | 1.6394 | | 0.9763 | 666.6667 | 50000 | 1.6391 | | 0.9763 | 668.0 | 50100 | 1.7599 | | 0.9763 | 669.3333 | 50200 | 1.7628 | | 0.9763 | 670.6667 | 50300 | 1.7541 | | 0.9763 | 672.0 | 50400 | 1.7541 | | 0.9701 | 673.3333 | 50500 | 1.7601 | | 0.9701 | 674.6667 | 50600 | 1.7487 | | 0.9701 | 676.0 | 50700 | 1.7574 | | 0.9701 | 677.3333 | 50800 | 1.7713 | | 0.9701 | 678.6667 | 50900 | 1.7429 | | 0.9776 | 680.0 | 51000 | 1.7331 | | 0.9776 | 681.3333 | 51100 | 1.7390 | | 0.9776 | 682.6667 | 51200 | 1.7458 | | 0.9776 | 684.0 | 51300 | 1.7793 | | 0.9776 | 685.3333 | 51400 | 1.7582 | | 0.9879 | 686.6667 | 51500 | 1.6378 | | 0.9879 | 688.0 | 51600 | 1.7654 | | 0.9879 | 689.3333 | 51700 | 1.8032 | | 0.9879 | 690.6667 | 51800 | 1.7764 | | 0.9879 | 692.0 | 51900 | 1.7827 | | 0.972 | 693.3333 | 52000 | 1.7853 | | 0.972 | 694.6667 | 52100 | 1.7600 | | 0.972 | 696.0 | 52200 | 1.7468 | | 0.972 | 697.3333 | 52300 | 1.7261 | | 0.972 | 698.6667 | 52400 | 1.7252 | | 0.984 | 700.0 | 52500 | 1.6726 | | 0.984 | 701.3333 | 52600 | 1.7238 | | 0.984 | 702.6667 | 52700 | 1.7596 | | 0.984 | 704.0 | 52800 | 1.7719 | | 0.984 | 705.3333 | 52900 | 1.7889 | | 0.9784 | 706.6667 | 53000 | 1.8150 | | 0.9784 | 708.0 | 53100 | 1.7816 | | 0.9784 | 709.3333 | 53200 | 1.7753 | | 0.9784 | 710.6667 | 53300 | 1.7961 | | 0.9784 | 712.0 | 53400 | 1.7825 | | 0.9961 | 713.3333 | 53500 | 1.7892 | | 0.9961 | 714.6667 | 53600 | 1.7977 | | 0.9961 | 716.0 | 53700 | 1.7891 | | 0.9961 | 717.3333 | 53800 | 1.7800 | | 0.9961 | 718.6667 | 53900 | 1.8111 | | 0.9735 | 720.0 | 54000 | 1.8086 | | 0.9735 | 721.3333 | 54100 | 1.7823 | | 0.9735 | 722.6667 | 54200 | 1.7697 | | 0.9735 | 724.0 | 54300 | 1.8578 | | 0.9735 | 725.3333 | 54400 | 1.7846 | | 0.9722 | 726.6667 | 54500 | 1.7788 | | 0.9722 | 728.0 | 54600 | 1.7930 | | 0.9722 | 729.3333 | 54700 | 1.7929 | | 0.9722 | 730.6667 | 54800 | 1.7887 | | 0.9722 | 732.0 | 54900 | 1.7773 | | 0.9764 | 733.3333 | 55000 | 1.7724 | | 0.9764 | 734.6667 | 55100 | 1.7711 | | 0.9764 | 736.0 | 55200 | 1.7671 | | 0.9764 | 737.3333 | 55300 | 1.7742 | | 0.9764 | 738.6667 | 55400 | 1.7693 | | 0.9724 | 740.0 | 55500 | 1.7697 | | 0.9724 | 741.3333 | 55600 | 1.7726 | | 0.9724 | 742.6667 | 55700 | 1.7720 | | 0.9724 | 744.0 | 55800 | 1.7682 | | 0.9724 | 745.3333 | 55900 | 1.7703 | | 0.9801 | 746.6667 | 56000 | 1.7634 | | 0.9801 | 748.0 | 56100 | 1.7664 | | 0.9801 | 749.3333 | 56200 | 1.7591 | | 0.9801 | 750.6667 | 56300 | 1.7657 | | 0.9801 | 752.0 | 56400 | 1.7648 | | 0.9817 | 753.3333 | 56500 | 1.7628 | | 0.9817 | 754.6667 | 56600 | 1.7615 | | 0.9817 | 756.0 | 56700 | 1.7646 | | 0.9817 | 757.3333 | 56800 | 1.7689 | | 0.9817 | 758.6667 | 56900 | 1.8117 | | 0.9688 | 760.0 | 57000 | 1.8124 | | 0.9688 | 761.3333 | 57100 | 1.7966 | | 0.9688 | 762.6667 | 57200 | 1.9901 | | 0.9688 | 764.0 | 57300 | 1.7721 | | 0.9688 | 765.3333 | 57400 | 1.8064 | | 0.9712 | 766.6667 | 57500 | 1.7842 | | 0.9712 | 768.0 | 57600 | 1.7626 | | 0.9712 | 769.3333 | 57700 | 1.7606 | | 0.9712 | 770.6667 | 57800 | 1.7561 | | 0.9712 | 772.0 | 57900 | 1.8055 | | 0.9802 | 773.3333 | 58000 | 1.7570 | | 0.9802 | 774.6667 | 58100 | 1.6272 | | 0.9802 | 776.0 | 58200 | 1.7638 | | 0.9802 | 777.3333 | 58300 | 1.7548 | | 0.9802 | 778.6667 | 58400 | 1.7789 | | 0.9779 | 780.0 | 58500 | 1.8975 | | 0.9779 | 781.3333 | 58600 | 1.7797 | | 0.9779 | 782.6667 | 58700 | 1.7794 | | 0.9779 | 784.0 | 58800 | 1.7835 | | 0.9779 | 785.3333 | 58900 | 1.7745 | | 0.9772 | 786.6667 | 59000 | 1.5808 | | 0.9772 | 788.0 | 59100 | 1.7921 | | 0.9772 | 789.3333 | 59200 | 1.8162 | | 0.9772 | 790.6667 | 59300 | 1.7851 | | 0.9772 | 792.0 | 59400 | 1.8117 | | 0.9736 | 793.3333 | 59500 | 1.8234 | | 0.9736 | 794.6667 | 59600 | 1.8043 | | 0.9736 | 796.0 | 59700 | 1.8074 | | 0.9736 | 797.3333 | 59800 | 1.7648 | | 0.9736 | 798.6667 | 59900 | 1.7626 | | 0.9771 | 800.0 | 60000 | 1.8125 | | 0.9771 | 801.3333 | 60100 | 1.8087 | | 0.9771 | 802.6667 | 60200 | 1.8008 | | 0.9771 | 804.0 | 60300 | 1.8300 | | 0.9771 | 805.3333 | 60400 | 1.7893 | | 0.9765 | 806.6667 | 60500 | 1.7676 | | 0.9765 | 808.0 | 60600 | 1.6956 | | 0.9765 | 809.3333 | 60700 | 1.7825 | | 0.9765 | 810.6667 | 60800 | 1.6787 | | 0.9765 | 812.0 | 60900 | 1.7716 | | 0.984 | 813.3333 | 61000 | 1.8037 | | 0.984 | 814.6667 | 61100 | 1.8009 | | 0.984 | 816.0 | 61200 | 1.7911 | | 0.984 | 817.3333 | 61300 | 1.8005 | | 0.984 | 818.6667 | 61400 | 1.7862 | | 0.9678 | 820.0 | 61500 | 1.7463 | | 0.9678 | 821.3333 | 61600 | 1.7833 | | 0.9678 | 822.6667 | 61700 | 1.7831 | | 0.9678 | 824.0 | 61800 | 1.7775 | | 0.9678 | 825.3333 | 61900 | 1.7873 | | 0.9803 | 826.6667 | 62000 | 1.7959 | | 0.9803 | 828.0 | 62100 | 1.8055 | | 0.9803 | 829.3333 | 62200 | 1.8094 | | 0.9803 | 830.6667 | 62300 | 1.8108 | | 0.9803 | 832.0 | 62400 | 1.8201 | | 0.9756 | 833.3333 | 62500 | 1.8311 | | 0.9756 | 834.6667 | 62600 | 1.8178 | | 0.9756 | 836.0 | 62700 | 1.7941 | | 0.9756 | 837.3333 | 62800 | 1.7446 | | 0.9756 | 838.6667 | 62900 | 1.7396 | | 0.9814 | 840.0 | 63000 | 1.7364 | | 0.9814 | 841.3333 | 63100 | 1.7567 | | 0.9814 | 842.6667 | 63200 | 1.7456 | | 0.9814 | 844.0 | 63300 | 1.7258 | | 0.9814 | 845.3333 | 63400 | 1.7533 | | 0.9788 | 846.6667 | 63500 | 1.7578 | | 0.9788 | 848.0 | 63600 | 1.7655 | | 0.9788 | 849.3333 | 63700 | 1.7662 | | 0.9788 | 850.6667 | 63800 | 1.7634 | | 0.9788 | 852.0 | 63900 | 1.7632 | | 0.9764 | 853.3333 | 64000 | 1.7601 | | 0.9764 | 854.6667 | 64100 | 1.7544 | | 0.9764 | 856.0 | 64200 | 1.7494 | | 0.9764 | 857.3333 | 64300 | 1.7504 | | 0.9764 | 858.6667 | 64400 | 1.7478 | | 0.9679 | 860.0 | 64500 | 1.7418 | | 0.9679 | 861.3333 | 64600 | 1.7489 | | 0.9679 | 862.6667 | 64700 | 1.7406 | | 0.9679 | 864.0 | 64800 | 1.7420 | | 0.9679 | 865.3333 | 64900 | 1.7384 | | 0.9712 | 866.6667 | 65000 | 1.7425 | | 0.9712 | 868.0 | 65100 | 1.7456 | | 0.9712 | 869.3333 | 65200 | 1.7438 | | 0.9712 | 870.6667 | 65300 | 1.7426 | | 0.9712 | 872.0 | 65400 | 1.7444 | | 0.9858 | 873.3333 | 65500 | 1.7450 | | 0.9858 | 874.6667 | 65600 | 1.7455 | | 0.9858 | 876.0 | 65700 | 1.7523 | | 0.9858 | 877.3333 | 65800 | 1.7495 | | 0.9858 | 878.6667 | 65900 | 1.7484 | | 0.9741 | 880.0 | 66000 | 1.7534 | | 0.9741 | 881.3333 | 66100 | 1.7553 | | 0.9741 | 882.6667 | 66200 | 1.7525 | | 0.9741 | 884.0 | 66300 | 1.7524 | | 0.9741 | 885.3333 | 66400 | 1.7549 | | 0.9791 | 886.6667 | 66500 | 1.7520 | | 0.9791 | 888.0 | 66600 | 1.7501 | | 0.9791 | 889.3333 | 66700 | 1.7498 | | 0.9791 | 890.6667 | 66800 | 1.7464 | | 0.9791 | 892.0 | 66900 | 1.7526 | | 0.9866 | 893.3333 | 67000 | 1.7551 | | 0.9866 | 894.6667 | 67100 | 1.7563 | | 0.9866 | 896.0 | 67200 | 1.7578 | | 0.9866 | 897.3333 | 67300 | 1.7577 | | 0.9866 | 898.6667 | 67400 | 1.7585 | | 0.9886 | 900.0 | 67500 | 1.7605 | | 0.9886 | 901.3333 | 67600 | 1.7590 | | 0.9886 | 902.6667 | 67700 | 1.7606 | | 0.9886 | 904.0 | 67800 | 1.7571 | | 0.9886 | 905.3333 | 67900 | 1.7540 | | 0.9781 | 906.6667 | 68000 | 1.7557 | | 0.9781 | 908.0 | 68100 | 1.7576 | | 0.9781 | 909.3333 | 68200 | 1.7636 | | 0.9781 | 910.6667 | 68300 | 1.7624 | | 0.9781 | 912.0 | 68400 | 1.7664 | | 0.9754 | 913.3333 | 68500 | 1.7649 | | 0.9754 | 914.6667 | 68600 | 1.7645 | | 0.9754 | 916.0 | 68700 | 1.7646 | | 0.9754 | 917.3333 | 68800 | 1.7644 | | 0.9754 | 918.6667 | 68900 | 1.7620 | | 0.975 | 920.0 | 69000 | 1.7634 | | 0.975 | 921.3333 | 69100 | 1.7608 | | 0.975 | 922.6667 | 69200 | 1.7607 | | 0.975 | 924.0 | 69300 | 1.7627 | | 0.975 | 925.3333 | 69400 | 1.7658 | | 0.9695 | 926.6667 | 69500 | 1.7679 | | 0.9695 | 928.0 | 69600 | 1.7663 | | 0.9695 | 929.3333 | 69700 | 1.7646 | | 0.9695 | 930.6667 | 69800 | 1.7712 | | 0.9695 | 932.0 | 69900 | 1.7727 | | 0.9687 | 933.3333 | 70000 | 1.7744 | | 0.9687 | 934.6667 | 70100 | 1.7724 | | 0.9687 | 936.0 | 70200 | 1.7733 | | 0.9687 | 937.3333 | 70300 | 1.7753 | | 0.9687 | 938.6667 | 70400 | 1.7781 | | 0.9851 | 940.0 | 70500 | 1.7847 | | 0.9851 | 941.3333 | 70600 | 1.7847 | | 0.9851 | 942.6667 | 70700 | 1.7831 | | 0.9851 | 944.0 | 70800 | 1.7809 | | 0.9851 | 945.3333 | 70900 | 1.7873 | | 0.9675 | 946.6667 | 71000 | 1.7981 | | 0.9675 | 948.0 | 71100 | 1.7869 | | 0.9675 | 949.3333 | 71200 | 1.7895 | | 0.9675 | 950.6667 | 71300 | 1.7933 | | 0.9675 | 952.0 | 71400 | 1.8012 | | 0.9779 | 953.3333 | 71500 | 1.7844 | | 0.9779 | 954.6667 | 71600 | 1.7828 | | 0.9779 | 956.0 | 71700 | 1.7794 | | 0.9779 | 957.3333 | 71800 | 1.7819 | | 0.9779 | 958.6667 | 71900 | 1.7818 | | 0.9845 | 960.0 | 72000 | 1.7836 | | 0.9845 | 961.3333 | 72100 | 1.7782 | | 0.9845 | 962.6667 | 72200 | 1.7784 | | 0.9845 | 964.0 | 72300 | 1.7777 | | 0.9845 | 965.3333 | 72400 | 1.7767 | | 0.9718 | 966.6667 | 72500 | 1.7781 | | 0.9718 | 968.0 | 72600 | 1.7800 | | 0.9718 | 969.3333 | 72700 | 1.7817 | | 0.9718 | 970.6667 | 72800 | 1.7833 | | 0.9718 | 972.0 | 72900 | 1.7834 | | 0.9779 | 973.3333 | 73000 | 1.7839 | | 0.9779 | 974.6667 | 73100 | 1.7852 | | 0.9779 | 976.0 | 73200 | 1.7862 | | 0.9779 | 977.3333 | 73300 | 1.7873 | | 0.9779 | 978.6667 | 73400 | 1.7845 | | 0.9743 | 980.0 | 73500 | 1.7859 | | 0.9743 | 981.3333 | 73600 | 1.7844 | | 0.9743 | 982.6667 | 73700 | 1.7850 | | 0.9743 | 984.0 | 73800 | 1.7846 | | 0.9743 | 985.3333 | 73900 | 1.7853 | | 0.9786 | 986.6667 | 74000 | 1.7871 | | 0.9786 | 988.0 | 74100 | 1.7876 | | 0.9786 | 989.3333 | 74200 | 1.7873 | | 0.9786 | 990.6667 | 74300 | 1.7883 | | 0.9786 | 992.0 | 74400 | 1.7887 | | 0.9788 | 993.3333 | 74500 | 1.7889 | | 0.9788 | 994.6667 | 74600 | 1.7890 | | 0.9788 | 996.0 | 74700 | 1.7884 | | 0.9788 | 997.3333 | 74800 | 1.7885 | | 0.9788 | 998.6667 | 74900 | 1.7885 | | 0.9749 | 1000.0 | 75000 | 1.7885 | ### Framework versions - Transformers 4.50.0.dev0 - Pytorch 2.5.1 - Datasets 3.3.2 - Tokenizers 0.21.0