<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
es_fi_orig_quy
This model is a fine-tuned version of Helsinki-NLP/opus-mt-es-fi on the AmericasNLP2023 Original Task's dataset for Quechua. It achieves the following results on the evaluation set:
- Loss: 0.5414
- Bleu: 2.4777
- Chrf: 35.3072
- Gen Len: 33.2767
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf | Gen Len |
---|---|---|---|---|---|---|
0.9069 | 0.06 | 500 | 0.7130 | 0.7729 | 17.9749 | 44.4678 |
0.539 | 0.12 | 1000 | 0.6747 | 0.7711 | 20.5427 | 40.504 |
0.4832 | 0.18 | 1500 | 0.6461 | 0.8605 | 21.6266 | 40.7505 |
0.45 | 0.24 | 2000 | 0.6304 | 0.9152 | 22.8153 | 35.6489 |
0.4192 | 0.31 | 2500 | 0.6239 | 0.9358 | 23.6102 | 34.1469 |
0.4061 | 0.37 | 3000 | 0.6108 | 1.183 | 25.1705 | 34.0684 |
0.3864 | 0.43 | 3500 | 0.5939 | 1.2459 | 26.0102 | 33.6217 |
0.3762 | 0.49 | 4000 | 0.5876 | 1.3822 | 26.3468 | 33.7304 |
0.3669 | 0.55 | 4500 | 0.5796 | 1.6164 | 26.7314 | 32.5785 |
0.3591 | 0.61 | 5000 | 0.5795 | 1.2637 | 26.7829 | 31.6338 |
0.3471 | 0.67 | 5500 | 0.5758 | 1.6099 | 28.2004 | 33.7042 |
0.3368 | 0.73 | 6000 | 0.5678 | 1.5843 | 28.6728 | 36.1087 |
0.332 | 0.8 | 6500 | 0.5623 | 1.4817 | 28.141 | 33.2062 |
0.3305 | 0.86 | 7000 | 0.5592 | 1.6164 | 28.5089 | 33.7968 |
0.325 | 0.92 | 7500 | 0.5554 | 1.7755 | 29.4873 | 33.659 |
0.3148 | 0.98 | 8000 | 0.5534 | 1.4771 | 29.2475 | 32.9517 |
0.306 | 1.04 | 8500 | 0.5503 | 1.6723 | 30.3463 | 34.3541 |
0.2999 | 1.1 | 9000 | 0.5498 | 1.7604 | 30.4026 | 34.3531 |
0.2979 | 1.16 | 9500 | 0.5470 | 1.6658 | 30.6424 | 34.3038 |
0.2875 | 1.22 | 10000 | 0.5447 | 1.6232 | 30.6178 | 32.7374 |
0.2885 | 1.29 | 10500 | 0.5468 | 1.4892 | 30.536 | 33.5704 |
0.2914 | 1.35 | 11000 | 0.5397 | 1.7088 | 30.4463 | 32.665 |
0.2873 | 1.41 | 11500 | 0.5385 | 1.4307 | 31.359 | 32.6006 |
0.2821 | 1.47 | 12000 | 0.5391 | 1.6375 | 31.2201 | 33.7616 |
0.2813 | 1.53 | 12500 | 0.5343 | 1.7664 | 31.2716 | 32.8048 |
0.2795 | 1.59 | 13000 | 0.5390 | 1.6373 | 31.4692 | 33.2354 |
0.2766 | 1.65 | 13500 | 0.5333 | 1.6973 | 31.9842 | 34.3099 |
0.2726 | 1.71 | 14000 | 0.5342 | 1.9934 | 32.0932 | 34.7022 |
0.2696 | 1.77 | 14500 | 0.5316 | 1.7776 | 32.1299 | 33.3531 |
0.2732 | 1.84 | 15000 | 0.5274 | 1.5068 | 32.156 | 33.7404 |
0.2732 | 1.9 | 15500 | 0.5281 | 1.8983 | 32.123 | 32.7274 |
0.2695 | 1.96 | 16000 | 0.5285 | 1.7102 | 32.3456 | 34.7596 |
0.2609 | 2.02 | 16500 | 0.5299 | 1.8289 | 32.4311 | 32.169 |
0.2566 | 2.08 | 17000 | 0.5259 | 2.3307 | 32.4029 | 32.6801 |
0.2546 | 2.14 | 17500 | 0.5262 | 1.7847 | 32.4796 | 32.5594 |
0.2575 | 2.2 | 18000 | 0.5278 | 1.7378 | 32.6314 | 33.5493 |
0.2537 | 2.26 | 18500 | 0.5256 | 1.8299 | 32.4598 | 32.7515 |
0.2496 | 2.33 | 19000 | 0.5269 | 1.4243 | 32.4538 | 32.6368 |
0.2492 | 2.39 | 19500 | 0.5264 | 1.7878 | 32.4759 | 32.7958 |
0.2511 | 2.45 | 20000 | 0.5230 | 1.7877 | 32.7906 | 33.0956 |
0.2502 | 2.51 | 20500 | 0.5211 | 1.8735 | 33.2824 | 34.0503 |
0.2468 | 2.57 | 21000 | 0.5227 | 2.0487 | 33.1002 | 32.9849 |
0.2445 | 2.63 | 21500 | 0.5206 | 2.0547 | 33.3626 | 32.7867 |
0.2455 | 2.69 | 22000 | 0.5202 | 1.968 | 33.0031 | 32.9658 |
0.2489 | 2.75 | 22500 | 0.5195 | 2.0145 | 32.9789 | 32.5926 |
0.2385 | 2.82 | 23000 | 0.5180 | 2.0486 | 33.2563 | 33.337 |
0.2421 | 2.88 | 23500 | 0.5162 | 2.1097 | 33.0014 | 33.4105 |
0.2414 | 2.94 | 24000 | 0.5148 | 1.9033 | 33.1448 | 33.4175 |
0.2445 | 3.0 | 24500 | 0.5207 | 1.8791 | 32.9875 | 32.8018 |
0.2329 | 3.06 | 25000 | 0.5216 | 2.2176 | 33.6869 | 33.8642 |
0.2289 | 3.12 | 25500 | 0.5160 | 1.8891 | 33.3863 | 32.2857 |
0.2336 | 3.18 | 26000 | 0.5144 | 2.0862 | 33.4626 | 33.6097 |
0.2279 | 3.24 | 26500 | 0.5163 | 2.1618 | 33.7683 | 32.8773 |
0.2308 | 3.3 | 27000 | 0.5188 | 2.3628 | 34.06 | 33.7133 |
0.2313 | 3.37 | 27500 | 0.5188 | 1.6833 | 33.9596 | 33.7032 |
0.2308 | 3.43 | 28000 | 0.5165 | 2.1626 | 33.651 | 33.4507 |
0.2238 | 3.49 | 28500 | 0.5162 | 1.8525 | 33.2934 | 32.3511 |
0.2263 | 3.55 | 29000 | 0.5163 | 2.0621 | 33.4168 | 32.8561 |
0.2265 | 3.61 | 29500 | 0.5134 | 2.361 | 34.0822 | 33.0272 |
0.2256 | 3.67 | 30000 | 0.5128 | 2.289 | 33.938 | 33.6016 |
0.2277 | 3.73 | 30500 | 0.5153 | 1.8415 | 33.7406 | 34.1761 |
0.227 | 3.79 | 31000 | 0.5130 | 2.0473 | 33.2757 | 33.3571 |
0.2296 | 3.86 | 31500 | 0.5140 | 1.9687 | 33.6899 | 33.1459 |
0.2256 | 3.92 | 32000 | 0.5145 | 2.1504 | 33.8796 | 33.6278 |
0.2279 | 3.98 | 32500 | 0.5101 | 1.802 | 33.982 | 33.2414 |
0.2172 | 4.04 | 33000 | 0.5180 | 2.3048 | 34.348 | 33.167 |
0.2135 | 4.1 | 33500 | 0.5154 | 2.2467 | 34.1301 | 33.0382 |
0.2154 | 4.16 | 34000 | 0.5159 | 1.9384 | 34.2688 | 33.5855 |
0.2169 | 4.22 | 34500 | 0.5177 | 2.3588 | 34.2068 | 33.3954 |
0.216 | 4.28 | 35000 | 0.5160 | 2.0115 | 33.7004 | 33.3612 |
0.216 | 4.35 | 35500 | 0.5139 | 1.5035 | 33.8102 | 32.6217 |
0.2139 | 4.41 | 36000 | 0.5126 | 2.359 | 34.1215 | 33.6761 |
0.2168 | 4.47 | 36500 | 0.5105 | 2.1176 | 33.7094 | 32.5352 |
0.2155 | 4.53 | 37000 | 0.5144 | 2.1564 | 33.3474 | 32.1881 |
0.2156 | 4.59 | 37500 | 0.5118 | 2.0 | 33.9916 | 32.9537 |
0.2135 | 4.65 | 38000 | 0.5124 | 2.3122 | 34.095 | 32.667 |
0.2138 | 4.71 | 38500 | 0.5115 | 1.9716 | 33.9118 | 32.5644 |
0.2107 | 4.77 | 39000 | 0.5145 | 2.2866 | 34.4234 | 33.2153 |
0.2083 | 4.83 | 39500 | 0.5122 | 2.0444 | 34.6246 | 33.8491 |
0.2141 | 4.9 | 40000 | 0.5125 | 2.0011 | 34.6505 | 33.7384 |
0.2087 | 4.96 | 40500 | 0.5149 | 2.3504 | 34.1777 | 33.339 |
0.2113 | 5.02 | 41000 | 0.5160 | 2.2727 | 34.0993 | 33.4779 |
0.2019 | 5.08 | 41500 | 0.5143 | 2.3324 | 34.613 | 33.4376 |
0.206 | 5.14 | 42000 | 0.5154 | 2.1462 | 34.758 | 33.4437 |
0.2013 | 5.2 | 42500 | 0.5175 | 2.3562 | 34.2422 | 32.3511 |
0.2032 | 5.26 | 43000 | 0.5160 | 2.3984 | 34.645 | 32.5604 |
0.2068 | 5.32 | 43500 | 0.5159 | 2.2794 | 34.4269 | 32.8742 |
0.204 | 5.39 | 44000 | 0.5132 | 2.3506 | 34.7618 | 33.9487 |
0.2028 | 5.45 | 44500 | 0.5153 | 2.4088 | 34.9393 | 33.5131 |
0.2004 | 5.51 | 45000 | 0.5172 | 2.4071 | 34.3887 | 33.1006 |
0.2021 | 5.57 | 45500 | 0.5106 | 2.0544 | 34.1071 | 33.7404 |
0.2058 | 5.63 | 46000 | 0.5126 | 1.9098 | 34.6397 | 33.7807 |
0.2015 | 5.69 | 46500 | 0.5115 | 2.3614 | 34.25 | 32.8571 |
0.2038 | 5.75 | 47000 | 0.5094 | 2.0321 | 34.1132 | 32.6932 |
0.2021 | 5.81 | 47500 | 0.5147 | 2.2524 | 34.7776 | 33.4276 |
0.2041 | 5.88 | 48000 | 0.5154 | 2.2605 | 34.323 | 32.9769 |
0.2009 | 5.94 | 48500 | 0.5137 | 2.2593 | 34.8502 | 33.499 |
0.2025 | 6.0 | 49000 | 0.5103 | 2.3048 | 34.4908 | 33.4789 |
0.193 | 6.06 | 49500 | 0.5170 | 2.1498 | 34.3672 | 33.3612 |
0.193 | 6.12 | 50000 | 0.5151 | 2.5941 | 34.9481 | 33.336 |
0.1936 | 6.18 | 50500 | 0.5169 | 2.2235 | 34.6028 | 32.5744 |
0.196 | 6.24 | 51000 | 0.5162 | 2.2306 | 34.6904 | 32.4517 |
0.1949 | 6.3 | 51500 | 0.5129 | 2.3903 | 35.1637 | 33.2113 |
0.194 | 6.36 | 52000 | 0.5134 | 2.1318 | 34.7602 | 33.5885 |
0.1941 | 6.43 | 52500 | 0.5152 | 2.3425 | 34.4858 | 32.9135 |
0.1935 | 6.49 | 53000 | 0.5145 | 2.6653 | 35.0061 | 32.8984 |
0.191 | 6.55 | 53500 | 0.5134 | 2.2906 | 34.8134 | 33.5412 |
0.1971 | 6.61 | 54000 | 0.5188 | 2.1944 | 34.8164 | 33.1378 |
0.1951 | 6.67 | 54500 | 0.5130 | 2.4214 | 34.5857 | 32.8249 |
0.1921 | 6.73 | 55000 | 0.5137 | 2.2722 | 34.8066 | 32.6298 |
0.1928 | 6.79 | 55500 | 0.5136 | 2.316 | 34.7798 | 34.0654 |
0.1945 | 6.85 | 56000 | 0.5114 | 2.1866 | 34.8094 | 32.6922 |
0.1936 | 6.92 | 56500 | 0.5133 | 2.3216 | 34.6351 | 33.0805 |
0.1957 | 6.98 | 57000 | 0.5123 | 2.2095 | 34.9906 | 33.8893 |
0.1888 | 7.04 | 57500 | 0.5172 | 2.2208 | 34.772 | 33.334 |
0.1842 | 7.1 | 58000 | 0.5167 | 1.9387 | 34.6291 | 32.6278 |
0.1866 | 7.16 | 58500 | 0.5154 | 2.1733 | 35.019 | 32.8179 |
0.1869 | 7.22 | 59000 | 0.5187 | 2.0185 | 34.7933 | 33.4386 |
0.1851 | 7.28 | 59500 | 0.5158 | 2.2565 | 34.9985 | 33.3934 |
0.1846 | 7.34 | 60000 | 0.5182 | 2.087 | 35.3032 | 33.6207 |
0.1844 | 7.41 | 60500 | 0.5163 | 2.2813 | 34.9024 | 33.1127 |
0.1888 | 7.47 | 61000 | 0.5140 | 2.3832 | 35.0925 | 33.4527 |
0.1883 | 7.53 | 61500 | 0.5140 | 2.4389 | 35.3911 | 33.0121 |
0.1866 | 7.59 | 62000 | 0.5186 | 2.1768 | 35.0476 | 33.331 |
0.1854 | 7.65 | 62500 | 0.5182 | 2.1011 | 34.9619 | 33.7274 |
0.1895 | 7.71 | 63000 | 0.5166 | 2.2003 | 35.1485 | 33.2384 |
0.1907 | 7.77 | 63500 | 0.5167 | 2.1704 | 34.7886 | 33.1499 |
0.1868 | 7.83 | 64000 | 0.5177 | 2.4642 | 35.3304 | 33.494 |
0.1845 | 7.89 | 64500 | 0.5185 | 1.8674 | 35.2574 | 33.5372 |
0.1853 | 7.96 | 65000 | 0.5139 | 2.2624 | 35.2208 | 33.5604 |
0.1843 | 8.02 | 65500 | 0.5198 | 2.3718 | 35.0122 | 33.2485 |
0.1792 | 8.08 | 66000 | 0.5195 | 2.2219 | 34.6203 | 33.008 |
0.1813 | 8.14 | 66500 | 0.5213 | 2.2907 | 34.9642 | 33.4889 |
0.1783 | 8.2 | 67000 | 0.5181 | 2.4924 | 35.0622 | 32.996 |
0.1793 | 8.26 | 67500 | 0.5177 | 2.521 | 35.1152 | 33.3652 |
0.1815 | 8.32 | 68000 | 0.5197 | 2.186 | 34.9455 | 32.8964 |
0.1807 | 8.38 | 68500 | 0.5203 | 2.0672 | 34.8115 | 32.9658 |
0.1793 | 8.45 | 69000 | 0.5209 | 1.8363 | 35.0798 | 33.0674 |
0.1799 | 8.51 | 69500 | 0.5196 | 2.3825 | 35.3234 | 33.9738 |
0.179 | 8.57 | 70000 | 0.5219 | 2.275 | 34.7929 | 32.8239 |
0.1783 | 8.63 | 70500 | 0.5197 | 2.3194 | 35.0171 | 33.6288 |
0.1813 | 8.69 | 71000 | 0.5171 | 2.2258 | 35.1631 | 33.3873 |
0.1809 | 8.75 | 71500 | 0.5190 | 2.5308 | 35.1173 | 33.34 |
0.1805 | 8.81 | 72000 | 0.5171 | 1.9332 | 35.0571 | 32.9678 |
0.1786 | 8.87 | 72500 | 0.5157 | 2.2382 | 35.0783 | 32.9406 |
0.1811 | 8.94 | 73000 | 0.5201 | 2.2583 | 35.0626 | 33.4859 |
0.1804 | 9.0 | 73500 | 0.5177 | 2.278 | 34.693 | 33.1942 |
0.1745 | 9.06 | 74000 | 0.5210 | 2.2431 | 35.1854 | 33.6841 |
0.1731 | 9.12 | 74500 | 0.5219 | 2.3838 | 35.0609 | 33.7626 |
0.1745 | 9.18 | 75000 | 0.5205 | 2.3049 | 35.049 | 33.2394 |
0.1733 | 9.24 | 75500 | 0.5239 | 2.5352 | 35.2192 | 33.8048 |
0.1749 | 9.3 | 76000 | 0.5216 | 2.3165 | 34.7239 | 33.1087 |
0.1726 | 9.36 | 76500 | 0.5214 | 2.4599 | 34.9216 | 33.4487 |
0.175 | 9.42 | 77000 | 0.5245 | 2.5992 | 35.0381 | 33.1167 |
0.1753 | 9.49 | 77500 | 0.5248 | 2.2165 | 34.9097 | 33.1529 |
0.1751 | 9.55 | 78000 | 0.5208 | 2.7439 | 35.1761 | 33.2123 |
0.1751 | 9.61 | 78500 | 0.5207 | 2.5099 | 35.1488 | 32.8642 |
0.1729 | 9.67 | 79000 | 0.5239 | 2.534 | 35.0639 | 33.3682 |
0.1763 | 9.73 | 79500 | 0.5228 | 2.3696 | 34.5217 | 32.669 |
0.1719 | 9.79 | 80000 | 0.5241 | 2.4858 | 34.8637 | 33.2716 |
0.1753 | 9.85 | 80500 | 0.5204 | 2.3656 | 34.9314 | 32.7535 |
0.177 | 9.91 | 81000 | 0.5197 | 2.2903 | 35.0575 | 33.0634 |
0.1752 | 9.98 | 81500 | 0.5238 | 2.1415 | 34.9044 | 33.0392 |
0.1695 | 10.04 | 82000 | 0.5237 | 2.1674 | 34.9343 | 33.0926 |
0.1696 | 10.1 | 82500 | 0.5254 | 2.5423 | 34.91 | 33.0322 |
0.1667 | 10.16 | 83000 | 0.5278 | 1.9003 | 34.8527 | 32.7414 |
0.1701 | 10.22 | 83500 | 0.5283 | 2.4784 | 34.913 | 32.832 |
0.1689 | 10.28 | 84000 | 0.5232 | 2.492 | 35.2142 | 33.2374 |
0.1706 | 10.34 | 84500 | 0.5262 | 2.5049 | 35.2206 | 33.2817 |
0.1698 | 10.4 | 85000 | 0.5239 | 2.3618 | 34.9215 | 32.8119 |
0.1717 | 10.47 | 85500 | 0.5265 | 2.4575 | 34.9778 | 32.6026 |
0.1678 | 10.53 | 86000 | 0.5249 | 2.3199 | 34.8019 | 33.3028 |
0.1703 | 10.59 | 86500 | 0.5219 | 2.4114 | 34.9716 | 33.3089 |
0.1708 | 10.65 | 87000 | 0.5239 | 2.0047 | 34.8404 | 32.7777 |
0.1704 | 10.71 | 87500 | 0.5253 | 2.5167 | 35.2791 | 33.4588 |
0.1692 | 10.77 | 88000 | 0.5242 | 2.5192 | 35.1455 | 33.006 |
0.172 | 10.83 | 88500 | 0.5218 | 2.2699 | 35.1763 | 33.326 |
0.1712 | 10.89 | 89000 | 0.5246 | 2.332 | 35.2355 | 33.1247 |
0.1669 | 10.95 | 89500 | 0.5227 | 2.2954 | 35.279 | 33.2746 |
0.1663 | 11.02 | 90000 | 0.5250 | 2.4965 | 35.2613 | 33.3421 |
0.1653 | 11.08 | 90500 | 0.5278 | 2.324 | 35.1194 | 33.328 |
0.1656 | 11.14 | 91000 | 0.5257 | 2.2204 | 35.0059 | 33.1922 |
0.1643 | 11.2 | 91500 | 0.5261 | 2.2693 | 34.9625 | 33.2324 |
0.1654 | 11.26 | 92000 | 0.5271 | 2.5063 | 35.3606 | 33.4738 |
0.1634 | 11.32 | 92500 | 0.5255 | 2.303 | 35.0965 | 33.4688 |
0.1653 | 11.38 | 93000 | 0.5259 | 2.4993 | 34.8866 | 33.164 |
0.1662 | 11.44 | 93500 | 0.5257 | 2.0667 | 35.0151 | 33.505 |
0.1632 | 11.51 | 94000 | 0.5254 | 2.5568 | 35.0299 | 33.3883 |
0.1652 | 11.57 | 94500 | 0.5278 | 2.5814 | 34.992 | 32.5664 |
0.1639 | 11.63 | 95000 | 0.5304 | 2.41 | 34.9007 | 33.161 |
0.1622 | 11.69 | 95500 | 0.5247 | 2.4703 | 34.993 | 32.9457 |
0.1673 | 11.75 | 96000 | 0.5268 | 2.3927 | 35.0372 | 33.2938 |
0.1677 | 11.81 | 96500 | 0.5281 | 2.6505 | 34.8506 | 32.494 |
0.165 | 11.87 | 97000 | 0.5303 | 2.4796 | 35.0554 | 33.2183 |
0.1662 | 11.93 | 97500 | 0.5254 | 2.5202 | 35.1451 | 33.5986 |
0.1658 | 12.0 | 98000 | 0.5277 | 2.2551 | 35.2497 | 33.4869 |
0.1603 | 12.06 | 98500 | 0.5288 | 2.5281 | 35.103 | 33.338 |
0.1614 | 12.12 | 99000 | 0.5304 | 2.3583 | 35.3678 | 33.008 |
0.1585 | 12.18 | 99500 | 0.5289 | 2.1341 | 34.9736 | 33.2284 |
0.1616 | 12.24 | 100000 | 0.5299 | 2.2275 | 35.3401 | 33.5322 |
0.1592 | 12.3 | 100500 | 0.5268 | 2.1927 | 35.1932 | 33.5322 |
0.1606 | 12.36 | 101000 | 0.5315 | 2.2762 | 34.8855 | 33.2002 |
0.1617 | 12.42 | 101500 | 0.5304 | 1.919 | 35.2037 | 33.4688 |
0.1617 | 12.48 | 102000 | 0.5276 | 2.3777 | 35.0109 | 33.0724 |
0.1618 | 12.55 | 102500 | 0.5320 | 2.4878 | 35.1188 | 33.0674 |
0.163 | 12.61 | 103000 | 0.5296 | 2.6783 | 35.09 | 33.3632 |
0.1601 | 12.67 | 103500 | 0.5295 | 2.5972 | 34.8251 | 32.7837 |
0.1625 | 12.73 | 104000 | 0.5308 | 2.5953 | 34.816 | 33.2223 |
0.1628 | 12.79 | 104500 | 0.5291 | 2.6627 | 34.9021 | 33.1046 |
0.1594 | 12.85 | 105000 | 0.5320 | 2.185 | 35.2024 | 33.499 |
0.1641 | 12.91 | 105500 | 0.5282 | 2.2681 | 35.1077 | 33.2918 |
0.1632 | 12.97 | 106000 | 0.5267 | 2.6085 | 34.9718 | 33.0453 |
0.1592 | 13.04 | 106500 | 0.5314 | 2.6758 | 34.8983 | 33.1539 |
0.1593 | 13.1 | 107000 | 0.5336 | 2.431 | 34.8698 | 33.0624 |
0.1567 | 13.16 | 107500 | 0.5336 | 2.4034 | 34.7205 | 32.9245 |
0.1613 | 13.22 | 108000 | 0.5319 | 2.4685 | 35.1304 | 33.0493 |
0.1572 | 13.28 | 108500 | 0.5319 | 2.701 | 34.8217 | 33.0201 |
0.1586 | 13.34 | 109000 | 0.5324 | 2.6884 | 34.9147 | 32.8109 |
0.1565 | 13.4 | 109500 | 0.5327 | 1.9804 | 35.0132 | 33.2978 |
0.1578 | 13.46 | 110000 | 0.5310 | 2.4774 | 35.0983 | 33.4085 |
0.1593 | 13.53 | 110500 | 0.5310 | 2.5479 | 35.4449 | 33.7062 |
0.1559 | 13.59 | 111000 | 0.5338 | 2.3537 | 34.9088 | 33.0433 |
0.1592 | 13.65 | 111500 | 0.5321 | 2.2951 | 34.9337 | 32.7264 |
0.1599 | 13.71 | 112000 | 0.5323 | 2.1814 | 35.0657 | 33.4316 |
0.1549 | 13.77 | 112500 | 0.5343 | 2.4706 | 35.0882 | 33.4628 |
0.1583 | 13.83 | 113000 | 0.5296 | 2.5468 | 35.0331 | 32.9386 |
0.1579 | 13.89 | 113500 | 0.5303 | 2.6679 | 35.309 | 32.996 |
0.1582 | 13.95 | 114000 | 0.5323 | 2.4064 | 35.1723 | 33.2555 |
0.1563 | 14.01 | 114500 | 0.5348 | 2.4503 | 35.111 | 33.4195 |
0.1517 | 14.08 | 115000 | 0.5355 | 2.5443 | 35.3299 | 33.5372 |
0.1537 | 14.14 | 115500 | 0.5350 | 2.354 | 34.975 | 33.3089 |
0.1549 | 14.2 | 116000 | 0.5354 | 2.6566 | 34.9697 | 33.3561 |
0.154 | 14.26 | 116500 | 0.5342 | 2.5811 | 34.9067 | 33.338 |
0.1562 | 14.32 | 117000 | 0.5334 | 2.8386 | 35.1147 | 33.0634 |
0.1555 | 14.38 | 117500 | 0.5356 | 2.621 | 35.235 | 33.332 |
0.1551 | 14.44 | 118000 | 0.5345 | 2.6434 | 34.9156 | 32.9759 |
0.1553 | 14.5 | 118500 | 0.5343 | 2.8222 | 35.0846 | 33.336 |
0.1548 | 14.57 | 119000 | 0.5341 | 2.5853 | 34.8771 | 32.9306 |
0.1545 | 14.63 | 119500 | 0.5334 | 2.608 | 35.1324 | 33.1569 |
0.1565 | 14.69 | 120000 | 0.5333 | 2.3449 | 35.2465 | 33.3008 |
0.1578 | 14.75 | 120500 | 0.5334 | 2.4331 | 35.0261 | 33.1268 |
0.1565 | 14.81 | 121000 | 0.5338 | 2.5126 | 35.1174 | 33.0855 |
0.1576 | 14.87 | 121500 | 0.5319 | 2.643 | 35.2291 | 33.3461 |
0.1535 | 14.93 | 122000 | 0.5318 | 2.6643 | 35.0675 | 33.0835 |
0.1544 | 14.99 | 122500 | 0.5328 | 2.7986 | 35.221 | 33.4517 |
0.1527 | 15.06 | 123000 | 0.5364 | 2.433 | 35.3005 | 33.6217 |
0.1531 | 15.12 | 123500 | 0.5367 | 2.4569 | 35.1446 | 33.2706 |
0.1512 | 15.18 | 124000 | 0.5369 | 2.5325 | 34.9011 | 32.994 |
0.1511 | 15.24 | 124500 | 0.5378 | 2.4247 | 35.0081 | 32.9517 |
0.1494 | 15.3 | 125000 | 0.5354 | 2.6675 | 35.2802 | 33.3451 |
0.1513 | 15.36 | 125500 | 0.5380 | 2.706 | 35.3454 | 32.9779 |
0.1556 | 15.42 | 126000 | 0.5349 | 2.6606 | 35.2983 | 33.2384 |
0.152 | 15.48 | 126500 | 0.5374 | 2.7716 | 35.1135 | 33.1429 |
0.1539 | 15.54 | 127000 | 0.5357 | 2.4622 | 35.1187 | 33.0302 |
0.1522 | 15.61 | 127500 | 0.5376 | 2.7958 | 35.2546 | 33.1489 |
0.155 | 15.67 | 128000 | 0.5366 | 2.4966 | 34.9292 | 32.7143 |
0.1523 | 15.73 | 128500 | 0.5347 | 2.5537 | 34.9162 | 33.1046 |
0.1554 | 15.79 | 129000 | 0.5349 | 2.7393 | 35.1069 | 33.2082 |
0.1527 | 15.85 | 129500 | 0.5361 | 2.3551 | 35.2359 | 33.3893 |
0.1532 | 15.91 | 130000 | 0.5373 | 2.3327 | 35.0024 | 33.0141 |
0.1505 | 15.97 | 130500 | 0.5386 | 2.4325 | 34.8422 | 32.827 |
0.1519 | 16.03 | 131000 | 0.5370 | 2.7083 | 35.196 | 33.0744 |
0.1492 | 16.1 | 131500 | 0.5382 | 2.4176 | 35.2017 | 33.1509 |
0.1502 | 16.16 | 132000 | 0.5382 | 1.9908 | 34.9532 | 33.1026 |
0.1505 | 16.22 | 132500 | 0.5378 | 2.3938 | 34.8257 | 33.1398 |
0.1497 | 16.28 | 133000 | 0.5394 | 2.5119 | 35.1199 | 33.3139 |
0.15 | 16.34 | 133500 | 0.5381 | 2.5172 | 35.0647 | 32.9718 |
0.1501 | 16.4 | 134000 | 0.5387 | 2.6483 | 35.1301 | 33.3139 |
0.1496 | 16.46 | 134500 | 0.5387 | 2.3792 | 35.0936 | 33.1358 |
0.1507 | 16.52 | 135000 | 0.5383 | 2.2621 | 35.3078 | 33.3763 |
0.1493 | 16.59 | 135500 | 0.5389 | 2.744 | 35.3558 | 33.2525 |
0.1494 | 16.65 | 136000 | 0.5386 | 2.3218 | 35.0754 | 33.2425 |
0.1516 | 16.71 | 136500 | 0.5395 | 2.3908 | 34.9863 | 33.0302 |
0.1491 | 16.77 | 137000 | 0.5397 | 2.4509 | 35.0017 | 33.4044 |
0.1512 | 16.83 | 137500 | 0.5395 | 2.5314 | 35.0975 | 33.2042 |
0.1509 | 16.89 | 138000 | 0.5389 | 2.4688 | 34.8711 | 33.0493 |
0.1517 | 16.95 | 138500 | 0.5388 | 2.3796 | 35.1383 | 33.1982 |
0.1516 | 17.01 | 139000 | 0.5396 | 2.5719 | 34.9446 | 33.4195 |
0.1467 | 17.07 | 139500 | 0.5406 | 2.76 | 34.9953 | 33.2525 |
0.1498 | 17.14 | 140000 | 0.5410 | 2.4061 | 35.1196 | 33.0946 |
0.1491 | 17.2 | 140500 | 0.5396 | 2.6469 | 35.2868 | 33.5473 |
0.1492 | 17.26 | 141000 | 0.5411 | 2.5395 | 35.1808 | 33.4225 |
0.1506 | 17.32 | 141500 | 0.5405 | 2.5481 | 35.1489 | 33.5111 |
0.1461 | 17.38 | 142000 | 0.5417 | 2.3111 | 35.0102 | 33.1278 |
0.1505 | 17.44 | 142500 | 0.5401 | 2.4497 | 35.0826 | 33.4175 |
0.1477 | 17.5 | 143000 | 0.5389 | 2.5452 | 34.9631 | 33.3109 |
0.1476 | 17.56 | 143500 | 0.5418 | 2.7374 | 34.8662 | 32.9044 |
0.1489 | 17.63 | 144000 | 0.5403 | 2.5838 | 35.0227 | 33.0513 |
0.1499 | 17.69 | 144500 | 0.5397 | 2.4883 | 35.3753 | 33.3028 |
0.1459 | 17.75 | 145000 | 0.5393 | 2.3722 | 35.0427 | 33.1268 |
0.1473 | 17.81 | 145500 | 0.5401 | 2.6967 | 34.9388 | 33.3672 |
0.1484 | 17.87 | 146000 | 0.5406 | 2.5086 | 34.9813 | 33.0734 |
0.1489 | 17.93 | 146500 | 0.5403 | 2.7184 | 35.1614 | 33.1137 |
0.1488 | 17.99 | 147000 | 0.5413 | 2.7788 | 35.2434 | 33.5201 |
0.1462 | 18.05 | 147500 | 0.5415 | 2.7858 | 35.1306 | 33.3521 |
0.148 | 18.12 | 148000 | 0.5406 | 2.7313 | 34.9823 | 32.9588 |
0.1459 | 18.18 | 148500 | 0.5414 | 2.4159 | 35.047 | 33.2455 |
0.1492 | 18.24 | 149000 | 0.5412 | 2.4617 | 35.0451 | 33.2213 |
0.1466 | 18.3 | 149500 | 0.5411 | 2.3902 | 35.0494 | 33.1901 |
0.1475 | 18.36 | 150000 | 0.5406 | 2.6175 | 35.0336 | 32.9909 |
0.1453 | 18.42 | 150500 | 0.5407 | 2.4948 | 35.0448 | 32.9366 |
0.1443 | 18.48 | 151000 | 0.5403 | 2.6749 | 35.1871 | 33.1861 |
0.1473 | 18.54 | 151500 | 0.5401 | 2.5487 | 35.2026 | 33.0604 |
0.1456 | 18.6 | 152000 | 0.5398 | 2.5826 | 35.0012 | 32.9879 |
0.1467 | 18.67 | 152500 | 0.5398 | 2.4385 | 35.0235 | 33.0201 |
0.1483 | 18.73 | 153000 | 0.5410 | 2.5969 | 34.9183 | 33.0543 |
0.1484 | 18.79 | 153500 | 0.5414 | 2.707 | 35.163 | 33.2093 |
0.1486 | 18.85 | 154000 | 0.5400 | 2.4765 | 35.0631 | 33.0573 |
0.1477 | 18.91 | 154500 | 0.5403 | 2.5421 | 35.1549 | 32.9346 |
0.148 | 18.97 | 155000 | 0.5414 | 2.4963 | 34.9687 | 33.1298 |
0.1457 | 19.03 | 155500 | 0.5418 | 2.5232 | 34.9675 | 32.9577 |
0.1464 | 19.09 | 156000 | 0.5416 | 2.4857 | 35.1609 | 33.2978 |
0.1462 | 19.16 | 156500 | 0.5414 | 2.6489 | 35.1326 | 33.2233 |
0.1443 | 19.22 | 157000 | 0.5421 | 2.6008 | 35.218 | 33.2555 |
0.1447 | 19.28 | 157500 | 0.5415 | 2.4443 | 34.9947 | 33.1328 |
0.146 | 19.34 | 158000 | 0.5415 | 2.6343 | 35.1218 | 33.159 |
0.146 | 19.4 | 158500 | 0.5419 | 2.6944 | 35.2223 | 33.3722 |
0.1458 | 19.46 | 159000 | 0.5419 | 2.4237 | 35.1222 | 33.2646 |
0.1459 | 19.52 | 159500 | 0.5422 | 2.6489 | 35.0196 | 33.1811 |
0.1481 | 19.58 | 160000 | 0.5423 | 2.5228 | 35.1774 | 33.3209 |
0.145 | 19.65 | 160500 | 0.5419 | 2.6893 | 35.2431 | 33.1841 |
0.1463 | 19.71 | 161000 | 0.5415 | 2.5176 | 35.1588 | 33.2847 |
0.1465 | 19.77 | 161500 | 0.5413 | 2.6651 | 35.295 | 33.2686 |
0.1463 | 19.83 | 162000 | 0.5413 | 2.472 | 35.3013 | 33.2968 |
0.1455 | 19.89 | 162500 | 0.5415 | 2.4636 | 35.2344 | 33.2455 |
0.1473 | 19.95 | 163000 | 0.5414 | 2.4777 | 35.3072 | 33.2767 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3