--- license: apache-2.0 tags: - generated_from_trainer metrics: - bleu model-index: - name: es_en_orig_quy results: [] --- # es_en_orig_quy This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-en](https://huggingface.co/Helsinki-NLP/opus-mt-es-en) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6309 - Bleu: 2.751 - Chrf: 34.8573 - Gen Len: 28.8089 ## 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 | |:-------------:|:-----:|:------:|:---------------:|:------:|:-------:|:-------:| | 1.0473 | 0.06 | 500 | 0.8214 | 0.7111 | 17.0433 | 36.2626 | | 0.6378 | 0.12 | 1000 | 0.7779 | 1.4359 | 20.4891 | 29.9628 | | 0.573 | 0.18 | 1500 | 0.7528 | 1.119 | 18.8909 | 31.7354 | | 0.536 | 0.24 | 2000 | 0.7324 | 1.0531 | 21.6629 | 28.5372 | | 0.4989 | 0.31 | 2500 | 0.7180 | 1.2347 | 22.7997 | 29.7867 | | 0.4878 | 0.37 | 3000 | 0.7022 | 1.3464 | 24.4726 | 29.668 | | 0.463 | 0.43 | 3500 | 0.6895 | 1.1066 | 23.793 | 28.5423 | | 0.4509 | 0.49 | 4000 | 0.6807 | 1.7455 | 25.5336 | 27.4074 | | 0.4401 | 0.55 | 4500 | 0.6711 | 1.3845 | 25.1955 | 26.3813 | | 0.4319 | 0.61 | 5000 | 0.6644 | 1.6155 | 26.1489 | 27.1942 | | 0.4188 | 0.67 | 5500 | 0.6625 | 1.7162 | 27.3032 | 29.4437 | | 0.4055 | 0.73 | 6000 | 0.6537 | 1.7053 | 27.2539 | 27.8048 | | 0.3994 | 0.8 | 6500 | 0.6531 | 1.8675 | 27.4833 | 27.1419 | | 0.3977 | 0.86 | 7000 | 0.6516 | 1.8732 | 27.8791 | 27.5674 | | 0.3928 | 0.92 | 7500 | 0.6468 | 1.991 | 28.6175 | 27.6549 | | 0.3795 | 0.98 | 8000 | 0.6455 | 2.1076 | 28.2005 | 31.829 | | 0.3677 | 1.04 | 8500 | 0.6411 | 1.991 | 29.4649 | 28.8431 | | 0.3609 | 1.1 | 9000 | 0.6364 | 2.0195 | 29.2979 | 29.0986 | | 0.3599 | 1.16 | 9500 | 0.6340 | 1.9495 | 29.3148 | 27.7485 | | 0.3461 | 1.22 | 10000 | 0.6301 | 1.9755 | 30.2666 | 28.998 | | 0.3494 | 1.29 | 10500 | 0.6337 | 2.0774 | 29.7977 | 29.4195 | | 0.3506 | 1.35 | 11000 | 0.6277 | 2.0211 | 29.9298 | 28.0986 | | 0.3453 | 1.41 | 11500 | 0.6289 | 2.0223 | 30.3173 | 28.7757 | | 0.3398 | 1.47 | 12000 | 0.6243 | 2.3935 | 30.9222 | 29.0986 | | 0.3373 | 1.53 | 12500 | 0.6260 | 2.4454 | 31.0784 | 27.999 | | 0.3354 | 1.59 | 13000 | 0.6222 | 2.0863 | 30.3551 | 27.9125 | | 0.3323 | 1.65 | 13500 | 0.6206 | 2.2159 | 30.9396 | 28.8441 | | 0.3271 | 1.71 | 14000 | 0.6213 | 2.2952 | 31.2255 | 28.7978 | | 0.324 | 1.77 | 14500 | 0.6160 | 2.1755 | 31.4069 | 28.8219 | | 0.328 | 1.84 | 15000 | 0.6105 | 2.1062 | 31.3412 | 28.3551 | | 0.3283 | 1.9 | 15500 | 0.6118 | 2.1662 | 31.8505 | 29.0241 | | 0.3252 | 1.96 | 16000 | 0.6125 | 2.0541 | 31.6742 | 29.335 | | 0.3127 | 2.02 | 16500 | 0.6119 | 2.0167 | 31.3788 | 27.1499 | | 0.3073 | 2.08 | 17000 | 0.6111 | 2.1154 | 31.1741 | 28.8159 | | 0.3061 | 2.14 | 17500 | 0.6128 | 2.2594 | 31.9415 | 28.0563 | | 0.3086 | 2.2 | 18000 | 0.6108 | 2.0102 | 31.6106 | 29.2384 | | 0.3053 | 2.26 | 18500 | 0.6096 | 2.2419 | 32.3603 | 28.2012 | | 0.3001 | 2.33 | 19000 | 0.6145 | 2.2228 | 32.0512 | 28.2082 | | 0.2995 | 2.39 | 19500 | 0.6130 | 2.2832 | 31.975 | 27.9809 | | 0.3018 | 2.45 | 20000 | 0.6084 | 2.0829 | 31.8214 | 28.6368 | | 0.301 | 2.51 | 20500 | 0.6076 | 2.0945 | 32.4369 | 29.1569 | | 0.2975 | 2.57 | 21000 | 0.6045 | 2.1488 | 32.5463 | 28.9014 | | 0.2935 | 2.63 | 21500 | 0.6072 | 2.1841 | 32.4359 | 28.5191 | | 0.294 | 2.69 | 22000 | 0.6045 | 1.9572 | 31.7954 | 28.2344 | | 0.2989 | 2.75 | 22500 | 0.6029 | 2.238 | 32.5904 | 28.8581 | | 0.2851 | 2.82 | 23000 | 0.6042 | 1.9788 | 32.3171 | 30.0734 | | 0.2913 | 2.88 | 23500 | 0.6021 | 2.1175 | 32.7805 | 30.1137 | | 0.2898 | 2.94 | 24000 | 0.6013 | 2.2142 | 32.7427 | 28.7002 | | 0.2931 | 3.0 | 24500 | 0.6041 | 2.4647 | 32.4348 | 28.8008 | | 0.2799 | 3.06 | 25000 | 0.6015 | 2.3744 | 33.0465 | 29.3632 | | 0.2748 | 3.12 | 25500 | 0.5991 | 2.3361 | 32.311 | 28.9306 | | 0.2787 | 3.18 | 26000 | 0.6023 | 2.3149 | 32.6274 | 28.5382 | | 0.274 | 3.24 | 26500 | 0.6003 | 2.4224 | 33.4939 | 29.1459 | | 0.2763 | 3.3 | 27000 | 0.6020 | 2.5508 | 33.5462 | 28.5654 | | 0.2771 | 3.37 | 27500 | 0.6032 | 2.1693 | 32.952 | 30.5624 | | 0.277 | 3.43 | 28000 | 0.5981 | 2.2154 | 33.081 | 30.5644 | | 0.2681 | 3.49 | 28500 | 0.5992 | 2.4107 | 33.079 | 28.3783 | | 0.2718 | 3.55 | 29000 | 0.5977 | 2.3299 | 33.083 | 29.2586 | | 0.2722 | 3.61 | 29500 | 0.5983 | 2.4453 | 33.8041 | 29.7344 | | 0.27 | 3.67 | 30000 | 0.5992 | 2.3506 | 32.9997 | 29.495 | | 0.2734 | 3.73 | 30500 | 0.5985 | 2.3399 | 33.4602 | 29.1368 | | 0.2723 | 3.79 | 31000 | 0.5966 | 2.4153 | 33.1652 | 28.9527 | | 0.2748 | 3.86 | 31500 | 0.5974 | 2.1353 | 33.0986 | 30.0563 | | 0.2708 | 3.92 | 32000 | 0.5939 | 2.3157 | 32.8473 | 29.0825 | | 0.2726 | 3.98 | 32500 | 0.5938 | 2.434 | 33.3837 | 29.4346 | | 0.2617 | 4.04 | 33000 | 0.6028 | 2.4655 | 33.4206 | 28.6841 | | 0.2557 | 4.1 | 33500 | 0.6058 | 2.1632 | 32.9109 | 28.9215 | | 0.2579 | 4.16 | 34000 | 0.5967 | 2.4645 | 33.5773 | 28.9527 | | 0.2609 | 4.22 | 34500 | 0.6004 | 2.383 | 33.5559 | 29.0221 | | 0.2587 | 4.28 | 35000 | 0.5991 | 2.5586 | 33.5029 | 28.4256 | | 0.2596 | 4.35 | 35500 | 0.5974 | 2.5072 | 34.0648 | 28.7867 | | 0.2564 | 4.41 | 36000 | 0.5974 | 2.4318 | 33.8429 | 29.6419 | | 0.2599 | 4.47 | 36500 | 0.5952 | 2.488 | 33.605 | 28.5875 | | 0.2572 | 4.53 | 37000 | 0.5942 | 2.5619 | 33.298 | 28.7646 | | 0.2578 | 4.59 | 37500 | 0.5962 | 2.4273 | 33.529 | 28.6187 | | 0.2551 | 4.65 | 38000 | 0.5967 | 2.8284 | 33.7729 | 28.8903 | | 0.2555 | 4.71 | 38500 | 0.5929 | 2.6018 | 33.4159 | 28.8189 | | 0.2532 | 4.77 | 39000 | 0.5971 | 2.4928 | 33.6924 | 29.839 | | 0.2489 | 4.83 | 39500 | 0.5963 | 2.4986 | 33.6991 | 28.8742 | | 0.2567 | 4.9 | 40000 | 0.5972 | 2.3907 | 33.8456 | 29.7294 | | 0.2506 | 4.96 | 40500 | 0.5933 | 2.4751 | 33.7787 | 28.5714 | | 0.2533 | 5.02 | 41000 | 0.5989 | 2.5127 | 34.1493 | 28.6187 | | 0.2426 | 5.08 | 41500 | 0.5968 | 2.4641 | 33.3581 | 28.2103 | | 0.2466 | 5.14 | 42000 | 0.5931 | 2.4291 | 33.7823 | 28.4457 | | 0.2407 | 5.2 | 42500 | 0.6031 | 2.4711 | 33.5649 | 28.334 | | 0.2432 | 5.26 | 43000 | 0.5978 | 2.5116 | 33.8456 | 28.3239 | | 0.2477 | 5.32 | 43500 | 0.6016 | 2.4278 | 33.7941 | 28.6932 | | 0.2448 | 5.39 | 44000 | 0.5987 | 2.3864 | 34.2909 | 29.6962 | | 0.2423 | 5.45 | 44500 | 0.6027 | 2.5332 | 34.1102 | 29.2264 | | 0.2402 | 5.51 | 45000 | 0.5985 | 2.3967 | 33.7756 | 28.668 | | 0.2427 | 5.57 | 45500 | 0.5966 | 2.5785 | 33.7703 | 29.3018 | | 0.2447 | 5.63 | 46000 | 0.5957 | 2.2929 | 33.8479 | 29.6056 | | 0.2414 | 5.69 | 46500 | 0.5977 | 2.3125 | 33.8854 | 28.3692 | | 0.2443 | 5.75 | 47000 | 0.5927 | 2.3626 | 34.0472 | 28.9165 | | 0.2423 | 5.81 | 47500 | 0.5945 | 2.4395 | 34.3819 | 28.9507 | | 0.2444 | 5.88 | 48000 | 0.5957 | 2.2577 | 33.8561 | 28.168 | | 0.241 | 5.94 | 48500 | 0.5972 | 2.4453 | 34.1828 | 28.8672 | | 0.2418 | 6.0 | 49000 | 0.5968 | 2.2104 | 34.0775 | 29.6016 | | 0.2313 | 6.06 | 49500 | 0.5972 | 2.4209 | 33.904 | 28.7726 | | 0.2311 | 6.12 | 50000 | 0.5956 | 2.4796 | 34.5869 | 28.8561 | | 0.2316 | 6.18 | 50500 | 0.6004 | 2.4623 | 34.0937 | 28.4175 | | 0.2357 | 6.24 | 51000 | 0.5979 | 2.3804 | 34.5132 | 29.0201 | | 0.234 | 6.3 | 51500 | 0.5992 | 2.3018 | 34.1685 | 29.3058 | | 0.2322 | 6.36 | 52000 | 0.5981 | 2.4152 | 33.9227 | 28.1137 | | 0.2322 | 6.43 | 52500 | 0.5956 | 2.5334 | 34.1155 | 29.0221 | | 0.2308 | 6.49 | 53000 | 0.6005 | 2.1759 | 33.7251 | 29.0724 | | 0.2288 | 6.55 | 53500 | 0.5943 | 2.4034 | 34.1537 | 28.6328 | | 0.2357 | 6.61 | 54000 | 0.5985 | 2.5652 | 33.8533 | 28.2877 | | 0.2333 | 6.67 | 54500 | 0.6000 | 2.35 | 34.0026 | 29.336 | | 0.2302 | 6.73 | 55000 | 0.5981 | 2.6286 | 34.4534 | 29.0252 | | 0.2307 | 6.79 | 55500 | 0.5958 | 2.4327 | 34.3027 | 28.8249 | | 0.233 | 6.85 | 56000 | 0.5959 | 2.5109 | 34.6236 | 28.7042 | | 0.2318 | 6.92 | 56500 | 0.5980 | 2.6031 | 34.4364 | 28.2887 | | 0.2344 | 6.98 | 57000 | 0.5972 | 2.4921 | 34.5806 | 29.0553 | | 0.2261 | 7.04 | 57500 | 0.5999 | 2.521 | 34.1198 | 28.6791 | | 0.2209 | 7.1 | 58000 | 0.6033 | 2.5297 | 34.5014 | 28.8883 | | 0.2231 | 7.16 | 58500 | 0.6005 | 2.6356 | 34.6424 | 29.0111 | | 0.2239 | 7.22 | 59000 | 0.6030 | 2.4542 | 34.563 | 28.7616 | | 0.2216 | 7.28 | 59500 | 0.6030 | 2.3768 | 34.4505 | 28.6811 | | 0.2207 | 7.34 | 60000 | 0.5998 | 2.3748 | 34.4635 | 28.3783 | | 0.2206 | 7.41 | 60500 | 0.5975 | 2.3457 | 34.5259 | 28.4859 | | 0.2252 | 7.47 | 61000 | 0.6005 | 2.6533 | 34.4452 | 28.3843 | | 0.2249 | 7.53 | 61500 | 0.5988 | 2.4764 | 34.322 | 28.4235 | | 0.2236 | 7.59 | 62000 | 0.6066 | 2.3159 | 34.5787 | 29.0835 | | 0.2226 | 7.65 | 62500 | 0.6018 | 2.3104 | 34.755 | 28.9024 | | 0.2265 | 7.71 | 63000 | 0.6026 | 2.4038 | 34.1573 | 28.1761 | | 0.2287 | 7.77 | 63500 | 0.6000 | 2.2903 | 34.5371 | 28.7525 | | 0.2229 | 7.83 | 64000 | 0.6022 | 2.4527 | 34.2531 | 28.8421 | | 0.2208 | 7.89 | 64500 | 0.5999 | 2.5312 | 34.4476 | 28.992 | | 0.2213 | 7.96 | 65000 | 0.6021 | 2.5112 | 34.4451 | 28.7455 | | 0.2204 | 8.02 | 65500 | 0.6034 | 2.4801 | 34.5879 | 28.832 | | 0.2149 | 8.08 | 66000 | 0.6016 | 2.4674 | 34.6048 | 29.3441 | | 0.2166 | 8.14 | 66500 | 0.6026 | 2.3395 | 34.6422 | 29.4165 | | 0.2124 | 8.2 | 67000 | 0.6048 | 2.4233 | 34.4643 | 28.5523 | | 0.2149 | 8.26 | 67500 | 0.6024 | 2.4689 | 34.5844 | 29.0191 | | 0.217 | 8.32 | 68000 | 0.6040 | 2.4434 | 34.5775 | 28.3753 | | 0.2158 | 8.38 | 68500 | 0.6079 | 2.5131 | 34.186 | 28.9115 | | 0.2142 | 8.45 | 69000 | 0.6049 | 2.5492 | 34.3894 | 28.832 | | 0.2153 | 8.51 | 69500 | 0.6033 | 2.466 | 34.6952 | 29.4567 | | 0.2145 | 8.57 | 70000 | 0.6055 | 2.4537 | 34.3353 | 28.5765 | | 0.2133 | 8.63 | 70500 | 0.6021 | 2.2953 | 34.5461 | 28.666 | | 0.2165 | 8.69 | 71000 | 0.6028 | 2.3889 | 34.706 | 28.8561 | | 0.2171 | 8.75 | 71500 | 0.6058 | 2.2679 | 34.3039 | 28.7555 | | 0.2169 | 8.81 | 72000 | 0.6048 | 2.41 | 34.7099 | 28.8913 | | 0.2138 | 8.87 | 72500 | 0.6041 | 2.4994 | 34.256 | 28.5262 | | 0.2165 | 8.94 | 73000 | 0.6066 | 2.306 | 34.4452 | 29.1841 | | 0.2158 | 9.0 | 73500 | 0.6060 | 2.2252 | 34.6494 | 29.1237 | | 0.2081 | 9.06 | 74000 | 0.6065 | 2.409 | 34.5011 | 29.6459 | | 0.2067 | 9.12 | 74500 | 0.6077 | 2.4688 | 34.453 | 29.2636 | | 0.208 | 9.18 | 75000 | 0.6116 | 2.4359 | 34.3253 | 28.7032 | | 0.2072 | 9.24 | 75500 | 0.6071 | 2.3814 | 34.7431 | 29.0523 | | 0.2093 | 9.3 | 76000 | 0.6070 | 2.5564 | 34.6551 | 29.1016 | | 0.2068 | 9.36 | 76500 | 0.6091 | 2.4882 | 34.6221 | 28.7314 | | 0.2092 | 9.42 | 77000 | 0.6087 | 2.4984 | 34.4045 | 28.5292 | | 0.2092 | 9.49 | 77500 | 0.6116 | 2.5316 | 34.2851 | 28.8632 | | 0.2097 | 9.55 | 78000 | 0.6096 | 2.4282 | 34.4743 | 29.0121 | | 0.2088 | 9.61 | 78500 | 0.6079 | 2.4584 | 34.6955 | 28.7847 | | 0.2073 | 9.67 | 79000 | 0.6089 | 2.5481 | 34.6829 | 29.2364 | | 0.211 | 9.73 | 79500 | 0.6076 | 2.4617 | 34.6341 | 28.4306 | | 0.2055 | 9.79 | 80000 | 0.6101 | 2.3738 | 34.4435 | 28.9708 | | 0.2099 | 9.85 | 80500 | 0.6098 | 2.424 | 34.4798 | 28.8813 | | 0.2116 | 9.91 | 81000 | 0.6062 | 2.5077 | 34.6985 | 28.9688 | | 0.21 | 9.98 | 81500 | 0.6067 | 2.3215 | 34.3473 | 28.7696 | | 0.2029 | 10.04 | 82000 | 0.6118 | 2.3372 | 34.5901 | 28.9779 | | 0.2026 | 10.1 | 82500 | 0.6096 | 2.296 | 34.8033 | 28.7857 | | 0.1994 | 10.16 | 83000 | 0.6148 | 2.3403 | 34.3745 | 29.002 | | 0.2031 | 10.22 | 83500 | 0.6138 | 2.335 | 34.3731 | 28.8531 | | 0.2019 | 10.28 | 84000 | 0.6106 | 2.4463 | 34.7185 | 29.1922 | | 0.2037 | 10.34 | 84500 | 0.6109 | 2.2655 | 34.8919 | 29.1831 | | 0.2026 | 10.4 | 85000 | 0.6133 | 2.5375 | 34.9363 | 28.8219 | | 0.2056 | 10.47 | 85500 | 0.6109 | 2.4682 | 34.7983 | 29.159 | | 0.2012 | 10.53 | 86000 | 0.6141 | 2.4703 | 34.8893 | 28.9316 | | 0.2032 | 10.59 | 86500 | 0.6093 | 2.5175 | 35.033 | 29.1801 | | 0.2035 | 10.65 | 87000 | 0.6091 | 2.4736 | 34.9436 | 28.6066 | | 0.2043 | 10.71 | 87500 | 0.6109 | 2.4897 | 34.9335 | 28.8078 | | 0.2031 | 10.77 | 88000 | 0.6098 | 2.5124 | 34.9311 | 28.8853 | | 0.2046 | 10.83 | 88500 | 0.6093 | 2.5219 | 35.055 | 29.0272 | | 0.2053 | 10.89 | 89000 | 0.6096 | 2.6349 | 34.88 | 28.8169 | | 0.1995 | 10.95 | 89500 | 0.6080 | 2.6063 | 34.6953 | 28.6932 | | 0.1987 | 11.02 | 90000 | 0.6120 | 2.6177 | 35.026 | 28.9074 | | 0.1982 | 11.08 | 90500 | 0.6124 | 2.4237 | 34.5952 | 28.7062 | | 0.1979 | 11.14 | 91000 | 0.6110 | 2.367 | 34.2564 | 28.5694 | | 0.1963 | 11.2 | 91500 | 0.6096 | 2.6414 | 34.8418 | 28.4738 | | 0.1989 | 11.26 | 92000 | 0.6109 | 2.5492 | 34.7083 | 28.5181 | | 0.1951 | 11.32 | 92500 | 0.6130 | 2.4833 | 34.9199 | 28.7233 | | 0.1973 | 11.38 | 93000 | 0.6156 | 2.5606 | 34.7202 | 28.7656 | | 0.1973 | 11.44 | 93500 | 0.6147 | 2.3841 | 34.6415 | 28.5473 | | 0.1952 | 11.51 | 94000 | 0.6140 | 2.4045 | 34.5362 | 28.4256 | | 0.1971 | 11.57 | 94500 | 0.6142 | 2.383 | 34.7052 | 28.7515 | | 0.196 | 11.63 | 95000 | 0.6147 | 2.5442 | 34.7816 | 28.5755 | | 0.1934 | 11.69 | 95500 | 0.6134 | 2.6019 | 34.8241 | 28.7525 | | 0.2003 | 11.75 | 96000 | 0.6121 | 2.5126 | 34.6382 | 28.5412 | | 0.2008 | 11.81 | 96500 | 0.6117 | 2.509 | 34.898 | 28.5704 | | 0.1969 | 11.87 | 97000 | 0.6144 | 2.5595 | 34.6971 | 28.661 | | 0.1987 | 11.93 | 97500 | 0.6141 | 2.3949 | 34.6216 | 28.6449 | | 0.1977 | 12.0 | 98000 | 0.6157 | 2.3919 | 34.5717 | 28.7093 | | 0.1918 | 12.06 | 98500 | 0.6166 | 2.5262 | 34.5272 | 28.3732 | | 0.1919 | 12.12 | 99000 | 0.6160 | 2.4698 | 34.6751 | 28.5262 | | 0.1885 | 12.18 | 99500 | 0.6154 | 2.4553 | 34.4928 | 28.6781 | | 0.1939 | 12.24 | 100000 | 0.6153 | 2.4935 | 34.7791 | 28.9386 | | 0.1897 | 12.3 | 100500 | 0.6167 | 2.438 | 34.5046 | 28.9688 | | 0.1921 | 12.36 | 101000 | 0.6174 | 2.522 | 34.5481 | 28.9276 | | 0.1935 | 12.42 | 101500 | 0.6168 | 2.3808 | 34.6962 | 28.9799 | | 0.1931 | 12.48 | 102000 | 0.6172 | 2.3268 | 34.3722 | 28.828 | | 0.1928 | 12.55 | 102500 | 0.6154 | 2.5262 | 34.5165 | 28.7686 | | 0.1951 | 12.61 | 103000 | 0.6153 | 2.4008 | 34.5959 | 28.995 | | 0.1918 | 12.67 | 103500 | 0.6165 | 2.4971 | 34.907 | 28.6881 | | 0.1937 | 12.73 | 104000 | 0.6172 | 2.4809 | 34.7468 | 28.7575 | | 0.1947 | 12.79 | 104500 | 0.6171 | 2.5153 | 34.7974 | 28.838 | | 0.1911 | 12.85 | 105000 | 0.6173 | 2.5098 | 34.4954 | 28.503 | | 0.1964 | 12.91 | 105500 | 0.6154 | 2.6444 | 34.6928 | 29.0151 | | 0.195 | 12.97 | 106000 | 0.6162 | 2.473 | 34.9597 | 28.835 | | 0.1896 | 13.04 | 106500 | 0.6198 | 2.6084 | 34.7626 | 28.7998 | | 0.1904 | 13.1 | 107000 | 0.6210 | 2.5528 | 34.8396 | 28.7817 | | 0.1873 | 13.16 | 107500 | 0.6199 | 2.4733 | 34.5978 | 28.6247 | | 0.1928 | 13.22 | 108000 | 0.6206 | 2.2296 | 34.7016 | 28.7425 | | 0.1877 | 13.28 | 108500 | 0.6202 | 2.2818 | 34.6314 | 28.6288 | | 0.1894 | 13.34 | 109000 | 0.6203 | 2.4791 | 34.5125 | 28.7787 | | 0.1871 | 13.4 | 109500 | 0.6194 | 2.4788 | 34.6466 | 28.8753 | | 0.1882 | 13.46 | 110000 | 0.6190 | 2.4903 | 34.6736 | 28.4708 | | 0.1901 | 13.53 | 110500 | 0.6178 | 2.4224 | 34.7781 | 29.172 | | 0.1856 | 13.59 | 111000 | 0.6226 | 2.7529 | 34.8907 | 28.9316 | | 0.1899 | 13.65 | 111500 | 0.6190 | 2.7389 | 34.8182 | 28.7012 | | 0.1906 | 13.71 | 112000 | 0.6183 | 2.66 | 34.7846 | 28.7887 | | 0.1845 | 13.77 | 112500 | 0.6192 | 2.5404 | 34.8479 | 28.8793 | | 0.1894 | 13.83 | 113000 | 0.6168 | 2.4759 | 35.0083 | 28.9819 | | 0.1881 | 13.89 | 113500 | 0.6211 | 2.5217 | 34.8921 | 28.8813 | | 0.1891 | 13.95 | 114000 | 0.6183 | 2.5463 | 34.8198 | 28.659 | | 0.1866 | 14.01 | 114500 | 0.6211 | 2.6312 | 34.645 | 28.8763 | | 0.1822 | 14.08 | 115000 | 0.6228 | 2.561 | 34.903 | 28.8934 | | 0.1837 | 14.14 | 115500 | 0.6225 | 2.5487 | 34.7725 | 28.8913 | | 0.1858 | 14.2 | 116000 | 0.6219 | 2.5928 | 34.7858 | 28.7666 | | 0.1837 | 14.26 | 116500 | 0.6222 | 2.5209 | 34.5277 | 28.7726 | | 0.186 | 14.32 | 117000 | 0.6216 | 2.5951 | 34.9747 | 29.1308 | | 0.1853 | 14.38 | 117500 | 0.6215 | 2.4401 | 34.9479 | 29.329 | | 0.1855 | 14.44 | 118000 | 0.6223 | 2.5228 | 34.6737 | 28.9809 | | 0.1854 | 14.5 | 118500 | 0.6219 | 2.4152 | 34.7626 | 29.0231 | | 0.1844 | 14.57 | 119000 | 0.6214 | 2.5697 | 34.4064 | 28.6871 | | 0.1852 | 14.63 | 119500 | 0.6212 | 2.4173 | 34.9831 | 29.0362 | | 0.1872 | 14.69 | 120000 | 0.6189 | 2.5666 | 35.0505 | 28.9487 | | 0.1883 | 14.75 | 120500 | 0.6206 | 2.4874 | 35.0116 | 29.2596 | | 0.1867 | 14.81 | 121000 | 0.6208 | 2.5295 | 35.0846 | 28.8843 | | 0.188 | 14.87 | 121500 | 0.6212 | 2.4124 | 34.8342 | 28.9044 | | 0.1827 | 14.93 | 122000 | 0.6223 | 2.4926 | 34.8856 | 29.2445 | | 0.1845 | 14.99 | 122500 | 0.6207 | 2.5557 | 34.941 | 28.827 | | 0.1822 | 15.06 | 123000 | 0.6220 | 2.5741 | 34.7359 | 28.5775 | | 0.1824 | 15.12 | 123500 | 0.6251 | 2.5393 | 34.8589 | 28.8521 | | 0.1803 | 15.18 | 124000 | 0.6252 | 2.509 | 35.0319 | 29.1368 | | 0.1806 | 15.24 | 124500 | 0.6248 | 2.6374 | 34.7482 | 28.8581 | | 0.1784 | 15.3 | 125000 | 0.6254 | 2.4306 | 34.5308 | 28.5282 | | 0.1807 | 15.36 | 125500 | 0.6267 | 2.4254 | 34.6103 | 28.7928 | | 0.1856 | 15.42 | 126000 | 0.6236 | 2.5149 | 34.464 | 28.4769 | | 0.1826 | 15.48 | 126500 | 0.6248 | 2.5421 | 34.7899 | 28.7525 | | 0.1835 | 15.54 | 127000 | 0.6247 | 2.5838 | 34.6669 | 28.9799 | | 0.1815 | 15.61 | 127500 | 0.6253 | 2.6119 | 34.6821 | 28.9245 | | 0.1846 | 15.67 | 128000 | 0.6242 | 2.599 | 34.7133 | 28.6227 | | 0.1823 | 15.73 | 128500 | 0.6254 | 2.5391 | 34.7756 | 28.9205 | | 0.1856 | 15.79 | 129000 | 0.6244 | 2.469 | 34.9484 | 29.0825 | | 0.1814 | 15.85 | 129500 | 0.6235 | 2.5316 | 35.0045 | 29.001 | | 0.1826 | 15.91 | 130000 | 0.6261 | 2.5732 | 34.606 | 28.5584 | | 0.1795 | 15.97 | 130500 | 0.6245 | 2.5493 | 35.0103 | 29.0292 | | 0.1815 | 16.03 | 131000 | 0.6271 | 2.6712 | 34.9971 | 28.7435 | | 0.1783 | 16.1 | 131500 | 0.6279 | 2.5753 | 34.7197 | 28.8431 | | 0.1797 | 16.16 | 132000 | 0.6265 | 2.4547 | 34.6509 | 28.7988 | | 0.1799 | 16.22 | 132500 | 0.6267 | 2.6017 | 34.9454 | 28.6781 | | 0.1787 | 16.28 | 133000 | 0.6284 | 2.5852 | 34.6931 | 28.5875 | | 0.1789 | 16.34 | 133500 | 0.6270 | 2.5806 | 34.7731 | 28.998 | | 0.1793 | 16.4 | 134000 | 0.6277 | 2.6962 | 34.6517 | 28.7948 | | 0.1778 | 16.46 | 134500 | 0.6260 | 2.5917 | 34.6919 | 29.0604 | | 0.1798 | 16.52 | 135000 | 0.6271 | 2.6003 | 34.7628 | 29.0332 | | 0.1783 | 16.59 | 135500 | 0.6260 | 2.6648 | 34.781 | 28.7515 | | 0.1776 | 16.65 | 136000 | 0.6267 | 2.644 | 34.8913 | 28.9427 | | 0.1806 | 16.71 | 136500 | 0.6287 | 2.642 | 34.7232 | 28.671 | | 0.1785 | 16.77 | 137000 | 0.6261 | 2.6244 | 34.862 | 28.9286 | | 0.1802 | 16.83 | 137500 | 0.6285 | 2.6106 | 34.9525 | 28.8934 | | 0.1802 | 16.89 | 138000 | 0.6266 | 2.4873 | 34.4422 | 28.7877 | | 0.1808 | 16.95 | 138500 | 0.6281 | 2.5479 | 34.7034 | 29.1167 | | 0.1811 | 17.01 | 139000 | 0.6271 | 2.5462 | 34.7687 | 28.9748 | | 0.175 | 17.07 | 139500 | 0.6287 | 2.5574 | 34.8786 | 29.0684 | | 0.1786 | 17.14 | 140000 | 0.6286 | 2.6459 | 34.9833 | 28.9034 | | 0.1781 | 17.2 | 140500 | 0.6301 | 2.6564 | 34.8437 | 28.9034 | | 0.1773 | 17.26 | 141000 | 0.6291 | 2.4694 | 35.0778 | 29.0966 | | 0.1789 | 17.32 | 141500 | 0.6291 | 2.7069 | 34.7801 | 28.8531 | | 0.1742 | 17.38 | 142000 | 0.6296 | 2.5806 | 35.0719 | 28.7696 | | 0.1791 | 17.44 | 142500 | 0.6286 | 2.6497 | 34.8104 | 28.8119 | | 0.1768 | 17.5 | 143000 | 0.6288 | 2.5836 | 34.9395 | 28.673 | | 0.1765 | 17.56 | 143500 | 0.6295 | 2.6236 | 34.6219 | 28.7606 | | 0.1785 | 17.63 | 144000 | 0.6281 | 2.6064 | 34.5671 | 28.6378 | | 0.1785 | 17.69 | 144500 | 0.6291 | 2.6307 | 34.7851 | 28.7304 | | 0.1746 | 17.75 | 145000 | 0.6291 | 2.6569 | 34.7762 | 28.9165 | | 0.1762 | 17.81 | 145500 | 0.6296 | 2.5294 | 34.8672 | 29.0493 | | 0.1779 | 17.87 | 146000 | 0.6289 | 2.5837 | 34.7269 | 28.7243 | | 0.1772 | 17.93 | 146500 | 0.6295 | 2.5655 | 34.7131 | 28.8853 | | 0.178 | 17.99 | 147000 | 0.6292 | 2.7107 | 34.8452 | 28.8924 | | 0.1745 | 18.05 | 147500 | 0.6302 | 2.6626 | 34.8329 | 28.9024 | | 0.1756 | 18.12 | 148000 | 0.6294 | 2.7256 | 34.6914 | 28.6791 | | 0.1752 | 18.18 | 148500 | 0.6306 | 2.6617 | 34.8721 | 29.0382 | | 0.1783 | 18.24 | 149000 | 0.6311 | 2.5843 | 34.6449 | 28.7062 | | 0.1746 | 18.3 | 149500 | 0.6300 | 2.6503 | 34.6579 | 28.7948 | | 0.1768 | 18.36 | 150000 | 0.6289 | 2.6644 | 34.8421 | 28.7596 | | 0.1735 | 18.42 | 150500 | 0.6298 | 2.6592 | 34.8831 | 28.9266 | | 0.1726 | 18.48 | 151000 | 0.6303 | 2.6662 | 34.7957 | 28.9205 | | 0.1765 | 18.54 | 151500 | 0.6298 | 2.6464 | 34.867 | 28.8632 | | 0.1737 | 18.6 | 152000 | 0.6296 | 2.572 | 34.9667 | 28.9296 | | 0.1755 | 18.67 | 152500 | 0.6289 | 2.6626 | 34.8297 | 28.8783 | | 0.1774 | 18.73 | 153000 | 0.6305 | 2.6593 | 34.8033 | 28.7445 | | 0.1773 | 18.79 | 153500 | 0.6307 | 2.6628 | 34.8469 | 28.8793 | | 0.1772 | 18.85 | 154000 | 0.6305 | 2.7617 | 34.8576 | 28.7686 | | 0.1767 | 18.91 | 154500 | 0.6295 | 2.7162 | 34.8489 | 28.6781 | | 0.1764 | 18.97 | 155000 | 0.6309 | 2.6794 | 34.9801 | 28.8119 | | 0.1745 | 19.03 | 155500 | 0.6312 | 2.7008 | 34.942 | 28.8602 | | 0.175 | 19.09 | 156000 | 0.6308 | 2.7038 | 35.1077 | 29.0624 | | 0.1749 | 19.16 | 156500 | 0.6302 | 2.7338 | 34.8444 | 28.831 | | 0.1719 | 19.22 | 157000 | 0.6307 | 2.7141 | 34.797 | 28.9668 | | 0.1726 | 19.28 | 157500 | 0.6321 | 2.6579 | 34.8974 | 28.7193 | | 0.1739 | 19.34 | 158000 | 0.6311 | 2.7274 | 34.9123 | 28.837 | | 0.1736 | 19.4 | 158500 | 0.6310 | 2.622 | 34.9064 | 28.7163 | | 0.174 | 19.46 | 159000 | 0.6318 | 2.7009 | 34.8667 | 28.7857 | | 0.1748 | 19.52 | 159500 | 0.6315 | 2.7481 | 34.92 | 28.7767 | | 0.1765 | 19.58 | 160000 | 0.6316 | 2.7351 | 34.941 | 28.7686 | | 0.1733 | 19.65 | 160500 | 0.6314 | 2.7531 | 34.9317 | 28.7545 | | 0.175 | 19.71 | 161000 | 0.6316 | 2.7314 | 34.9079 | 28.8521 | | 0.175 | 19.77 | 161500 | 0.6307 | 2.7682 | 34.8455 | 28.7213 | | 0.1748 | 19.83 | 162000 | 0.6311 | 2.7593 | 34.902 | 28.7767 | | 0.174 | 19.89 | 162500 | 0.6311 | 2.7523 | 34.9226 | 28.8008 | | 0.1758 | 19.95 | 163000 | 0.6309 | 2.751 | 34.8573 | 28.8089 | ### Framework versions - Transformers 4.28.1 - Pytorch 2.0.0+cu117 - Datasets 2.11.0 - Tokenizers 0.13.3