Terjman-Large-v2.0
This model is a fine-tuned version of Helsinki-NLP/opus-mt-tc-big-en-ar on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.2174
- Bleu: 5.5922
- Gen Len: 12.3639
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 100
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
5.7091 | 0.2818 | 1000 | 4.6208 | 1.6751 | 11.0442 |
4.4751 | 0.5635 | 2000 | 3.8954 | 3.2105 | 45.6684 |
3.8872 | 0.8453 | 3000 | 3.4826 | 4.6044 | 28.3214 |
3.6822 | 1.1271 | 4000 | 3.2918 | 5.0765 | 24.0017 |
3.7157 | 1.4088 | 5000 | 3.1687 | 4.3485 | 18.2415 |
3.3868 | 1.6906 | 6000 | 3.0875 | 6.5395 | 20.1395 |
3.4344 | 1.9724 | 7000 | 2.9994 | 5.0153 | 19.4541 |
2.9016 | 2.2542 | 8000 | 3.0285 | 6.7175 | 12.8844 |
3.1902 | 2.5359 | 9000 | 3.0102 | 5.33 | 12.8435 |
3.1222 | 2.8177 | 10000 | 2.9850 | 5.9288 | 15.8878 |
2.4111 | 3.0995 | 11000 | 3.0385 | 6.6549 | 14.3946 |
2.7917 | 3.3812 | 12000 | 3.0630 | 5.4164 | 21.2908 |
2.9785 | 3.6630 | 13000 | 3.1000 | 4.7618 | 15.3861 |
2.9419 | 3.9448 | 14000 | 3.0776 | 6.79 | 12.6956 |
2.556 | 4.2265 | 15000 | 3.1566 | 5.9548 | 14.4201 |
2.9118 | 4.5083 | 16000 | 3.1179 | 6.1051 | 12.6871 |
2.9287 | 4.7901 | 17000 | 3.1186 | 5.8292 | 12.5578 |
2.5689 | 5.0719 | 18000 | 3.1538 | 6.1599 | 13.3929 |
2.654 | 5.3536 | 19000 | 3.2165 | 5.6401 | 14.2687 |
2.6656 | 5.6354 | 20000 | 3.1460 | 5.9354 | 16.8418 |
2.6774 | 5.9172 | 21000 | 3.1474 | 5.2765 | 16.4371 |
2.4631 | 6.1989 | 22000 | 3.2058 | 5.1774 | 21.7415 |
2.3928 | 6.4807 | 23000 | 3.2062 | 6.0163 | 17.8503 |
2.4675 | 6.7625 | 24000 | 3.2010 | 5.7372 | 14.216 |
2.1843 | 7.0442 | 25000 | 3.2269 | 5.9204 | 14.3571 |
2.174 | 7.3260 | 26000 | 3.2315 | 6.1916 | 27.2704 |
2.0871 | 7.6078 | 27000 | 3.2224 | 5.2812 | 15.2534 |
2.4648 | 7.8895 | 28000 | 3.2453 | 4.3586 | 14.3912 |
2.0176 | 8.1713 | 29000 | 3.2207 | 5.2763 | 15.6905 |
2.0596 | 8.4531 | 30000 | 3.2442 | 4.9459 | 15.1412 |
2.1006 | 8.7349 | 31000 | 3.2239 | 6.2316 | 18.182 |
1.8592 | 9.0166 | 32000 | 3.2716 | 6.3071 | 16.0578 |
1.7812 | 9.2984 | 33000 | 3.2953 | 5.7082 | 12.5051 |
1.9135 | 9.5802 | 34000 | 3.3387 | 5.4711 | 14.9303 |
1.9691 | 9.8619 | 35000 | 3.3025 | 5.2453 | 19.6071 |
1.5649 | 10.1437 | 36000 | 3.2968 | 5.46 | 12.381 |
1.8979 | 10.4255 | 37000 | 3.3133 | 5.1668 | 15.4575 |
1.7104 | 10.7072 | 38000 | 3.3196 | 5.2871 | 16.3044 |
1.7178 | 10.9890 | 39000 | 3.2803 | 5.3452 | 15.0646 |
1.4212 | 11.2708 | 40000 | 3.3241 | 6.7079 | 16.3503 |
1.6208 | 11.5526 | 41000 | 3.3598 | 6.1538 | 12.9643 |
1.6371 | 11.8343 | 42000 | 3.3249 | 5.022 | 16.2687 |
1.3699 | 12.1161 | 43000 | 3.4188 | 5.7854 | 15.8401 |
1.4002 | 12.3979 | 44000 | 3.3946 | 4.0433 | 13.5867 |
1.443 | 12.6796 | 45000 | 3.4262 | 7.0729 | 15.4915 |
1.4715 | 12.9614 | 46000 | 3.4057 | 4.8983 | 14.3078 |
1.3485 | 13.2432 | 47000 | 3.4490 | 5.5586 | 15.7789 |
1.3186 | 13.5249 | 48000 | 3.3755 | 5.3413 | 20.5442 |
1.3606 | 13.8067 | 49000 | 3.4440 | 5.2075 | 18.7976 |
1.1196 | 14.0885 | 50000 | 3.4588 | 6.9244 | 13.0527 |
1.2259 | 14.3702 | 51000 | 3.4283 | 4.7976 | 20.148 |
1.3454 | 14.6520 | 52000 | 3.4386 | 6.2805 | 18.3861 |
1.2071 | 14.9338 | 53000 | 3.4999 | 6.1639 | 15.4575 |
1.0883 | 15.2156 | 54000 | 3.4771 | 5.1804 | 14.318 |
1.0924 | 15.4973 | 55000 | 3.4729 | 6.4881 | 13.1497 |
1.3062 | 15.7791 | 56000 | 3.4888 | 6.4346 | 14.9303 |
0.9508 | 16.0609 | 57000 | 3.4448 | 5.4072 | 12.7296 |
0.9997 | 16.3426 | 58000 | 3.5151 | 6.0067 | 13.7891 |
1.0896 | 16.6244 | 59000 | 3.5060 | 5.87 | 14.9592 |
1.1456 | 16.9062 | 60000 | 3.4721 | 4.8112 | 12.6412 |
0.9323 | 17.1879 | 61000 | 3.6005 | 5.5004 | 13.9252 |
1.0008 | 17.4697 | 62000 | 3.5297 | 5.653 | 12.165 |
0.9612 | 17.7515 | 63000 | 3.5733 | 4.6506 | 12.602 |
0.8908 | 18.0332 | 64000 | 3.6032 | 4.7716 | 13.398 |
0.8792 | 18.3150 | 65000 | 3.6248 | 5.1855 | 13.4524 |
1.0069 | 18.5968 | 66000 | 3.5257 | 5.9816 | 14.0612 |
0.9801 | 18.8786 | 67000 | 3.5263 | 5.0801 | 13.318 |
0.9 | 19.1603 | 68000 | 3.5767 | 5.8642 | 12.3265 |
0.7857 | 19.4421 | 69000 | 3.5906 | 5.0489 | 13.2075 |
0.9145 | 19.7239 | 70000 | 3.6221 | 5.0626 | 14.1667 |
0.9316 | 20.0056 | 71000 | 3.6629 | 5.3033 | 12.2653 |
0.8223 | 20.2874 | 72000 | 3.6865 | 5.113 | 14.2568 |
0.8133 | 20.5692 | 73000 | 3.6414 | 6.7491 | 12.3418 |
0.7663 | 20.8509 | 74000 | 3.6461 | 5.4057 | 12.4762 |
0.7687 | 21.1327 | 75000 | 3.6988 | 4.9812 | 13.1037 |
0.7146 | 21.4145 | 76000 | 3.6972 | 4.8229 | 13.3044 |
0.6764 | 21.6963 | 77000 | 3.7065 | 5.4779 | 13.3146 |
0.8708 | 21.9780 | 78000 | 3.6634 | 4.9879 | 12.6412 |
0.6919 | 22.2598 | 79000 | 3.7094 | 6.0958 | 12.3741 |
0.6602 | 22.5416 | 80000 | 3.7489 | 5.7765 | 12.466 |
0.6252 | 22.8233 | 81000 | 3.7087 | 5.5933 | 12.5901 |
0.6636 | 23.1051 | 82000 | 3.7460 | 5.4878 | 14.9116 |
0.7271 | 23.3869 | 83000 | 3.7501 | 5.7453 | 12.3367 |
0.7436 | 23.6686 | 84000 | 3.7736 | 5.4395 | 12.5153 |
0.6545 | 23.9504 | 85000 | 3.7165 | 5.7506 | 15.1378 |
0.5805 | 24.2322 | 86000 | 3.7657 | 5.3011 | 13.119 |
0.7037 | 24.5139 | 87000 | 3.7930 | 5.1185 | 12.4762 |
0.7806 | 24.7957 | 88000 | 3.7498 | 5.3765 | 12.4779 |
0.7899 | 25.0775 | 89000 | 3.7972 | 6.0777 | 12.602 |
0.6825 | 25.3593 | 90000 | 3.7681 | 5.5679 | 13.0204 |
0.6788 | 25.6410 | 91000 | 3.8146 | 5.7538 | 14.631 |
0.7137 | 25.9228 | 92000 | 3.7659 | 5.5225 | 15.8793 |
0.5414 | 26.2046 | 93000 | 3.8027 | 5.5672 | 13.4881 |
0.5583 | 26.4863 | 94000 | 3.7823 | 6.1698 | 13.3146 |
0.6059 | 26.7681 | 95000 | 3.7994 | 5.7206 | 12.3197 |
0.6441 | 27.0499 | 96000 | 3.8365 | 5.2677 | 12.3759 |
0.5776 | 27.3316 | 97000 | 3.8469 | 6.1722 | 13.0119 |
0.6611 | 27.6134 | 98000 | 3.8836 | 5.2605 | 12.4116 |
0.5442 | 27.8952 | 99000 | 3.8491 | 5.6572 | 12.2109 |
0.5299 | 28.1770 | 100000 | 3.9033 | 6.0417 | 12.4507 |
0.5466 | 28.4587 | 101000 | 3.8823 | 5.8737 | 12.6071 |
0.6516 | 28.7405 | 102000 | 3.8938 | 5.7557 | 14.2296 |
0.484 | 29.0223 | 103000 | 3.9346 | 6.1763 | 13.0867 |
0.5312 | 29.3040 | 104000 | 3.9029 | 6.4509 | 12.5374 |
0.5909 | 29.5858 | 105000 | 3.9000 | 6.2686 | 12.2483 |
0.5426 | 29.8676 | 106000 | 3.8847 | 6.0843 | 12.3112 |
0.5757 | 30.1493 | 107000 | 3.9217 | 6.8405 | 12.3622 |
0.5239 | 30.4311 | 108000 | 3.8981 | 6.591 | 13.2823 |
0.5227 | 30.7129 | 109000 | 3.8752 | 5.7338 | 16.7585 |
0.5214 | 30.9946 | 110000 | 3.9323 | 6.1676 | 12.369 |
0.4046 | 31.2764 | 111000 | 3.9300 | 5.4601 | 12.3316 |
0.4708 | 31.5582 | 112000 | 3.9518 | 5.0917 | 12.4031 |
0.5464 | 31.8400 | 113000 | 3.9458 | 5.673 | 12.3844 |
0.5058 | 32.1217 | 114000 | 3.9858 | 5.7958 | 12.5085 |
0.4773 | 32.4035 | 115000 | 4.0046 | 5.3235 | 12.5527 |
0.5515 | 32.6853 | 116000 | 3.9291 | 5.7086 | 12.3707 |
0.5617 | 32.9670 | 117000 | 3.9472 | 6.0259 | 12.5391 |
0.4717 | 33.2488 | 118000 | 3.9546 | 5.31 | 13.3044 |
0.453 | 33.5306 | 119000 | 3.9866 | 5.3223 | 12.5442 |
0.4299 | 33.8123 | 120000 | 3.9729 | 5.9574 | 12.5374 |
0.485 | 34.0941 | 121000 | 3.9677 | 5.4835 | 12.4558 |
0.3856 | 34.3759 | 122000 | 3.9672 | 6.433 | 12.3588 |
0.3966 | 34.6577 | 123000 | 3.9938 | 5.5857 | 12.3759 |
0.4719 | 34.9394 | 124000 | 3.9698 | 5.3294 | 12.4915 |
0.386 | 35.2212 | 125000 | 3.9844 | 5.6156 | 12.5697 |
0.505 | 35.5030 | 126000 | 4.0194 | 5.6851 | 12.5459 |
0.3879 | 35.7847 | 127000 | 3.9993 | 6.0431 | 12.3929 |
0.4216 | 36.0665 | 128000 | 4.0755 | 5.3128 | 12.7143 |
0.4429 | 36.3483 | 129000 | 4.0022 | 5.4492 | 12.6105 |
0.4668 | 36.6300 | 130000 | 3.9904 | 5.9034 | 12.8061 |
0.4041 | 36.9118 | 131000 | 3.9880 | 5.0601 | 12.3469 |
0.4432 | 37.1936 | 132000 | 4.0306 | 5.5354 | 12.3793 |
0.4285 | 37.4753 | 133000 | 4.0258 | 5.1167 | 12.2925 |
0.523 | 37.7571 | 134000 | 4.0267 | 5.8047 | 12.4524 |
0.3715 | 38.0389 | 135000 | 4.0438 | 5.7597 | 12.4354 |
0.3674 | 38.3207 | 136000 | 3.9930 | 6.1216 | 12.4541 |
0.3793 | 38.6024 | 137000 | 4.0552 | 6.1108 | 13.3435 |
0.3747 | 38.8842 | 138000 | 4.0168 | 5.5696 | 12.5221 |
0.389 | 39.1660 | 139000 | 4.0175 | 6.3965 | 12.3129 |
0.4061 | 39.4477 | 140000 | 4.0798 | 5.1006 | 12.3639 |
0.3338 | 39.7295 | 141000 | 4.0164 | 6.1101 | 12.5527 |
0.3705 | 40.0113 | 142000 | 4.0444 | 5.792 | 12.5816 |
0.3427 | 40.2930 | 143000 | 4.0447 | 6.168 | 12.3299 |
0.3149 | 40.5748 | 144000 | 4.0265 | 5.8231 | 12.5136 |
0.3472 | 40.8566 | 145000 | 4.0345 | 5.7867 | 12.4082 |
0.3223 | 41.1383 | 146000 | 4.0590 | 5.6241 | 12.3231 |
0.3431 | 41.4201 | 147000 | 4.0349 | 5.5822 | 12.4269 |
0.4395 | 41.7019 | 148000 | 4.0302 | 6.5229 | 12.4847 |
0.3938 | 41.9837 | 149000 | 4.0265 | 5.342 | 12.6378 |
0.2599 | 42.2654 | 150000 | 4.0707 | 5.9793 | 12.2704 |
0.3762 | 42.5472 | 151000 | 4.0224 | 5.6363 | 12.4201 |
0.3179 | 42.8290 | 152000 | 4.0305 | 5.9502 | 12.398 |
0.3543 | 43.1107 | 153000 | 4.0813 | 5.2724 | 12.5544 |
0.2945 | 43.3925 | 154000 | 4.0662 | 5.7222 | 12.6173 |
0.3365 | 43.6743 | 155000 | 4.0486 | 5.8204 | 12.3844 |
0.3968 | 43.9560 | 156000 | 4.0360 | 6.4448 | 12.3946 |
0.2953 | 44.2378 | 157000 | 4.0809 | 5.8909 | 12.3316 |
0.3124 | 44.5196 | 158000 | 4.0680 | 6.0724 | 12.3673 |
0.3541 | 44.8014 | 159000 | 4.1235 | 5.4862 | 12.4643 |
0.3498 | 45.0831 | 160000 | 4.1072 | 5.4988 | 12.4218 |
0.2302 | 45.3649 | 161000 | 4.0866 | 6.1131 | 12.4949 |
0.3334 | 45.6467 | 162000 | 4.0705 | 5.4186 | 12.2636 |
0.2553 | 45.9284 | 163000 | 4.0683 | 5.1222 | 12.4235 |
0.3323 | 46.2102 | 164000 | 4.0826 | 5.6747 | 12.3435 |
0.3727 | 46.4920 | 165000 | 4.1045 | 5.2927 | 12.4915 |
0.2719 | 46.7737 | 166000 | 4.0688 | 5.7933 | 12.602 |
0.2438 | 47.0555 | 167000 | 4.0558 | 5.8802 | 12.4201 |
0.299 | 47.3373 | 168000 | 4.0920 | 5.8004 | 12.4677 |
0.2265 | 47.6190 | 169000 | 4.0865 | 5.3323 | 12.2959 |
0.3394 | 47.9008 | 170000 | 4.0811 | 6.06 | 12.4728 |
0.3171 | 48.1826 | 171000 | 4.1194 | 5.5842 | 12.2602 |
0.2449 | 48.4644 | 172000 | 4.1103 | 5.6735 | 12.3963 |
0.251 | 48.7461 | 173000 | 4.1100 | 5.8379 | 12.4286 |
0.2751 | 49.0279 | 174000 | 4.1099 | 6.2188 | 12.335 |
0.2092 | 49.3097 | 175000 | 4.1246 | 5.4312 | 12.5 |
0.3027 | 49.5914 | 176000 | 4.1020 | 5.9656 | 12.4235 |
0.2726 | 49.8732 | 177000 | 4.0975 | 5.8563 | 12.352 |
0.3355 | 50.1550 | 178000 | 4.1400 | 5.5961 | 12.4048 |
0.3318 | 50.4367 | 179000 | 4.1176 | 5.552 | 12.2398 |
0.258 | 50.7185 | 180000 | 4.1026 | 5.5698 | 12.5612 |
0.2844 | 51.0003 | 181000 | 4.1100 | 5.8385 | 12.3844 |
0.3333 | 51.2821 | 182000 | 4.1544 | 5.279 | 12.5357 |
0.3354 | 51.5638 | 183000 | 4.1294 | 5.8542 | 12.3401 |
0.3696 | 51.8456 | 184000 | 4.1218 | 6.1838 | 12.6973 |
0.2531 | 52.1274 | 185000 | 4.1469 | 5.7601 | 12.4643 |
0.3164 | 52.4091 | 186000 | 4.1404 | 5.7835 | 12.483 |
0.2798 | 52.6909 | 187000 | 4.1363 | 5.5416 | 12.4558 |
0.3451 | 52.9727 | 188000 | 4.1060 | 5.9834 | 12.199 |
0.2367 | 53.2544 | 189000 | 4.1065 | 5.5443 | 12.2517 |
0.3097 | 53.5362 | 190000 | 4.1561 | 5.0586 | 12.2721 |
0.3095 | 53.8180 | 191000 | 4.1224 | 5.0179 | 12.3605 |
0.3136 | 54.0997 | 192000 | 4.1166 | 5.3843 | 12.2092 |
0.3378 | 54.3815 | 193000 | 4.1014 | 5.3635 | 12.4354 |
0.2455 | 54.6633 | 194000 | 4.1045 | 5.6129 | 12.2993 |
0.2602 | 54.9451 | 195000 | 4.1279 | 5.4261 | 12.3265 |
0.1915 | 55.2268 | 196000 | 4.1436 | 5.7783 | 12.3707 |
0.3043 | 55.5086 | 197000 | 4.1118 | 6.2683 | 12.2789 |
0.2176 | 55.7904 | 198000 | 4.1652 | 6.6306 | 12.4779 |
0.248 | 56.0721 | 199000 | 4.1313 | 5.9143 | 12.4575 |
0.206 | 56.3539 | 200000 | 4.1675 | 5.5853 | 12.2568 |
0.2585 | 56.6357 | 201000 | 4.1577 | 6.0128 | 12.2109 |
0.2898 | 56.9174 | 202000 | 4.1651 | 5.4022 | 12.3605 |
0.2148 | 57.1992 | 203000 | 4.1522 | 6.0579 | 12.4116 |
0.2166 | 57.4810 | 204000 | 4.1468 | 5.7765 | 12.3503 |
0.1717 | 57.7628 | 205000 | 4.1773 | 5.4721 | 12.3844 |
0.2307 | 58.0445 | 206000 | 4.1929 | 5.5199 | 12.4728 |
0.2147 | 58.3263 | 207000 | 4.1864 | 5.8921 | 12.398 |
0.3206 | 58.6081 | 208000 | 4.1580 | 5.5847 | 12.3759 |
0.2578 | 58.8898 | 209000 | 4.1650 | 6.0606 | 12.6327 |
0.2452 | 59.1716 | 210000 | 4.1734 | 5.9271 | 12.4898 |
0.3153 | 59.4534 | 211000 | 4.1873 | 5.6806 | 12.4014 |
0.2537 | 59.7351 | 212000 | 4.1678 | 6.0832 | 12.4779 |
0.2766 | 60.0169 | 213000 | 4.1804 | 5.8076 | 12.5629 |
0.2737 | 60.2987 | 214000 | 4.1697 | 6.2846 | 12.466 |
0.2482 | 60.5804 | 215000 | 4.1712 | 5.6849 | 12.5425 |
0.1802 | 60.8622 | 216000 | 4.1557 | 5.8134 | 12.6003 |
0.2827 | 61.1440 | 217000 | 4.1656 | 6.0754 | 12.3776 |
0.2857 | 61.4258 | 218000 | 4.1624 | 5.9286 | 12.5391 |
0.291 | 61.7075 | 219000 | 4.1544 | 6.145 | 12.4507 |
0.2214 | 61.9893 | 220000 | 4.1949 | 5.9543 | 12.4949 |
0.2436 | 62.2711 | 221000 | 4.1727 | 6.1127 | 12.4303 |
0.2582 | 62.5528 | 222000 | 4.2067 | 5.7992 | 12.5136 |
0.23 | 62.8346 | 223000 | 4.1694 | 5.4996 | 12.4286 |
0.209 | 63.1164 | 224000 | 4.1618 | 5.8511 | 12.3997 |
0.2134 | 63.3981 | 225000 | 4.1621 | 5.2983 | 12.4354 |
0.2226 | 63.6799 | 226000 | 4.1655 | 5.6395 | 12.4235 |
0.2861 | 63.9617 | 227000 | 4.1641 | 5.9785 | 12.2517 |
0.2351 | 64.2434 | 228000 | 4.1837 | 5.8553 | 12.3639 |
0.2261 | 64.5252 | 229000 | 4.1830 | 6.0539 | 12.4898 |
0.2255 | 64.8070 | 230000 | 4.1711 | 6.0776 | 12.3299 |
0.2613 | 65.0888 | 231000 | 4.1731 | 5.8676 | 12.233 |
0.1856 | 65.3705 | 232000 | 4.1887 | 5.5836 | 12.4524 |
0.312 | 65.6523 | 233000 | 4.1753 | 6.0583 | 12.2619 |
0.2257 | 65.9341 | 234000 | 4.1714 | 5.8171 | 12.3078 |
0.1503 | 66.2158 | 235000 | 4.1956 | 5.426 | 12.3759 |
0.1848 | 66.4976 | 236000 | 4.1898 | 5.6991 | 12.4014 |
0.3011 | 66.7794 | 237000 | 4.1736 | 5.8647 | 12.2874 |
0.1732 | 67.0611 | 238000 | 4.1728 | 6.1514 | 12.3656 |
0.234 | 67.3429 | 239000 | 4.1752 | 6.0253 | 12.3605 |
0.2339 | 67.6247 | 240000 | 4.1823 | 5.9876 | 12.3537 |
0.2308 | 67.9065 | 241000 | 4.1771 | 5.8004 | 12.318 |
0.1786 | 68.1882 | 242000 | 4.1900 | 5.7665 | 12.3776 |
0.2798 | 68.4700 | 243000 | 4.1912 | 5.3805 | 12.4813 |
0.1909 | 68.7518 | 244000 | 4.1957 | 5.5789 | 12.3316 |
0.2507 | 69.0335 | 245000 | 4.1827 | 6.3051 | 12.3571 |
0.2624 | 69.3153 | 246000 | 4.1974 | 5.5198 | 12.4864 |
0.1791 | 69.5971 | 247000 | 4.1976 | 5.7578 | 12.3656 |
0.1775 | 69.8788 | 248000 | 4.1961 | 5.6335 | 12.3963 |
0.2513 | 70.1606 | 249000 | 4.2038 | 5.6398 | 12.4779 |
0.2948 | 70.4424 | 250000 | 4.2009 | 5.393 | 12.3997 |
0.2242 | 70.7241 | 251000 | 4.1999 | 6.0895 | 12.4048 |
0.2233 | 71.0059 | 252000 | 4.1914 | 5.9331 | 12.3844 |
0.2887 | 71.2877 | 253000 | 4.2089 | 5.74 | 12.3895 |
0.1813 | 71.5695 | 254000 | 4.1956 | 5.9129 | 12.3231 |
0.1833 | 71.8512 | 255000 | 4.2093 | 6.0013 | 12.3656 |
0.2388 | 72.1330 | 256000 | 4.2115 | 6.1846 | 12.4014 |
0.1976 | 72.4148 | 257000 | 4.1903 | 6.3826 | 12.3588 |
0.2634 | 72.6965 | 258000 | 4.1972 | 6.386 | 12.3776 |
0.2941 | 72.9783 | 259000 | 4.1984 | 6.2805 | 12.3095 |
0.216 | 73.2601 | 260000 | 4.2034 | 6.3926 | 12.4269 |
0.1399 | 73.5418 | 261000 | 4.1849 | 5.9895 | 12.369 |
0.2904 | 73.8236 | 262000 | 4.2011 | 6.1283 | 12.4065 |
0.2138 | 74.1054 | 263000 | 4.1925 | 6.066 | 12.4507 |
0.1536 | 74.3872 | 264000 | 4.2179 | 6.1395 | 12.381 |
0.2372 | 74.6689 | 265000 | 4.2120 | 6.0845 | 12.3299 |
0.2804 | 74.9507 | 266000 | 4.2006 | 6.1166 | 12.2636 |
0.1871 | 75.2325 | 267000 | 4.1990 | 5.8443 | 12.3469 |
0.1961 | 75.5142 | 268000 | 4.2011 | 6.0937 | 12.3759 |
0.2312 | 75.7960 | 269000 | 4.1971 | 5.5331 | 12.4048 |
0.1819 | 76.0778 | 270000 | 4.2077 | 6.038 | 12.4473 |
0.2367 | 76.3595 | 271000 | 4.2041 | 6.2777 | 12.2483 |
0.1884 | 76.6413 | 272000 | 4.1892 | 5.9922 | 12.3401 |
0.1694 | 76.9231 | 273000 | 4.1823 | 6.2656 | 12.4048 |
0.1893 | 77.2048 | 274000 | 4.2002 | 5.9031 | 12.3793 |
0.2318 | 77.4866 | 275000 | 4.2000 | 5.7382 | 12.3912 |
0.2575 | 77.7684 | 276000 | 4.2083 | 5.768 | 12.3912 |
0.2384 | 78.0502 | 277000 | 4.2102 | 5.9539 | 12.3248 |
0.268 | 78.3319 | 278000 | 4.1935 | 5.707 | 12.3401 |
0.2658 | 78.6137 | 279000 | 4.2094 | 5.7808 | 12.3776 |
0.2589 | 78.8955 | 280000 | 4.2178 | 5.5411 | 12.4116 |
0.2225 | 79.1772 | 281000 | 4.2021 | 5.7789 | 12.3367 |
0.2213 | 79.4590 | 282000 | 4.2116 | 5.767 | 12.369 |
0.2081 | 79.7408 | 283000 | 4.2114 | 5.7176 | 12.3078 |
0.2786 | 80.0225 | 284000 | 4.2036 | 6.129 | 12.4099 |
0.2541 | 80.3043 | 285000 | 4.2132 | 5.5592 | 12.4235 |
0.2255 | 80.5861 | 286000 | 4.2178 | 5.7686 | 12.4031 |
0.2093 | 80.8679 | 287000 | 4.2179 | 5.4645 | 12.4201 |
0.17 | 81.1496 | 288000 | 4.1991 | 5.7745 | 12.466 |
0.2063 | 81.4314 | 289000 | 4.2089 | 6.1465 | 12.3827 |
0.1792 | 81.7132 | 290000 | 4.2184 | 5.7794 | 12.4048 |
0.2161 | 81.9949 | 291000 | 4.2161 | 5.6144 | 12.4201 |
0.2446 | 82.2767 | 292000 | 4.2256 | 5.4788 | 12.3861 |
0.2079 | 82.5585 | 293000 | 4.2191 | 6.1511 | 12.3588 |
0.2454 | 82.8402 | 294000 | 4.2200 | 5.961 | 12.3759 |
0.2071 | 83.1220 | 295000 | 4.2177 | 5.7499 | 12.3027 |
0.1933 | 83.4038 | 296000 | 4.2114 | 5.678 | 12.4405 |
0.2021 | 83.6855 | 297000 | 4.2143 | 5.9974 | 12.3282 |
0.1171 | 83.9673 | 298000 | 4.2149 | 6.1963 | 12.2653 |
0.2037 | 84.2491 | 299000 | 4.2155 | 5.8778 | 12.3741 |
0.2334 | 84.5309 | 300000 | 4.2185 | 6.118 | 12.3503 |
0.2249 | 84.8126 | 301000 | 4.2220 | 5.5555 | 12.352 |
0.165 | 85.0944 | 302000 | 4.2190 | 5.7333 | 12.466 |
0.221 | 85.3762 | 303000 | 4.2166 | 5.7269 | 12.381 |
0.2096 | 85.6579 | 304000 | 4.2178 | 6.0586 | 12.3741 |
0.1987 | 85.9397 | 305000 | 4.2190 | 5.7207 | 12.4048 |
0.167 | 86.2215 | 306000 | 4.2173 | 6.0351 | 12.3707 |
0.2393 | 86.5032 | 307000 | 4.2182 | 5.7082 | 12.3929 |
0.1534 | 86.7850 | 308000 | 4.2126 | 6.0868 | 12.352 |
0.2111 | 87.0668 | 309000 | 4.2144 | 5.7289 | 12.4252 |
0.1406 | 87.3485 | 310000 | 4.2186 | 5.6563 | 12.3622 |
0.2101 | 87.6303 | 311000 | 4.2136 | 6.1556 | 12.284 |
0.299 | 87.9121 | 312000 | 4.2133 | 6.1065 | 12.4048 |
0.1847 | 88.1939 | 313000 | 4.2171 | 5.6516 | 12.415 |
0.21 | 88.4756 | 314000 | 4.2103 | 5.5123 | 12.3724 |
0.21 | 88.7574 | 315000 | 4.2190 | 5.6371 | 12.3622 |
0.2084 | 89.0392 | 316000 | 4.2176 | 5.8385 | 12.3418 |
0.2804 | 89.3209 | 317000 | 4.2187 | 5.7461 | 12.2976 |
0.1835 | 89.6027 | 318000 | 4.2159 | 5.6402 | 12.3571 |
0.2133 | 89.8845 | 319000 | 4.2195 | 5.6875 | 12.335 |
0.1721 | 90.1662 | 320000 | 4.2174 | 5.7841 | 12.3912 |
0.2426 | 90.4480 | 321000 | 4.2199 | 5.6429 | 12.3588 |
0.2258 | 90.7298 | 322000 | 4.2182 | 5.7101 | 12.3724 |
0.1557 | 91.0116 | 323000 | 4.2216 | 5.8473 | 12.3299 |
0.2095 | 91.2933 | 324000 | 4.2167 | 5.6265 | 12.3844 |
0.1772 | 91.5751 | 325000 | 4.2194 | 5.6292 | 12.3639 |
0.1749 | 91.8569 | 326000 | 4.2198 | 5.6485 | 12.4167 |
0.1701 | 92.1386 | 327000 | 4.2191 | 5.6476 | 12.3707 |
0.175 | 92.4204 | 328000 | 4.2155 | 5.645 | 12.3724 |
0.1707 | 92.7022 | 329000 | 4.2192 | 5.6179 | 12.3759 |
0.2148 | 92.9839 | 330000 | 4.2193 | 5.7088 | 12.3929 |
0.1856 | 93.2657 | 331000 | 4.2184 | 5.7813 | 12.4184 |
0.1708 | 93.5475 | 332000 | 4.2202 | 6.0236 | 12.3759 |
0.2343 | 93.8292 | 333000 | 4.2163 | 5.6981 | 12.3605 |
0.1501 | 94.1110 | 334000 | 4.2171 | 5.646 | 12.3724 |
0.1712 | 94.3928 | 335000 | 4.2171 | 5.5863 | 12.3435 |
0.1829 | 94.6746 | 336000 | 4.2179 | 5.6682 | 12.369 |
0.2103 | 94.9563 | 337000 | 4.2161 | 5.6451 | 12.3469 |
0.2558 | 95.2381 | 338000 | 4.2193 | 5.6779 | 12.3605 |
0.1588 | 95.5199 | 339000 | 4.2154 | 5.631 | 12.3571 |
0.2006 | 95.8016 | 340000 | 4.2179 | 5.6801 | 12.3588 |
0.1557 | 96.0834 | 341000 | 4.2189 | 5.6284 | 12.3486 |
0.1578 | 96.3652 | 342000 | 4.2187 | 5.6162 | 12.3673 |
0.2362 | 96.6469 | 343000 | 4.2175 | 5.6229 | 12.3469 |
0.1842 | 96.9287 | 344000 | 4.2155 | 5.6873 | 12.3707 |
0.1538 | 97.2105 | 345000 | 4.2186 | 5.6718 | 12.3673 |
0.1835 | 97.4923 | 346000 | 4.2176 | 5.6941 | 12.3776 |
0.2025 | 97.7740 | 347000 | 4.2179 | 5.6932 | 12.3741 |
0.237 | 98.0558 | 348000 | 4.2172 | 5.7099 | 12.3639 |
0.2197 | 98.3376 | 349000 | 4.2184 | 5.6963 | 12.369 |
0.2156 | 98.6193 | 350000 | 4.2177 | 5.6641 | 12.3282 |
0.2155 | 98.9011 | 351000 | 4.2173 | 5.6229 | 12.3946 |
0.257 | 99.1829 | 352000 | 4.2169 | 5.6288 | 12.3861 |
0.2328 | 99.4646 | 353000 | 4.2171 | 5.6672 | 12.398 |
0.1887 | 99.7464 | 354000 | 4.2174 | 5.5922 | 12.3639 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0
- Downloads last month
- 17
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for BounharAbdelaziz/Terjman-Large-v2.0
Base model
Helsinki-NLP/opus-mt-tc-big-en-ar