--- license: mit base_model: facebook/m2m100_418M tags: - generated_from_trainer model-index: - name: output results: [] --- # output This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co./facebook/m2m100_418M) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6652 ## 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-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 15 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 3.8819 | 0.07 | 100 | 0.7677 | | 0.7529 | 0.13 | 200 | 0.6311 | | 0.6575 | 0.2 | 300 | 0.6079 | | 0.6478 | 0.27 | 400 | 0.5925 | | 0.5882 | 0.33 | 500 | 0.5750 | | 0.5882 | 0.4 | 600 | 0.5681 | | 0.5635 | 0.47 | 700 | 0.5575 | | 0.6301 | 0.53 | 800 | 0.5525 | | 0.5667 | 0.6 | 900 | 0.5472 | | 0.5591 | 0.66 | 1000 | 0.5430 | | 0.5761 | 0.73 | 1100 | 0.5298 | | 0.556 | 0.8 | 1200 | 0.5318 | | 0.5664 | 0.86 | 1300 | 0.5235 | | 0.5494 | 0.93 | 1400 | 0.5200 | | 0.5416 | 1.0 | 1500 | 0.5171 | | 0.4251 | 1.06 | 1600 | 0.5248 | | 0.4447 | 1.13 | 1700 | 0.5271 | | 0.437 | 1.2 | 1800 | 0.5172 | | 0.4064 | 1.26 | 1900 | 0.5146 | | 0.413 | 1.33 | 2000 | 0.5130 | | 0.4364 | 1.4 | 2100 | 0.5132 | | 0.4002 | 1.46 | 2200 | 0.5203 | | 0.4441 | 1.53 | 2300 | 0.5078 | | 0.4179 | 1.6 | 2400 | 0.5057 | | 0.4438 | 1.66 | 2500 | 0.5039 | | 0.4394 | 1.73 | 2600 | 0.5064 | | 0.4581 | 1.8 | 2700 | 0.5007 | | 0.4366 | 1.86 | 2800 | 0.4977 | | 0.4464 | 1.93 | 2900 | 0.4965 | | 0.447 | 1.99 | 3000 | 0.4940 | | 0.3333 | 2.06 | 3100 | 0.5052 | | 0.3355 | 2.13 | 3200 | 0.5053 | | 0.3227 | 2.19 | 3300 | 0.5066 | | 0.3298 | 2.26 | 3400 | 0.5072 | | 0.3276 | 2.33 | 3500 | 0.5075 | | 0.3252 | 2.39 | 3600 | 0.5025 | | 0.3132 | 2.46 | 3700 | 0.5022 | | 0.3247 | 2.53 | 3800 | 0.5062 | | 0.3311 | 2.59 | 3900 | 0.5010 | | 0.3385 | 2.66 | 4000 | 0.5019 | | 0.3496 | 2.73 | 4100 | 0.5010 | | 0.3164 | 2.79 | 4200 | 0.4975 | | 0.3458 | 2.86 | 4300 | 0.4989 | | 0.3288 | 2.93 | 4400 | 0.5002 | | 0.3341 | 2.99 | 4500 | 0.5034 | | 0.2293 | 3.06 | 4600 | 0.5090 | | 0.2301 | 3.12 | 4700 | 0.5108 | | 0.2253 | 3.19 | 4800 | 0.5088 | | 0.2288 | 3.26 | 4900 | 0.5117 | | 0.238 | 3.32 | 5000 | 0.5157 | | 0.2487 | 3.39 | 5100 | 0.5129 | | 0.2358 | 3.46 | 5200 | 0.5139 | | 0.2491 | 3.52 | 5300 | 0.5185 | | 0.2326 | 3.59 | 5400 | 0.5097 | | 0.243 | 3.66 | 5500 | 0.5142 | | 0.2635 | 3.72 | 5600 | 0.5094 | | 0.2568 | 3.79 | 5700 | 0.5136 | | 0.2608 | 3.86 | 5800 | 0.5053 | | 0.2709 | 3.92 | 5900 | 0.5104 | | 0.2442 | 3.99 | 6000 | 0.5116 | | 0.183 | 4.06 | 6100 | 0.5199 | | 0.1657 | 4.12 | 6200 | 0.5228 | | 0.1537 | 4.19 | 6300 | 0.5230 | | 0.1634 | 4.26 | 6400 | 0.5232 | | 0.1679 | 4.32 | 6500 | 0.5270 | | 0.1695 | 4.39 | 6600 | 0.5293 | | 0.1872 | 4.45 | 6700 | 0.5279 | | 0.1723 | 4.52 | 6800 | 0.5256 | | 0.1624 | 4.59 | 6900 | 0.5320 | | 0.1708 | 4.65 | 7000 | 0.5289 | | 0.1826 | 4.72 | 7100 | 0.5369 | | 0.1772 | 4.79 | 7200 | 0.5331 | | 0.1672 | 4.85 | 7300 | 0.5287 | | 0.1824 | 4.92 | 7400 | 0.5317 | | 0.1782 | 4.99 | 7500 | 0.5309 | | 0.1177 | 5.05 | 7600 | 0.5414 | | 0.1114 | 5.12 | 7700 | 0.5450 | | 0.1117 | 5.19 | 7800 | 0.5491 | | 0.1118 | 5.25 | 7900 | 0.5474 | | 0.1105 | 5.32 | 8000 | 0.5478 | | 0.1015 | 5.39 | 8100 | 0.5515 | | 0.1085 | 5.45 | 8200 | 0.5502 | | 0.1165 | 5.52 | 8300 | 0.5581 | | 0.1193 | 5.59 | 8400 | 0.5529 | | 0.1233 | 5.65 | 8500 | 0.5556 | | 0.122 | 5.72 | 8600 | 0.5494 | | 0.1261 | 5.78 | 8700 | 0.5515 | | 0.126 | 5.85 | 8800 | 0.5516 | | 0.1165 | 5.92 | 8900 | 0.5488 | | 0.1208 | 5.98 | 9000 | 0.5505 | | 0.0772 | 6.05 | 9100 | 0.5591 | | 0.0709 | 6.12 | 9200 | 0.5588 | | 0.0759 | 6.18 | 9300 | 0.5642 | | 0.0672 | 6.25 | 9400 | 0.5669 | | 0.0736 | 6.32 | 9500 | 0.5630 | | 0.0785 | 6.38 | 9600 | 0.5730 | | 0.0721 | 6.45 | 9700 | 0.5720 | | 0.0809 | 6.52 | 9800 | 0.5769 | | 0.0787 | 6.58 | 9900 | 0.5790 | | 0.0776 | 6.65 | 10000 | 0.5713 | | 0.0821 | 6.72 | 10100 | 0.5713 | | 0.0735 | 6.78 | 10200 | 0.5727 | | 0.0742 | 6.85 | 10300 | 0.5780 | | 0.0813 | 6.91 | 10400 | 0.5747 | | 0.0823 | 6.98 | 10500 | 0.5731 | | 0.0521 | 7.05 | 10600 | 0.5849 | | 0.0471 | 7.11 | 10700 | 0.5842 | | 0.0433 | 7.18 | 10800 | 0.5870 | | 0.0463 | 7.25 | 10900 | 0.5889 | | 0.0512 | 7.31 | 11000 | 0.5913 | | 0.0461 | 7.38 | 11100 | 0.5874 | | 0.0521 | 7.45 | 11200 | 0.5943 | | 0.0434 | 7.51 | 11300 | 0.5940 | | 0.0522 | 7.58 | 11400 | 0.5980 | | 0.0607 | 7.65 | 11500 | 0.5891 | | 0.049 | 7.71 | 11600 | 0.5916 | | 0.0494 | 7.78 | 11700 | 0.5960 | | 0.0526 | 7.85 | 11800 | 0.5942 | | 0.0505 | 7.91 | 11900 | 0.5972 | | 0.0579 | 7.98 | 12000 | 0.5930 | | 0.038 | 8.05 | 12100 | 0.6054 | | 0.0295 | 8.11 | 12200 | 0.6017 | | 0.0303 | 8.18 | 12300 | 0.6020 | | 0.0348 | 8.24 | 12400 | 0.6052 | | 0.0318 | 8.31 | 12500 | 0.6103 | | 0.0369 | 8.38 | 12600 | 0.6079 | | 0.0373 | 8.44 | 12700 | 0.6050 | | 0.0319 | 8.51 | 12800 | 0.6095 | | 0.0348 | 8.58 | 12900 | 0.6066 | | 0.0326 | 8.64 | 13000 | 0.6084 | | 0.0335 | 8.71 | 13100 | 0.6148 | | 0.0303 | 8.78 | 13200 | 0.6142 | | 0.0409 | 8.84 | 13300 | 0.6190 | | 0.0357 | 8.91 | 13400 | 0.6121 | | 0.0351 | 8.98 | 13500 | 0.6121 | | 0.0254 | 9.04 | 13600 | 0.6203 | | 0.0215 | 9.11 | 13700 | 0.6235 | | 0.0214 | 9.18 | 13800 | 0.6243 | | 0.0226 | 9.24 | 13900 | 0.6199 | | 0.0224 | 9.31 | 14000 | 0.6225 | | 0.0226 | 9.38 | 14100 | 0.6236 | | 0.0224 | 9.44 | 14200 | 0.6261 | | 0.0262 | 9.51 | 14300 | 0.6259 | | 0.022 | 9.57 | 14400 | 0.6223 | | 0.0248 | 9.64 | 14500 | 0.6275 | | 0.0236 | 9.71 | 14600 | 0.6261 | | 0.022 | 9.77 | 14700 | 0.6303 | | 0.0225 | 9.84 | 14800 | 0.6290 | | 0.0248 | 9.91 | 14900 | 0.6299 | | 0.0233 | 9.97 | 15000 | 0.6302 | | 0.021 | 10.04 | 15100 | 0.6297 | | 0.0153 | 10.11 | 15200 | 0.6355 | | 0.015 | 10.17 | 15300 | 0.6321 | | 0.0153 | 10.24 | 15400 | 0.6349 | | 0.0168 | 10.31 | 15500 | 0.6310 | | 0.0155 | 10.37 | 15600 | 0.6352 | | 0.0153 | 10.44 | 15700 | 0.6391 | | 0.0189 | 10.51 | 15800 | 0.6373 | | 0.0166 | 10.57 | 15900 | 0.6370 | | 0.016 | 10.64 | 16000 | 0.6348 | | 0.0191 | 10.7 | 16100 | 0.6381 | | 0.0172 | 10.77 | 16200 | 0.6394 | | 0.0171 | 10.84 | 16300 | 0.6408 | | 0.0185 | 10.9 | 16400 | 0.6378 | | 0.0167 | 10.97 | 16500 | 0.6437 | | 0.016 | 11.04 | 16600 | 0.6447 | | 0.0127 | 11.1 | 16700 | 0.6408 | | 0.0131 | 11.17 | 16800 | 0.6454 | | 0.0117 | 11.24 | 16900 | 0.6471 | | 0.0125 | 11.3 | 17000 | 0.6484 | | 0.0135 | 11.37 | 17100 | 0.6517 | | 0.0122 | 11.44 | 17200 | 0.6462 | | 0.0132 | 11.5 | 17300 | 0.6505 | | 0.012 | 11.57 | 17400 | 0.6524 | | 0.0152 | 11.64 | 17500 | 0.6491 | | 0.0147 | 11.7 | 17600 | 0.6506 | | 0.0144 | 11.77 | 17700 | 0.6482 | | 0.0143 | 11.84 | 17800 | 0.6482 | | 0.0121 | 11.9 | 17900 | 0.6475 | | 0.0131 | 11.97 | 18000 | 0.6480 | | 0.0113 | 12.03 | 18100 | 0.6491 | | 0.0117 | 12.1 | 18200 | 0.6543 | | 0.0092 | 12.17 | 18300 | 0.6575 | | 0.0102 | 12.23 | 18400 | 0.6530 | | 0.0099 | 12.3 | 18500 | 0.6612 | | 0.0099 | 12.37 | 18600 | 0.6547 | | 0.0089 | 12.43 | 18700 | 0.6553 | | 0.01 | 12.5 | 18800 | 0.6581 | | 0.0092 | 12.57 | 18900 | 0.6579 | | 0.0092 | 12.63 | 19000 | 0.6558 | | 0.0099 | 12.7 | 19100 | 0.6563 | | 0.0099 | 12.77 | 19200 | 0.6578 | | 0.0103 | 12.83 | 19300 | 0.6589 | | 0.0093 | 12.9 | 19400 | 0.6582 | | 0.0093 | 12.97 | 19500 | 0.6582 | | 0.0078 | 13.03 | 19600 | 0.6604 | | 0.0073 | 13.1 | 19700 | 0.6606 | | 0.0082 | 13.16 | 19800 | 0.6582 | | 0.0075 | 13.23 | 19900 | 0.6614 | | 0.0073 | 13.3 | 20000 | 0.6636 | | 0.0072 | 13.36 | 20100 | 0.6578 | | 0.0074 | 13.43 | 20200 | 0.6606 | | 0.009 | 13.5 | 20300 | 0.6623 | | 0.0149 | 13.56 | 20400 | 0.6615 | | 0.0078 | 13.63 | 20500 | 0.6616 | | 0.0069 | 13.7 | 20600 | 0.6653 | | 0.0085 | 13.76 | 20700 | 0.6607 | | 0.0074 | 13.83 | 20800 | 0.6619 | | 0.0088 | 13.9 | 20900 | 0.6621 | | 0.0069 | 13.96 | 21000 | 0.6613 | | 0.0076 | 14.03 | 21100 | 0.6630 | | 0.0062 | 14.1 | 21200 | 0.6635 | | 0.007 | 14.16 | 21300 | 0.6623 | | 0.0066 | 14.23 | 21400 | 0.6627 | | 0.0067 | 14.3 | 21500 | 0.6620 | | 0.0066 | 14.36 | 21600 | 0.6604 | | 0.0068 | 14.43 | 21700 | 0.6620 | | 0.0069 | 14.49 | 21800 | 0.6629 | | 0.0088 | 14.56 | 21900 | 0.6625 | | 0.0069 | 14.63 | 22000 | 0.6642 | | 0.0063 | 14.69 | 22100 | 0.6645 | | 0.0074 | 14.76 | 22200 | 0.6652 | | 0.0053 | 14.83 | 22300 | 0.6652 | | 0.0076 | 14.89 | 22400 | 0.6652 | | 0.0068 | 14.96 | 22500 | 0.6652 | ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.2 - Datasets 2.1.0 - Tokenizers 0.15.2