--- library_name: transformers license: apache-2.0 base_model: HuggingFaceTB/SmolLM2-135M tags: - generated_from_trainer model-index: - name: smolchess results: [] --- # smolchess This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.8688 ## 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: 3e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Use grokadamw with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - num_epochs: 0.25 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 1.4847 | 0.0025 | 4 | 1.3890 | | 1.2333 | 0.0050 | 8 | 1.2242 | | 1.2154 | 0.0075 | 12 | 1.1705 | | 1.1268 | 0.0100 | 16 | 1.1241 | | 1.0556 | 0.0125 | 20 | 1.1055 | | 1.0629 | 0.0150 | 24 | 1.0848 | | 1.1023 | 0.0176 | 28 | 1.0764 | | 1.102 | 0.0201 | 32 | 1.0554 | | 1.0798 | 0.0226 | 36 | 1.0567 | | 0.9436 | 0.0251 | 40 | 1.0365 | | 1.0524 | 0.0276 | 44 | 1.0275 | | 1.1201 | 0.0301 | 48 | 1.0198 | | 1.0565 | 0.0326 | 52 | 1.0135 | | 0.9082 | 0.0351 | 56 | 1.0084 | | 1.0544 | 0.0376 | 60 | 0.9970 | | 1.0034 | 0.0401 | 64 | 0.9939 | | 0.8859 | 0.0426 | 68 | 0.9852 | | 1.018 | 0.0451 | 72 | 0.9816 | | 0.8901 | 0.0476 | 76 | 0.9761 | | 0.8943 | 0.0502 | 80 | 0.9723 | | 1.0486 | 0.0527 | 84 | 0.9718 | | 1.0102 | 0.0552 | 88 | 0.9680 | | 0.9617 | 0.0577 | 92 | 0.9602 | | 0.9879 | 0.0602 | 96 | 0.9607 | | 0.9482 | 0.0627 | 100 | 0.9523 | | 1.0265 | 0.0652 | 104 | 0.9518 | | 0.8865 | 0.0677 | 108 | 0.9493 | | 1.0046 | 0.0702 | 112 | 0.9448 | | 0.9593 | 0.0727 | 116 | 0.9384 | | 1.0167 | 0.0752 | 120 | 0.9377 | | 0.9041 | 0.0777 | 124 | 0.9345 | | 0.8702 | 0.0803 | 128 | 0.9311 | | 0.9117 | 0.0828 | 132 | 0.9333 | | 0.936 | 0.0853 | 136 | 0.9262 | | 0.9341 | 0.0878 | 140 | 0.9237 | | 0.913 | 0.0903 | 144 | 0.9219 | | 0.9205 | 0.0928 | 148 | 0.9204 | | 0.9081 | 0.0953 | 152 | 0.9183 | | 0.8826 | 0.0978 | 156 | 0.9162 | | 0.9578 | 0.1003 | 160 | 0.9142 | | 0.845 | 0.1028 | 164 | 0.9128 | | 0.9254 | 0.1053 | 168 | 0.9102 | | 0.9622 | 0.1078 | 172 | 0.9096 | | 0.7854 | 0.1103 | 176 | 0.9085 | | 0.9143 | 0.1129 | 180 | 0.9071 | | 0.99 | 0.1154 | 184 | 0.9043 | | 0.9855 | 0.1179 | 188 | 0.9038 | | 0.9745 | 0.1204 | 192 | 0.9017 | | 0.9532 | 0.1229 | 196 | 0.8998 | | 0.9464 | 0.1254 | 200 | 0.8989 | | 0.8713 | 0.1279 | 204 | 0.8962 | | 0.8501 | 0.1304 | 208 | 0.8942 | | 0.9065 | 0.1329 | 212 | 0.8936 | | 0.8949 | 0.1354 | 216 | 0.8924 | | 0.9504 | 0.1379 | 220 | 0.8900 | | 0.9059 | 0.1404 | 224 | 0.8900 | | 0.909 | 0.1429 | 228 | 0.8881 | | 0.9684 | 0.1455 | 232 | 0.8864 | | 0.968 | 0.1480 | 236 | 0.8865 | | 0.9436 | 0.1505 | 240 | 0.8853 | | 0.9166 | 0.1530 | 244 | 0.8841 | | 0.977 | 0.1555 | 248 | 0.8825 | | 0.9011 | 0.1580 | 252 | 0.8820 | | 0.8842 | 0.1605 | 256 | 0.8812 | | 0.9399 | 0.1630 | 260 | 0.8806 | | 0.9211 | 0.1655 | 264 | 0.8791 | | 0.8043 | 0.1680 | 268 | 0.8785 | | 0.8406 | 0.1705 | 272 | 0.8778 | | 0.8463 | 0.1730 | 276 | 0.8765 | | 0.8638 | 0.1755 | 280 | 0.8762 | | 0.894 | 0.1781 | 284 | 0.8761 | | 0.8925 | 0.1806 | 288 | 0.8753 | | 0.9029 | 0.1831 | 292 | 0.8754 | | 0.809 | 0.1856 | 296 | 0.8749 | | 0.9558 | 0.1881 | 300 | 0.8742 | | 0.8286 | 0.1906 | 304 | 0.8736 | | 0.8714 | 0.1931 | 308 | 0.8730 | | 0.8562 | 0.1956 | 312 | 0.8728 | | 0.858 | 0.1981 | 316 | 0.8723 | | 0.9027 | 0.2006 | 320 | 0.8719 | | 0.9023 | 0.2031 | 324 | 0.8716 | | 0.856 | 0.2056 | 328 | 0.8712 | | 0.8455 | 0.2082 | 332 | 0.8709 | | 0.8886 | 0.2107 | 336 | 0.8705 | | 0.8717 | 0.2132 | 340 | 0.8703 | | 0.9145 | 0.2157 | 344 | 0.8700 | | 0.9618 | 0.2182 | 348 | 0.8698 | | 0.9083 | 0.2207 | 352 | 0.8697 | | 0.9448 | 0.2232 | 356 | 0.8695 | | 0.9188 | 0.2257 | 360 | 0.8693 | | 0.8006 | 0.2282 | 364 | 0.8692 | | 0.8222 | 0.2307 | 368 | 0.8691 | | 0.8936 | 0.2332 | 372 | 0.8690 | | 0.9366 | 0.2357 | 376 | 0.8689 | | 0.9336 | 0.2382 | 380 | 0.8689 | | 0.6878 | 0.2408 | 384 | 0.8689 | | 0.9405 | 0.2433 | 388 | 0.8688 | | 0.9022 | 0.2458 | 392 | 0.8688 | | 0.8499 | 0.2483 | 396 | 0.8688 | ### Framework versions - Transformers 4.46.1 - Pytorch 2.4.1+cu121 - Datasets 3.1.0 - Tokenizers 0.20.1