--- library_name: transformers license: apache-2.0 base_model: amd/AMD-Llama-135m tags: - generated_from_trainer model-index: - name: amdchess-v4 results: [] --- <!-- 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. --> # amdchess-v4 This model is a fine-tuned version of [amd/AMD-Llama-135m](https://huggingface.co/amd/AMD-Llama-135m) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.7971 ## 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 | |:-------------:|:------:|:----:|:---------------:| | 9.9629 | 0.0030 | 5 | 5.6096 | | 3.7446 | 0.0059 | 10 | 3.3680 | | 2.524 | 0.0089 | 15 | 2.3223 | | 1.9286 | 0.0118 | 20 | 1.7446 | | 1.5475 | 0.0148 | 25 | 2.0681 | | 1.2838 | 0.0177 | 30 | 1.4096 | | 1.3152 | 0.0207 | 35 | 1.2730 | | 1.2488 | 0.0236 | 40 | 1.2203 | | 1.088 | 0.0266 | 45 | 1.1461 | | 1.0479 | 0.0295 | 50 | 1.1139 | | 1.0758 | 0.0325 | 55 | 1.0844 | | 1.1275 | 0.0354 | 60 | 1.0443 | | 1.1378 | 0.0384 | 65 | 1.0260 | | 1.0147 | 0.0413 | 70 | 0.9939 | | 0.993 | 0.0443 | 75 | 1.0074 | | 1.0132 | 0.0472 | 80 | 0.9866 | | 0.9155 | 0.0502 | 85 | 0.9697 | | 0.9656 | 0.0531 | 90 | 0.9757 | | 1.0402 | 0.0561 | 95 | 0.9633 | | 0.9759 | 0.0590 | 100 | 0.9528 | | 0.9505 | 0.0620 | 105 | 0.9501 | | 1.0114 | 0.0649 | 110 | 0.9405 | | 1.0182 | 0.0679 | 115 | 0.9212 | | 0.9396 | 0.0708 | 120 | 0.9284 | | 0.902 | 0.0738 | 125 | 0.9262 | | 0.9533 | 0.0767 | 130 | 0.9121 | | 0.8755 | 0.0797 | 135 | 0.9160 | | 0.9349 | 0.0826 | 140 | 0.9083 | | 0.9585 | 0.0856 | 145 | 0.8993 | | 0.8349 | 0.0885 | 150 | 0.9000 | | 0.9541 | 0.0915 | 155 | 0.8887 | | 0.9108 | 0.0945 | 160 | 0.8837 | | 0.9196 | 0.0974 | 165 | 0.8806 | | 0.9094 | 0.1004 | 170 | 0.8776 | | 0.8514 | 0.1033 | 175 | 0.8759 | | 0.7515 | 0.1063 | 180 | 0.8684 | | 0.8031 | 0.1092 | 185 | 0.8676 | | 0.8639 | 0.1122 | 190 | 0.8661 | | 0.8002 | 0.1151 | 195 | 0.8556 | | 0.7812 | 0.1181 | 200 | 0.8574 | | 0.9163 | 0.1210 | 205 | 0.8582 | | 0.8824 | 0.1240 | 210 | 0.8515 | | 0.8759 | 0.1269 | 215 | 0.8502 | | 0.8384 | 0.1299 | 220 | 0.8467 | | 0.8436 | 0.1328 | 225 | 0.8427 | | 0.8329 | 0.1358 | 230 | 0.8398 | | 0.87 | 0.1387 | 235 | 0.8393 | | 0.8405 | 0.1417 | 240 | 0.8356 | | 0.8634 | 0.1446 | 245 | 0.8339 | | 0.8298 | 0.1476 | 250 | 0.8315 | | 0.7582 | 0.1505 | 255 | 0.8278 | | 0.7912 | 0.1535 | 260 | 0.8257 | | 0.8878 | 0.1564 | 265 | 0.8247 | | 0.8443 | 0.1594 | 270 | 0.8229 | | 0.8965 | 0.1623 | 275 | 0.8206 | | 0.8298 | 0.1653 | 280 | 0.8178 | | 0.7496 | 0.1682 | 285 | 0.8177 | | 0.7794 | 0.1712 | 290 | 0.8148 | | 0.8354 | 0.1741 | 295 | 0.8137 | | 0.8861 | 0.1771 | 300 | 0.8124 | | 0.7683 | 0.1800 | 305 | 0.8118 | | 0.8414 | 0.1830 | 310 | 0.8106 | | 0.8624 | 0.1860 | 315 | 0.8083 | | 0.7753 | 0.1889 | 320 | 0.8076 | | 0.778 | 0.1919 | 325 | 0.8060 | | 0.8171 | 0.1948 | 330 | 0.8051 | | 0.7006 | 0.1978 | 335 | 0.8049 | | 0.8365 | 0.2007 | 340 | 0.8032 | | 0.8057 | 0.2037 | 345 | 0.8021 | | 0.7914 | 0.2066 | 350 | 0.8015 | | 0.9043 | 0.2096 | 355 | 0.8008 | | 0.8317 | 0.2125 | 360 | 0.8001 | | 0.7631 | 0.2155 | 365 | 0.7997 | | 0.8301 | 0.2184 | 370 | 0.7993 | | 0.8701 | 0.2214 | 375 | 0.7988 | | 0.7469 | 0.2243 | 380 | 0.7985 | | 0.7643 | 0.2273 | 385 | 0.7981 | | 0.8388 | 0.2302 | 390 | 0.7978 | | 0.8808 | 0.2332 | 395 | 0.7975 | | 0.7441 | 0.2361 | 400 | 0.7974 | | 0.7641 | 0.2391 | 405 | 0.7972 | | 0.727 | 0.2420 | 410 | 0.7971 | | 0.771 | 0.2450 | 415 | 0.7971 | | 0.7442 | 0.2479 | 420 | 0.7971 | ### Framework versions - Transformers 4.46.0 - Pytorch 2.5.0+cu121 - Datasets 3.0.2 - Tokenizers 0.20.1