amdchess-v5
This model is a fine-tuned version of amd/AMD-Llama-135m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7610
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 |
|---|---|---|---|
| 2.9045 | 0.0030 | 5 | 2.7322 |
| 1.5833 | 0.0059 | 10 | 1.7005 |
| 1.5115 | 0.0089 | 15 | 1.3183 |
| 1.0591 | 0.0118 | 20 | 1.3213 |
| 1.1079 | 0.0148 | 25 | 1.1174 |
| 1.1004 | 0.0177 | 30 | 1.1248 |
| 1.0783 | 0.0207 | 35 | 1.0751 |
| 1.0209 | 0.0236 | 40 | 1.0297 |
| 1.0955 | 0.0266 | 45 | 1.0330 |
| 1.1106 | 0.0295 | 50 | 1.0172 |
| 1.0855 | 0.0325 | 55 | 0.9780 |
| 0.979 | 0.0354 | 60 | 0.9635 |
| 0.8885 | 0.0384 | 65 | 0.9590 |
| 0.9195 | 0.0413 | 70 | 0.9452 |
| 0.9518 | 0.0443 | 75 | 0.9325 |
| 0.9609 | 0.0472 | 80 | 0.9332 |
| 0.9327 | 0.0502 | 85 | 0.9229 |
| 0.9621 | 0.0531 | 90 | 0.9157 |
| 0.9956 | 0.0561 | 95 | 0.9094 |
| 0.8193 | 0.0590 | 100 | 0.8958 |
| 0.9361 | 0.0620 | 105 | 0.8915 |
| 0.9039 | 0.0649 | 110 | 0.8882 |
| 0.8757 | 0.0679 | 115 | 0.8813 |
| 0.8875 | 0.0708 | 120 | 0.8776 |
| 0.8989 | 0.0738 | 125 | 0.8805 |
| 0.9478 | 0.0767 | 130 | 0.8706 |
| 0.9132 | 0.0797 | 135 | 0.8645 |
| 0.8755 | 0.0826 | 140 | 0.8607 |
| 0.9304 | 0.0856 | 145 | 0.8559 |
| 0.8711 | 0.0885 | 150 | 0.8466 |
| 0.8511 | 0.0915 | 155 | 0.8480 |
| 0.8768 | 0.0945 | 160 | 0.8410 |
| 0.6914 | 0.0974 | 165 | 0.8407 |
| 0.8625 | 0.1004 | 170 | 0.8342 |
| 0.8219 | 0.1033 | 175 | 0.8370 |
| 0.9106 | 0.1063 | 180 | 0.8296 |
| 0.8512 | 0.1092 | 185 | 0.8253 |
| 0.8286 | 0.1122 | 190 | 0.8251 |
| 0.9075 | 0.1151 | 195 | 0.8214 |
| 0.8733 | 0.1181 | 200 | 0.8199 |
| 0.7881 | 0.1210 | 205 | 0.8164 |
| 0.9131 | 0.1240 | 210 | 0.8150 |
| 0.8421 | 0.1269 | 215 | 0.8104 |
| 0.8589 | 0.1299 | 220 | 0.8083 |
| 0.7674 | 0.1328 | 225 | 0.8065 |
| 0.8566 | 0.1358 | 230 | 0.8065 |
| 0.8657 | 0.1387 | 235 | 0.8019 |
| 0.7534 | 0.1417 | 240 | 0.7992 |
| 0.7988 | 0.1446 | 245 | 0.7970 |
| 0.8197 | 0.1476 | 250 | 0.7937 |
| 0.8175 | 0.1505 | 255 | 0.7931 |
| 0.8831 | 0.1535 | 260 | 0.7915 |
| 0.8714 | 0.1564 | 265 | 0.7882 |
| 0.8097 | 0.1594 | 270 | 0.7864 |
| 0.7864 | 0.1623 | 275 | 0.7849 |
| 0.7521 | 0.1653 | 280 | 0.7845 |
| 0.8208 | 0.1682 | 285 | 0.7820 |
| 0.7658 | 0.1712 | 290 | 0.7802 |
| 0.8623 | 0.1741 | 295 | 0.7782 |
| 0.8526 | 0.1771 | 300 | 0.7765 |
| 0.8304 | 0.1800 | 305 | 0.7749 |
| 0.823 | 0.1830 | 310 | 0.7737 |
| 0.762 | 0.1860 | 315 | 0.7726 |
| 0.7545 | 0.1889 | 320 | 0.7715 |
| 0.7818 | 0.1919 | 325 | 0.7699 |
| 0.7601 | 0.1948 | 330 | 0.7699 |
| 0.7414 | 0.1978 | 335 | 0.7689 |
| 0.8397 | 0.2007 | 340 | 0.7682 |
| 0.8282 | 0.2037 | 345 | 0.7668 |
| 0.7676 | 0.2066 | 350 | 0.7655 |
| 0.7768 | 0.2096 | 355 | 0.7644 |
| 0.7249 | 0.2125 | 360 | 0.7639 |
| 0.7633 | 0.2155 | 365 | 0.7635 |
| 0.721 | 0.2184 | 370 | 0.7632 |
| 0.798 | 0.2214 | 375 | 0.7624 |
| 0.7601 | 0.2243 | 380 | 0.7620 |
| 0.8439 | 0.2273 | 385 | 0.7618 |
| 0.777 | 0.2302 | 390 | 0.7616 |
| 0.6739 | 0.2332 | 395 | 0.7614 |
| 0.802 | 0.2361 | 400 | 0.7612 |
| 0.7868 | 0.2391 | 405 | 0.7611 |
| 0.6621 | 0.2420 | 410 | 0.7610 |
| 0.7723 | 0.2450 | 415 | 0.7610 |
| 0.8052 | 0.2479 | 420 | 0.7610 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1