|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: amd/AMD-Llama-135m |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: amdchess-v7 |
|
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-v7 |
|
|
|
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: 0.7964 |
|
|
|
## 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 OptimizerNames.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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 6.2092 | 0.0030 | 5 | 5.2057 | |
|
| 1.9922 | 0.0059 | 10 | 1.8157 | |
|
| 1.7403 | 0.0089 | 15 | 1.6004 | |
|
| 1.3742 | 0.0118 | 20 | 1.3543 | |
|
| 1.3517 | 0.0148 | 25 | 1.2096 | |
|
| 1.215 | 0.0177 | 30 | 1.1421 | |
|
| 1.2121 | 0.0207 | 35 | 1.1437 | |
|
| 1.097 | 0.0236 | 40 | 1.0869 | |
|
| 1.1186 | 0.0266 | 45 | 1.0722 | |
|
| 1.0991 | 0.0295 | 50 | 1.0526 | |
|
| 0.9758 | 0.0325 | 55 | 1.0194 | |
|
| 0.9827 | 0.0354 | 60 | 1.0219 | |
|
| 1.0428 | 0.0384 | 65 | 0.9899 | |
|
| 0.9846 | 0.0413 | 70 | 1.0065 | |
|
| 0.996 | 0.0443 | 75 | 0.9968 | |
|
| 0.9908 | 0.0472 | 80 | 0.9694 | |
|
| 1.0172 | 0.0502 | 85 | 0.9688 | |
|
| 0.9956 | 0.0531 | 90 | 0.9557 | |
|
| 0.9629 | 0.0561 | 95 | 0.9466 | |
|
| 1.0187 | 0.0590 | 100 | 0.9421 | |
|
| 0.9079 | 0.0620 | 105 | 0.9248 | |
|
| 0.8152 | 0.0649 | 110 | 0.9273 | |
|
| 0.953 | 0.0679 | 115 | 0.9179 | |
|
| 0.9545 | 0.0708 | 120 | 0.9109 | |
|
| 0.8649 | 0.0738 | 125 | 0.9023 | |
|
| 0.9308 | 0.0767 | 130 | 0.8915 | |
|
| 0.9197 | 0.0797 | 135 | 0.8992 | |
|
| 0.9684 | 0.0826 | 140 | 0.8931 | |
|
| 0.9329 | 0.0856 | 145 | 0.8973 | |
|
| 0.8679 | 0.0885 | 150 | 0.8864 | |
|
| 0.8754 | 0.0915 | 155 | 0.8890 | |
|
| 0.8532 | 0.0945 | 160 | 0.8793 | |
|
| 0.8818 | 0.0974 | 165 | 0.8777 | |
|
| 0.9161 | 0.1004 | 170 | 0.8765 | |
|
| 0.7303 | 0.1033 | 175 | 0.8744 | |
|
| 0.9087 | 0.1063 | 180 | 0.8697 | |
|
| 0.884 | 0.1092 | 185 | 0.8648 | |
|
| 0.9259 | 0.1122 | 190 | 0.8589 | |
|
| 0.866 | 0.1151 | 195 | 0.8574 | |
|
| 0.8716 | 0.1181 | 200 | 0.8517 | |
|
| 0.8068 | 0.1210 | 205 | 0.8488 | |
|
| 0.8382 | 0.1240 | 210 | 0.8478 | |
|
| 0.8372 | 0.1269 | 215 | 0.8462 | |
|
| 0.8477 | 0.1299 | 220 | 0.8433 | |
|
| 0.838 | 0.1328 | 225 | 0.8425 | |
|
| 0.8585 | 0.1358 | 230 | 0.8403 | |
|
| 0.892 | 0.1387 | 235 | 0.8378 | |
|
| 0.8794 | 0.1417 | 240 | 0.8360 | |
|
| 0.8468 | 0.1446 | 245 | 0.8321 | |
|
| 0.8417 | 0.1476 | 250 | 0.8305 | |
|
| 0.8785 | 0.1505 | 255 | 0.8267 | |
|
| 0.9016 | 0.1535 | 260 | 0.8258 | |
|
| 0.86 | 0.1564 | 265 | 0.8243 | |
|
| 0.8777 | 0.1594 | 270 | 0.8214 | |
|
| 0.6465 | 0.1623 | 275 | 0.8210 | |
|
| 0.7967 | 0.1653 | 280 | 0.8186 | |
|
| 0.774 | 0.1682 | 285 | 0.8173 | |
|
| 0.7545 | 0.1712 | 290 | 0.8162 | |
|
| 0.8684 | 0.1741 | 295 | 0.8147 | |
|
| 0.7596 | 0.1771 | 300 | 0.8132 | |
|
| 0.8279 | 0.1800 | 305 | 0.8108 | |
|
| 0.7538 | 0.1830 | 310 | 0.8087 | |
|
| 0.848 | 0.1860 | 315 | 0.8075 | |
|
| 0.8526 | 0.1889 | 320 | 0.8064 | |
|
| 0.8053 | 0.1919 | 325 | 0.8057 | |
|
| 0.8598 | 0.1948 | 330 | 0.8040 | |
|
| 0.8076 | 0.1978 | 335 | 0.8026 | |
|
| 0.7292 | 0.2007 | 340 | 0.8028 | |
|
| 0.8058 | 0.2037 | 345 | 0.8015 | |
|
| 0.8 | 0.2066 | 350 | 0.8003 | |
|
| 0.8038 | 0.2096 | 355 | 0.8002 | |
|
| 0.7639 | 0.2125 | 360 | 0.7998 | |
|
| 0.7838 | 0.2155 | 365 | 0.7991 | |
|
| 0.8139 | 0.2184 | 370 | 0.7986 | |
|
| 0.844 | 0.2214 | 375 | 0.7982 | |
|
| 0.7417 | 0.2243 | 380 | 0.7978 | |
|
| 0.7987 | 0.2273 | 385 | 0.7975 | |
|
| 0.8319 | 0.2302 | 390 | 0.7971 | |
|
| 0.7383 | 0.2332 | 395 | 0.7968 | |
|
| 0.7886 | 0.2361 | 400 | 0.7966 | |
|
| 0.8127 | 0.2391 | 405 | 0.7965 | |
|
| 0.8213 | 0.2420 | 410 | 0.7964 | |
|
| 0.7952 | 0.2450 | 415 | 0.7964 | |
|
| 0.8518 | 0.2479 | 420 | 0.7964 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 3.0.2 |
|
- Tokenizers 0.20.1 |
|
|
