2and3_apps_30k_v6
This model is a fine-tuned version of Qwen/Qwen2.5-7B on the 2and3_apps_30k_v6 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1718
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 4
- total_eval_batch_size: 4
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2769 | 0.0137 | 100 | 0.2641 |
| 0.2417 | 0.0274 | 200 | 0.2440 |
| 0.191 | 0.0410 | 300 | 0.2346 |
| 0.2466 | 0.0547 | 400 | 0.2327 |
| 0.2261 | 0.0684 | 500 | 0.2279 |
| 0.2394 | 0.0821 | 600 | 0.2231 |
| 0.228 | 0.0958 | 700 | 0.2237 |
| 0.1909 | 0.1094 | 800 | 0.2225 |
| 0.2277 | 0.1231 | 900 | 0.2201 |
| 0.2108 | 0.1368 | 1000 | 0.2182 |
| 0.1904 | 0.1505 | 1100 | 0.2172 |
| 0.2012 | 0.1642 | 1200 | 0.2130 |
| 0.2042 | 0.1778 | 1300 | 0.2143 |
| 0.2516 | 0.1915 | 1400 | 0.2161 |
| 0.2591 | 0.2052 | 1500 | 0.2122 |
| 0.2037 | 0.2189 | 1600 | 0.2097 |
| 0.2319 | 0.2326 | 1700 | 0.2108 |
| 0.2162 | 0.2462 | 1800 | 0.2093 |
| 0.2157 | 0.2599 | 1900 | 0.2022 |
| 0.2117 | 0.2736 | 2000 | 0.2046 |
| 0.2004 | 0.2873 | 2100 | 0.2018 |
| 0.2174 | 0.3010 | 2200 | 0.2039 |
| 0.2266 | 0.3146 | 2300 | 0.2030 |
| 0.2164 | 0.3283 | 2400 | 0.2006 |
| 0.211 | 0.3420 | 2500 | 0.1958 |
| 0.2614 | 0.3557 | 2600 | 0.1964 |
| 0.193 | 0.3694 | 2700 | 0.1935 |
| 0.1974 | 0.3830 | 2800 | 0.1949 |
| 0.206 | 0.3967 | 2900 | 0.1953 |
| 0.2133 | 0.4104 | 3000 | 0.1925 |
| 0.2151 | 0.4241 | 3100 | 0.1928 |
| 0.1837 | 0.4378 | 3200 | 0.1912 |
| 0.1663 | 0.4514 | 3300 | 0.1882 |
| 0.2099 | 0.4651 | 3400 | 0.1903 |
| 0.2328 | 0.4788 | 3500 | 0.1898 |
| 0.1812 | 0.4925 | 3600 | 0.1867 |
| 0.1645 | 0.5062 | 3700 | 0.1866 |
| 0.2001 | 0.5198 | 3800 | 0.1859 |
| 0.1751 | 0.5335 | 3900 | 0.1841 |
| 0.1873 | 0.5472 | 4000 | 0.1833 |
| 0.1578 | 0.5609 | 4100 | 0.1833 |
| 0.1765 | 0.5746 | 4200 | 0.1814 |
| 0.2 | 0.5882 | 4300 | 0.1819 |
| 0.1796 | 0.6019 | 4400 | 0.1820 |
| 0.1925 | 0.6156 | 4500 | 0.1808 |
| 0.183 | 0.6293 | 4600 | 0.1786 |
| 0.2281 | 0.6430 | 4700 | 0.1792 |
| 0.1815 | 0.6566 | 4800 | 0.1780 |
| 0.2287 | 0.6703 | 4900 | 0.1781 |
| 0.1469 | 0.6840 | 5000 | 0.1774 |
| 0.19 | 0.6977 | 5100 | 0.1769 |
| 0.2257 | 0.7114 | 5200 | 0.1765 |
| 0.2059 | 0.7250 | 5300 | 0.1757 |
| 0.1917 | 0.7387 | 5400 | 0.1759 |
| 0.1715 | 0.7524 | 5500 | 0.1753 |
| 0.173 | 0.7661 | 5600 | 0.1738 |
| 0.1404 | 0.7798 | 5700 | 0.1741 |
| 0.1819 | 0.7934 | 5800 | 0.1735 |
| 0.144 | 0.8071 | 5900 | 0.1731 |
| 0.1597 | 0.8208 | 6000 | 0.1729 |
| 0.2092 | 0.8345 | 6100 | 0.1731 |
| 0.1837 | 0.8482 | 6200 | 0.1726 |
| 0.1839 | 0.8618 | 6300 | 0.1723 |
| 0.1997 | 0.8755 | 6400 | 0.1725 |
| 0.1485 | 0.8892 | 6500 | 0.1723 |
| 0.1837 | 0.9029 | 6600 | 0.1721 |
| 0.1809 | 0.9166 | 6700 | 0.1720 |
| 0.1512 | 0.9302 | 6800 | 0.1720 |
| 0.1755 | 0.9439 | 6900 | 0.1721 |
| 0.183 | 0.9576 | 7000 | 0.1720 |
| 0.1727 | 0.9713 | 7100 | 0.1719 |
| 0.1811 | 0.9850 | 7200 | 0.1718 |
| 0.2091 | 0.9986 | 7300 | 0.1718 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 2
Model tree for cutelemonlili/Qwen-7B-2and3_apps_30k_v6
Base model
Qwen/Qwen2.5-7B