sayakpaul/glpn-nyu-finetuned-diode-221116-054332做al视频怎么赚钱
glpn元宝大模型-nyu-finetuned-diode-221116-054332
This model is a fine-tuned version of vinvino02/glpn-nyu on the diode-subset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6028
- Rmse: nan
Model description
More information needed快问ai
Intended uses & limitations
More information needed下载官方即梦a1
Training and evaluation data
More information needed元宝大模型
Training procedure
Training hyperparameters
The following hyperparameters were used during training:制作ai的软件
- learning_rate: 1e-05
- train_batch_size: 24
- eval_batch_size: 48
- seed: 2022
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rmse |
|---|---|---|---|---|
| 1.6801 | 1.0 | 72 | 1.3466 | nan |
| 1.2071 | 2.0 | 144 | 0.8388 | nan |
| 0.7548 | 3.0 | 216 | 0.6771 | nan |
| 0.6401 | 4.0 | 288 | 0.6443 | nan |
| 0.629 | 5.0 | 360 | 0.6452 | nan |
| 0.5892 | 6.0 | 432 | 0.6202 | nan |
| 0.5773 | 7.0 | 504 | 0.6262 | nan |
| 0.5532 | 8.0 | 576 | 0.6151 | nan |
| 0.5268 | 9.0 | 648 | 0.5995 | nan |
| 0.5416 | 10.0 | 720 | 0.6028 | nan |
Framework versions
数据统计
数据评估
本站菠萝导航提供的sayakpaul/glpn-nyu-finetuned-diode-221116-054332都来源于网络，不保证外部链接的准确性和完整性，同时，对于该外部链接的指向，不由菠萝导航实际控制，在2023年5月15日 下午3:11收录时，该网页上的内容，都属于合规合法，后期网页的内容如出现违规，可以直接联系网站管理员进行删除，菠萝导航不承担任何责任。即梦下载官方
相关导航
