glpn-nyu-finetuned-diode-221116-062619
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: 0.5480
- Rmse: nan
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: 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: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rmse |
|---|---|---|---|---|
| 1.6855 | 1.0 | 72 | 1.3740 | nan |
| 1.3941 | 2.0 | 144 | 0.9261 | nan |
| 0.7567 | 3.0 | 216 | 0.6298 | nan |
| 0.6331 | 4.0 | 288 | 0.6080 | nan |
| 0.6029 | 5.0 | 360 | 0.6025 | nan |
| 0.5607 | 6.0 | 432 | 0.5777 | nan |
| 0.5333 | 7.0 | 504 | 0.5553 | nan |
| 0.5018 | 8.0 | 576 | 0.5648 | nan |
| 0.497 | 9.0 | 648 | 0.5552 | nan |
| 0.4838 | 10.0 | 720 | 0.5539 | nan |
| 0.4557 | 11.0 | 792 | 0.5468 | nan |
| 0.4689 | 12.0 | 864 | 0.5484 | nan |
| 0.4735 | 13.0 | 936 | 0.5459 | nan |
| 0.4546 | 14.0 | 1008 | 0.5468 | nan |
| 0.4608 | 15.0 | 1080 | 0.5480 | nan |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0+cu117
- Tokenizers 0.13.2
- Downloads last month
- 8