<!-- 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. -->
glpn-nyu-finetuned-diode
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: 0.4359
- Rmse: 0.4276
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: 2e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 13 | 1.2498 | 0.9726 |
| 0.8469 | 2.0 | 26 | 1.0661 | nan |
| 0.8469 | 3.0 | 39 | 0.9959 | 0.5287 |
| 0.6946 | 4.0 | 52 | 0.8550 | 0.4084 |
| 0.586 | 5.0 | 65 | 0.7679 | 0.3603 |
| 0.586 | 6.0 | 78 | 0.6650 | 0.3119 |
| 0.5195 | 7.0 | 91 | 0.6837 | 0.3370 |
| 0.4737 | 8.0 | 104 | 0.6638 | 0.3366 |
| 0.4737 | 9.0 | 117 | 0.6522 | 0.3250 |
| 0.4663 | 10.0 | 130 | 0.6461 | 0.3153 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Tokenizers 0.13.2
