sayakpaul
/
glpn-nyu-finetuned-diode
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update model card README.md

This commit is contained in:
Sayak Paul 2022-11-11 06:07:13 +00:00
parent c449770270
commit 382b9486c1
1 changed files with 16 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
README.md
View File

@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
This model is a fine-tuned version of [vinvino02/glpn-nyu](https://huggingface.co/vinvino02/glpn-nyu) on the diode-subset dataset. This model is a fine-tuned version of [vinvino02/glpn-nyu](https://huggingface.co/vinvino02/glpn-nyu) on the diode-subset dataset.
It achieves the following results on the evaluation set: It achieves the following results on the evaluation set:
- Loss: 0.8193 - Loss: 0.4359
- Rmse: 0.8077 - Rmse: 0.4276
## Model description ## Model description
@ -36,29 +36,30 @@ More information needed
### Training hyperparameters ### Training hyperparameters
The following hyperparameters were used during training: The following hyperparameters were used during training:
- learning_rate: 1e-05 - learning_rate: 2e-05
- train_batch_size: 32 - train_batch_size: 24
- eval_batch_size: 32 - eval_batch_size: 24
- seed: 42 - seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear - lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1 - lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10 - num_epochs: 10
- mixed_precision_training: Native AMP
### Training results ### Training results
| Training Loss | Epoch | Step | Validation Loss | Rmse | | Training Loss | Epoch | Step | Validation Loss | Rmse |
|:-------------:|:-----:|:----:|:---------------:|:------:| |:-------------:|:-----:|:----:|:---------------:|:------:|
| No log | 1.0 | 10 | 0.9152 | nan | | No log | 1.0 | 13 | 1.2498 | 0.9726 |
| 0.8958 | 2.0 | 20 | 0.8413 | nan | | 0.8469 | 2.0 | 26 | 1.0661 | nan |
| 0.8958 | 3.0 | 30 | 0.7873 | 1.0697 | | 0.8469 | 3.0 | 39 | 0.9959 | 0.5287 |
| 0.7472 | 4.0 | 40 | 0.7405 | 0.9340 | | 0.6946 | 4.0 | 52 | 0.8550 | 0.4084 |
| 0.7472 | 5.0 | 50 | 0.7017 | 0.8441 | | 0.586 | 5.0 | 65 | 0.7679 | 0.3603 |
| 0.6999 | 6.0 | 60 | 0.6785 | 0.7959 | | 0.586 | 6.0 | 78 | 0.6650 | 0.3119 |
| 0.6999 | 7.0 | 70 | 0.6656 | 0.7672 | | 0.5195 | 7.0 | 91 | 0.6837 | 0.3370 |
| 0.6917 | 8.0 | 80 | 0.6490 | 0.7413 | | 0.4737 | 8.0 | 104 | 0.6638 | 0.3366 |
| 0.6917 | 9.0 | 90 | 0.6413 | 0.7212 | | 0.4737 | 9.0 | 117 | 0.6522 | 0.3250 |
| 0.6527 | 10.0 | 100 | 0.6408 | 0.7146 | | 0.4663 | 10.0 | 130 | 0.6461 | 0.3153 |
### Framework versions ### Framework versions