diff --git a/README.md b/README.md
index f5b9b48..25e1a48 100644
--- a/README.md
+++ b/README.md
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [vinvino02/glpn-kitti](https://huggingface.co/vinvino02/glpn-kitti) on the diode-subset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4947
-- Rmse: 0.4399
+- Loss: 0.8818
+- Rmse: 0.7721
 
 ## Model description
 
@@ -47,18 +47,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rmse   |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.8555        | 1.0   | 10   | 0.6764          | 0.5844 |
-| 0.7688        | 2.0   | 20   | 0.6335          | 0.5344 |
-| 0.7099        | 3.0   | 30   | 0.5967          | 0.5203 |
-| 0.6526        | 4.0   | 40   | 0.5602          | 0.4932 |
-| 0.5928        | 5.0   | 50   | 0.5235          | 0.4576 |
-| 0.5746        | 6.0   | 60   | 0.4981          | 0.4160 |
-| 0.5335        | 7.0   | 70   | 0.4794          | 0.3926 |
-| 0.5009        | 8.0   | 80   | 0.4697          | 0.3816 |
-| 0.4811        | 9.0   | 90   | 0.4629          | nan    |
-| 0.473         | 10.0  | 100  | 0.4633          | 0.3714 |
+| Training Loss | Epoch | Step | Validation Loss | Rmse |
+|:-------------:|:-----:|:----:|:---------------:|:----:|
+| No log        | 1.0   | 10   | 0.8395          | nan  |
+| 0.9442        | 2.0   | 20   | 0.8097          | nan  |
+| 0.894         | 3.0   | 30   | 0.7852          | nan  |
+| 0.894         | 4.0   | 40   | 0.7784          | nan  |
+| 0.8759        | 5.0   | 50   | 0.7690          | nan  |
+| 0.8475        | 6.0   | 60   | 0.7591          | nan  |
+| 0.8475        | 7.0   | 70   | 0.7493          | nan  |
+| 0.8312        | 8.0   | 80   | 0.7440          | nan  |
+| 0.83          | 9.0   | 90   | 0.7400          | nan  |
+| 0.83          | 10.0  | 100  | 0.7404          | nan  |
 
 
 ### Framework versions