End of training

README.md

@@ -15,17 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0079
-- eval_mean_iou: 1.0
-- eval_mean_accuracy: 1.0
-- eval_overall_accuracy: 1.0
-- eval_per_category_iou: [1.0]
-- eval_per_category_accuracy: [1.0]
-- eval_runtime: 58.744
-- eval_samples_per_second: 0.851
-- eval_steps_per_second: 0.426
-- epoch: 1.6
-- step: 80
+- Loss: 0.0020
+- Mean Iou: 1.0
+- Mean Accuracy: 1.0
+- Overall Accuracy: 1.0
+- Per Category Iou: [1.0]
+- Per Category Accuracy: [1.0]
 
 ## Model description
 
@@ -52,6 +47,24 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 5
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:----------------:|:---------------------:|
+| 0.0119        | 0.4   | 20   | 0.0266          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+| 0.0049        | 0.8   | 40   | 0.0080          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+| 0.0014        | 1.2   | 60   | 0.0038          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+| 0.0043        | 1.6   | 80   | 0.0048          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+| 0.0014        | 2.0   | 100  | 0.0032          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+| 0.0009        | 2.4   | 120  | 0.0034          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+| 0.0029        | 2.8   | 140  | 0.0027          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+| 0.0007        | 3.2   | 160  | 0.0024          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+| 0.0021        | 3.6   | 180  | 0.0025          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+| 0.0014        | 4.0   | 200  | 0.0023          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+| 0.0012        | 4.4   | 220  | 0.0021          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+| 0.0027        | 4.8   | 240  | 0.0020          | 1.0      | 1.0           | 1.0              | [1.0]            | [1.0]                 |
+
+
 ### Framework versions
 
 - Transformers 4.35.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:516dfdf45ffd3c36ab2b9adab6021af826e8c9cf5e26c9ade6e77018f514cfb6
+oid sha256:77a4f823dd95109fcb4e9070000206ca7b14d8c5de833423dde2077dec1f8109
 size 14883748

runs/Dec20_02-45-45_37b315fcf8c8/events.out.tfevents.1703040347.37b315fcf8c8.804.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95107fe70f4b44c0eb31f8512c543e2c467258b2e208cabd0398d19e3aa8ab9e
-size 47176
+oid sha256:06e55e4b1d464491a513236c1a95026141bb7a54219775aa084bbf40871d7c7b
+size 49100