End of training

README.md

@@ -1,6 +1,6 @@
 ---
-base_model: nvidia/mit-b0
 license: other
+base_model: nvidia/mit-b0
 tags:
 - vision
 - image-segmentation
@@ -17,16 +17,16 @@ 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 the saad7489/SixraygunTest dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1371
-- Mean Iou: 0.0
-- Mean Accuracy: nan
-- Overall Accuracy: nan
+- Loss: 0.4835
+- Mean Iou: 0.4419
+- Mean Accuracy: 0.6869
+- Overall Accuracy: 0.6897
 - Accuracy No-label: nan
-- Accuracy Object1: nan
-- Accuracy Object2: nan
+- Accuracy Object1: 0.6189
+- Accuracy Object2: 0.7549
 - Iou No-label: 0.0
-- Iou Object1: 0.0
-- Iou Object2: nan
+- Iou Object1: 0.6011
+- Iou Object2: 0.7247
 
 ## Model description
 
@@ -57,9 +57,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy No-label | Accuracy Object1 | Accuracy Object2 | Iou No-label | Iou Object1 | Iou Object2 |
 |:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-----------------:|:----------------:|:----------------:|:------------:|:-----------:|:-----------:|
-| 0.1901        | 2.8571 | 20   | 0.2299          | 0.0      | nan           | nan              | nan               | nan              | nan              | 0.0          | 0.0         | nan         |
-| 0.139         | 5.7143 | 40   | 0.1660          | 0.0      | nan           | nan              | nan               | nan              | nan              | 0.0          | 0.0         | nan         |
-| 0.1037        | 8.5714 | 60   | 0.1371          | 0.0      | nan           | nan              | nan               | nan              | nan              | 0.0          | 0.0         | nan         |
+| 0.7477        | 2.8571 | 20   | 0.7879          | 0.4630   | 0.7491        | 0.7527           | nan               | 0.6609           | 0.8373           | 0.0          | 0.6247      | 0.7643      |
+| 0.5719        | 5.7143 | 40   | 0.5524          | 0.4398   | 0.6865        | 0.6903           | nan               | 0.5941           | 0.7788           | 0.0          | 0.5759      | 0.7436      |
+| 0.5369        | 8.5714 | 60   | 0.4835          | 0.4419   | 0.6869        | 0.6897           | nan               | 0.6189           | 0.7549           | 0.0          | 0.6011      | 0.7247      |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "saad7489/segformer-b0-finetuned-segments-SixrayKnife8-19-2024",
+  "_name_or_path": "nvidia/mit-b0",
   "architectures": [
     "SegformerForSemanticSegmentation"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d06db0d92729aca66e11d3049184d4d528e095bb8298da57593db3dec87800
+oid sha256:57cf5e65e423044f96b71e1c57c99450df1dafaab98548c74724f3de8f4e75d9
 size 14885804

runs/Aug20_07-21-10_bdedd370450b/events.out.tfevents.1724138488.bdedd370450b.897.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304154f7574e09cfe2054f4f211b0feba069d736037cc30d8be8f49162a55571
+size 22635

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f96fdb1c17b49e4be834915a7be4ebeae0b9679400cc508cf356e42ef1b413
+oid sha256:d6901954e5d1f58acd74724fff131d870172893454d3042f56e39cd60c826e08
 size 5240