Training in progress epoch 0

README.md

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nvidia/segformer-b0-finetuned-ade-512-512](https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5448
-- Validation Loss: 1.0024
-- Epoch: 2
+- Train Loss: 0.4891
+- Validation Loss: 0.7011
+- Epoch: 0
 
 ## Model description
 
@@ -43,14 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.4843     | 0.9437          | 0     |
-| 0.5116     | 0.8503          | 1     |
-| 0.5448     | 1.0024          | 2     |
+| 0.4891     | 0.7011          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.37.0
+- Transformers 4.37.2
 - TensorFlow 2.10.0
 - Datasets 3.6.0
 - Tokenizers 0.15.2

config.json

@@ -74,5 +74,5 @@
     2
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.37.0"
+  "transformers_version": "4.37.2"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56911706329fb00633ee7161a317f9cce2ce9f1babac20894f7cb497fbec325e
+oid sha256:8dc69c755a432f079212784bba5f696a1246e9d4603f4534de4159c66039f3fc
 size 15133552