Model save

README.md

@@ -2,8 +2,6 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
-- image-classification
-- vision
 - generated_from_trainer
 metrics:
 - accuracy
@@ -17,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-beans
 
-This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5654
 - Accuracy: 0.9699
+- Loss: 0.5654
 
 ## Model description
 
@@ -49,11 +47,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.9886        | 1.0   | 17   | 0.7760          | 0.9248   |
-| 0.7227        | 2.0   | 34   | 0.6205          | 0.9549   |
-| 0.6045        | 3.0   | 51   | 0.5654          | 0.9699   |
+| Training Loss | Epoch | Step | Accuracy | Validation Loss |
+|:-------------:|:-----:|:----:|:--------:|:---------------:|
+| 0.9886        | 1.0   | 17   | 0.9248   | 0.7760          |
+| 0.7227        | 2.0   | 34   | 0.9549   | 0.6205          |
+| 0.6045        | 3.0   | 51   | 0.9699   | 0.5654          |
 
 
 ### Framework versions

config.json

@@ -28,7 +28,6 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
-  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.43.0.dev0"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:908864980426b2063e9626476bb1885d75a019e3288ccd8e74f676467b086954
+oid sha256:842e315bd4533c35e5e48d226e65f931ccc1eebcec787bd58002026eeccb43eb
 size 5176