Model save

README.md

@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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 imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.6406
 - Loss: 0.6651
+- Accuracy: 0.6406
 
 ## Model description
 
@@ -62,13 +62,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Accuracy | Validation Loss |
-|:-------------:|:-----:|:----:|:--------:|:---------------:|
-| No log        | 1.0   | 2    | 0.5625   | 0.6905          |
-| No log        | 2.0   | 4    | 0.6562   | 0.6797          |
-| No log        | 3.0   | 6    | 0.6562   | 0.6719          |
-| No log        | 4.0   | 8    | 0.6562   | 0.6671          |
-| 0.6483        | 5.0   | 10   | 0.6406   | 0.6651          |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 2    | 0.6905          | 0.5625   |
+| No log        | 2.0   | 4    | 0.6797          | 0.6562   |
+| No log        | 3.0   | 6    | 0.6719          | 0.6562   |
+| No log        | 4.0   | 8    | 0.6671          | 0.6562   |
+| 0.6483        | 5.0   | 10   | 0.6651          | 0.6406   |
 
 
 ### Framework versions

config.json

@@ -26,6 +26,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.38.2"

runs/Apr04_00-20-17_a49f736592db/events.out.tfevents.1712190024.a49f736592db.1180.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b0f9aecf942650b45f9a90f929575abca0b4877801b2ae2e867d57d033c5bb
+size 6747

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda3fa65d715d1e5d4318d323d240a596ff6650a76d3d9fd260a1b1a7bcacb2b
+oid sha256:941677b45b6c2e3b4598d49c64e89ac88a36d917c65c1197f29bb3099e85d45c
 size 4920