End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.45
+      value: 0.5125
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -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:
-- Loss: 1.6195
-- Accuracy: 0.45
+- Loss: 1.4561
+- Accuracy: 0.5125
 
 ## Model description
 
@@ -52,33 +52,35 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
+- learning_rate: 5e-05
 - train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 14
+- num_epochs: 16
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 10   | 2.0386          | 0.25     |
-| No log        | 2.0   | 20   | 1.9873          | 0.3563   |
-| No log        | 3.0   | 30   | 1.9264          | 0.3875   |
-| No log        | 4.0   | 40   | 1.8662          | 0.4188   |
-| No log        | 5.0   | 50   | 1.8088          | 0.4188   |
-| No log        | 6.0   | 60   | 1.7597          | 0.4313   |
-| No log        | 7.0   | 70   | 1.7167          | 0.4188   |
-| No log        | 8.0   | 80   | 1.6899          | 0.4188   |
-| No log        | 9.0   | 90   | 1.6582          | 0.4437   |
-| No log        | 10.0  | 100  | 1.6435          | 0.4437   |
-| No log        | 11.0  | 110  | 1.6284          | 0.4313   |
-| No log        | 12.0  | 120  | 1.6195          | 0.45     |
-| No log        | 13.0  | 130  | 1.6141          | 0.45     |
-| No log        | 14.0  | 140  | 1.6119          | 0.4437   |
+| No log        | 1.0   | 10   | 1.9952          | 0.2562   |
+| No log        | 2.0   | 20   | 1.8898          | 0.3312   |
+| No log        | 3.0   | 30   | 1.7876          | 0.3875   |
+| No log        | 4.0   | 40   | 1.7055          | 0.375    |
+| No log        | 5.0   | 50   | 1.6422          | 0.4437   |
+| No log        | 6.0   | 60   | 1.5976          | 0.4688   |
+| No log        | 7.0   | 70   | 1.5605          | 0.4688   |
+| No log        | 8.0   | 80   | 1.5305          | 0.5      |
+| No log        | 9.0   | 90   | 1.5002          | 0.4938   |
+| No log        | 10.0  | 100  | 1.4880          | 0.4938   |
+| No log        | 11.0  | 110  | 1.4728          | 0.4625   |
+| No log        | 12.0  | 120  | 1.4561          | 0.5125   |
+| No log        | 13.0  | 130  | 1.4592          | 0.475    |
+| No log        | 14.0  | 140  | 1.4568          | 0.475    |
+| No log        | 15.0  | 150  | 1.4480          | 0.4813   |
+| No log        | 16.0  | 160  | 1.4512          | 0.475    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7632bef3758c1591627d760f3571ef1834613c83d40b67416e92d761a07414a5
+oid sha256:5513b3937d4363310028022516cee9cac72cee5b104a48cd3b1ee79f1aa3f701
 size 343242432

runs/Jul20_09-21-13_e55f09b4413c/events.out.tfevents.1721469109.e55f09b4413c.1185.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6089eff697c856a0737f8d8a6563d40071c8a915cfa9abb0e3731d9238a76a8c
+size 411