End of training

README.md

@@ -1,6 +1,7 @@
 ---
+library_name: transformers
 license: apache-2.0
-base_model: google/vit-large-patch16-224-in21k
+base_model: google/vit-base-patch16-224-in21k
 tags:
 - generated_from_trainer
 datasets:
@@ -22,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.51875
+      value: 0.6125
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # image_classification
 
-This model is a fine-tuned version of [google/vit-large-patch16-224-in21k](https://huggingface.co/google/vit-large-patch16-224-in21k) on the imagefolder 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 the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5386
-- Accuracy: 0.5188
+- Loss: 1.1555
+- Accuracy: 0.6125
 
 ## Model description
 
@@ -53,45 +54,50 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 20
+- num_epochs: 25
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.0473        | 1.0   | 20   | 2.0179          | 0.175    |
-| 1.6184        | 2.0   | 40   | 1.7787          | 0.2437   |
-| 1.2134        | 3.0   | 60   | 1.5985          | 0.3625   |
-| 1.0157        | 4.0   | 80   | 1.3311          | 0.4813   |
-| 0.8578        | 5.0   | 100  | 1.3041          | 0.4875   |
-| 0.6496        | 6.0   | 120  | 1.3222          | 0.5062   |
-| 0.5972        | 7.0   | 140  | 1.5594          | 0.4562   |
-| 0.5073        | 8.0   | 160  | 1.4126          | 0.4813   |
-| 0.3964        | 9.0   | 180  | 1.3702          | 0.525    |
-| 0.4054        | 10.0  | 200  | 1.3894          | 0.5188   |
-| 0.2845        | 11.0  | 220  | 1.4471          | 0.5188   |
-| 0.2262        | 12.0  | 240  | 1.5165          | 0.525    |
-| 0.2412        | 13.0  | 260  | 1.4684          | 0.5125   |
-| 0.2229        | 14.0  | 280  | 1.4005          | 0.525    |
-| 0.2078        | 15.0  | 300  | 1.5629          | 0.5062   |
-| 0.1619        | 16.0  | 320  | 1.6014          | 0.525    |
-| 0.1834        | 17.0  | 340  | 1.4821          | 0.5125   |
-| 0.1594        | 18.0  | 360  | 1.5195          | 0.5375   |
-| 0.1249        | 19.0  | 380  | 1.5585          | 0.5188   |
-| 0.1117        | 20.0  | 400  | 1.4735          | 0.5687   |
+| 1.7108        | 1.0   | 10   | 1.8424          | 0.4188   |
+| 1.6278        | 2.0   | 20   | 1.7495          | 0.45     |
+| 1.465         | 3.0   | 30   | 1.6153          | 0.5062   |
+| 1.2862        | 4.0   | 40   | 1.5099          | 0.55     |
+| 1.1151        | 5.0   | 50   | 1.4399          | 0.5312   |
+| 0.9631        | 6.0   | 60   | 1.3803          | 0.5375   |
+| 0.8242        | 7.0   | 70   | 1.3213          | 0.5875   |
+| 0.6939        | 8.0   | 80   | 1.2673          | 0.575    |
+| 0.576         | 9.0   | 90   | 1.2463          | 0.5938   |
+| 0.4801        | 10.0  | 100  | 1.2108          | 0.6      |
+| 0.4008        | 11.0  | 110  | 1.2093          | 0.575    |
+| 0.3426        | 12.0  | 120  | 1.1744          | 0.5687   |
+| 0.2976        | 13.0  | 130  | 1.1710          | 0.5938   |
+| 0.2667        | 14.0  | 140  | 1.1545          | 0.5875   |
+| 0.2434        | 15.0  | 150  | 1.1622          | 0.6      |
+| 0.2261        | 16.0  | 160  | 1.1522          | 0.5875   |
+| 0.2119        | 17.0  | 170  | 1.1486          | 0.6062   |
+| 0.2016        | 18.0  | 180  | 1.1555          | 0.6125   |
+| 0.1932        | 19.0  | 190  | 1.1487          | 0.6062   |
+| 0.1857        | 20.0  | 200  | 1.1422          | 0.5938   |
+| 0.1812        | 21.0  | 210  | 1.1438          | 0.6      |
+| 0.1772        | 22.0  | 220  | 1.1521          | 0.5687   |
+| 0.1735        | 23.0  | 230  | 1.1428          | 0.5938   |
+| 0.1714        | 24.0  | 240  | 1.1487          | 0.6      |
+| 0.1703        | 25.0  | 250  | 1.1462          | 0.6      |
 
 
 ### Framework versions
 
-- Transformers 4.42.4
+- Transformers 4.44.2
 - Pytorch 2.4.0+cu121
 - Datasets 2.21.0
 - Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac830574556dc7a4ada4e74065e061ddd5645f1265f4bcac3b3450d558732ce
+oid sha256:6ad3b1d68275af8c5ef822963ed2219a3607171ac406ea49736d15a1ab3936ba
 size 343242432

runs/Sep05_00-12-04_8837de964a95/events.out.tfevents.1725495134.8837de964a95.2043.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a31cfa65bd0db82fd7ef565b8b01127d096b692a244c263d7e4e8c1b7b8917
-size 18157
+oid sha256:d5eabbb20dd077c085369e03808031411177922f1386f3f3667afdeb91b1c5f8
+size 18834

runs/Sep05_00-12-04_8837de964a95/events.out.tfevents.1725496628.8837de964a95.2043.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a15f0fbe68a0f5e07167f1f5a7f831914beeef9afddc684b71893471a68039fa
+size 411