End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5625
+      value: 0.56875
 ---
 
 <!-- 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: 1.3486
-- Accuracy: 0.5625
+- Loss: 1.2074
+- Accuracy: 0.5687
 
 ## Model description
 
@@ -53,33 +53,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 18
-- num_epochs: 15
+- lr_scheduler_warmup_steps: 8
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 2.0210          | 0.2437   |
-| No log        | 2.0   | 80   | 1.7511          | 0.3187   |
-| No log        | 3.0   | 120  | 1.6444          | 0.3688   |
-| No log        | 4.0   | 160  | 1.5294          | 0.4188   |
-| No log        | 5.0   | 200  | 1.4306          | 0.45     |
-| No log        | 6.0   | 240  | 1.3968          | 0.4813   |
-| No log        | 7.0   | 280  | 1.3403          | 0.5312   |
-| No log        | 8.0   | 320  | 1.3413          | 0.4688   |
-| No log        | 9.0   | 360  | 1.3573          | 0.4437   |
-| No log        | 10.0  | 400  | 1.4416          | 0.4562   |
-| No log        | 11.0  | 440  | 1.3263          | 0.5188   |
-| No log        | 12.0  | 480  | 1.3960          | 0.4813   |
-| 1.1068        | 13.0  | 520  | 1.3476          | 0.5125   |
-| 1.1068        | 14.0  | 560  | 1.3720          | 0.5125   |
-| 1.1068        | 15.0  | 600  | 1.3614          | 0.4562   |
+| No log        | 1.0   | 80   | 1.7180          | 0.3812   |
+| No log        | 2.0   | 160  | 1.5309          | 0.3625   |
+| No log        | 3.0   | 240  | 1.4981          | 0.4188   |
+| No log        | 4.0   | 320  | 1.4135          | 0.4313   |
+| No log        | 5.0   | 400  | 1.3722          | 0.4562   |
+| No log        | 6.0   | 480  | 1.3234          | 0.5188   |
+| 1.3335        | 7.0   | 560  | 1.2675          | 0.525    |
+| 1.3335        | 8.0   | 640  | 1.3068          | 0.5125   |
+| 1.3335        | 9.0   | 720  | 1.2965          | 0.5437   |
+| 1.3335        | 10.0  | 800  | 1.3408          | 0.5125   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a0ec6f6305294ee867e8202e1351e241f22d384049eb51ebc486553f405563b
+oid sha256:e110359f426fd127cac11ac3ea760a085bf501186e44ac99962422029592ebff
 size 343242432

runs/Jun04_17-01-32_deb04761fe34/events.out.tfevents.1717520775.deb04761fe34.33.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7dbfa9867b8327b7555f48663c8a8f919a1a25731d64249a4598c902e707610
+size 4610