End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.55625
+      value: 0.60625
 ---
 
 <!-- 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: 1.4585
-- Accuracy: 0.5563
+- Loss: 1.1926
+- Accuracy: 0.6062
 
 ## Model description
 
@@ -56,8 +56,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 128
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine_with_restarts
 - lr_scheduler_warmup_ratio: 0.05
@@ -67,21 +67,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 5    | 2.0530          | 0.1938   |
-| No log        | 2.0   | 10   | 2.0087          | 0.2625   |
-| No log        | 3.0   | 15   | 1.9485          | 0.375    |
-| 1.9944        | 4.0   | 20   | 1.8570          | 0.475    |
-| 1.9944        | 5.0   | 25   | 1.7607          | 0.4625   |
-| 1.9944        | 6.0   | 30   | 1.6686          | 0.5      |
-| 1.9944        | 7.0   | 35   | 1.5817          | 0.475    |
-| 1.6565        | 8.0   | 40   | 1.5427          | 0.5312   |
-| 1.6565        | 9.0   | 45   | 1.5079          | 0.5312   |
-| 1.6565        | 10.0  | 50   | 1.4815          | 0.5375   |
-| 1.6565        | 11.0  | 55   | 1.4573          | 0.5312   |
-| 1.4397        | 12.0  | 60   | 1.4802          | 0.5062   |
-| 1.4397        | 13.0  | 65   | 1.4401          | 0.575    |
-| 1.4397        | 14.0  | 70   | 1.4584          | 0.5437   |
-| 1.4397        | 15.0  | 75   | 1.4537          | 0.5625   |
+| 2.0693        | 1.0   | 20   | 2.0243          | 0.2313   |
+| 1.916         | 2.0   | 40   | 1.8164          | 0.4      |
+| 1.6741        | 3.0   | 60   | 1.5824          | 0.4437   |
+| 1.4887        | 4.0   | 80   | 1.4664          | 0.4938   |
+| 1.3379        | 5.0   | 100  | 1.3701          | 0.525    |
+| 1.2678        | 6.0   | 120  | 1.3660          | 0.525    |
+| 1.1523        | 7.0   | 140  | 1.2695          | 0.55     |
+| 1.056         | 8.0   | 160  | 1.2339          | 0.5687   |
+| 1.0013        | 9.0   | 180  | 1.2399          | 0.5625   |
+| 0.9213        | 10.0  | 200  | 1.2267          | 0.6      |
+| 0.8827        | 11.0  | 220  | 1.1863          | 0.5563   |
+| 0.8336        | 12.0  | 240  | 1.2650          | 0.5437   |
+| 0.8523        | 13.0  | 260  | 1.1883          | 0.5625   |
+| 0.8497        | 14.0  | 280  | 1.2290          | 0.5625   |
+| 0.8145        | 15.0  | 300  | 1.1911          | 0.6062   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0be37d58b85cf0bf9ce63988d278b35a16296b964b235025dda13cbdafd58a3
+oid sha256:eabd9dbcb31cc6c306cda0750191915f0c69994dc9bbdf60053c5158bbb99146
 size 343242432

runs/Sep02_11-22-10_f45e9a1b66b5/events.out.tfevents.1725276138.f45e9a1b66b5.36.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1e4cf753e1374ff9cf17950d0bdc8c8cc11c3d83ec082f4ace4012c44f8f39e
-size 17702
+oid sha256:81f3557e8ff4053bef66ec6e47ba0cdd7ba0de59b68a68bf222973a50fc1651a
+size 18590

runs/Sep02_11-22-10_f45e9a1b66b5/events.out.tfevents.1725276424.f45e9a1b66b5.36.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7d93cc0cfeb00cd4432f66c79b9f24e30055875b0393317c661e67ec94dbd5a
+size 411