End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google/vit-base-patch16-224-in21k
+base_model: dima806/facial_emotions_image_detection
 tags:
 - generated_from_trainer
 datasets:
@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.56875
+      value: 0.6125
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-emotional-classifier
 
-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.
+This model is a fine-tuned version of [dima806/facial_emotions_image_detection](https://huggingface.co/dima806/facial_emotions_image_detection) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2330
-- Accuracy: 0.5687
+- Loss: 1.2566
+- Accuracy: 0.6125
 
 ## Model description
 
@@ -53,57 +53,27 @@ 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: 32
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine_with_restarts
-- num_epochs: 20
+- lr_scheduler_type: linear
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.0354        | 0.5   | 20   | 1.9924          | 0.275    |
-| 1.9057        | 1.0   | 40   | 1.8266          | 0.3937   |
-| 1.67          | 1.5   | 60   | 1.6951          | 0.3438   |
-| 1.6237        | 2.0   | 80   | 1.5888          | 0.4437   |
-| 1.5413        | 2.5   | 100  | 1.5295          | 0.45     |
-| 1.4604        | 3.0   | 120  | 1.5311          | 0.4437   |
-| 1.4092        | 3.5   | 140  | 1.5212          | 0.4562   |
-| 1.4291        | 4.0   | 160  | 1.5151          | 0.4188   |
-| 1.4044        | 4.5   | 180  | 1.4869          | 0.4313   |
-| 1.3961        | 5.0   | 200  | 1.4961          | 0.4062   |
-| 1.2358        | 5.5   | 220  | 1.3494          | 0.55     |
-| 1.1714        | 6.0   | 240  | 1.3767          | 0.4875   |
-| 1.0897        | 6.5   | 260  | 1.3382          | 0.5125   |
-| 1.1153        | 7.0   | 280  | 1.2991          | 0.525    |
-| 1.0265        | 7.5   | 300  | 1.3381          | 0.5188   |
-| 1.0261        | 8.0   | 320  | 1.3143          | 0.5188   |
-| 1.0227        | 8.5   | 340  | 1.3201          | 0.5125   |
-| 0.9978        | 9.0   | 360  | 1.3939          | 0.4375   |
-| 0.9222        | 9.5   | 380  | 1.3469          | 0.4875   |
-| 0.9489        | 10.0  | 400  | 1.2344          | 0.525    |
-| 0.8079        | 10.5  | 420  | 1.1800          | 0.5938   |
-| 0.7336        | 11.0  | 440  | 1.1935          | 0.5687   |
-| 0.7158        | 11.5  | 460  | 1.2030          | 0.5813   |
-| 0.7004        | 12.0  | 480  | 1.2705          | 0.525    |
-| 0.7589        | 12.5  | 500  | 1.2186          | 0.5687   |
-| 0.6966        | 13.0  | 520  | 1.2049          | 0.6125   |
-| 0.5767        | 13.5  | 540  | 1.2057          | 0.55     |
-| 0.6569        | 14.0  | 560  | 1.2047          | 0.5312   |
-| 0.5291        | 14.5  | 580  | 1.2649          | 0.55     |
-| 0.4644        | 15.0  | 600  | 1.2103          | 0.5938   |
-| 0.4895        | 15.5  | 620  | 1.2741          | 0.5687   |
-| 0.4769        | 16.0  | 640  | 1.2278          | 0.5875   |
-| 0.4804        | 16.5  | 660  | 1.3078          | 0.5188   |
-| 0.5169        | 17.0  | 680  | 1.2963          | 0.5      |
-| 0.4137        | 17.5  | 700  | 1.3284          | 0.55     |
-| 0.3856        | 18.0  | 720  | 1.2393          | 0.5563   |
-| 0.4545        | 18.5  | 740  | 1.2368          | 0.5687   |
-| 0.4186        | 19.0  | 760  | 1.2490          | 0.5938   |
-| 0.3814        | 19.5  | 780  | 1.2246          | 0.55     |
-| 0.3813        | 20.0  | 800  | 1.3488          | 0.5375   |
+| 1.8894        | 1.0   | 20   | 1.8158          | 0.3875   |
+| 1.5847        | 2.0   | 40   | 1.5658          | 0.475    |
+| 1.3711        | 3.0   | 60   | 1.4249          | 0.5125   |
+| 1.205         | 4.0   | 80   | 1.3139          | 0.5875   |
+| 1.1244        | 5.0   | 100  | 1.2566          | 0.6125   |
+| 0.9923        | 6.0   | 120  | 1.2256          | 0.6062   |
+| 0.8801        | 7.0   | 140  | 1.1949          | 0.5875   |
+| 0.8631        | 8.0   | 160  | 1.1929          | 0.575    |
+| 0.8277        | 9.0   | 180  | 1.1734          | 0.6      |
+| 0.786         | 10.0  | 200  | 1.1779          | 0.6      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3039c4c036cb75252cac79484c05989551be9f634bf1d5c3c8a1e5e45a1de822
+oid sha256:5292229cc65e3c9646a6ddaa9b17b520cf959b3e0f6cf1a690e2f94f3ff86631
 size 343242432

runs/Jun05_08-36-31_02ebc0950e27/events.out.tfevents.1717576598.02ebc0950e27.473.19

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5028f15963d94d4853b4301bf29d931e17be9a4804f6d452aeb73db0ee319e92
-size 12519
+oid sha256:6024f70d9b73ba9c060d202062dbd6dad3a58942a893c96574a48a4bd976bc3e
+size 12873

runs/Jun05_08-36-31_02ebc0950e27/events.out.tfevents.1717576948.02ebc0950e27.473.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:317a7ee3adfe2f0c377cdf2d5350d32db5acd2e59b99c03e0204027f333b03b2
+size 411