tejp/custom_dataset

README.md

@@ -2,12 +2,32 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224
 tags:
+- image-classification
 - generated_from_trainer
 datasets:
 - imagefolder
+metrics:
+- accuracy
+- f1
 model-index:
 - name: fine-tuned
-  results: []
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: custom_dataset
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.2857142857142857
+    - name: F1
+      type: f1
+      value: 0.20303030303030303
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +35,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fine-tuned
 
-This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the custom_dataset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0068
+- Accuracy: 0.2857
+- F1: 0.2030
 
 ## Model description
 

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.42857142857142855,
-    "eval_f1": 0.23982683982683983,
-    "eval_loss": 1.3223016262054443,
-    "eval_runtime": 6.2481,
-    "eval_samples_per_second": 2.241,
-    "eval_steps_per_second": 0.32,
+    "eval_accuracy": 0.2857142857142857,
+    "eval_f1": 0.20303030303030303,
+    "eval_loss": 2.0067503452301025,
+    "eval_runtime": 41.6687,
+    "eval_samples_per_second": 0.336,
+    "eval_steps_per_second": 0.048,
     "total_flos": 3254926098493440.0,
-    "train_loss": 1.8808091481526692,
-    "train_runtime": 34.0039,
-    "train_samples_per_second": 1.235,
-    "train_steps_per_second": 0.088
+    "train_loss": 2.3485514322916665,
+    "train_runtime": 131.9053,
+    "train_samples_per_second": 0.318,
+    "train_steps_per_second": 0.023
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.42857142857142855,
-    "eval_f1": 0.23982683982683983,
-    "eval_loss": 1.3223016262054443,
-    "eval_runtime": 6.2481,
-    "eval_samples_per_second": 2.241,
-    "eval_steps_per_second": 0.32
+    "eval_accuracy": 0.2857142857142857,
+    "eval_f1": 0.20303030303030303,
+    "eval_loss": 2.0067503452301025,
+    "eval_runtime": 41.6687,
+    "eval_samples_per_second": 0.336,
+    "eval_steps_per_second": 0.048
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 3254926098493440.0,
-    "train_loss": 1.8808091481526692,
-    "train_runtime": 34.0039,
-    "train_samples_per_second": 1.235,
-    "train_steps_per_second": 0.088
+    "train_loss": 2.3485514322916665,
+    "train_runtime": 131.9053,
+    "train_samples_per_second": 0.318,
+    "train_steps_per_second": 0.023
 }

trainer_state.json

@@ -12,10 +12,10 @@
       "epoch": 3.0,
       "step": 3,
       "total_flos": 3254926098493440.0,
-      "train_loss": 1.8808091481526692,
-      "train_runtime": 34.0039,
-      "train_samples_per_second": 1.235,
-      "train_steps_per_second": 0.088
+      "train_loss": 2.3485514322916665,
+      "train_runtime": 131.9053,
+      "train_samples_per_second": 0.318,
+      "train_steps_per_second": 0.023
     }
   ],
   "logging_steps": 1000,