🍻 cheers

README.md

@@ -2,12 +2,30 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- image-feature-extraction
+- image-to-text
 - generated_from_trainer
 datasets:
 - imagefolder
+metrics:
+- accuracy
 model-index:
 - name: vit-finetune-scrap
-  results: []
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: d071696/scraps1
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9666666666666667
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +33,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-finetune-scrap
 
-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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the d071696/scraps1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6106
+- Accuracy: 0.9667
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.8666666666666667,
-    "eval_loss": 1.6352765560150146,
-    "eval_runtime": 1.6898,
-    "eval_samples_per_second": 17.753,
-    "eval_steps_per_second": 2.367,
+    "eval_accuracy": 0.9666666666666667,
+    "eval_loss": 1.6106475591659546,
+    "eval_runtime": 2.2515,
+    "eval_samples_per_second": 13.325,
+    "eval_steps_per_second": 1.777,
     "total_flos": 9299872197181440.0,
-    "train_loss": 2.0607935786247253,
-    "train_runtime": 16.8831,
-    "train_samples_per_second": 7.108,
-    "train_steps_per_second": 0.948
+    "train_loss": 2.0597532987594604,
+    "train_runtime": 8.5801,
+    "train_samples_per_second": 13.986,
+    "train_steps_per_second": 1.865
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.8666666666666667,
-    "eval_loss": 1.6352765560150146,
-    "eval_runtime": 1.6898,
-    "eval_samples_per_second": 17.753,
-    "eval_steps_per_second": 2.367
+    "eval_accuracy": 0.9666666666666667,
+    "eval_loss": 1.6106475591659546,
+    "eval_runtime": 2.2515,
+    "eval_samples_per_second": 13.325,
+    "eval_steps_per_second": 1.777
 }

runs/Mar22_10-44-15_X5C922065N/events.out.tfevents.1711100691.X5C922065N.52576.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42bdb712b4bfcbead734836ee1929d93d8a3fa30306033c3c1fab46c4cd898d9
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 9299872197181440.0,
-    "train_loss": 2.0607935786247253,
-    "train_runtime": 16.8831,
-    "train_samples_per_second": 7.108,
-    "train_steps_per_second": 0.948
+    "train_loss": 2.0597532987594604,
+    "train_runtime": 8.5801,
+    "train_samples_per_second": 13.986,
+    "train_steps_per_second": 1.865
 }

trainer_state.json

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 2.5,
-      "grad_norm": 2.7056047916412354,
+      "grad_norm": 2.4165334701538086,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 2.239,
+      "loss": 2.2555,
       "step": 10
     },
     {
       "epoch": 4.0,
       "step": 16,
       "total_flos": 9299872197181440.0,
-      "train_loss": 2.0607935786247253,
-      "train_runtime": 16.8831,
-      "train_samples_per_second": 7.108,
-      "train_steps_per_second": 0.948
+      "train_loss": 2.0597532987594604,
+      "train_runtime": 8.5801,
+      "train_samples_per_second": 13.986,
+      "train_steps_per_second": 1.865
     }
   ],
   "logging_steps": 10,