🍻 cheers

README.md

@@ -2,12 +2,30 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- feature-extraction
+- zero-shot-image-classification
 - 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: 0.9
 ---
 
 <!-- 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: 1.5546
+- Accuracy: 0.9
 
 ## Model description
 

all_results.json

@@ -2,12 +2,12 @@
     "epoch": 4.0,
     "eval_accuracy": 0.9,
     "eval_loss": 1.5546358823776245,
-    "eval_runtime": 1.978,
-    "eval_samples_per_second": 15.167,
-    "eval_steps_per_second": 2.022,
+    "eval_runtime": 1.2287,
+    "eval_samples_per_second": 24.416,
+    "eval_steps_per_second": 3.255,
     "total_flos": 9299872197181440.0,
     "train_loss": 2.0122132897377014,
-    "train_runtime": 9.4925,
-    "train_samples_per_second": 12.642,
-    "train_steps_per_second": 1.686
+    "train_runtime": 8.672,
+    "train_samples_per_second": 13.838,
+    "train_steps_per_second": 1.845
 }

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 4.0,
     "eval_accuracy": 0.9,
     "eval_loss": 1.5546358823776245,
-    "eval_runtime": 1.978,
-    "eval_samples_per_second": 15.167,
-    "eval_steps_per_second": 2.022
+    "eval_runtime": 1.2287,
+    "eval_samples_per_second": 24.416,
+    "eval_steps_per_second": 3.255
 }

runs/Mar22_11-05-25_X5C922065N/events.out.tfevents.1711101946.X5C922065N.52576.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0d3e0eb44e5842785dc1a8dcb6dc1b0f6558076db6026c447ed3657e9301af
+size 405

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 4.0,
     "total_flos": 9299872197181440.0,
     "train_loss": 2.0122132897377014,
-    "train_runtime": 9.4925,
-    "train_samples_per_second": 12.642,
-    "train_steps_per_second": 1.686
+    "train_runtime": 8.672,
+    "train_samples_per_second": 13.838,
+    "train_steps_per_second": 1.845
 }

trainer_state.json

@@ -20,9 +20,9 @@
       "step": 16,
       "total_flos": 9299872197181440.0,
       "train_loss": 2.0122132897377014,
-      "train_runtime": 9.4925,
-      "train_samples_per_second": 12.642,
-      "train_steps_per_second": 1.686
+      "train_runtime": 8.672,
+      "train_samples_per_second": 13.838,
+      "train_steps_per_second": 1.845
     }
   ],
   "logging_steps": 10,