🍻 cheers

README.md

@@ -2,9 +2,13 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- image-feature-extraction
 - generated_from_trainer
 datasets:
 - imagefolder
+metrics:
+- accuracy
 model-index:
 - name: vit-finetune-scrap
   results: []
@@ -15,7 +19,10 @@ 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: 0.9895
+- Accuracy: 1.0
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.9666666666666667,
-    "eval_loss": 1.6106475591659546,
-    "eval_runtime": 2.2515,
-    "eval_samples_per_second": 13.325,
-    "eval_steps_per_second": 1.777,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.9895318150520325,
+    "eval_runtime": 1.779,
+    "eval_samples_per_second": 16.863,
+    "eval_steps_per_second": 2.248,
     "total_flos": 9299872197181440.0,
-    "train_loss": 2.0122132897377014,
-    "train_runtime": 8.9154,
-    "train_samples_per_second": 13.46,
-    "train_steps_per_second": 1.795
+    "train_loss": 1.3567551374435425,
+    "train_runtime": 9.1428,
+    "train_samples_per_second": 13.125,
+    "train_steps_per_second": 1.75
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.9666666666666667,
-    "eval_loss": 1.6106475591659546,
-    "eval_runtime": 2.2515,
-    "eval_samples_per_second": 13.325,
-    "eval_steps_per_second": 1.777
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.9895318150520325,
+    "eval_runtime": 1.779,
+    "eval_samples_per_second": 16.863,
+    "eval_steps_per_second": 2.248
 }

runs/Mar22_10-48-55_X5C922065N/events.out.tfevents.1711100963.X5C922065N.52576.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91957aa64ea0fb4c4a581da8075453363bfc3c46fce20b36f01510224e0ed413
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 9299872197181440.0,
-    "train_loss": 2.0122132897377014,
-    "train_runtime": 8.9154,
-    "train_samples_per_second": 13.46,
-    "train_steps_per_second": 1.795
+    "train_loss": 1.3567551374435425,
+    "train_runtime": 9.1428,
+    "train_samples_per_second": 13.125,
+    "train_steps_per_second": 1.75
 }

trainer_state.json

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 2.5,
-      "grad_norm": 2.5313448905944824,
+      "grad_norm": 2.364220142364502,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 2.2157,
+      "loss": 1.5278,
       "step": 10
     },
     {
       "epoch": 4.0,
       "step": 16,
       "total_flos": 9299872197181440.0,
-      "train_loss": 2.0122132897377014,
-      "train_runtime": 8.9154,
-      "train_samples_per_second": 13.46,
-      "train_steps_per_second": 1.795
+      "train_loss": 1.3567551374435425,
+      "train_runtime": 9.1428,
+      "train_samples_per_second": 13.125,
+      "train_steps_per_second": 1.75
     }
   ],
   "logging_steps": 10,