🍻 cheers

README.md

@@ -2,7 +2,11 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: vit-base-beans
   results: []
@@ -13,7 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-beans
 
-This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown 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 beans dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0244
+- Accuracy: 1.0
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.02922426350414753,
-    "eval_runtime": 2.5047,
-    "eval_samples_per_second": 23.157,
-    "eval_steps_per_second": 3.194,
+    "eval_loss": 0.024416429921984673,
+    "eval_runtime": 2.0478,
+    "eval_samples_per_second": 28.324,
+    "eval_steps_per_second": 3.907,
     "total_flos": 1.7978141590585344e+16,
-    "train_loss": 0.3442591349283854,
-    "train_runtime": 23.0063,
-    "train_samples_per_second": 10.084,
-    "train_steps_per_second": 2.608
+    "train_loss": 0.3237314224243164,
+    "train_runtime": 22.8416,
+    "train_samples_per_second": 10.157,
+    "train_steps_per_second": 2.627
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.02922426350414753,
-    "eval_runtime": 2.5047,
-    "eval_samples_per_second": 23.157,
-    "eval_steps_per_second": 3.194
+    "eval_loss": 0.024416429921984673,
+    "eval_runtime": 2.0478,
+    "eval_samples_per_second": 28.324,
+    "eval_steps_per_second": 3.907
 }

runs/Aug30_08-42-59_7e2de4304170/events.out.tfevents.1725007425.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffeafa0116c34c29065fac406dcd41e2c145fe7cb64566306100e83767e93ccc
+size 40

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 1.7978141590585344e+16,
-    "train_loss": 0.3442591349283854,
-    "train_runtime": 23.0063,
-    "train_samples_per_second": 10.084,
-    "train_steps_per_second": 2.608
+    "train_loss": 0.3237314224243164,
+    "train_runtime": 22.8416,
+    "train_samples_per_second": 10.157,
+    "train_steps_per_second": 2.627
 }

trainer_state.json

@@ -10,54 +10,54 @@
   "log_history": [
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 2.396704912185669,
+      "grad_norm": 2.1028881072998047,
       "learning_rate": 0.0001666666666666667,
-      "loss": 0.616,
+      "loss": 0.609,
       "step": 10
     },
     {
       "epoch": 1.3333333333333333,
-      "grad_norm": 2.4850783348083496,
+      "grad_norm": 5.82706880569458,
       "learning_rate": 0.00013333333333333334,
-      "loss": 0.7095,
+      "loss": 0.6172,
       "step": 20
     },
     {
       "epoch": 2.0,
-      "grad_norm": 15.093992233276367,
+      "grad_norm": 10.371822357177734,
       "learning_rate": 0.0001,
-      "loss": 0.4833,
+      "loss": 0.4026,
       "step": 30
     },
     {
       "epoch": 2.6666666666666665,
-      "grad_norm": 1.8995352983474731,
+      "grad_norm": 0.941929817199707,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 0.1775,
+      "loss": 0.171,
       "step": 40
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.27144622802734375,
+      "grad_norm": 0.1865934133529663,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.0467,
+      "loss": 0.114,
       "step": 50
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.5607824921607971,
+      "grad_norm": 0.20858462154865265,
       "learning_rate": 0.0,
-      "loss": 0.0327,
+      "loss": 0.0287,
       "step": 60
     },
     {
       "epoch": 4.0,
       "step": 60,
       "total_flos": 1.7978141590585344e+16,
-      "train_loss": 0.3442591349283854,
-      "train_runtime": 23.0063,
-      "train_samples_per_second": 10.084,
-      "train_steps_per_second": 2.608
+      "train_loss": 0.3237314224243164,
+      "train_runtime": 22.8416,
+      "train_samples_per_second": 10.157,
+      "train_steps_per_second": 2.627
     }
   ],
   "logging_steps": 10,