🍻 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: 0.0112
+- Accuracy: 1.0
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.009642996825277805,
-    "eval_runtime": 2.6862,
-    "eval_samples_per_second": 30.526,
-    "eval_steps_per_second": 4.095,
+    "eval_loss": 0.011184412986040115,
+    "eval_runtime": 2.4321,
+    "eval_samples_per_second": 33.716,
+    "eval_steps_per_second": 4.523,
     "total_flos": 2.5417372593586176e+16,
-    "train_loss": 0.15871779123942056,
-    "train_runtime": 30.4881,
-    "train_samples_per_second": 10.758,
-    "train_steps_per_second": 2.755
+    "train_loss": 0.17717325119745164,
+    "train_runtime": 30.5569,
+    "train_samples_per_second": 10.734,
+    "train_steps_per_second": 2.749
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.009642996825277805,
-    "eval_runtime": 2.6862,
-    "eval_samples_per_second": 30.526,
-    "eval_steps_per_second": 4.095
+    "eval_loss": 0.011184412986040115,
+    "eval_runtime": 2.4321,
+    "eval_samples_per_second": 33.716,
+    "eval_steps_per_second": 4.523
 }

runs/Aug30_09-29-42_7e2de4304170/events.out.tfevents.1725010236.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf50be6d15565b53866532cffbcf7f080dc27998c7c25b58283a1c4af8efac9
+size 40

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 2.5417372593586176e+16,
-    "train_loss": 0.15871779123942056,
-    "train_runtime": 30.4881,
-    "train_samples_per_second": 10.758,
-    "train_steps_per_second": 2.755
+    "train_loss": 0.17717325119745164,
+    "train_runtime": 30.5569,
+    "train_samples_per_second": 10.734,
+    "train_steps_per_second": 2.749
 }

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.47619047619047616,
-      "grad_norm": 2.812675952911377,
+      "grad_norm": 2.757856845855713,
       "learning_rate": 0.0001761904761904762,
-      "loss": 0.5907,
+      "loss": 0.5843,
       "step": 10
     },
     {
       "epoch": 0.9523809523809523,
-      "grad_norm": 5.478332996368408,
+      "grad_norm": 3.4689693450927734,
       "learning_rate": 0.00015238095238095237,
-      "loss": 0.4214,
+      "loss": 0.5473,
       "step": 20
     },
     {
       "epoch": 1.4285714285714286,
-      "grad_norm": 1.4264696836471558,
+      "grad_norm": 0.5666776299476624,
       "learning_rate": 0.00012857142857142858,
-      "loss": 0.1644,
+      "loss": 0.1833,
       "step": 30
     },
     {
       "epoch": 1.9047619047619047,
-      "grad_norm": 0.1871589571237564,
+      "grad_norm": 0.2773081362247467,
       "learning_rate": 0.00010476190476190477,
-      "loss": 0.1012,
+      "loss": 0.1073,
       "step": 40
     },
     {
       "epoch": 2.380952380952381,
-      "grad_norm": 0.10930836200714111,
+      "grad_norm": 0.14523948729038239,
       "learning_rate": 8.095238095238096e-05,
-      "loss": 0.0177,
+      "loss": 0.0217,
       "step": 50
     },
     {
       "epoch": 2.857142857142857,
-      "grad_norm": 0.09269272536039352,
+      "grad_norm": 0.10562175512313843,
       "learning_rate": 5.714285714285714e-05,
-      "loss": 0.0132,
+      "loss": 0.0158,
       "step": 60
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.08020050823688507,
+      "grad_norm": 0.09110253304243088,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.0107,
+      "loss": 0.0125,
       "step": 70
     },
     {
       "epoch": 3.8095238095238093,
-      "grad_norm": 0.08233410120010376,
+      "grad_norm": 0.09965213388204575,
       "learning_rate": 9.523809523809523e-06,
-      "loss": 0.0098,
+      "loss": 0.0116,
       "step": 80
     },
     {
       "epoch": 4.0,
       "step": 84,
       "total_flos": 2.5417372593586176e+16,
-      "train_loss": 0.15871779123942056,
-      "train_runtime": 30.4881,
-      "train_samples_per_second": 10.758,
-      "train_steps_per_second": 2.755
+      "train_loss": 0.17717325119745164,
+      "train_runtime": 30.5569,
+      "train_samples_per_second": 10.734,
+      "train_steps_per_second": 2.749
     }
   ],
   "logging_steps": 10,