🍻 cheers

README.md

@@ -2,7 +2,11 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224
 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](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the beans dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0002
+- Accuracy: 1.0
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.00037778005935251713,
-    "eval_runtime": 3.7977,
-    "eval_samples_per_second": 21.592,
-    "eval_steps_per_second": 2.896,
-    "total_flos": 2.6605778719997952e+17,
-    "train_loss": 0.34859154408886317,
-    "train_runtime": 81.3001,
-    "train_samples_per_second": 4.034,
-    "train_steps_per_second": 1.033
+    "eval_loss": 0.0001566599094076082,
+    "eval_runtime": 2.4776,
+    "eval_samples_per_second": 33.097,
+    "eval_steps_per_second": 4.44,
+    "total_flos": 2.5417372593586176e+16,
+    "train_loss": 0.1902264037302562,
+    "train_runtime": 30.4122,
+    "train_samples_per_second": 10.785,
+    "train_steps_per_second": 2.762
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.00037778005935251713,
-    "eval_runtime": 3.7977,
-    "eval_samples_per_second": 21.592,
-    "eval_steps_per_second": 2.896
+    "eval_loss": 0.0001566599094076082,
+    "eval_runtime": 2.4776,
+    "eval_samples_per_second": 33.097,
+    "eval_steps_per_second": 4.44
 }

runs/Aug30_10-01-18_7e2de4304170/events.out.tfevents.1725012136.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b65dd299fff61a93ef7adae902ae0ea57aec74cc26da58fb98d0011d2d4cdf2
+size 40

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "total_flos": 2.6605778719997952e+17,
-    "train_loss": 0.34859154408886317,
-    "train_runtime": 81.3001,
-    "train_samples_per_second": 4.034,
-    "train_steps_per_second": 1.033
+    "total_flos": 2.5417372593586176e+16,
+    "train_loss": 0.1902264037302562,
+    "train_runtime": 30.4122,
+    "train_samples_per_second": 10.785,
+    "train_steps_per_second": 2.762
 }

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.47619047619047616,
-      "grad_norm": 6.629721164703369,
+      "grad_norm": 6.1757893562316895,
       "learning_rate": 0.0001785714285714286,
-      "loss": 1.0185,
+      "loss": 0.5829,
       "step": 10
     },
     {
       "epoch": 0.9523809523809523,
-      "grad_norm": 18.000343322753906,
+      "grad_norm": 3.337554931640625,
       "learning_rate": 0.00015476190476190478,
-      "loss": 0.7882,
+      "loss": 0.7423,
       "step": 20
     },
     {
       "epoch": 1.4285714285714286,
-      "grad_norm": 0.8654012680053711,
+      "grad_norm": 0.07775535434484482,
       "learning_rate": 0.00013095238095238096,
-      "loss": 0.3069,
+      "loss": 0.0198,
       "step": 30
     },
     {
       "epoch": 1.9047619047619047,
-      "grad_norm": 25.521047592163086,
+      "grad_norm": 0.0923432782292366,
       "learning_rate": 0.00010714285714285715,
-      "loss": 0.6619,
+      "loss": 0.2508,
       "step": 40
     },
     {
       "epoch": 2.380952380952381,
-      "grad_norm": 0.016277112066745758,
+      "grad_norm": 0.010310073383152485,
       "learning_rate": 8.333333333333334e-05,
-      "loss": 0.1038,
+      "loss": 0.0006,
       "step": 50
     },
     {
       "epoch": 2.857142857142857,
-      "grad_norm": 0.021812940016388893,
+      "grad_norm": 0.022837914526462555,
       "learning_rate": 5.9523809523809524e-05,
-      "loss": 0.0386,
+      "loss": 0.0011,
       "step": 60
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.006898158695548773,
+      "grad_norm": 0.0032586820889264345,
       "learning_rate": 3.571428571428572e-05,
-      "loss": 0.0006,
+      "loss": 0.0002,
       "step": 70
     },
     {
       "epoch": 3.8095238095238093,
-      "grad_norm": 0.003354752669110894,
+      "grad_norm": 0.00261130603030324,
       "learning_rate": 1.1904761904761905e-05,
-      "loss": 0.0093,
+      "loss": 0.0001,
       "step": 80
     },
     {
       "epoch": 4.0,
       "step": 84,
-      "total_flos": 2.6605778719997952e+17,
-      "train_loss": 0.34859154408886317,
-      "train_runtime": 81.3001,
-      "train_samples_per_second": 4.034,
-      "train_steps_per_second": 1.033
+      "total_flos": 2.5417372593586176e+16,
+      "train_loss": 0.1902264037302562,
+      "train_runtime": 30.4122,
+      "train_samples_per_second": 10.785,
+      "train_steps_per_second": 2.762
     }
   ],
   "logging_steps": 10,
@@ -91,7 +91,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6605778719997952e+17,
+  "total_flos": 2.5417372593586176e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null