End of training

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 metrics:
 - accuracy
@@ -15,10 +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:
-- Accuracy: 0.9699
 - Loss: 0.5654
+- Accuracy: 0.9699
 
 ## Model description
 

all_results.json

@@ -2,12 +2,12 @@
     "epoch": 3.0,
     "eval_accuracy": 0.9699248120300752,
     "eval_loss": 0.5654206275939941,
-    "eval_runtime": 1.6395,
-    "eval_samples_per_second": 81.121,
-    "eval_steps_per_second": 1.83,
+    "eval_runtime": 13.0062,
+    "eval_samples_per_second": 10.226,
+    "eval_steps_per_second": 0.231,
     "total_flos": 2.4038230623573197e+17,
-    "train_loss": 0.7545152774044112,
-    "train_runtime": 73.3826,
-    "train_samples_per_second": 42.272,
-    "train_steps_per_second": 0.695
+    "train_loss": 0.0,
+    "train_runtime": 0.3673,
+    "train_samples_per_second": 8444.655,
+    "train_steps_per_second": 138.839
 }

config.json

@@ -28,6 +28,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.43.0.dev0"

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 3.0,
     "eval_accuracy": 0.9699248120300752,
     "eval_loss": 0.5654206275939941,
-    "eval_runtime": 1.6395,
-    "eval_samples_per_second": 81.121,
-    "eval_steps_per_second": 1.83
+    "eval_runtime": 13.0062,
+    "eval_samples_per_second": 10.226,
+    "eval_steps_per_second": 0.231
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 2.4038230623573197e+17,
-    "train_loss": 0.7545152774044112,
-    "train_runtime": 73.3826,
-    "train_samples_per_second": 42.272,
-    "train_steps_per_second": 0.695
+    "train_loss": 0.0,
+    "train_runtime": 0.3673,
+    "train_samples_per_second": 8444.655,
+    "train_steps_per_second": 138.839
 }

trainer_state.json

@@ -74,10 +74,10 @@
       "epoch": 3.0,
       "step": 51,
       "total_flos": 2.4038230623573197e+17,
-      "train_loss": 0.7545152774044112,
-      "train_runtime": 73.3826,
-      "train_samples_per_second": 42.272,
-      "train_steps_per_second": 0.695
+      "train_loss": 0.0,
+      "train_runtime": 0.3673,
+      "train_samples_per_second": 8444.655,
+      "train_steps_per_second": 138.839
     }
   ],
   "logging_steps": 10,