End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 datasets:
 - imagefolder
@@ -23,7 +25,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9774436090225563
+      value: 0.9924812030075187
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.9774
-- Loss: 0.0837
+- Loss: 0.0650
+- Accuracy: 0.9925
 
 ## Model description
 

all_results.json

@@ -2,12 +2,12 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9924812030075187,
     "eval_loss": 0.06499230116605759,
-    "eval_runtime": 1.097,
-    "eval_samples_per_second": 121.24,
-    "eval_steps_per_second": 15.497,
+    "eval_runtime": 1.0883,
+    "eval_samples_per_second": 122.212,
+    "eval_steps_per_second": 15.621,
     "total_flos": 4.006371770595533e+17,
     "train_loss": 0.0,
-    "train_runtime": 0.0787,
-    "train_samples_per_second": 65712.953,
-    "train_steps_per_second": 8261.783
+    "train_runtime": 0.0792,
+    "train_samples_per_second": 65303.31,
+    "train_steps_per_second": 8210.281
 }

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": "4.45.0.dev0"

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9924812030075187,
     "eval_loss": 0.06499230116605759,
-    "eval_runtime": 1.097,
-    "eval_samples_per_second": 121.24,
-    "eval_steps_per_second": 15.497
+    "eval_runtime": 1.0883,
+    "eval_samples_per_second": 122.212,
+    "eval_steps_per_second": 15.621
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 5.0,
     "total_flos": 4.006371770595533e+17,
     "train_loss": 0.0,
-    "train_runtime": 0.0787,
-    "train_samples_per_second": 65712.953,
-    "train_steps_per_second": 8261.783
+    "train_runtime": 0.0792,
+    "train_samples_per_second": 65303.31,
+    "train_steps_per_second": 8210.281
 }

trainer_state.json

@@ -513,9 +513,9 @@
       "step": 650,
       "total_flos": 4.006371770595533e+17,
       "train_loss": 0.0,
-      "train_runtime": 0.0787,
-      "train_samples_per_second": 65712.953,
-      "train_steps_per_second": 8261.783
+      "train_runtime": 0.0792,
+      "train_samples_per_second": 65303.31,
+      "train_steps_per_second": 8210.281
     }
   ],
   "logging_steps": 10,