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
 metrics:
 - accuracy
@@ -16,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-cifar100-cifar100
 
-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 cifar100 dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.9241
 - Loss: 0.2955
+- Accuracy: 0.9241
 
 ## Model description
 

all_results.json

@@ -2,12 +2,12 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9241333333333334,
     "eval_loss": 0.2954551577568054,
-    "eval_runtime": 121.8517,
-    "eval_samples_per_second": 61.55,
-    "eval_steps_per_second": 7.698,
+    "eval_runtime": 26.7539,
+    "eval_samples_per_second": 280.333,
+    "eval_steps_per_second": 35.06,
     "total_flos": 1.64815115092992e+19,
-    "train_loss": 1.1898613937197713,
-    "train_runtime": 10288.1641,
-    "train_samples_per_second": 20.655,
-    "train_steps_per_second": 2.582
+    "train_loss": 0.0,
+    "train_runtime": 0.0821,
+    "train_samples_per_second": 2587573.233,
+    "train_steps_per_second": 323477.096
 }

config.json

@@ -222,6 +222,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.44.2"

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9241333333333334,
     "eval_loss": 0.2954551577568054,
-    "eval_runtime": 121.8517,
-    "eval_samples_per_second": 61.55,
-    "eval_steps_per_second": 7.698
+    "eval_runtime": 26.7539,
+    "eval_samples_per_second": 280.333,
+    "eval_steps_per_second": 35.06
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 1.64815115092992e+19,
-    "train_loss": 1.1898613937197713,
-    "train_runtime": 10288.1641,
-    "train_samples_per_second": 20.655,
-    "train_steps_per_second": 2.582
+    "train_loss": 0.0,
+    "train_runtime": 0.0821,
+    "train_samples_per_second": 2587573.233,
+    "train_steps_per_second": 323477.096
 }

trainer_state.json

@@ -18649,10 +18649,10 @@
       "epoch": 5.0,
       "step": 26565,
       "total_flos": 1.64815115092992e+19,
-      "train_loss": 1.1898613937197713,
-      "train_runtime": 10288.1641,
-      "train_samples_per_second": 20.655,
-      "train_steps_per_second": 2.582
+      "train_loss": 0.0,
+      "train_runtime": 0.0821,
+      "train_samples_per_second": 2587573.233,
+      "train_steps_per_second": 323477.096
     }
   ],
   "logging_steps": 10,