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-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: 0.9774
-- Loss: 0.0817
+- Loss: 0.0656
+- Accuracy: 0.9925
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 5.0,
     "eval_accuracy": 0.9924812030075187,
-    "eval_loss": 0.06558172404766083,
-    "eval_runtime": 1.0482,
-    "eval_samples_per_second": 126.888,
-    "eval_steps_per_second": 16.219,
+    "eval_loss": 0.06560193002223969,
+    "eval_runtime": 0.8157,
+    "eval_samples_per_second": 163.052,
+    "eval_steps_per_second": 11.034,
     "total_flos": 4.006371770595533e+17,
-    "train_loss": 0.21942725667586693,
-    "train_runtime": 100.7972,
-    "train_samples_per_second": 51.291,
-    "train_steps_per_second": 6.449
+    "train_loss": 0.0,
+    "train_runtime": 3.5904,
+    "train_samples_per_second": 1439.946,
+    "train_steps_per_second": 90.519
 }

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

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "eval_accuracy": 0.9924812030075187,
-    "eval_loss": 0.06558172404766083,
-    "eval_runtime": 1.0482,
-    "eval_samples_per_second": 126.888,
-    "eval_steps_per_second": 16.219
+    "eval_loss": 0.06560193002223969,
+    "eval_runtime": 0.8157,
+    "eval_samples_per_second": 163.052,
+    "eval_steps_per_second": 11.034
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 4.006371770595533e+17,
-    "train_loss": 0.21942725667586693,
-    "train_runtime": 100.7972,
-    "train_samples_per_second": 51.291,
-    "train_steps_per_second": 6.449
+    "train_loss": 0.0,
+    "train_runtime": 3.5904,
+    "train_samples_per_second": 1439.946,
+    "train_steps_per_second": 90.519
 }

trainer_state.json

@@ -512,14 +512,14 @@
       "epoch": 5.0,
       "step": 650,
       "total_flos": 4.006371770595533e+17,
-      "train_loss": 0.21942725667586693,
-      "train_runtime": 100.7972,
-      "train_samples_per_second": 51.291,
-      "train_steps_per_second": 6.449
+      "train_loss": 0.0,
+      "train_runtime": 3.5904,
+      "train_samples_per_second": 1439.946,
+      "train_steps_per_second": 90.519
     }
   ],
   "logging_steps": 10,
-  "max_steps": 650,
+  "max_steps": 325,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,