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: 1.0
 - Loss: 0.0079
+- Accuracy: 1.0
 
 ## Model description
 

all_results.json

@@ -2,12 +2,12 @@
     "epoch": 50.0,
     "eval_accuracy": 1.0,
     "eval_loss": 0.007947824895381927,
-    "eval_runtime": 0.7147,
-    "eval_samples_per_second": 186.093,
-    "eval_steps_per_second": 12.593,
+    "eval_runtime": 0.7572,
+    "eval_samples_per_second": 175.64,
+    "eval_steps_per_second": 11.885,
     "total_flos": 3.6243328994998477e+18,
     "train_loss": 0.0,
-    "train_runtime": 0.0797,
-    "train_samples_per_second": 38914.671,
-    "train_steps_per_second": 2446.28
+    "train_runtime": 0.0791,
+    "train_samples_per_second": 65335.775,
+    "train_steps_per_second": 4107.181
 }

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": 50.0,
     "eval_accuracy": 1.0,
     "eval_loss": 0.007947824895381927,
-    "eval_runtime": 0.7147,
-    "eval_samples_per_second": 186.093,
-    "eval_steps_per_second": 12.593
+    "eval_runtime": 0.7572,
+    "eval_samples_per_second": 175.64,
+    "eval_steps_per_second": 11.885
 }

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 50.0,
     "total_flos": 3.6243328994998477e+18,
     "train_loss": 0.0,
-    "train_runtime": 0.0797,
-    "train_samples_per_second": 38914.671,
-    "train_steps_per_second": 2446.28
+    "train_runtime": 0.0791,
+    "train_samples_per_second": 65335.775,
+    "train_steps_per_second": 4107.181
 }

trainer_state.json

@@ -2693,15 +2693,15 @@
       "step": 3250,
       "total_flos": 3.6243328994998477e+18,
       "train_loss": 0.0,
-      "train_runtime": 0.0797,
-      "train_samples_per_second": 38914.671,
-      "train_steps_per_second": 2446.28
+      "train_runtime": 0.0791,
+      "train_samples_per_second": 65335.775,
+      "train_steps_per_second": 4107.181
     }
   ],
   "logging_steps": 10,
-  "max_steps": 195,
+  "max_steps": 325,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {