End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224
 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-cocoa
 
-This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the SemilleroCV/Cocoa-dataset dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.9350
-- Loss: 0.5570
+- Loss: 0.2061
+- Accuracy: 0.9278
 
 ## Model description
 

all_results.json

@@ -2,12 +2,12 @@
     "epoch": 100.0,
     "eval_accuracy": 0.927797833935018,
     "eval_loss": 0.20614954829216003,
-    "eval_runtime": 1.0793,
-    "eval_samples_per_second": 256.658,
-    "eval_steps_per_second": 32.43,
+    "eval_runtime": 1.2179,
+    "eval_samples_per_second": 227.438,
+    "eval_steps_per_second": 28.738,
     "total_flos": 1.2135680631115776e+19,
-    "train_loss": 0.06464558898389924,
-    "train_runtime": 1480.7558,
-    "train_samples_per_second": 105.757,
-    "train_steps_per_second": 13.236
+    "train_loss": 0.0,
+    "train_runtime": 1.4004,
+    "train_samples_per_second": 111828.931,
+    "train_steps_per_second": 13996.469
 }

config.json

@@ -34,6 +34,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.0.dev0"

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 100.0,
     "eval_accuracy": 0.927797833935018,
     "eval_loss": 0.20614954829216003,
-    "eval_runtime": 1.0793,
-    "eval_samples_per_second": 256.658,
-    "eval_steps_per_second": 32.43
+    "eval_runtime": 1.2179,
+    "eval_samples_per_second": 227.438,
+    "eval_steps_per_second": 28.738
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 100.0,
     "total_flos": 1.2135680631115776e+19,
-    "train_loss": 0.06464558898389924,
-    "train_runtime": 1480.7558,
-    "train_samples_per_second": 105.757,
-    "train_steps_per_second": 13.236
+    "train_loss": 0.0,
+    "train_runtime": 1.4004,
+    "train_samples_per_second": 111828.931,
+    "train_steps_per_second": 13996.469
 }

trainer_state.json

@@ -14632,10 +14632,10 @@
       "epoch": 100.0,
       "step": 19600,
       "total_flos": 1.2135680631115776e+19,
-      "train_loss": 0.06464558898389924,
-      "train_runtime": 1480.7558,
-      "train_samples_per_second": 105.757,
-      "train_steps_per_second": 13.236
+      "train_loss": 0.0,
+      "train_runtime": 1.4004,
+      "train_samples_per_second": 111828.931,
+      "train_steps_per_second": 13996.469
     }
   ],
   "logging_steps": 10,