End of training

README.md

@@ -3,6 +3,7 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224
 tags:
+- image-classification, screenshots detection
 - generated_from_trainer
 metrics:
 - accuracy
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Screenshots_detection_to_classification
 
-This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the None dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the private_images_dataset dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.2538
 - Accuracy: 0.9524

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.975609756097561,
-    "eval_loss": 0.14302679896354675,
-    "eval_runtime": 7.6666,
-    "eval_samples_per_second": 10.696,
-    "eval_steps_per_second": 1.435,
-    "total_flos": 1.0042961854051123e+17,
-    "train_loss": 0.0985631244938548,
-    "train_runtime": 148.8516,
-    "train_samples_per_second": 8.707,
-    "train_steps_per_second": 1.102
+    "eval_accuracy": 0.9523809523809523,
+    "eval_loss": 0.25383907556533813,
+    "eval_runtime": 8.444,
+    "eval_samples_per_second": 9.948,
+    "eval_steps_per_second": 1.303,
+    "total_flos": 1.0352929812509491e+17,
+    "train_loss": 0.13229456402006604,
+    "train_runtime": 163.4534,
+    "train_samples_per_second": 8.174,
+    "train_steps_per_second": 1.028
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 0.975609756097561,
-    "eval_loss": 0.14302679896354675,
-    "eval_runtime": 7.6666,
-    "eval_samples_per_second": 10.696,
-    "eval_steps_per_second": 1.435
+    "eval_accuracy": 0.9523809523809523,
+    "eval_loss": 0.25383907556533813,
+    "eval_runtime": 8.444,
+    "eval_samples_per_second": 9.948,
+    "eval_steps_per_second": 1.303
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "total_flos": 1.0042961854051123e+17,
-    "train_loss": 0.0985631244938548,
-    "train_runtime": 148.8516,
-    "train_samples_per_second": 8.707,
-    "train_steps_per_second": 1.102
+    "total_flos": 1.0352929812509491e+17,
+    "train_loss": 0.13229456402006604,
+    "train_runtime": 163.4534,
+    "train_samples_per_second": 8.174,
+    "train_steps_per_second": 1.028
 }

trainer_state.json

@@ -3,32 +3,32 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 164,
+  "global_step": 168,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 4.0,
-      "step": 164,
-      "total_flos": 1.0042961854051123e+17,
-      "train_loss": 0.0985631244938548,
-      "train_runtime": 148.8516,
-      "train_samples_per_second": 8.707,
-      "train_steps_per_second": 1.102
+      "step": 168,
+      "total_flos": 1.0352929812509491e+17,
+      "train_loss": 0.13229456402006604,
+      "train_runtime": 163.4534,
+      "train_samples_per_second": 8.174,
+      "train_steps_per_second": 1.028
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.975609756097561,
-      "eval_loss": 0.14302679896354675,
-      "eval_runtime": 7.6666,
-      "eval_samples_per_second": 10.696,
-      "eval_steps_per_second": 1.435,
-      "step": 164
+      "eval_accuracy": 0.9523809523809523,
+      "eval_loss": 0.25383907556533813,
+      "eval_runtime": 8.444,
+      "eval_samples_per_second": 9.948,
+      "eval_steps_per_second": 1.303,
+      "step": 168
     }
   ],
   "logging_steps": 500,
-  "max_steps": 164,
+  "max_steps": 168,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 500,
@@ -44,7 +44,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0042961854051123e+17,
+  "total_flos": 1.0352929812509491e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null