tejp/custom_dataset_augmented

README.md

@@ -2,12 +2,32 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224
 tags:
+- image-classification
 - generated_from_trainer
 datasets:
 - imagefolder
+metrics:
+- accuracy
+- f1
 model-index:
 - name: fine-tuned-augmented
-  results: []
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: custom_dataset_augmented
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.4672131147540984
+    - name: F1
+      type: f1
+      value: 0.08120213120213123
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +35,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fine-tuned-augmented
 
-This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the custom_dataset_augmented dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5780
+- Accuracy: 0.4672
+- F1: 0.0812
 
 ## Model description
 

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.7692307692307693,
-    "eval_f1": 0.6336996336996338,
-    "eval_loss": 1.3636784553527832,
-    "eval_runtime": 42.9996,
-    "eval_samples_per_second": 0.302,
-    "eval_steps_per_second": 0.047,
-    "total_flos": 3022323029526528.0,
-    "train_loss": 1.8923139572143555,
-    "train_runtime": 145.5181,
-    "train_samples_per_second": 0.268,
-    "train_steps_per_second": 0.021
+    "eval_accuracy": 0.4672131147540984,
+    "eval_f1": 0.08120213120213123,
+    "eval_loss": 1.5779949426651,
+    "eval_runtime": 465.1675,
+    "eval_samples_per_second": 0.262,
+    "eval_steps_per_second": 0.034,
+    "total_flos": 2.8365118601895936e+16,
+    "train_loss": 1.9596904118855794,
+    "train_runtime": 1931.2052,
+    "train_samples_per_second": 0.19,
+    "train_steps_per_second": 0.006
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.7692307692307693,
-    "eval_f1": 0.6336996336996338,
-    "eval_loss": 1.3636784553527832,
-    "eval_runtime": 42.9996,
-    "eval_samples_per_second": 0.302,
-    "eval_steps_per_second": 0.047
+    "eval_accuracy": 0.4672131147540984,
+    "eval_f1": 0.08120213120213123,
+    "eval_loss": 1.5779949426651,
+    "eval_runtime": 465.1675,
+    "eval_samples_per_second": 0.262,
+    "eval_steps_per_second": 0.034
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "total_flos": 3022323029526528.0,
-    "train_loss": 1.8923139572143555,
-    "train_runtime": 145.5181,
-    "train_samples_per_second": 0.268,
-    "train_steps_per_second": 0.021
+    "total_flos": 2.8365118601895936e+16,
+    "train_loss": 1.9596904118855794,
+    "train_runtime": 1931.2052,
+    "train_samples_per_second": 0.19,
+    "train_steps_per_second": 0.006
 }

trainer_state.json

@@ -3,26 +3,26 @@
   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 1000,
-  "global_step": 3,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 3.0,
-      "step": 3,
-      "total_flos": 3022323029526528.0,
-      "train_loss": 1.8923139572143555,
-      "train_runtime": 145.5181,
-      "train_samples_per_second": 0.268,
-      "train_steps_per_second": 0.021
+      "step": 12,
+      "total_flos": 2.8365118601895936e+16,
+      "train_loss": 1.9596904118855794,
+      "train_runtime": 1931.2052,
+      "train_samples_per_second": 0.19,
+      "train_steps_per_second": 0.006
     }
   ],
   "logging_steps": 1000,
-  "max_steps": 3,
+  "max_steps": 12,
   "num_train_epochs": 3,
   "save_steps": 1000,
-  "total_flos": 3022323029526528.0,
+  "total_flos": 2.8365118601895936e+16,
   "trial_name": null,
   "trial_params": null
 }