End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8431372549019608
+      value: 0.8823529411764706
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.5157
-- Accuracy: 0.8431
+- Loss: 0.5051
+- Accuracy: 0.8824
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 11.43,
+    "eval_accuracy": 0.8823529411764706,
+    "eval_loss": 0.5051466822624207,
+    "eval_runtime": 1.1156,
+    "eval_samples_per_second": 45.714,
+    "eval_steps_per_second": 1.793,
+    "train_loss": 0.5383468767007192,
+    "train_runtime": 372.5798,
+    "train_samples_per_second": 64.738,
+    "train_steps_per_second": 0.483
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.43,
+    "eval_accuracy": 0.8823529411764706,
+    "eval_loss": 0.5051466822624207,
+    "eval_runtime": 1.1156,
+    "eval_samples_per_second": 45.714,
+    "eval_steps_per_second": 1.793
+}

runs/Jun11_09-06-07_DESKTOP-SKBE9FB/events.out.tfevents.1718118811.DESKTOP-SKBE9FB.14372.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca1140bbfe02810aa18d6794f0b2499dd681313f7809974f327e770398fafe41
+size 411

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 11.43,
+    "train_loss": 0.5383468767007192,
+    "train_runtime": 372.5798,
+    "train_samples_per_second": 64.738,
+    "train_steps_per_second": 0.483
+}

trainer_state.json

@@ -0,0 +1,246 @@
+{
+  "best_metric": 0.8823529411764706,
+  "best_model_checkpoint": "vit-base-patch16-224-ve-U10-12\\checkpoint-173",
+  "epoch": 11.428571428571429,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.467836257309941e-05,
+      "loss": 1.3634,
+      "step": 10
+    },
+    {
+      "epoch": 0.95,
+      "eval_accuracy": 0.49019607843137253,
+      "eval_loss": 1.2283450365066528,
+      "eval_runtime": 0.7465,
+      "eval_samples_per_second": 68.323,
+      "eval_steps_per_second": 2.679,
+      "step": 15
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.1461988304093566e-05,
+      "loss": 1.242,
+      "step": 20
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 4.824561403508772e-05,
+      "loss": 1.0982,
+      "step": 30
+    },
+    {
+      "epoch": 1.97,
+      "eval_accuracy": 0.6862745098039216,
+      "eval_loss": 1.0088202953338623,
+      "eval_runtime": 0.783,
+      "eval_samples_per_second": 65.13,
+      "eval_steps_per_second": 2.554,
+      "step": 31
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 4.502923976608187e-05,
+      "loss": 0.924,
+      "step": 40
+    },
+    {
+      "epoch": 2.98,
+      "eval_accuracy": 0.6274509803921569,
+      "eval_loss": 0.9266212582588196,
+      "eval_runtime": 0.7846,
+      "eval_samples_per_second": 65.003,
+      "eval_steps_per_second": 2.549,
+      "step": 47
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 4.1812865497076025e-05,
+      "loss": 0.7823,
+      "step": 50
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 3.859649122807018e-05,
+      "loss": 0.6951,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6470588235294118,
+      "eval_loss": 0.8556224703788757,
+      "eval_runtime": 0.7589,
+      "eval_samples_per_second": 67.205,
+      "eval_steps_per_second": 2.636,
+      "step": 63
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 3.5380116959064324e-05,
+      "loss": 0.5827,
+      "step": 70
+    },
+    {
+      "epoch": 4.95,
+      "eval_accuracy": 0.7843137254901961,
+      "eval_loss": 0.6390604972839355,
+      "eval_runtime": 0.7479,
+      "eval_samples_per_second": 68.187,
+      "eval_steps_per_second": 2.674,
+      "step": 78
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 3.216374269005848e-05,
+      "loss": 0.5048,
+      "step": 80
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 2.894736842105263e-05,
+      "loss": 0.3992,
+      "step": 90
+    },
+    {
+      "epoch": 5.97,
+      "eval_accuracy": 0.8235294117647058,
+      "eval_loss": 0.5915952324867249,
+      "eval_runtime": 0.8303,
+      "eval_samples_per_second": 61.423,
+      "eval_steps_per_second": 2.409,
+      "step": 94
+    },
+    {
+      "epoch": 6.35,
+      "learning_rate": 2.5730994152046783e-05,
+      "loss": 0.3192,
+      "step": 100
+    },
+    {
+      "epoch": 6.98,
+      "learning_rate": 2.2514619883040936e-05,
+      "loss": 0.2781,
+      "step": 110
+    },
+    {
+      "epoch": 6.98,
+      "eval_accuracy": 0.8235294117647058,
+      "eval_loss": 0.6181738972663879,
+      "eval_runtime": 0.8149,
+      "eval_samples_per_second": 62.583,
+      "eval_steps_per_second": 2.454,
+      "step": 110
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 1.929824561403509e-05,
+      "loss": 0.2351,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7843137254901961,
+      "eval_loss": 0.6340680122375488,
+      "eval_runtime": 0.8111,
+      "eval_samples_per_second": 62.876,
+      "eval_steps_per_second": 2.466,
+      "step": 126
+    },
+    {
+      "epoch": 8.25,
+      "learning_rate": 1.608187134502924e-05,
+      "loss": 0.2462,
+      "step": 130
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 1.2865497076023392e-05,
+      "loss": 0.2377,
+      "step": 140
+    },
+    {
+      "epoch": 8.95,
+      "eval_accuracy": 0.8235294117647058,
+      "eval_loss": 0.5843695402145386,
+      "eval_runtime": 0.8269,
+      "eval_samples_per_second": 61.677,
+      "eval_steps_per_second": 2.419,
+      "step": 141
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 9.649122807017545e-06,
+      "loss": 0.2223,
+      "step": 150
+    },
+    {
+      "epoch": 9.97,
+      "eval_accuracy": 0.8235294117647058,
+      "eval_loss": 0.561729371547699,
+      "eval_runtime": 0.8196,
+      "eval_samples_per_second": 62.226,
+      "eval_steps_per_second": 2.44,
+      "step": 157
+    },
+    {
+      "epoch": 10.16,
+      "learning_rate": 6.432748538011696e-06,
+      "loss": 0.202,
+      "step": 160
+    },
+    {
+      "epoch": 10.79,
+      "learning_rate": 3.216374269005848e-06,
+      "loss": 0.1804,
+      "step": 170
+    },
+    {
+      "epoch": 10.98,
+      "eval_accuracy": 0.8823529411764706,
+      "eval_loss": 0.5051466822624207,
+      "eval_runtime": 0.7889,
+      "eval_samples_per_second": 64.647,
+      "eval_steps_per_second": 2.535,
+      "step": 173
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 0.0,
+      "loss": 0.1775,
+      "step": 180
+    },
+    {
+      "epoch": 11.43,
+      "eval_accuracy": 0.8431372549019608,
+      "eval_loss": 0.5156883001327515,
+      "eval_runtime": 0.7742,
+      "eval_samples_per_second": 65.872,
+      "eval_steps_per_second": 2.583,
+      "step": 180
+    },
+    {
+      "epoch": 11.43,
+      "step": 180,
+      "total_flos": 1.7803328819545866e+18,
+      "train_loss": 0.5383468767007192,
+      "train_runtime": 372.5798,
+      "train_samples_per_second": 64.738,
+      "train_steps_per_second": 0.483
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "total_flos": 1.7803328819545866e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}