End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.717391304347826
+      value: 0.7391304347826086
 ---
 
 <!-- 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: 0.8058
-- Accuracy: 0.7174
+- Loss: 0.7887
+- Accuracy: 0.7391
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 11.23,
+    "eval_accuracy": 0.7391304347826086,
+    "eval_loss": 0.7887189388275146,
+    "eval_runtime": 0.8635,
+    "eval_samples_per_second": 53.271,
+    "eval_steps_per_second": 2.316,
+    "train_loss": 0.696734961235162,
+    "train_runtime": 274.4703,
+    "train_samples_per_second": 65.187,
+    "train_steps_per_second": 0.481
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.23,
+    "eval_accuracy": 0.7391304347826086,
+    "eval_loss": 0.7887189388275146,
+    "eval_runtime": 0.8635,
+    "eval_samples_per_second": 53.271,
+    "eval_steps_per_second": 2.316
+}

runs/Jun11_07-47-11_DESKTOP-SKBE9FB/events.out.tfevents.1718114164.DESKTOP-SKBE9FB.15312.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a66b1d2a4d8236d23898a9910a4c46f89f8949b7e1d46c45695c966e8c76cd
+size 411

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 11.23,
+    "train_loss": 0.696734961235162,
+    "train_runtime": 274.4703,
+    "train_samples_per_second": 65.187,
+    "train_steps_per_second": 0.481
+}

trainer_state.json

@@ -0,0 +1,216 @@
+{
+  "best_metric": 0.7391304347826086,
+  "best_model_checkpoint": "vit-base-patch16-224-RX2-12\\checkpoint-117",
+  "epoch": 11.23404255319149,
+  "eval_steps": 500,
+  "global_step": 132,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.368e-05,
+      "loss": 1.3604,
+      "step": 10
+    },
+    {
+      "epoch": 0.94,
+      "eval_accuracy": 0.4782608695652174,
+      "eval_loss": 1.2834274768829346,
+      "eval_runtime": 0.8665,
+      "eval_samples_per_second": 53.085,
+      "eval_steps_per_second": 2.308,
+      "step": 11
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.928e-05,
+      "loss": 1.2312,
+      "step": 20
+    },
+    {
+      "epoch": 1.96,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 1.1355512142181396,
+      "eval_runtime": 0.7027,
+      "eval_samples_per_second": 65.465,
+      "eval_steps_per_second": 2.846,
+      "step": 23
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 4.488e-05,
+      "loss": 1.0933,
+      "step": 30
+    },
+    {
+      "epoch": 2.98,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 1.0385559797286987,
+      "eval_runtime": 0.722,
+      "eval_samples_per_second": 63.714,
+      "eval_steps_per_second": 2.77,
+      "step": 35
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 4.048e-05,
+      "loss": 0.936,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.9049469232559204,
+      "eval_runtime": 0.7063,
+      "eval_samples_per_second": 65.13,
+      "eval_steps_per_second": 2.832,
+      "step": 47
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 3.608e-05,
+      "loss": 0.8011,
+      "step": 50
+    },
+    {
+      "epoch": 4.94,
+      "eval_accuracy": 0.6086956521739131,
+      "eval_loss": 0.9847387075424194,
+      "eval_runtime": 0.7006,
+      "eval_samples_per_second": 65.657,
+      "eval_steps_per_second": 2.855,
+      "step": 58
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 3.168e-05,
+      "loss": 0.7012,
+      "step": 60
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 2.728e-05,
+      "loss": 0.616,
+      "step": 70
+    },
+    {
+      "epoch": 5.96,
+      "eval_accuracy": 0.6304347826086957,
+      "eval_loss": 0.9236001372337341,
+      "eval_runtime": 0.7209,
+      "eval_samples_per_second": 63.807,
+      "eval_steps_per_second": 2.774,
+      "step": 70
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 2.288e-05,
+      "loss": 0.5251,
+      "step": 80
+    },
+    {
+      "epoch": 6.98,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 0.8640467524528503,
+      "eval_runtime": 0.7379,
+      "eval_samples_per_second": 62.336,
+      "eval_steps_per_second": 2.71,
+      "step": 82
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 1.8480000000000003e-05,
+      "loss": 0.4618,
+      "step": 90
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.861157238483429,
+      "eval_runtime": 0.6967,
+      "eval_samples_per_second": 66.021,
+      "eval_steps_per_second": 2.87,
+      "step": 94
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 1.408e-05,
+      "loss": 0.3974,
+      "step": 100
+    },
+    {
+      "epoch": 8.94,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 0.8460871577262878,
+      "eval_runtime": 0.6825,
+      "eval_samples_per_second": 67.402,
+      "eval_steps_per_second": 2.931,
+      "step": 105
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 9.68e-06,
+      "loss": 0.3532,
+      "step": 110
+    },
+    {
+      "epoch": 9.96,
+      "eval_accuracy": 0.7391304347826086,
+      "eval_loss": 0.7887189388275146,
+      "eval_runtime": 0.7285,
+      "eval_samples_per_second": 63.142,
+      "eval_steps_per_second": 2.745,
+      "step": 117
+    },
+    {
+      "epoch": 10.21,
+      "learning_rate": 5.28e-06,
+      "loss": 0.335,
+      "step": 120
+    },
+    {
+      "epoch": 10.98,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.7994726300239563,
+      "eval_runtime": 0.7107,
+      "eval_samples_per_second": 64.724,
+      "eval_steps_per_second": 2.814,
+      "step": 129
+    },
+    {
+      "epoch": 11.06,
+      "learning_rate": 8.8e-07,
+      "loss": 0.3211,
+      "step": 130
+    },
+    {
+      "epoch": 11.23,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.8058299422264099,
+      "eval_runtime": 0.6829,
+      "eval_samples_per_second": 67.36,
+      "eval_steps_per_second": 2.929,
+      "step": 132
+    },
+    {
+      "epoch": 11.23,
+      "step": 132,
+      "total_flos": 1.298246573142909e+18,
+      "train_loss": 0.696734961235162,
+      "train_runtime": 274.4703,
+      "train_samples_per_second": 65.187,
+      "train_steps_per_second": 0.481
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 132,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "total_flos": 1.298246573142909e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}