End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8
+      value: 0.8833333333333333
 ---
 
 <!-- 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: 0.4801
-- Accuracy: 0.8
+- Loss: 0.5606
+- Accuracy: 0.8833
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8833333333333333,
+    "eval_loss": 0.5605930089950562,
+    "eval_runtime": 1.1904,
+    "eval_samples_per_second": 50.402,
+    "eval_steps_per_second": 1.68,
+    "train_loss": 0.5282567453384399,
+    "train_runtime": 413.7424,
+    "train_samples_per_second": 61.391,
+    "train_steps_per_second": 0.483
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8833333333333333,
+    "eval_loss": 0.5605930089950562,
+    "eval_runtime": 1.1904,
+    "eval_samples_per_second": 50.402,
+    "eval_steps_per_second": 1.68
+}

runs/May23_07-42-50_DESKTOP-SKBE9FB/events.out.tfevents.1716472393.DESKTOP-SKBE9FB.9576.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f77219ea7c0562d9dfee331a23b301a66cde8c373656e83e7f5f2bef2f800d5
+size 411

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.5282567453384399,
+    "train_runtime": 413.7424,
+    "train_samples_per_second": 61.391,
+    "train_steps_per_second": 0.483
+}

trainer_state.json

@@ -0,0 +1,240 @@
+{
+  "best_metric": 0.8833333333333333,
+  "best_model_checkpoint": "vit-base-patch16-224-U8-10\\checkpoint-80",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.5e-05,
+      "loss": 1.3694,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 5.210526315789474e-05,
+      "loss": 1.2473,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5833333333333334,
+      "eval_loss": 1.180356740951538,
+      "eval_runtime": 1.2404,
+      "eval_samples_per_second": 48.373,
+      "eval_steps_per_second": 1.612,
+      "step": 20
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 4.921052631578948e-05,
+      "loss": 1.118,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.631578947368421e-05,
+      "loss": 0.9555,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.65,
+      "eval_loss": 0.937011182308197,
+      "eval_runtime": 0.9974,
+      "eval_samples_per_second": 60.155,
+      "eval_steps_per_second": 2.005,
+      "step": 40
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 4.342105263157895e-05,
+      "loss": 0.8425,
+      "step": 50
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.0526315789473684e-05,
+      "loss": 0.727,
+      "step": 60
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6833333333333333,
+      "eval_loss": 0.7202315926551819,
+      "eval_runtime": 0.9698,
+      "eval_samples_per_second": 61.867,
+      "eval_steps_per_second": 2.062,
+      "step": 60
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 3.7631578947368425e-05,
+      "loss": 0.6194,
+      "step": 70
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.473684210526316e-05,
+      "loss": 0.5288,
+      "step": 80
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8833333333333333,
+      "eval_loss": 0.5605930089950562,
+      "eval_runtime": 0.9974,
+      "eval_samples_per_second": 60.157,
+      "eval_steps_per_second": 2.005,
+      "step": 80
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 3.1842105263157895e-05,
+      "loss": 0.4548,
+      "step": 90
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.894736842105263e-05,
+      "loss": 0.3876,
+      "step": 100
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7666666666666667,
+      "eval_loss": 0.6481745839118958,
+      "eval_runtime": 1.0316,
+      "eval_samples_per_second": 58.161,
+      "eval_steps_per_second": 1.939,
+      "step": 100
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 2.605263157894737e-05,
+      "loss": 0.3178,
+      "step": 110
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.3157894736842103e-05,
+      "loss": 0.296,
+      "step": 120
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7166666666666667,
+      "eval_loss": 0.7458098530769348,
+      "eval_runtime": 1.0314,
+      "eval_samples_per_second": 58.173,
+      "eval_steps_per_second": 1.939,
+      "step": 120
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 2.0263157894736842e-05,
+      "loss": 0.2773,
+      "step": 130
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1.736842105263158e-05,
+      "loss": 0.236,
+      "step": 140
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8833333333333333,
+      "eval_loss": 0.4677261412143707,
+      "eval_runtime": 0.982,
+      "eval_samples_per_second": 61.101,
+      "eval_steps_per_second": 2.037,
+      "step": 140
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 1.4473684210526315e-05,
+      "loss": 0.2338,
+      "step": 150
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.1578947368421052e-05,
+      "loss": 0.2129,
+      "step": 160
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8333333333333334,
+      "eval_loss": 0.5137569308280945,
+      "eval_runtime": 1.0009,
+      "eval_samples_per_second": 59.944,
+      "eval_steps_per_second": 1.998,
+      "step": 160
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 8.68421052631579e-06,
+      "loss": 0.1907,
+      "step": 170
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 5.789473684210526e-06,
+      "loss": 0.1781,
+      "step": 180
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.85,
+      "eval_loss": 0.47364673018455505,
+      "eval_runtime": 1.0669,
+      "eval_samples_per_second": 56.238,
+      "eval_steps_per_second": 1.875,
+      "step": 180
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 2.894736842105263e-06,
+      "loss": 0.187,
+      "step": 190
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.1854,
+      "step": 200
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.4800596237182617,
+      "eval_runtime": 1.0276,
+      "eval_samples_per_second": 58.39,
+      "eval_steps_per_second": 1.946,
+      "step": 200
+    },
+    {
+      "epoch": 10.0,
+      "step": 200,
+      "total_flos": 1.9683318186491904e+18,
+      "train_loss": 0.5282567453384399,
+      "train_runtime": 413.7424,
+      "train_samples_per_second": 61.391,
+      "train_steps_per_second": 0.483
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.9683318186491904e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}