End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.952443857331572
+      value: 0.9564068692206077
 ---
 
 <!-- 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-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1405
-- Accuracy: 0.9524
+- Loss: 0.1456
+- Accuracy: 0.9564
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.842105263157895,
+    "eval_accuracy": 0.9564068692206077,
+    "eval_loss": 0.145552858710289,
+    "eval_runtime": 13.7179,
+    "eval_samples_per_second": 55.183,
+    "eval_steps_per_second": 1.75,
+    "total_flos": 4.0192166172247327e+18,
+    "train_loss": 0.28673774859179624,
+    "train_runtime": 831.1321,
+    "train_samples_per_second": 18.216,
+    "train_steps_per_second": 0.138
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.842105263157895,
+    "eval_accuracy": 0.9564068692206077,
+    "eval_loss": 0.145552858710289,
+    "eval_runtime": 13.7179,
+    "eval_samples_per_second": 55.183,
+    "eval_steps_per_second": 1.75
+}

runs/Jun10_03-10-45_b21d3f8dfe73/events.out.tfevents.1717989973.b21d3f8dfe73.3221.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0646ec9064efd8d0dc9e0ee9d8ecf09d9377563c4c78360038e4a2a85b632913
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.842105263157895,
+    "total_flos": 4.0192166172247327e+18,
+    "train_loss": 0.28673774859179624,
+    "train_runtime": 831.1321,
+    "train_samples_per_second": 18.216,
+    "train_steps_per_second": 0.138
+}

trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_metric": 0.9564068692206077,
+  "best_model_checkpoint": "vit-large-patch16-224-finetuned-landscape-test/checkpoint-95",
+  "epoch": 4.842105263157895,
+  "eval_steps": 500,
+  "global_step": 115,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 2.8438663482666016,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.483,
+      "step": 10
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 1.8428654670715332,
+      "learning_rate": 4.611650485436894e-05,
+      "loss": 0.3395,
+      "step": 20
+    },
+    {
+      "epoch": 0.968421052631579,
+      "eval_accuracy": 0.9379128137384413,
+      "eval_loss": 0.18436767160892487,
+      "eval_runtime": 13.7525,
+      "eval_samples_per_second": 55.045,
+      "eval_steps_per_second": 1.745,
+      "step": 23
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 2.5257349014282227,
+      "learning_rate": 4.12621359223301e-05,
+      "loss": 0.2331,
+      "step": 30
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 2.2784433364868164,
+      "learning_rate": 3.6407766990291265e-05,
+      "loss": 0.2125,
+      "step": 40
+    },
+    {
+      "epoch": 1.9789473684210526,
+      "eval_accuracy": 0.9365918097754293,
+      "eval_loss": 0.16518810391426086,
+      "eval_runtime": 13.7671,
+      "eval_samples_per_second": 54.986,
+      "eval_steps_per_second": 1.743,
+      "step": 47
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.9819332957267761,
+      "learning_rate": 3.155339805825243e-05,
+      "loss": 0.2093,
+      "step": 50
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 2.5721793174743652,
+      "learning_rate": 2.6699029126213593e-05,
+      "loss": 0.1478,
+      "step": 60
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 1.9163882732391357,
+      "learning_rate": 2.1844660194174756e-05,
+      "loss": 0.1725,
+      "step": 70
+    },
+    {
+      "epoch": 2.9894736842105263,
+      "eval_accuracy": 0.9498018494055482,
+      "eval_loss": 0.1384432017803192,
+      "eval_runtime": 13.786,
+      "eval_samples_per_second": 54.911,
+      "eval_steps_per_second": 1.741,
+      "step": 71
+    },
+    {
+      "epoch": 3.3684210526315788,
+      "grad_norm": 1.7644811868667603,
+      "learning_rate": 1.6990291262135926e-05,
+      "loss": 0.1155,
+      "step": 80
+    },
+    {
+      "epoch": 3.7894736842105265,
+      "grad_norm": 1.712578296661377,
+      "learning_rate": 1.2135922330097088e-05,
+      "loss": 0.1371,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9564068692206077,
+      "eval_loss": 0.145552858710289,
+      "eval_runtime": 13.7797,
+      "eval_samples_per_second": 54.936,
+      "eval_steps_per_second": 1.742,
+      "step": 95
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 1.6249809265136719,
+      "learning_rate": 7.281553398058253e-06,
+      "loss": 0.1134,
+      "step": 100
+    },
+    {
+      "epoch": 4.631578947368421,
+      "grad_norm": 0.8358253240585327,
+      "learning_rate": 2.4271844660194174e-06,
+      "loss": 0.096,
+      "step": 110
+    },
+    {
+      "epoch": 4.842105263157895,
+      "eval_accuracy": 0.952443857331572,
+      "eval_loss": 0.14051873981952667,
+      "eval_runtime": 13.8352,
+      "eval_samples_per_second": 54.716,
+      "eval_steps_per_second": 1.735,
+      "step": 115
+    },
+    {
+      "epoch": 4.842105263157895,
+      "step": 115,
+      "total_flos": 4.0192166172247327e+18,
+      "train_loss": 0.28673774859179624,
+      "train_runtime": 831.1321,
+      "train_samples_per_second": 18.216,
+      "train_steps_per_second": 0.138
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 115,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.0192166172247327e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}