End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9753086419753086,
+    "eval_loss": 0.07627594470977783,
+    "eval_runtime": 8.3856,
+    "eval_samples_per_second": 193.188,
+    "eval_steps_per_second": 3.101,
+    "total_flos": 1.0874439903456461e+18,
+    "train_loss": 0.42285745386143175,
+    "train_runtime": 401.9248,
+    "train_samples_per_second": 108.826,
+    "train_steps_per_second": 0.425
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9753086419753086,
+    "eval_loss": 0.07627594470977783,
+    "eval_runtime": 8.3856,
+    "eval_samples_per_second": 193.188,
+    "eval_steps_per_second": 3.101
+}

runs/Feb25_14-02-02_3a6453f2f3ac/events.out.tfevents.1740510650.3a6453f2f3ac.6905.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:470cbf7978f489efdf47a33648ebc89849d35a9c0484dbb79f3f44c817da5410
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.0874439903456461e+18,
+    "train_loss": 0.42285745386143175,
+    "train_runtime": 401.9248,
+    "train_samples_per_second": 108.826,
+    "train_steps_per_second": 0.425
+}

trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_metric": 0.9753086419753086,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-171",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 171,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 5.284176826477051,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 2.2361,
+      "step": 10
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 7.525365352630615,
+      "learning_rate": 4.9346405228758174e-05,
+      "loss": 1.5044,
+      "step": 20
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 8.623214721679688,
+      "learning_rate": 4.607843137254902e-05,
+      "loss": 0.5934,
+      "step": 30
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 18.792816162109375,
+      "learning_rate": 4.281045751633987e-05,
+      "loss": 0.3883,
+      "step": 40
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 12.664556503295898,
+      "learning_rate": 3.954248366013072e-05,
+      "loss": 0.2842,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9561728395061728,
+      "eval_loss": 0.1351327747106552,
+      "eval_runtime": 8.1127,
+      "eval_samples_per_second": 199.686,
+      "eval_steps_per_second": 3.205,
+      "step": 57
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 8.433908462524414,
+      "learning_rate": 3.627450980392157e-05,
+      "loss": 0.2388,
+      "step": 60
+    },
+    {
+      "epoch": 1.2280701754385965,
+      "grad_norm": 5.828427314758301,
+      "learning_rate": 3.300653594771242e-05,
+      "loss": 0.2341,
+      "step": 70
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 11.479358673095703,
+      "learning_rate": 2.9738562091503268e-05,
+      "loss": 0.2112,
+      "step": 80
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 8.366100311279297,
+      "learning_rate": 2.647058823529412e-05,
+      "loss": 0.1987,
+      "step": 90
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "grad_norm": 9.875587463378906,
+      "learning_rate": 2.320261437908497e-05,
+      "loss": 0.1931,
+      "step": 100
+    },
+    {
+      "epoch": 1.9298245614035088,
+      "grad_norm": 5.03447151184082,
+      "learning_rate": 1.993464052287582e-05,
+      "loss": 0.1742,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9734567901234568,
+      "eval_loss": 0.08444475382566452,
+      "eval_runtime": 8.0725,
+      "eval_samples_per_second": 200.682,
+      "eval_steps_per_second": 3.221,
+      "step": 114
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 10.818126678466797,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.1883,
+      "step": 120
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 11.784213066101074,
+      "learning_rate": 1.3398692810457516e-05,
+      "loss": 0.1442,
+      "step": 130
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 6.820158004760742,
+      "learning_rate": 1.0130718954248367e-05,
+      "loss": 0.1515,
+      "step": 140
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 5.029265880584717,
+      "learning_rate": 6.862745098039216e-06,
+      "loss": 0.1664,
+      "step": 150
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 9.942961692810059,
+      "learning_rate": 3.5947712418300652e-06,
+      "loss": 0.168,
+      "step": 160
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 6.980404853820801,
+      "learning_rate": 3.2679738562091505e-07,
+      "loss": 0.1412,
+      "step": 170
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9753086419753086,
+      "eval_loss": 0.07627594470977783,
+      "eval_runtime": 8.4641,
+      "eval_samples_per_second": 191.396,
+      "eval_steps_per_second": 3.072,
+      "step": 171
+    },
+    {
+      "epoch": 3.0,
+      "step": 171,
+      "total_flos": 1.0874439903456461e+18,
+      "train_loss": 0.42285745386143175,
+      "train_runtime": 401.9248,
+      "train_samples_per_second": 108.826,
+      "train_steps_per_second": 0.425
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 171,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.0874439903456461e+18,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}