End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.6305970149253731,
+    "eval_loss": 1.193472981452942,
+    "eval_runtime": 2.1429,
+    "eval_samples_per_second": 125.061,
+    "eval_steps_per_second": 4.2,
+    "total_flos": 2.988691675103232e+17,
+    "train_loss": 1.6160710937098453,
+    "train_runtime": 164.7223,
+    "train_samples_per_second": 72.971,
+    "train_steps_per_second": 0.577
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.6305970149253731,
+    "eval_loss": 1.193472981452942,
+    "eval_runtime": 2.1429,
+    "eval_samples_per_second": 125.061,
+    "eval_steps_per_second": 4.2
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.988691675103232e+17,
+    "train_loss": 1.6160710937098453,
+    "train_runtime": 164.7223,
+    "train_samples_per_second": 72.971,
+    "train_steps_per_second": 0.577
+}

trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": 0.6305970149253731,
+  "best_model_checkpoint": "/kaggle/working/swin-brain-tumor-type-classification/checkpoint-95",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 95,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 5.917788505554199,
+      "learning_rate": 5e-05,
+      "loss": 2.4881,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.34328358208955223,
+      "eval_loss": 2.0770931243896484,
+      "eval_runtime": 2.1455,
+      "eval_samples_per_second": 124.914,
+      "eval_steps_per_second": 4.195,
+      "step": 19
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 5.9123711585998535,
+      "learning_rate": 4.411764705882353e-05,
+      "loss": 2.1238,
+      "step": 20
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 9.100049018859863,
+      "learning_rate": 3.8235294117647055e-05,
+      "loss": 1.8506,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4626865671641791,
+      "eval_loss": 1.6409298181533813,
+      "eval_runtime": 2.1208,
+      "eval_samples_per_second": 126.369,
+      "eval_steps_per_second": 4.244,
+      "step": 38
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 9.174087524414062,
+      "learning_rate": 3.235294117647059e-05,
+      "loss": 1.6272,
+      "step": 40
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 8.365827560424805,
+      "learning_rate": 2.647058823529412e-05,
+      "loss": 1.5334,
+      "step": 50
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5708955223880597,
+      "eval_loss": 1.3730274438858032,
+      "eval_runtime": 2.1252,
+      "eval_samples_per_second": 126.105,
+      "eval_steps_per_second": 4.235,
+      "step": 57
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 8.513856887817383,
+      "learning_rate": 2.058823529411765e-05,
+      "loss": 1.3517,
+      "step": 60
+    },
+    {
+      "epoch": 3.6842105263157894,
+      "grad_norm": 9.485589981079102,
+      "learning_rate": 1.4705882352941177e-05,
+      "loss": 1.3096,
+      "step": 70
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6044776119402985,
+      "eval_loss": 1.228102445602417,
+      "eval_runtime": 2.1269,
+      "eval_samples_per_second": 126.007,
+      "eval_steps_per_second": 4.232,
+      "step": 76
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 7.229813098907471,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 1.245,
+      "step": 80
+    },
+    {
+      "epoch": 4.7368421052631575,
+      "grad_norm": 8.578031539916992,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 1.2162,
+      "step": 90
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6305970149253731,
+      "eval_loss": 1.193472981452942,
+      "eval_runtime": 2.2387,
+      "eval_samples_per_second": 119.71,
+      "eval_steps_per_second": 4.02,
+      "step": 95
+    },
+    {
+      "epoch": 5.0,
+      "step": 95,
+      "total_flos": 2.988691675103232e+17,
+      "train_loss": 1.6160710937098453,
+      "train_runtime": 164.7223,
+      "train_samples_per_second": 72.971,
+      "train_steps_per_second": 0.577
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 95,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "CustomEarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.988691675103232e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}