End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.98,
+    "eval_accuracy": 0.9537037037037037,
+    "eval_loss": 0.3152540624141693,
+    "eval_runtime": 4.9589,
+    "eval_samples_per_second": 152.454,
+    "eval_steps_per_second": 4.84,
+    "total_flos": 5.404642194185257e+17,
+    "train_loss": 0.9118886449120261,
+    "train_runtime": 406.5747,
+    "train_samples_per_second": 53.127,
+    "train_steps_per_second": 0.406
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.98,
+    "eval_accuracy": 0.9537037037037037,
+    "eval_loss": 0.3152540624141693,
+    "eval_runtime": 4.9589,
+    "eval_samples_per_second": 152.454,
+    "eval_steps_per_second": 4.84
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.98,
+    "total_flos": 5.404642194185257e+17,
+    "train_loss": 0.9118886449120261,
+    "train_runtime": 406.5747,
+    "train_samples_per_second": 53.127,
+    "train_steps_per_second": 0.406
+}

trainer_state.json

@@ -0,0 +1,166 @@
+{
+  "best_metric": 0.9537037037037037,
+  "best_model_checkpoint": "convnext-tiny-224-eurosat/checkpoint-132",
+  "epoch": 4.977777777777778,
+  "global_step": 165,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.9411764705882354e-05,
+      "loss": 2.2777,
+      "step": 10
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.8986486486486486e-05,
+      "loss": 2.1175,
+      "step": 20
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.560810810810811e-05,
+      "loss": 1.863,
+      "step": 30
+    },
+    {
+      "epoch": 0.98,
+      "eval_accuracy": 0.7619047619047619,
+      "eval_loss": 1.5775072574615479,
+      "eval_runtime": 4.8664,
+      "eval_samples_per_second": 155.351,
+      "eval_steps_per_second": 4.932,
+      "step": 33
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 4.222972972972973e-05,
+      "loss": 1.6756,
+      "step": 40
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.885135135135135e-05,
+      "loss": 1.2692,
+      "step": 50
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.547297297297297e-05,
+      "loss": 1.039,
+      "step": 60
+    },
+    {
+      "epoch": 1.98,
+      "eval_accuracy": 0.9007936507936508,
+      "eval_loss": 0.8142262101173401,
+      "eval_runtime": 5.0273,
+      "eval_samples_per_second": 150.378,
+      "eval_steps_per_second": 4.774,
+      "step": 66
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 3.20945945945946e-05,
+      "loss": 0.9573,
+      "step": 70
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.8716216216216217e-05,
+      "loss": 0.6887,
+      "step": 80
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.533783783783784e-05,
+      "loss": 0.5825,
+      "step": 90
+    },
+    {
+      "epoch": 2.98,
+      "eval_accuracy": 0.9338624338624338,
+      "eval_loss": 0.44418689608573914,
+      "eval_runtime": 4.8374,
+      "eval_samples_per_second": 156.283,
+      "eval_steps_per_second": 4.961,
+      "step": 99
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 2.195945945945946e-05,
+      "loss": 0.4985,
+      "step": 100
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 1.8581081081081082e-05,
+      "loss": 0.3986,
+      "step": 110
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.5202702702702704e-05,
+      "loss": 0.362,
+      "step": 120
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 1.1824324324324325e-05,
+      "loss": 0.3228,
+      "step": 130
+    },
+    {
+      "epoch": 3.98,
+      "eval_accuracy": 0.9537037037037037,
+      "eval_loss": 0.3152540624141693,
+      "eval_runtime": 5.0332,
+      "eval_samples_per_second": 150.203,
+      "eval_steps_per_second": 4.768,
+      "step": 132
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 8.445945945945946e-06,
+      "loss": 0.3257,
+      "step": 140
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 5.067567567567568e-06,
+      "loss": 0.2759,
+      "step": 150
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 1.6891891891891894e-06,
+      "loss": 0.2641,
+      "step": 160
+    },
+    {
+      "epoch": 4.98,
+      "eval_accuracy": 0.9523809523809523,
+      "eval_loss": 0.2867930233478546,
+      "eval_runtime": 4.8919,
+      "eval_samples_per_second": 154.542,
+      "eval_steps_per_second": 4.906,
+      "step": 165
+    },
+    {
+      "epoch": 4.98,
+      "step": 165,
+      "total_flos": 5.404642194185257e+17,
+      "train_loss": 0.9118886449120261,
+      "train_runtime": 406.5747,
+      "train_samples_per_second": 53.127,
+      "train_steps_per_second": 0.406
+    }
+  ],
+  "max_steps": 165,
+  "num_train_epochs": 5,
+  "total_flos": 5.404642194185257e+17,
+  "trial_name": null,
+  "trial_params": null
+}