End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.98,
+    "eval_accuracy": 0.8483033932135728,
+    "eval_loss": 0.41903090476989746,
+    "eval_runtime": 21.2949,
+    "eval_samples_per_second": 47.054,
+    "eval_steps_per_second": 1.503,
+    "total_flos": 2.124298819894358e+18,
+    "train_loss": 0.6434233381634666,
+    "train_runtime": 1365.6224,
+    "train_samples_per_second": 19.8,
+    "train_steps_per_second": 0.154
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.98,
+    "eval_accuracy": 0.8483033932135728,
+    "eval_loss": 0.41903090476989746,
+    "eval_runtime": 21.2949,
+    "eval_samples_per_second": 47.054,
+    "eval_steps_per_second": 1.503
+}

runs/Feb06_12-42-11_c60fb0bb745f/events.out.tfevents.1707224735.c60fb0bb745f.707.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96988aa234fefba97bed845998b4766bed48d61493d4aaa83ab6c53b7aceed8c
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.98,
+    "total_flos": 2.124298819894358e+18,
+    "train_loss": 0.6434233381634666,
+    "train_runtime": 1365.6224,
+    "train_samples_per_second": 19.8,
+    "train_steps_per_second": 0.154
+}

trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_metric": 0.8483033932135728,
+  "best_model_checkpoint": "convnext-base-224-22k-1k-finetuned-eurosat/checkpoint-210",
+  "epoch": 2.978723404255319,
+  "eval_steps": 500,
+  "global_step": 210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 1.7284,
+      "step": 10
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.0973,
+      "step": 20
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 0.9371,
+      "step": 30
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.4973544973544974e-05,
+      "loss": 0.8303,
+      "step": 40
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.232804232804233e-05,
+      "loss": 0.7507,
+      "step": 50
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 0.6892,
+      "step": 60
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.6643,
+      "step": 70
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.7754491017964071,
+      "eval_loss": 0.6090148687362671,
+      "eval_runtime": 20.9163,
+      "eval_samples_per_second": 47.905,
+      "eval_steps_per_second": 1.53,
+      "step": 70
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.439153439153439e-05,
+      "loss": 0.5865,
+      "step": 80
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 0.5835,
+      "step": 90
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.91005291005291e-05,
+      "loss": 0.5331,
+      "step": 100
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.6455026455026456e-05,
+      "loss": 0.542,
+      "step": 110
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.5329,
+      "step": 120
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.1164021164021164e-05,
+      "loss": 0.494,
+      "step": 130
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.4729,
+      "step": 140
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8253493013972056,
+      "eval_loss": 0.4640671908855438,
+      "eval_runtime": 20.9281,
+      "eval_samples_per_second": 47.878,
+      "eval_steps_per_second": 1.529,
+      "step": 141
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 0.4971,
+      "step": 150
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.3227513227513228e-05,
+      "loss": 0.4896,
+      "step": 160
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.0582010582010582e-05,
+      "loss": 0.4267,
+      "step": 170
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 0.4334,
+      "step": 180
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.291005291005291e-06,
+      "loss": 0.4326,
+      "step": 190
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.6455026455026455e-06,
+      "loss": 0.4045,
+      "step": 200
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0,
+      "loss": 0.3858,
+      "step": 210
+    },
+    {
+      "epoch": 2.98,
+      "eval_accuracy": 0.8483033932135728,
+      "eval_loss": 0.41903090476989746,
+      "eval_runtime": 21.0738,
+      "eval_samples_per_second": 47.547,
+      "eval_steps_per_second": 1.518,
+      "step": 210
+    },
+    {
+      "epoch": 2.98,
+      "step": 210,
+      "total_flos": 2.124298819894358e+18,
+      "train_loss": 0.6434233381634666,
+      "train_runtime": 1365.6224,
+      "train_samples_per_second": 19.8,
+      "train_steps_per_second": 0.154
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 210,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.124298819894358e+18,
+  "trial_name": null,
+  "trial_params": null
+}