End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.7077777777777777,
+    "eval_loss": 1.4816027879714966,
+    "eval_runtime": 641.844,
+    "eval_samples_per_second": 4.207,
+    "eval_steps_per_second": 0.132,
+    "total_flos": 3.46193285935104e+16,
+    "train_loss": 1.888448052657278,
+    "train_runtime": 6506.6547,
+    "train_samples_per_second": 3.735,
+    "train_steps_per_second": 0.029
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.7077777777777777,
+    "eval_loss": 1.4816027879714966,
+    "eval_runtime": 641.844,
+    "eval_samples_per_second": 4.207,
+    "eval_steps_per_second": 0.132
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 3.46193285935104e+16,
+    "train_loss": 1.888448052657278,
+    "train_runtime": 6506.6547,
+    "train_samples_per_second": 3.735,
+    "train_steps_per_second": 0.029
+}

trainer_state.json

@@ -0,0 +1,184 @@
+{
+  "best_metric": 0.7077777777777777,
+  "best_model_checkpoint": "mobilevit-xx-small-finetuned-eurosat/checkpoint-190",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 190,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 2.769803524017334,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 2.3038,
+      "step": 10
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2.190194845199585,
+      "learning_rate": 4.970760233918128e-05,
+      "loss": 2.274,
+      "step": 20
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 1.4383624792099,
+      "learning_rate": 4.678362573099415e-05,
+      "loss": 2.2234,
+      "step": 30
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 1.485850214958191,
+      "learning_rate": 4.3859649122807014e-05,
+      "loss": 2.1683,
+      "step": 40
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 2.191305637359619,
+      "learning_rate": 4.093567251461988e-05,
+      "loss": 2.1061,
+      "step": 50
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 1.3051410913467407,
+      "learning_rate": 3.8011695906432746e-05,
+      "loss": 2.041,
+      "step": 60
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 2.3702988624572754,
+      "learning_rate": 3.508771929824561e-05,
+      "loss": 1.9716,
+      "step": 70
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 2.241407632827759,
+      "learning_rate": 3.216374269005848e-05,
+      "loss": 1.9342,
+      "step": 80
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 2.113342761993408,
+      "learning_rate": 2.9239766081871346e-05,
+      "loss": 1.8809,
+      "step": 90
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 2.722937822341919,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 1.8315,
+      "step": 100
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 1.8281042575836182,
+      "learning_rate": 2.3391812865497074e-05,
+      "loss": 1.7732,
+      "step": 110
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 2.3748879432678223,
+      "learning_rate": 2.046783625730994e-05,
+      "loss": 1.7556,
+      "step": 120
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 2.6032354831695557,
+      "learning_rate": 1.7543859649122806e-05,
+      "loss": 1.7192,
+      "step": 130
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 2.2420711517333984,
+      "learning_rate": 1.4619883040935673e-05,
+      "loss": 1.6801,
+      "step": 140
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 2.757969379425049,
+      "learning_rate": 1.1695906432748537e-05,
+      "loss": 1.6544,
+      "step": 150
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 2.2312943935394287,
+      "learning_rate": 8.771929824561403e-06,
+      "loss": 1.6522,
+      "step": 160
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 2.1280195713043213,
+      "learning_rate": 5.8479532163742686e-06,
+      "loss": 1.6554,
+      "step": 170
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 2.137747287750244,
+      "learning_rate": 2.9239766081871343e-06,
+      "loss": 1.6283,
+      "step": 180
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.781912326812744,
+      "learning_rate": 0.0,
+      "loss": 1.6273,
+      "step": 190
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7077777777777777,
+      "eval_loss": 1.4816027879714966,
+      "eval_runtime": 639.7143,
+      "eval_samples_per_second": 4.221,
+      "eval_steps_per_second": 0.133,
+      "step": 190
+    },
+    {
+      "epoch": 1.0,
+      "step": 190,
+      "total_flos": 3.46193285935104e+16,
+      "train_loss": 1.888448052657278,
+      "train_runtime": 6506.6547,
+      "train_samples_per_second": 3.735,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 190,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 3.46193285935104e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}