first commit

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.6,
+    "eval_accuracy": 0.6896551724137931,
+    "eval_loss": 0.6992095708847046,
+    "eval_runtime": 2.7286,
+    "eval_samples_per_second": 31.884,
+    "eval_steps_per_second": 1.099,
+    "total_flos": 1.3344240210765005e+17,
+    "train_loss": 0.8767854997089931,
+    "train_runtime": 140.3985,
+    "train_samples_per_second": 15.257,
+    "train_steps_per_second": 0.1
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "building_exterior",
+    "1": "outdoor_area",
+    "2": "street_view"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "building_exterior": 0,
+    "outdoor_area": 1,
+    "street_view": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.6,
+    "eval_accuracy": 0.6896551724137931,
+    "eval_loss": 0.6992095708847046,
+    "eval_runtime": 2.7286,
+    "eval_samples_per_second": 31.884,
+    "eval_steps_per_second": 1.099
+}

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.6,
+    "total_flos": 1.3344240210765005e+17,
+    "train_loss": 0.8767854997089931,
+    "train_runtime": 140.3985,
+    "train_samples_per_second": 15.257,
+    "train_steps_per_second": 0.1
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": 0.6896551724137931,
+  "best_model_checkpoint": "UL_exterior_classification/checkpoint-10",
+  "epoch": 5.6,
+  "eval_steps": 500,
+  "global_step": 14,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.21839080459770116,
+      "eval_loss": 1.27083158493042,
+      "eval_runtime": 2.8018,
+      "eval_samples_per_second": 31.051,
+      "eval_steps_per_second": 1.071,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5977011494252874,
+      "eval_loss": 0.8931179046630859,
+      "eval_runtime": 3.492,
+      "eval_samples_per_second": 24.914,
+      "eval_steps_per_second": 0.859,
+      "step": 5
+    },
+    {
+      "epoch": 2.8,
+      "eval_accuracy": 0.6436781609195402,
+      "eval_loss": 0.7972615361213684,
+      "eval_runtime": 3.8271,
+      "eval_samples_per_second": 22.732,
+      "eval_steps_per_second": 0.784,
+      "step": 7
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.223552703857422,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.9888,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6896551724137931,
+      "eval_loss": 0.6992095708847046,
+      "eval_runtime": 2.7722,
+      "eval_samples_per_second": 31.383,
+      "eval_steps_per_second": 1.082,
+      "step": 10
+    },
+    {
+      "epoch": 4.8,
+      "eval_accuracy": 0.6896551724137931,
+      "eval_loss": 0.668693482875824,
+      "eval_runtime": 2.7395,
+      "eval_samples_per_second": 31.757,
+      "eval_steps_per_second": 1.095,
+      "step": 12
+    },
+    {
+      "epoch": 5.6,
+      "eval_accuracy": 0.6896551724137931,
+      "eval_loss": 0.6565638184547424,
+      "eval_runtime": 2.8164,
+      "eval_samples_per_second": 30.891,
+      "eval_steps_per_second": 1.065,
+      "step": 14
+    },
+    {
+      "epoch": 5.6,
+      "step": 14,
+      "total_flos": 1.3344240210765005e+17,
+      "train_loss": 0.8767854997089931,
+      "train_runtime": 140.3985,
+      "train_samples_per_second": 15.257,
+      "train_steps_per_second": 0.1
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 14,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 1.3344240210765005e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}