End of training

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: UL_interior_classification
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5875912408759124
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# UL_interior_classification
+
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2517
+- Accuracy: 0.5876
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 7
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 2.7547        | 0.9811 | 13   | 2.3422          | 0.3285   |
+| 1.7119        | 1.9623 | 26   | 1.8850          | 0.4964   |
+| 1.249         | 2.9434 | 39   | 1.5653          | 0.5292   |
+| 0.8838        | 4.0    | 53   | 1.3675          | 0.5693   |
+| 0.8896        | 4.9811 | 66   | 1.2907          | 0.5803   |
+| 0.7262        | 5.9623 | 79   | 1.2625          | 0.5803   |
+| 0.6817        | 6.8679 | 91   | 1.2517          | 0.5876   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 6.867924528301887,
+    "eval_accuracy": 0.5875912408759124,
+    "eval_loss": 1.251747727394104,
+    "eval_runtime": 9.2712,
+    "eval_samples_per_second": 29.554,
+    "eval_steps_per_second": 0.971,
+    "total_flos": 8.883485181176095e+17,
+    "train_loss": 1.1828759214380284,
+    "train_runtime": 1039.6912,
+    "train_samples_per_second": 11.21,
+    "train_steps_per_second": 0.088
+}

config.json

@@ -0,0 +1,66 @@
+{
+  "_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": "bicycle_storage",
+    "1": "building_interiors",
+    "2": "cinema_room",
+    "3": "communal_lounge",
+    "4": "dining_area",
+    "5": "entertainment_area",
+    "6": "fitness_room",
+    "7": "games_area",
+    "8": "gym",
+    "9": "laundry_area",
+    "10": "living_area",
+    "11": "living_area_shared_kitchen",
+    "12": "meeting_room",
+    "13": "parking",
+    "14": "reception",
+    "15": "rooftoop_area",
+    "16": "storage_lockers",
+    "17": "study_area",
+    "18": "swimming_pool"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bicycle_storage": 0,
+    "building_interiors": 1,
+    "cinema_room": 2,
+    "communal_lounge": 3,
+    "dining_area": 4,
+    "entertainment_area": 5,
+    "fitness_room": 6,
+    "games_area": 7,
+    "gym": 8,
+    "laundry_area": 9,
+    "living_area": 10,
+    "living_area_shared_kitchen": 11,
+    "meeting_room": 12,
+    "parking": 13,
+    "reception": 14,
+    "rooftoop_area": 15,
+    "storage_lockers": 16,
+    "study_area": 17,
+    "swimming_pool": 18
+  },
+  "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": 6.867924528301887,
+    "eval_accuracy": 0.5875912408759124,
+    "eval_loss": 1.251747727394104,
+    "eval_runtime": 9.2712,
+    "eval_samples_per_second": 29.554,
+    "eval_steps_per_second": 0.971
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6e204db9bd4ee26a44b11d1eb41a56c623af69fc5f24ad264339bde53bdf57
+size 343276268

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
+  }
+}

runs/Jun19_09-03-53_da3e1e4916a6/events.out.tfevents.1718787852.da3e1e4916a6.1298.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7738d4e3dde246d79ee7327081081094cedb7e0d10196f53ef18b412d235d353
+size 10158

runs/Jun19_09-03-53_da3e1e4916a6/events.out.tfevents.1718788926.da3e1e4916a6.1298.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea746f214435987ba37674ead2bf644e4bc2760c963ff82f977fd5cdde46b3e
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.867924528301887,
+    "total_flos": 8.883485181176095e+17,
+    "train_loss": 1.1828759214380284,
+    "train_runtime": 1039.6912,
+    "train_samples_per_second": 11.21,
+    "train_steps_per_second": 0.088
+}

trainer_state.json

@@ -0,0 +1,168 @@
+{
+  "best_metric": 0.5875912408759124,
+  "best_model_checkpoint": "UL_interior_classification/checkpoint-91",
+  "epoch": 6.867924528301887,
+  "eval_steps": 500,
+  "global_step": 91,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 4.003274440765381,
+      "learning_rate": 5e-05,
+      "loss": 2.7547,
+      "step": 10
+    },
+    {
+      "epoch": 0.9811320754716981,
+      "eval_accuracy": 0.3284671532846715,
+      "eval_loss": 2.342195510864258,
+      "eval_runtime": 10.3898,
+      "eval_samples_per_second": 26.372,
+      "eval_steps_per_second": 0.866,
+      "step": 13
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 2.726027011871338,
+      "learning_rate": 4.3827160493827164e-05,
+      "loss": 1.7119,
+      "step": 20
+    },
+    {
+      "epoch": 1.9622641509433962,
+      "eval_accuracy": 0.49635036496350365,
+      "eval_loss": 1.8849732875823975,
+      "eval_runtime": 9.8675,
+      "eval_samples_per_second": 27.768,
+      "eval_steps_per_second": 0.912,
+      "step": 26
+    },
+    {
+      "epoch": 2.2641509433962264,
+      "grad_norm": 2.424898624420166,
+      "learning_rate": 3.7654320987654326e-05,
+      "loss": 1.249,
+      "step": 30
+    },
+    {
+      "epoch": 2.9433962264150946,
+      "eval_accuracy": 0.5291970802919708,
+      "eval_loss": 1.5653367042541504,
+      "eval_runtime": 10.0672,
+      "eval_samples_per_second": 27.217,
+      "eval_steps_per_second": 0.894,
+      "step": 39
+    },
+    {
+      "epoch": 3.018867924528302,
+      "grad_norm": 6.8397016525268555,
+      "learning_rate": 3.148148148148148e-05,
+      "loss": 1.0982,
+      "step": 40
+    },
+    {
+      "epoch": 3.7735849056603774,
+      "grad_norm": 2.1824584007263184,
+      "learning_rate": 2.5308641975308646e-05,
+      "loss": 0.8838,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5693430656934306,
+      "eval_loss": 1.36745285987854,
+      "eval_runtime": 10.0511,
+      "eval_samples_per_second": 27.261,
+      "eval_steps_per_second": 0.895,
+      "step": 53
+    },
+    {
+      "epoch": 4.528301886792453,
+      "grad_norm": 1.9526816606521606,
+      "learning_rate": 1.91358024691358e-05,
+      "loss": 0.8896,
+      "step": 60
+    },
+    {
+      "epoch": 4.981132075471698,
+      "eval_accuracy": 0.5802919708029197,
+      "eval_loss": 1.2906520366668701,
+      "eval_runtime": 11.107,
+      "eval_samples_per_second": 24.669,
+      "eval_steps_per_second": 0.81,
+      "step": 66
+    },
+    {
+      "epoch": 5.283018867924528,
+      "grad_norm": 2.0880227088928223,
+      "learning_rate": 1.2962962962962962e-05,
+      "loss": 0.7262,
+      "step": 70
+    },
+    {
+      "epoch": 5.962264150943396,
+      "eval_accuracy": 0.5802919708029197,
+      "eval_loss": 1.2625008821487427,
+      "eval_runtime": 10.0312,
+      "eval_samples_per_second": 27.315,
+      "eval_steps_per_second": 0.897,
+      "step": 79
+    },
+    {
+      "epoch": 6.037735849056604,
+      "grad_norm": 1.8009761571884155,
+      "learning_rate": 6.790123456790123e-06,
+      "loss": 0.7061,
+      "step": 80
+    },
+    {
+      "epoch": 6.7924528301886795,
+      "grad_norm": 1.9284666776657104,
+      "learning_rate": 6.17283950617284e-07,
+      "loss": 0.6817,
+      "step": 90
+    },
+    {
+      "epoch": 6.867924528301887,
+      "eval_accuracy": 0.5875912408759124,
+      "eval_loss": 1.251747727394104,
+      "eval_runtime": 9.9685,
+      "eval_samples_per_second": 27.487,
+      "eval_steps_per_second": 0.903,
+      "step": 91
+    },
+    {
+      "epoch": 6.867924528301887,
+      "step": 91,
+      "total_flos": 8.883485181176095e+17,
+      "train_loss": 1.1828759214380284,
+      "train_runtime": 1039.6912,
+      "train_samples_per_second": 11.21,
+      "train_steps_per_second": 0.088
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 91,
+  "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": 8.883485181176095e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880333b1a69b402d8beafef381b29aaf91e09aa210d1c606c46c42e975415c6c
+size 5112