End of training

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: microsoft/swin-tiny-patch4-window7-224
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: swin-tiny-patch4-window7-224-finetuned-eurosat
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5238095238095238
+---
+
+<!-- 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. -->
+
+# swin-tiny-patch4-window7-224-finetuned-eurosat
+
+This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3752
+- Accuracy: 0.5238
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| No log        | 0.8889 | 4    | 1.7408          | 0.4444   |
+| No log        | 2.0    | 9    | 1.4351          | 0.4921   |
+| 1.7494        | 2.6667 | 12   | 1.3752          | 0.5238   |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.6666666666666665,
+    "eval_accuracy": 0.5238095238095238,
+    "eval_loss": 1.3751540184020996,
+    "eval_runtime": 23.1923,
+    "eval_samples_per_second": 2.716,
+    "eval_steps_per_second": 0.086,
+    "total_flos": 3.768799680376013e+16,
+    "train_loss": 1.699290931224823,
+    "train_runtime": 1294.0597,
+    "train_samples_per_second": 1.312,
+    "train_steps_per_second": 0.009
+}

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
+  "architectures": [
+    "SwinForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    6,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 96,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "amenities",
+    "1": "bathroom",
+    "2": "bedroom",
+    "3": "exterior",
+    "4": "floor_plan",
+    "5": "kitchen",
+    "6": "living_room",
+    "7": "others"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "amenities": 0,
+    "bathroom": 1,
+    "bedroom": 2,
+    "exterior": 3,
+    "floor_plan": 4,
+    "kitchen": 5,
+    "living_room": 6,
+    "others": 7
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
+  "num_channels": 3,
+  "num_heads": [
+    3,
+    6,
+    12,
+    24
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.6666666666666665,
+    "eval_accuracy": 0.5238095238095238,
+    "eval_loss": 1.3751540184020996,
+    "eval_runtime": 23.1923,
+    "eval_samples_per_second": 2.716,
+    "eval_steps_per_second": 0.086
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8ff454c280ea6a7b23ec27f826c2ee8bf0ab69bacafb4379c6198ce949661c
+size 110361288

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": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Apr27_10-05-01_6c9a76e1dd10/events.out.tfevents.1714212320.6c9a76e1dd10.2327.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794a5e6e6740c0a023b918694c6d2905755681fc08b35aa4ad49e0089c73dde4
+size 6895

runs/Apr27_10-05-01_6c9a76e1dd10/events.out.tfevents.1714213683.6c9a76e1dd10.2327.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ffaaa1e420777a846756e425f577f2f00eae401cc8842f1a1ec30a075fd76d
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.6666666666666665,
+    "total_flos": 3.768799680376013e+16,
+    "train_loss": 1.699290931224823,
+    "train_runtime": 1294.0597,
+    "train_samples_per_second": 1.312,
+    "train_steps_per_second": 0.009
+}

trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.5238095238095238,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-12",
+  "epoch": 2.6666666666666665,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8888888888888888,
+      "eval_accuracy": 0.4444444444444444,
+      "eval_loss": 1.740828037261963,
+      "eval_runtime": 17.227,
+      "eval_samples_per_second": 3.657,
+      "eval_steps_per_second": 0.116,
+      "step": 4
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.49206349206349204,
+      "eval_loss": 1.4351359605789185,
+      "eval_runtime": 16.2702,
+      "eval_samples_per_second": 3.872,
+      "eval_steps_per_second": 0.123,
+      "step": 9
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 5.383830547332764,
+      "learning_rate": 1e-05,
+      "loss": 1.7494,
+      "step": 10
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_accuracy": 0.5238095238095238,
+      "eval_loss": 1.3751540184020996,
+      "eval_runtime": 16.3345,
+      "eval_samples_per_second": 3.857,
+      "eval_steps_per_second": 0.122,
+      "step": 12
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "step": 12,
+      "total_flos": 3.768799680376013e+16,
+      "train_loss": 1.699290931224823,
+      "train_runtime": 1294.0597,
+      "train_samples_per_second": 1.312,
+      "train_steps_per_second": 0.009
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 12,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.768799680376013e+16,
+  "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:cd9a3de2951ff8bf514987e7c99588bc5b6dbcea08d1954853dcfea2aaf07a99
+size 5048