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: 0.8821752265861027
+---
+
+<!-- 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: 0.5173
+- Accuracy: 0.8822
+
+## 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: 224
+- eval_batch_size: 224
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 896
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.0945        | 1.0   | 10   | 1.3185          | 0.5569   |
+| 1.1055        | 2.0   | 20   | 0.6962          | 0.8379   |
+| 0.6974        | 3.0   | 30   | 0.5173          | 0.8822   |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.5
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8821752265861027,
+    "eval_loss": 0.5172543525695801,
+    "eval_runtime": 4.1466,
+    "eval_samples_per_second": 239.475,
+    "eval_steps_per_second": 1.206,
+    "total_flos": 6.66078011176919e+17,
+    "train_loss": 1.299128500620524,
+    "train_runtime": 138.8552,
+    "train_samples_per_second": 192.935,
+    "train_steps_per_second": 0.216
+}

config.json

@@ -0,0 +1,81 @@
+{
+  "_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": "battery",
+    "1": "biological",
+    "2": "brown-glass",
+    "3": "cardboard",
+    "4": "clothes",
+    "5": "green-glass",
+    "6": "metal",
+    "7": "paper",
+    "8": "plastic",
+    "9": "shoes",
+    "10": "trash",
+    "11": "white-glass"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "battery": 0,
+    "biological": 1,
+    "brown-glass": 2,
+    "cardboard": 3,
+    "clothes": 4,
+    "green-glass": 5,
+    "metal": 6,
+    "paper": 7,
+    "plastic": 8,
+    "shoes": 9,
+    "trash": 10,
+    "white-glass": 11
+  },
+  "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": "4.33.2",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8821752265861027,
+    "eval_loss": 0.5172543525695801,
+    "eval_runtime": 4.1466,
+    "eval_samples_per_second": 239.475,
+    "eval_steps_per_second": 1.206
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "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
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f51098613e4fab69a2bb96514d01b5c031c1cfc43477a38c4fcebf6973e0a43
+size 110425585

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 6.66078011176919e+17,
+    "train_loss": 1.299128500620524,
+    "train_runtime": 138.8552,
+    "train_samples_per_second": 192.935,
+    "train_steps_per_second": 0.216
+}

trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": 0.8821752265861027,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-30",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 2.0945,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5568982880161127,
+      "eval_loss": 1.3184599876403809,
+      "eval_runtime": 4.1159,
+      "eval_samples_per_second": 241.258,
+      "eval_steps_per_second": 1.215,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 1.1055,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.837865055387714,
+      "eval_loss": 0.696175217628479,
+      "eval_runtime": 3.8784,
+      "eval_samples_per_second": 256.033,
+      "eval_steps_per_second": 1.289,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.6974,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8821752265861027,
+      "eval_loss": 0.5172543525695801,
+      "eval_runtime": 4.1085,
+      "eval_samples_per_second": 241.693,
+      "eval_steps_per_second": 1.217,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "step": 30,
+      "total_flos": 6.66078011176919e+17,
+      "train_loss": 1.299128500620524,
+      "train_runtime": 138.8552,
+      "train_samples_per_second": 192.935,
+      "train_steps_per_second": 0.216
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 30,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 6.66078011176919e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8c2482aaa4956592af6d98b263d3d76b8b39e243bf186fd2a104d6ad3e295d
+size 4091