Training in progress, epoch 0

README.md

@@ -0,0 +1,81 @@
+---
+library_name: transformers
+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: 0.8990228013029316
+---
+
+<!-- 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: 0.2956
+- Accuracy: 0.8990
+
+## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.5698        | 0.9655 | 21   | 0.7486          | 0.6645   |
+| 0.2988        | 1.9655 | 42   | 0.2956          | 0.8990   |
+| 0.2695        | 2.9655 | 63   | 0.2595          | 0.8958   |
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.9655172413793105,
+    "eval_accuracy": 0.8990228013029316,
+    "eval_loss": 0.2956256568431854,
+    "eval_runtime": 16.6592,
+    "eval_samples_per_second": 18.428,
+    "eval_steps_per_second": 0.6,
+    "total_flos": 2.0203512366720614e+17,
+    "train_loss": 0.46530596036759636,
+    "train_runtime": 777.4672,
+    "train_samples_per_second": 10.638,
+    "train_steps_per_second": 0.081
+}

config.json

@@ -0,0 +1,63 @@
+{
+  "_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": "1",
+    "1": "2",
+    "2": "3"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "1": 0,
+    "2": 1,
+    "3": 2
+  },
+  "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": "4.48.3",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9655172413793105,
+    "eval_accuracy": 0.8990228013029316,
+    "eval_loss": 0.2956256568431854,
+    "eval_runtime": 16.6592,
+    "eval_samples_per_second": 18.428,
+    "eval_steps_per_second": 0.6
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23eac5a851f15b1c81dbd8722be160f0d7cc28e5a8a2878295c197d1438cf23
+size 110345908

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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/Mar09_14-54-37_6ea84fd0780b/events.out.tfevents.1741532164.6ea84fd0780b.386.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40961cfcb77125809c6a72ae253656b672a47ca703c98fb4b7238fc0a7926508
+size 8069

runs/Mar09_14-54-37_6ea84fd0780b/events.out.tfevents.1741532966.6ea84fd0780b.386.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf1e214935c22c03221f76f8456a3d68539ee3dd2b07df9151789a76a3bddf5
+size 405

runs/Mar09_17-18-53_6ea84fd0780b/events.out.tfevents.1741540746.6ea84fd0780b.386.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5355376540222ae009e49917e02b5b64004e296e47690f6fe1aa0896d0eb4486
+size 6259

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9655172413793105,
+    "total_flos": 2.0203512366720614e+17,
+    "train_loss": 0.46530596036759636,
+    "train_runtime": 777.4672,
+    "train_samples_per_second": 10.638,
+    "train_steps_per_second": 0.081
+}

trainer_state.json

@@ -0,0 +1,111 @@
+{
+  "best_metric": 0.8990228013029316,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-42",
+  "epoch": 2.9655172413793105,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 4.308095932006836,
+      "learning_rate": 4.732142857142857e-05,
+      "loss": 0.9696,
+      "step": 10
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 19.417911529541016,
+      "learning_rate": 3.839285714285715e-05,
+      "loss": 0.5698,
+      "step": 20
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "eval_accuracy": 0.6644951140065146,
+      "eval_loss": 0.7485707402229309,
+      "eval_runtime": 18.0627,
+      "eval_samples_per_second": 16.996,
+      "eval_steps_per_second": 0.554,
+      "step": 21
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 11.978184700012207,
+      "learning_rate": 2.9464285714285718e-05,
+      "loss": 0.4488,
+      "step": 30
+    },
+    {
+      "epoch": 1.8735632183908046,
+      "grad_norm": 5.141038417816162,
+      "learning_rate": 2.0535714285714285e-05,
+      "loss": 0.2988,
+      "step": 40
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "eval_accuracy": 0.8990228013029316,
+      "eval_loss": 0.2956256568431854,
+      "eval_runtime": 15.9558,
+      "eval_samples_per_second": 19.241,
+      "eval_steps_per_second": 0.627,
+      "step": 42
+    },
+    {
+      "epoch": 2.367816091954023,
+      "grad_norm": 6.264738082885742,
+      "learning_rate": 1.1607142857142857e-05,
+      "loss": 0.3026,
+      "step": 50
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 5.892236232757568,
+      "learning_rate": 2.6785714285714285e-06,
+      "loss": 0.2695,
+      "step": 60
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "eval_accuracy": 0.8957654723127035,
+      "eval_loss": 0.259478896856308,
+      "eval_runtime": 16.6934,
+      "eval_samples_per_second": 18.39,
+      "eval_steps_per_second": 0.599,
+      "step": 63
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "step": 63,
+      "total_flos": 2.0203512366720614e+17,
+      "train_loss": 0.46530596036759636,
+      "train_runtime": 777.4672,
+      "train_samples_per_second": 10.638,
+      "train_steps_per_second": 0.081
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 63,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.0203512366720614e+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 sha256:32b330fc12ad5f398fd4a9aac3bb70b4a425c1a6a7f9a5844cfa4cef4b05dbc0
+size 5432