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: 0.9781481481481481
+---
+
+<!-- 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: 0.0628
+- Accuracy: 0.9781
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.2876        | 1.0   | 190  | 0.1039          | 0.9659   |
+| 0.2083        | 2.0   | 380  | 0.0740          | 0.9722   |
+| 0.1625        | 3.0   | 570  | 0.0628          | 0.9781   |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9781481481481481,
+    "eval_loss": 0.06279285252094269,
+    "eval_runtime": 17.1656,
+    "eval_samples_per_second": 157.292,
+    "eval_steps_per_second": 4.952,
+    "total_flos": 1.8124066505760768e+18,
+    "train_loss": 0.3348683936554089,
+    "train_runtime": 1125.7736,
+    "train_samples_per_second": 64.755,
+    "train_steps_per_second": 0.506
+}

config.json

@@ -0,0 +1,77 @@
+{
+  "_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": "AnnualCrop",
+    "1": "Forest",
+    "2": "HerbaceousVegetation",
+    "3": "Highway",
+    "4": "Industrial",
+    "5": "Pasture",
+    "6": "PermanentCrop",
+    "7": "Residential",
+    "8": "River",
+    "9": "SeaLake"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "AnnualCrop": 0,
+    "Forest": 1,
+    "HerbaceousVegetation": 2,
+    "Highway": 3,
+    "Industrial": 4,
+    "Pasture": 5,
+    "PermanentCrop": 6,
+    "Residential": 7,
+    "River": 8,
+    "SeaLake": 9
+  },
+  "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": "4.35.0",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9781481481481481,
+    "eval_loss": 0.06279285252094269,
+    "eval_runtime": 17.1656,
+    "eval_samples_per_second": 157.292,
+    "eval_steps_per_second": 4.952
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1feab5b80bb49ef677d36789c160edae4918ea2d527fd8d1686c6ad1dbff0396
+size 110367448

runs/Nov03_20-01-45_e93b5b900954/events.out.tfevents.1699041712.e93b5b900954.3040.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13611ab15ba2459a36cfdd2f477e540e64bf76bb16cff3b074a267f6f3ad600b
+size 15273

runs/Nov03_20-01-45_e93b5b900954/events.out.tfevents.1699042856.e93b5b900954.3040.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b53de2681e96b7eb0baf735ebed941283ecaa57cd9513d1692550d4d1ebf4a5
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.8124066505760768e+18,
+    "train_loss": 0.3348683936554089,
+    "train_runtime": 1125.7736,
+    "train_samples_per_second": 64.755,
+    "train_steps_per_second": 0.506
+}

trainer_state.json

@@ -0,0 +1,397 @@
+{
+  "best_metric": 0.9781481481481481,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-570",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 570,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.771929824561403e-06,
+      "loss": 2.3094,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.7543859649122806e-05,
+      "loss": 2.1012,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 1.6596,
+      "step": 30
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.508771929824561e-05,
+      "loss": 1.0129,
+      "step": 40
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.3859649122807014e-05,
+      "loss": 0.5887,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.970760233918128e-05,
+      "loss": 0.4976,
+      "step": 60
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.8732943469785574e-05,
+      "loss": 0.4586,
+      "step": 70
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.7758284600389865e-05,
+      "loss": 0.3953,
+      "step": 80
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.678362573099415e-05,
+      "loss": 0.3735,
+      "step": 90
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.580896686159844e-05,
+      "loss": 0.3729,
+      "step": 100
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.483430799220273e-05,
+      "loss": 0.3011,
+      "step": 110
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.3859649122807014e-05,
+      "loss": 0.3308,
+      "step": 120
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.2884990253411305e-05,
+      "loss": 0.2981,
+      "step": 130
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.1910331384015596e-05,
+      "loss": 0.295,
+      "step": 140
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.093567251461988e-05,
+      "loss": 0.2531,
+      "step": 150
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.996101364522417e-05,
+      "loss": 0.2549,
+      "step": 160
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.898635477582846e-05,
+      "loss": 0.2486,
+      "step": 170
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.8011695906432746e-05,
+      "loss": 0.2907,
+      "step": 180
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.2876,
+      "step": 190
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.965925925925926,
+      "eval_loss": 0.10394594818353653,
+      "eval_runtime": 17.3596,
+      "eval_samples_per_second": 155.533,
+      "eval_steps_per_second": 4.896,
+      "step": 190
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.606237816764133e-05,
+      "loss": 0.2288,
+      "step": 200
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 3.508771929824561e-05,
+      "loss": 0.2496,
+      "step": 210
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.41130604288499e-05,
+      "loss": 0.2061,
+      "step": 220
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.313840155945419e-05,
+      "loss": 0.249,
+      "step": 230
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.216374269005848e-05,
+      "loss": 0.2377,
+      "step": 240
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.118908382066277e-05,
+      "loss": 0.204,
+      "step": 250
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 3.0214424951267055e-05,
+      "loss": 0.2296,
+      "step": 260
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.9239766081871346e-05,
+      "loss": 0.1968,
+      "step": 270
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.8265107212475634e-05,
+      "loss": 0.2173,
+      "step": 280
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.729044834307992e-05,
+      "loss": 0.1989,
+      "step": 290
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 0.17,
+      "step": 300
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.53411306042885e-05,
+      "loss": 0.2142,
+      "step": 310
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.4366471734892787e-05,
+      "loss": 0.1615,
+      "step": 320
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.3391812865497074e-05,
+      "loss": 0.1602,
+      "step": 330
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.2417153996101365e-05,
+      "loss": 0.1823,
+      "step": 340
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.1442495126705653e-05,
+      "loss": 0.2038,
+      "step": 350
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2.046783625730994e-05,
+      "loss": 0.1726,
+      "step": 360
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.949317738791423e-05,
+      "loss": 0.1927,
+      "step": 370
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.2083,
+      "step": 380
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9722222222222222,
+      "eval_loss": 0.07401775568723679,
+      "eval_runtime": 16.6423,
+      "eval_samples_per_second": 162.237,
+      "eval_steps_per_second": 5.107,
+      "step": 380
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.7543859649122806e-05,
+      "loss": 0.194,
+      "step": 390
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.6569200779727097e-05,
+      "loss": 0.1741,
+      "step": 400
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.5594541910331384e-05,
+      "loss": 0.1485,
+      "step": 410
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.4619883040935673e-05,
+      "loss": 0.1386,
+      "step": 420
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.364522417153996e-05,
+      "loss": 0.1547,
+      "step": 430
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.267056530214425e-05,
+      "loss": 0.163,
+      "step": 440
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.1695906432748537e-05,
+      "loss": 0.1703,
+      "step": 450
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.0721247563352826e-05,
+      "loss": 0.1342,
+      "step": 460
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 9.746588693957115e-06,
+      "loss": 0.173,
+      "step": 470
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 8.771929824561403e-06,
+      "loss": 0.1541,
+      "step": 480
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.797270955165692e-06,
+      "loss": 0.155,
+      "step": 490
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.82261208576998e-06,
+      "loss": 0.1276,
+      "step": 500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.8479532163742686e-06,
+      "loss": 0.1339,
+      "step": 510
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.873294346978558e-06,
+      "loss": 0.1468,
+      "step": 520
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 3.898635477582846e-06,
+      "loss": 0.1529,
+      "step": 530
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.9239766081871343e-06,
+      "loss": 0.132,
+      "step": 540
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.949317738791423e-06,
+      "loss": 0.1375,
+      "step": 550
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 9.746588693957115e-07,
+      "loss": 0.1218,
+      "step": 560
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.1625,
+      "step": 570
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9781481481481481,
+      "eval_loss": 0.06279285252094269,
+      "eval_runtime": 16.7672,
+      "eval_samples_per_second": 161.029,
+      "eval_steps_per_second": 5.069,
+      "step": 570
+    },
+    {
+      "epoch": 3.0,
+      "step": 570,
+      "total_flos": 1.8124066505760768e+18,
+      "train_loss": 0.3348683936554089,
+      "train_runtime": 1125.7736,
+      "train_samples_per_second": 64.755,
+      "train_steps_per_second": 0.506
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 570,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.8124066505760768e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8155db682ae1918f061ff618c07c3e69a30f286f4fd460b71b5fa250dfca6a2f
+size 4664