Training in progress, epoch 1

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: validation
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9476209516193522
+---
+
+<!-- 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: 0.1349
+- Accuracy: 0.9476
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.2131        | 1.0   | 51   | 0.1843          | 0.9320   |
+| 0.1521        | 2.0   | 102  | 0.1215          | 0.9552   |
+| 0.1318        | 3.0   | 153  | 0.1349          | 0.9476   |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 1.13.1
+- Datasets 2.16.1
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9586165533786486,
+    "eval_loss": 0.10476645827293396,
+    "eval_runtime": 455.4725,
+    "eval_samples_per_second": 10.982,
+    "eval_steps_per_second": 0.173,
+    "total_flos": 9.695327063822991e+17,
+    "train_loss": 0.22365938545831668,
+    "train_runtime": 8570.2671,
+    "train_samples_per_second": 4.551,
+    "train_steps_per_second": 0.018
+}

config.json

@@ -0,0 +1,61 @@
+{
+  "_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": "meme",
+    "1": "not_meme"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "meme": 0,
+    "not_meme": 1
+  },
+  "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": "4.37.2",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9586165533786486,
+    "eval_loss": 0.10476645827293396,
+    "eval_runtime": 455.4725,
+    "eval_samples_per_second": 10.982,
+    "eval_steps_per_second": 0.173
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc05b2f599c5c725aa494e5272e54fdde49324297645cc9c4b7dcb185f5b5b2
+size 110342832

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
+  }
+}

runs/Feb14_14-22-58_staff/events.out.tfevents.1707891894.staff.1131584.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a34d57a346535558f8610e18dc646cb28c22db4207e1f778af53f22d3f160b58
+size 8453

runs/Feb14_14-22-58_staff/events.out.tfevents.1707896585.staff.1131584.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06661ae147001450ffc627e0459290c1fe8614dfc0ba82de1bf6cde992c4034d
+size 8502

runs/Feb14_14-22-58_staff/events.out.tfevents.1707901870.staff.1131584.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f22cb5962ba8df93289cac38f8863278722c8796dc68cd2491e3ce7f4ef67d0
+size 411

runs/Feb15_10-05-12_staff/events.out.tfevents.1707963212.staff.1390720.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b09a04a22ee662da98e3f9e4d035e97ed33ffbf762ac11999293c212e69481
+size 8453

runs/Feb16_10-49-55_staff/events.out.tfevents.1708053147.staff.2184386.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48416fdf9aca2273b96a4d2e909966f84347fb8ac2f9d82d0caf20bbea1dc35d
+size 5911

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9.695327063822991e+17,
+    "train_loss": 0.22365938545831668,
+    "train_runtime": 8570.2671,
+    "train_samples_per_second": 4.551,
+    "train_steps_per_second": 0.018
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.955217912834866,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-102",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 153,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.125e-05,
+      "loss": 0.6793,
+      "step": 10
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.854014598540147e-05,
+      "loss": 0.4785,
+      "step": 20
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.489051094890511e-05,
+      "loss": 0.2911,
+      "step": 30
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.124087591240876e-05,
+      "loss": 0.2317,
+      "step": 40
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.759124087591241e-05,
+      "loss": 0.2131,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9320271891243502,
+      "eval_loss": 0.18428057432174683,
+      "eval_runtime": 169.576,
+      "eval_samples_per_second": 29.497,
+      "eval_steps_per_second": 0.466,
+      "step": 51
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 3.3941605839416055e-05,
+      "loss": 0.1782,
+      "step": 60
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 3.029197080291971e-05,
+      "loss": 0.1681,
+      "step": 70
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.664233576642336e-05,
+      "loss": 0.1598,
+      "step": 80
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.2992700729927008e-05,
+      "loss": 0.1517,
+      "step": 90
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.934306569343066e-05,
+      "loss": 0.1521,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.955217912834866,
+      "eval_loss": 0.12148739397525787,
+      "eval_runtime": 189.5006,
+      "eval_samples_per_second": 26.396,
+      "eval_steps_per_second": 0.417,
+      "step": 102
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.569343065693431e-05,
+      "loss": 0.1512,
+      "step": 110
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.2043795620437957e-05,
+      "loss": 0.1324,
+      "step": 120
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 8.394160583941606e-06,
+      "loss": 0.134,
+      "step": 130
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.744525547445255e-06,
+      "loss": 0.1269,
+      "step": 140
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.0948905109489052e-06,
+      "loss": 0.1318,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9476209516193522,
+      "eval_loss": 0.1348794549703598,
+      "eval_runtime": 1015.3639,
+      "eval_samples_per_second": 4.926,
+      "eval_steps_per_second": 0.078,
+      "step": 153
+    },
+    {
+      "epoch": 3.0,
+      "step": 153,
+      "total_flos": 9.695327063822991e+17,
+      "train_loss": 0.22365938545831668,
+      "train_runtime": 8570.2671,
+      "train_samples_per_second": 4.551,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 153,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 9.695327063822991e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d9e00e79ae54e7f1c4bccde9dc166bbd43ef823931d42a971d558e1137d9f4
+size 4347