End of training

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+base_model: microsoft/swin-tiny-patch4-window7-224
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: swin-tiny-patch4-window7-224-finetuned-eurosat
+  results: []
+---
+
+<!-- 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 an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9148
+- Accuracy: 0.3938
+
+## 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: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 2.6414        | 0.9630 | 13   | 2.4260          | 0.2746   |
+| 2.4558        | 2.0    | 27   | 2.1558          | 0.3368   |
+| 2.1176        | 2.9630 | 40   | 2.0164          | 0.3834   |
+| 2.0264        | 4.0    | 54   | 1.9314          | 0.3886   |
+| 1.9409        | 4.8148 | 65   | 1.9148          | 0.3938   |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.814814814814815,
+    "eval_accuracy": 0.39378238341968913,
+    "eval_loss": 1.9148268699645996,
+    "eval_runtime": 4.2598,
+    "eval_samples_per_second": 45.307,
+    "eval_steps_per_second": 1.643,
+    "total_flos": 1.0808265111345562e+18,
+    "train_loss": 2.2193346903874325,
+    "train_runtime": 316.4726,
+    "train_samples_per_second": 27.301,
+    "train_steps_per_second": 0.205
+}

config.json

@@ -0,0 +1,87 @@
+{
+  "_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": "Amoxicillin",
+    "1": "Ampicillin",
+    "2": "Aspirin",
+    "3": "Bleomycine",
+    "4": "Cefixime",
+    "5": "Cefotaxime",
+    "6": "Ceftriaxone",
+    "7": "Cefuroxime",
+    "8": "Ciprofloxacin",
+    "9": "Clopidogre",
+    "10": "Gentamycine",
+    "11": "Levofloxacin",
+    "12": "Losartan",
+    "13": "Neomycin",
+    "14": "Valsartan"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Amoxicillin": 0,
+    "Ampicillin": 1,
+    "Aspirin": 2,
+    "Bleomycine": 3,
+    "Cefixime": 4,
+    "Cefotaxime": 5,
+    "Ceftriaxone": 6,
+    "Cefuroxime": 7,
+    "Ciprofloxacin": 8,
+    "Clopidogre": 9,
+    "Gentamycine": 10,
+    "Levofloxacin": 11,
+    "Losartan": 12,
+    "Neomycin": 13,
+    "Valsartan": 14
+  },
+  "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": "4.40.2",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.814814814814815,
+    "eval_accuracy": 0.39378238341968913,
+    "eval_loss": 1.9148268699645996,
+    "eval_runtime": 4.2598,
+    "eval_samples_per_second": 45.307,
+    "eval_steps_per_second": 1.643
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41416dd74ed6d5ead67d64c9bfdf2fc0c2f4b36b3f4acd6b8a457eb728ffc72
+size 110382828

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/May18_22-58-23_aad0bb7717de/events.out.tfevents.1716073130.aad0bb7717de.2141.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45e9a62aa015331b8b1e21a8d6968df0ef0fd435fae3c0da130b777266566b11
+size 10368

runs/May18_22-58-23_aad0bb7717de/events.out.tfevents.1716073286.aad0bb7717de.2141.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f9f53239a1aa5686b6b0eea294f7fffca47a9d49d40c0f6b50acb4783c7561
+size 411

runs/May18_23-02-06_aad0bb7717de/events.out.tfevents.1716073333.aad0bb7717de.2141.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ef005a7267119445fc45f04257d7d4434692f40d7909006fcdbab0ea89574d
+size 5779

runs/May18_23-02-29_aad0bb7717de/events.out.tfevents.1716073354.aad0bb7717de.2141.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0676c4b1cb42e5b3395901ab27dd8aa8b73a4e14f6e688f0899ab7ad8064f369
+size 8955

runs/May18_23-02-29_aad0bb7717de/events.out.tfevents.1716073572.aad0bb7717de.2141.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0801e458300b1340df94d10ab9a4d3b56c3318db42309ad65e4c6233bbe1cd06
+size 405

runs/May18_23-07-12_aad0bb7717de/events.out.tfevents.1716073636.aad0bb7717de.2141.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af206ebefbef2d257c9a7c2d1a7e0f639ecda0a76529af0db6c8ae6d94d5ada2
+size 8906

runs/May18_23-07-12_aad0bb7717de/events.out.tfevents.1716073957.aad0bb7717de.2141.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c51dfcbe08e35be1b8a8f051387f13eb9ef1e1603a03c1db354a83dec1ab45
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.814814814814815,
+    "total_flos": 1.0808265111345562e+18,
+    "train_loss": 2.2193346903874325,
+    "train_runtime": 316.4726,
+    "train_samples_per_second": 27.301,
+    "train_steps_per_second": 0.205
+}

trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": 0.39378238341968913,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-65",
+  "epoch": 4.814814814814815,
+  "eval_steps": 500,
+  "global_step": 65,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 2.7531347274780273,
+      "learning_rate": 4.741379310344828e-05,
+      "loss": 2.6414,
+      "step": 10
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "eval_accuracy": 0.27461139896373055,
+      "eval_loss": 2.4260499477386475,
+      "eval_runtime": 4.2205,
+      "eval_samples_per_second": 45.729,
+      "eval_steps_per_second": 1.659,
+      "step": 13
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 6.018283843994141,
+      "learning_rate": 3.8793103448275865e-05,
+      "loss": 2.4558,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.33678756476683935,
+      "eval_loss": 2.15580415725708,
+      "eval_runtime": 4.3823,
+      "eval_samples_per_second": 44.04,
+      "eval_steps_per_second": 1.597,
+      "step": 27
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 8.673904418945312,
+      "learning_rate": 3.017241379310345e-05,
+      "loss": 2.2726,
+      "step": 30
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 10.522686004638672,
+      "learning_rate": 2.1551724137931033e-05,
+      "loss": 2.1176,
+      "step": 40
+    },
+    {
+      "epoch": 2.962962962962963,
+      "eval_accuracy": 0.38341968911917096,
+      "eval_loss": 2.01640248298645,
+      "eval_runtime": 4.245,
+      "eval_samples_per_second": 45.465,
+      "eval_steps_per_second": 1.649,
+      "step": 40
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 12.191962242126465,
+      "learning_rate": 1.2931034482758622e-05,
+      "loss": 2.0264,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.38860103626943004,
+      "eval_loss": 1.9313786029815674,
+      "eval_runtime": 4.1882,
+      "eval_samples_per_second": 46.082,
+      "eval_steps_per_second": 1.671,
+      "step": 54
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 8.964757919311523,
+      "learning_rate": 4.310344827586207e-06,
+      "loss": 1.9409,
+      "step": 60
+    },
+    {
+      "epoch": 4.814814814814815,
+      "eval_accuracy": 0.39378238341968913,
+      "eval_loss": 1.9148268699645996,
+      "eval_runtime": 4.182,
+      "eval_samples_per_second": 46.15,
+      "eval_steps_per_second": 1.674,
+      "step": 65
+    },
+    {
+      "epoch": 4.814814814814815,
+      "step": 65,
+      "total_flos": 1.0808265111345562e+18,
+      "train_loss": 2.2193346903874325,
+      "train_runtime": 316.4726,
+      "train_samples_per_second": 27.301,
+      "train_steps_per_second": 0.205
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 65,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.0808265111345562e+18,
+  "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:acb31e9d4d50d02e8532dbcc44d1d18bda3bffd7a9fe9bde163fc47c402866e6
+size 5048