End of training

README.md

@@ -0,0 +1,74 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: microsoft/swin-base-patch4-window7-224
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: 2025-01-21-15-57-43-swin-base-patch4-window7-224
+  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. -->
+
+# 2025-01-21-15-57-43-swin-base-patch4-window7-224
+
+This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0384
+- Precision: 0.9928
+- Recall: 0.9926
+- F1: 0.9926
+- Accuracy: 0.992
+- Top1 Accuracy: 0.9926
+- Error Rate: 0.0080
+
+## 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: 0.0002
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 3407
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy | Top1 Accuracy | Error Rate |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------------:|:----------:|
+| 0.732         | 1.0   | 34   | 0.3980          | 0.9165    | 0.8741 | 0.8590 | 0.8649   | 0.8741        | 0.1351     |
+| 0.2462        | 2.0   | 68   | 0.1051          | 0.9538    | 0.9481 | 0.9484 | 0.9499   | 0.9481        | 0.0501     |
+| 0.1991        | 3.0   | 102  | 0.0384          | 0.9928    | 0.9926 | 0.9926 | 0.992    | 0.9926        | 0.0080     |
+| 0.1559        | 4.0   | 136  | 0.0890          | 0.9802    | 0.9778 | 0.9780 | 0.9777   | 0.9778        | 0.0223     |
+| 0.1024        | 5.0   | 170  | 0.1092          | 0.9863    | 0.9852 | 0.9852 | 0.9846   | 0.9852        | 0.0154     |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,28 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.992,
+    "eval_error_rate": 0.008000000000000007,
+    "eval_f1": 0.9925797814417668,
+    "eval_loss": 0.03836945444345474,
+    "eval_precision": 0.9928395061728394,
+    "eval_recall": 0.9925925925925926,
+    "eval_runtime": 3.768,
+    "eval_samples_per_second": 35.828,
+    "eval_steps_per_second": 1.327,
+    "eval_top1_accuracy": 0.9925925925925926,
+    "test_accuracy": 1.0,
+    "test_error_rate": 0.0,
+    "test_f1": 1.0,
+    "test_loss": 0.03548692911863327,
+    "test_precision": 1.0,
+    "test_recall": 1.0,
+    "test_runtime": 3.845,
+    "test_samples_per_second": 35.111,
+    "test_steps_per_second": 1.3,
+    "test_top1_accuracy": 1.0,
+    "total_flos": 4.230809974960128e+17,
+    "train_loss": 0.2870972801657284,
+    "train_runtime": 294.683,
+    "train_samples_per_second": 36.65,
+    "train_steps_per_second": 1.154
+}

classification_report.csv

@@ -0,0 +1,9 @@
+,precision,recall,f1-score,support
+Ilang-ilang,1.0,1.0,1.0,26.0
+Mango,1.0,1.0,1.0,30.0
+Narra,1.0,1.0,1.0,30.0
+Royal Palm,1.0,1.0,1.0,24.0
+Tabebuia,1.0,1.0,1.0,25.0
+accuracy,1.0,1.0,1.0,1.0
+macro avg,1.0,1.0,1.0,135.0
+weighted avg,1.0,1.0,1.0,135.0

config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "microsoft/swin-base-patch4-window7-224",
+  "architectures": [
+    "SwinForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 128,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Ilang-ilang",
+    "1": "Mango",
+    "2": "Narra",
+    "3": "Royal Palm",
+    "4": "Tabebuia"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Ilang-ilang": 0,
+    "Mango": 1,
+    "Narra": 2,
+    "Royal Palm": 3,
+    "Tabebuia": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
+  "num_channels": 3,
+  "num_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
+  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.992,
+    "eval_error_rate": 0.008000000000000007,
+    "eval_f1": 0.9925797814417668,
+    "eval_loss": 0.03836945444345474,
+    "eval_precision": 0.9928395061728394,
+    "eval_recall": 0.9925925925925926,
+    "eval_runtime": 3.768,
+    "eval_samples_per_second": 35.828,
+    "eval_steps_per_second": 1.327,
+    "eval_top1_accuracy": 0.9925925925925926
+}

evaluation/classification_report.csv

@@ -0,0 +1,9 @@
+,precision,recall,f1-score,support
+Ilang-ilang,1.0,1.0,1.0,26.0
+Mango,1.0,1.0,1.0,30.0
+Narra,1.0,1.0,1.0,30.0
+Royal Palm,1.0,1.0,1.0,24.0
+Tabebuia,1.0,1.0,1.0,25.0
+accuracy,1.0,1.0,1.0,1.0
+macro avg,1.0,1.0,1.0,135.0
+weighted avg,1.0,1.0,1.0,135.0

evaluation/confusion_matrix.csv

@@ -0,0 +1,6 @@
+,Ilang-ilang,Mango,Narra,Royal Palm,Tabebuia
+Ilang-ilang,26,0,0,0,0
+Mango,0,30,0,0,0
+Narra,0,0,30,0,0
+Royal Palm,0,0,0,24,0
+Tabebuia,0,0,0,0,25

evaluation/results.log

@@ -0,0 +1,14 @@
+2025-01-21 16:06:13,120 - INFO - plot_confusion_matrix - Confusion Matrix:
+[[26  0  0  0  0]
+ [ 0 30  0  0  0]
+ [ 0  0 30  0  0]
+ [ 0  0  0 24  0]
+ [ 0  0  0  0 25]]
+2025-01-21 16:06:13,664 - INFO - plot_confusion_matrix - Confusion matrix saved to 2025-01-21-15-57-43-swin-base-patch4-window7-224/evaluation/confusion_matrix.png
+2025-01-21 16:06:13,668 - INFO - plot_confusion_matrix - Confusion matrix report saved to 2025-01-21-15-57-43-swin-base-patch4-window7-224/evaluation/confusion_matrix.csv
+2025-01-21 16:06:13,841 - INFO - classification_report_bar - Classification report saved to 2025-01-21-15-57-43-swin-base-patch4-window7-224/evaluation/classification_report.csv
+2025-01-21 16:06:14,595 - INFO - classification_report_bar - Classification report bar chart saved to 2025-01-21-15-57-43-swin-base-patch4-window7-224/evaluation/clf_bar.png
+2025-01-21 16:06:14,597 - INFO - classification_report_bar - Overall Accuracy: 1.000
+2025-01-21 16:06:15,423 - INFO - plot_classification_report_heatmap - Classification report heatmap saved to 2025-01-21-15-57-43-swin-base-patch4-window7-224/classification_report.png
+2025-01-21 16:06:15,589 - INFO - plot_classification_report_heatmap - Classification report saved to 2025-01-21-15-57-43-swin-base-patch4-window7-224/classification_report.csv
+2025-01-21 16:06:16,641 - INFO - plot_results - Training metrics saved to 2025-01-21-15-57-43-swin-base-patch4-window7-224/training_metrics.csv

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe06c0cd821439a29705fba1d4d3f60c22b26e1a66e26f448deb3886e479683
+size 347511116

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
+  }
+}

test_results.json

@@ -0,0 +1,12 @@
+{
+    "test_accuracy": 1.0,
+    "test_error_rate": 0.0,
+    "test_f1": 1.0,
+    "test_loss": 0.03548692911863327,
+    "test_precision": 1.0,
+    "test_recall": 1.0,
+    "test_runtime": 3.845,
+    "test_samples_per_second": 35.111,
+    "test_steps_per_second": 1.3,
+    "test_top1_accuracy": 1.0
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 4.230809974960128e+17,
+    "train_loss": 0.2870972801657284,
+    "train_runtime": 294.683,
+    "train_samples_per_second": 36.65,
+    "train_steps_per_second": 1.154
+}

trainer_state.json

@@ -0,0 +1,176 @@
+{
+  "best_metric": 0.992,
+  "best_model_checkpoint": "2025-01-21-15-57-43-swin-base-patch4-window7-224/checkpoint-102",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 170,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "train_accuracy": 0.7185185185185186
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 23.64792823791504,
+      "learning_rate": 0.0002,
+      "loss": 0.732,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.864857142857143,
+      "eval_error_rate": 0.135142857142857,
+      "eval_f1": 0.8590001766472355,
+      "eval_loss": 0.3980206549167633,
+      "eval_precision": 0.9164785420340976,
+      "eval_recall": 0.8740740740740741,
+      "eval_runtime": 3.5078,
+      "eval_samples_per_second": 38.486,
+      "eval_steps_per_second": 1.425,
+      "eval_top1_accuracy": 0.8740740740740741,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "train_accuracy": 0.9185185185185185
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.839152336120605,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.2462,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9499066705963257,
+      "eval_error_rate": 0.05009332940367428,
+      "eval_f1": 0.948411944708241,
+      "eval_loss": 0.10511945188045502,
+      "eval_precision": 0.9538222952016054,
+      "eval_recall": 0.9481481481481482,
+      "eval_runtime": 3.5401,
+      "eval_samples_per_second": 38.135,
+      "eval_steps_per_second": 1.412,
+      "eval_top1_accuracy": 0.9481481481481482,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "train_accuracy": 0.9349794238683128
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.658217430114746,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.1991,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.992,
+      "eval_error_rate": 0.008000000000000007,
+      "eval_f1": 0.9925797814417668,
+      "eval_loss": 0.03836945444345474,
+      "eval_precision": 0.9928395061728394,
+      "eval_recall": 0.9925925925925926,
+      "eval_runtime": 3.3904,
+      "eval_samples_per_second": 39.819,
+      "eval_steps_per_second": 1.475,
+      "eval_top1_accuracy": 0.9925925925925926,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "train_accuracy": 0.9530864197530864
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.14619779586792,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.1559,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9777188328912467,
+      "eval_error_rate": 0.022281167108753275,
+      "eval_f1": 0.9780454350411318,
+      "eval_loss": 0.08900710195302963,
+      "eval_precision": 0.98015873015873,
+      "eval_recall": 0.9777777777777777,
+      "eval_runtime": 3.432,
+      "eval_samples_per_second": 39.335,
+      "eval_steps_per_second": 1.457,
+      "eval_top1_accuracy": 0.9777777777777777,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "train_accuracy": 0.9703703703703703
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.705554008483887,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.1024,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9846153846153847,
+      "eval_error_rate": 0.01538461538461533,
+      "eval_f1": 0.9851737891737893,
+      "eval_loss": 0.10920833796262741,
+      "eval_precision": 0.9862825788751715,
+      "eval_recall": 0.9851851851851852,
+      "eval_runtime": 3.7553,
+      "eval_samples_per_second": 35.949,
+      "eval_steps_per_second": 1.331,
+      "eval_top1_accuracy": 0.9851851851851852,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "step": 170,
+      "total_flos": 4.230809974960128e+17,
+      "train_loss": 0.2870972801657284,
+      "train_runtime": 294.683,
+      "train_samples_per_second": 36.65,
+      "train_steps_per_second": 1.154
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 2
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.230809974960128e+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:a1a2887287c3d672c92c167523b2c6c3adf9289fb5fda4651f6df7ab84d3bf1c
+size 5176

training_metrics.csv

@@ -0,0 +1,6 @@
+Epoch,Train Loss,Eval Loss,Train Accuracy,Eval Accuracy
+1,0.732,0.3980206549167633,0.7185185185185186,0.864857142857143
+2,0.2462,0.10511945188045502,0.9185185185185185,0.9499066705963257
+3,0.1991,0.03836945444345474,0.9349794238683128,0.992
+4,0.1559,0.08900710195302963,0.9530864197530864,0.9777188328912467
+5,0.1024,0.10920833796262741,0.9703703703703703,0.9846153846153847