End of training

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: 2025-01-21-16-13-04-vit-base-patch16-224
+  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. -->
+
+# 2025-01-21-16-13-04-vit-base-patch16-224
+
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0188
+- Precision: 0.9929
+- Recall: 0.9926
+- F1: 0.9926
+- Accuracy: 0.9931
+- Top1 Accuracy: 0.9926
+- Error Rate: 0.0069
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------------:|:----------:|
+| 0.7465        | 1.0   | 34   | 0.1092          | 0.9536    | 0.9407 | 0.9400 | 0.9366   | 0.9407        | 0.0634     |
+| 0.212         | 2.0   | 68   | 0.2754          | 0.9338    | 0.9111 | 0.9061 | 0.9049   | 0.9111        | 0.0951     |
+| 0.115         | 3.0   | 102  | 0.0534          | 0.9854    | 0.9852 | 0.9852 | 0.9851   | 0.9852        | 0.0149     |
+| 0.0723        | 4.0   | 136  | 0.0188          | 0.9929    | 0.9926 | 0.9926 | 0.9931   | 0.9926        | 0.0069     |
+| 0.0716        | 5.0   | 170  | 0.0195          | 0.9928    | 0.9926 | 0.9926 | 0.992    | 0.9926        | 0.0080     |
+| 0.0161        | 6.0   | 204  | 0.0389          | 0.9791    | 0.9778 | 0.9778 | 0.9775   | 0.9778        | 0.0225     |
+
+
+### 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": 6.0,
+    "eval_accuracy": 0.993103448275862,
+    "eval_error_rate": 0.006896551724137945,
+    "eval_f1": 0.992600236975882,
+    "eval_loss": 0.01880481094121933,
+    "eval_precision": 0.9928774928774929,
+    "eval_recall": 0.9925925925925926,
+    "eval_runtime": 3.5639,
+    "eval_samples_per_second": 37.88,
+    "eval_steps_per_second": 1.403,
+    "eval_top1_accuracy": 0.9925925925925926,
+    "test_accuracy": 0.9933333333333334,
+    "test_error_rate": 0.006666666666666599,
+    "test_f1": 0.9925905344077058,
+    "test_loss": 0.02411273680627346,
+    "test_precision": 0.992831541218638,
+    "test_recall": 0.9925925925925926,
+    "test_runtime": 3.4349,
+    "test_samples_per_second": 39.302,
+    "test_steps_per_second": 1.456,
+    "test_top1_accuracy": 0.9925925925925926,
+    "total_flos": 5.0216159448612864e+17,
+    "train_loss": 0.2055974360190186,
+    "train_runtime": 303.9865,
+    "train_samples_per_second": 35.528,
+    "train_steps_per_second": 1.118
+}

classification_report.csv

@@ -0,0 +1,9 @@
+,precision,recall,f1-score,support
+Ilang-ilang,1.0,1.0,1.0,26.0
+Mango,1.0,0.9666666666666667,0.9830508474576272,30.0
+Narra,0.967741935483871,1.0,0.9836065573770492,30.0
+Royal Palm,1.0,1.0,1.0,24.0
+Tabebuia,1.0,1.0,1.0,25.0
+accuracy,0.9925925925925926,0.9925925925925926,0.9925925925925926,0.9925925925925926
+macro avg,0.9935483870967742,0.9933333333333334,0.9933314809669354,135.0
+weighted avg,0.992831541218638,0.9925925925925926,0.9925905344077058,135.0

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Ilang-ilang",
+    "1": "Mango",
+    "2": "Narra",
+    "3": "Royal Palm",
+    "4": "Tabebuia"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Ilang-ilang": 0,
+    "Mango": 1,
+    "Narra": 2,
+    "Royal Palm": 3,
+    "Tabebuia": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2"
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.993103448275862,
+    "eval_error_rate": 0.006896551724137945,
+    "eval_f1": 0.992600236975882,
+    "eval_loss": 0.01880481094121933,
+    "eval_precision": 0.9928774928774929,
+    "eval_recall": 0.9925925925925926,
+    "eval_runtime": 3.5639,
+    "eval_samples_per_second": 37.88,
+    "eval_steps_per_second": 1.403,
+    "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,1.0,0.9666666666666667,0.9830508474576272,30.0
+Narra,0.967741935483871,1.0,0.9836065573770492,30.0
+Royal Palm,1.0,1.0,1.0,24.0
+Tabebuia,1.0,1.0,1.0,25.0
+accuracy,0.9925925925925926,0.9925925925925926,0.9925925925925926,0.9925925925925926
+macro avg,0.9935483870967742,0.9933333333333334,0.9933314809669354,135.0
+weighted avg,0.992831541218638,0.9925925925925926,0.9925905344077058,135.0

evaluation/confusion_matrix.csv

@@ -0,0 +1,6 @@
+,Ilang-ilang,Mango,Narra,Royal Palm,Tabebuia
+Ilang-ilang,26,0,0,0,0
+Mango,0,29,1,0,0
+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 16:30:50,524 - INFO - plot_confusion_matrix - Confusion Matrix:
+[[26  0  0  0  0]
+ [ 0 29  1  0  0]
+ [ 0  0 30  0  0]
+ [ 0  0  0 24  0]
+ [ 0  0  0  0 25]]
+2025-01-21 16:30:51,295 - INFO - plot_confusion_matrix - Confusion matrix saved to 2025-01-21-16-13-04-vit-base-patch16-224/evaluation/confusion_matrix.png
+2025-01-21 16:30:51,301 - INFO - plot_confusion_matrix - Confusion matrix report saved to 2025-01-21-16-13-04-vit-base-patch16-224/evaluation/confusion_matrix.csv
+2025-01-21 16:30:51,549 - INFO - classification_report_bar - Classification report saved to 2025-01-21-16-13-04-vit-base-patch16-224/evaluation/classification_report.csv
+2025-01-21 16:30:52,723 - INFO - classification_report_bar - Classification report bar chart saved to 2025-01-21-16-13-04-vit-base-patch16-224/evaluation/clf_bar.png
+2025-01-21 16:30:52,725 - INFO - classification_report_bar - Overall Accuracy: 0.993
+2025-01-21 16:30:53,985 - INFO - plot_classification_report_heatmap - Classification report heatmap saved to 2025-01-21-16-13-04-vit-base-patch16-224/classification_report.png
+2025-01-21 16:30:54,262 - INFO - plot_classification_report_heatmap - Classification report saved to 2025-01-21-16-13-04-vit-base-patch16-224/classification_report.csv
+2025-01-21 16:30:55,612 - INFO - plot_results - Training metrics saved to 2025-01-21-16-13-04-vit-base-patch16-224/training_metrics.csv

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde6ecd4f010fa385a9908eb33e58a179c8060fdd0fe778604ea3da56e030246
+size 343233204

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

test_results.json

@@ -0,0 +1,12 @@
+{
+    "test_accuracy": 0.9933333333333334,
+    "test_error_rate": 0.006666666666666599,
+    "test_f1": 0.9925905344077058,
+    "test_loss": 0.02411273680627346,
+    "test_precision": 0.992831541218638,
+    "test_recall": 0.9925925925925926,
+    "test_runtime": 3.4349,
+    "test_samples_per_second": 39.302,
+    "test_steps_per_second": 1.456,
+    "test_top1_accuracy": 0.9925925925925926
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "total_flos": 5.0216159448612864e+17,
+    "train_loss": 0.2055974360190186,
+    "train_runtime": 303.9865,
+    "train_samples_per_second": 35.528,
+    "train_steps_per_second": 1.118
+}

trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": 0.01880481094121933,
+  "best_model_checkpoint": "2025-01-21-16-13-04-vit-base-patch16-224/checkpoint-136",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "train_accuracy": 0.7324074074074074
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.5079495906829834,
+      "learning_rate": 0.0002,
+      "loss": 0.7465,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9365925925925925,
+      "eval_error_rate": 0.06340740740740747,
+      "eval_f1": 0.9400418302275843,
+      "eval_loss": 0.10922861099243164,
+      "eval_precision": 0.9535535535535536,
+      "eval_recall": 0.9407407407407408,
+      "eval_runtime": 3.1454,
+      "eval_samples_per_second": 42.919,
+      "eval_steps_per_second": 1.59,
+      "eval_top1_accuracy": 0.9407407407407408,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "train_accuracy": 0.9325102880658436
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.9865288734436035,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.212,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9048571428571428,
+      "eval_error_rate": 0.0951428571428572,
+      "eval_f1": 0.9061150336512657,
+      "eval_loss": 0.2753830850124359,
+      "eval_precision": 0.9337830687830687,
+      "eval_recall": 0.9111111111111111,
+      "eval_runtime": 3.3128,
+      "eval_samples_per_second": 40.752,
+      "eval_steps_per_second": 1.509,
+      "eval_top1_accuracy": 0.9111111111111111,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "train_accuracy": 0.9547325102880658
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 5.545481204986572,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.115,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.985103448275862,
+      "eval_error_rate": 0.014896551724137952,
+      "eval_f1": 0.9851769394626537,
+      "eval_loss": 0.05338314175605774,
+      "eval_precision": 0.9854497354497354,
+      "eval_recall": 0.9851851851851852,
+      "eval_runtime": 3.7379,
+      "eval_samples_per_second": 36.117,
+      "eval_steps_per_second": 1.338,
+      "eval_top1_accuracy": 0.9851851851851852,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "train_accuracy": 0.9794238683127572
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.0631272941827774,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.0723,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.993103448275862,
+      "eval_error_rate": 0.006896551724137945,
+      "eval_f1": 0.992600236975882,
+      "eval_loss": 0.01880481094121933,
+      "eval_precision": 0.9928774928774929,
+      "eval_recall": 0.9925925925925926,
+      "eval_runtime": 3.324,
+      "eval_samples_per_second": 40.614,
+      "eval_steps_per_second": 1.504,
+      "eval_top1_accuracy": 0.9925925925925926,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "train_accuracy": 0.9769547325102881
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.755014657974243,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.0716,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.992,
+      "eval_error_rate": 0.008000000000000007,
+      "eval_f1": 0.9925797814417668,
+      "eval_loss": 0.019506702199578285,
+      "eval_precision": 0.9928395061728394,
+      "eval_recall": 0.9925925925925926,
+      "eval_runtime": 3.2893,
+      "eval_samples_per_second": 41.043,
+      "eval_steps_per_second": 1.52,
+      "eval_top1_accuracy": 0.9925925925925926,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "train_accuracy": 0.9934156378600824
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.016526084393262863,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.0161,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9774928774928775,
+      "eval_error_rate": 0.0225071225071225,
+      "eval_f1": 0.9777679307755747,
+      "eval_loss": 0.038870733231306076,
+      "eval_precision": 0.979122085048011,
+      "eval_recall": 0.9777777777777777,
+      "eval_runtime": 3.6761,
+      "eval_samples_per_second": 36.724,
+      "eval_steps_per_second": 1.36,
+      "eval_top1_accuracy": 0.9777777777777777,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "step": 204,
+      "total_flos": 5.0216159448612864e+17,
+      "train_loss": 0.2055974360190186,
+      "train_runtime": 303.9865,
+      "train_samples_per_second": 35.528,
+      "train_steps_per_second": 1.118
+    }
+  ],
+  "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": 5.0216159448612864e+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 sha256:0128ddd46646ceb0e846500d094231136c9428d22b1098b0c6840a62d4abd11a
+size 5176

training_metrics.csv

@@ -0,0 +1,7 @@
+Epoch,Train Loss,Eval Loss,Train Accuracy,Eval Accuracy
+1,0.7465,0.10922861099243164,0.7324074074074074,0.9365925925925925
+2,0.212,0.2753830850124359,0.9325102880658436,0.9048571428571428
+3,0.115,0.05338314175605774,0.9547325102880658,0.985103448275862
+4,0.0723,0.01880481094121933,0.9794238683127572,0.993103448275862
+5,0.0716,0.019506702199578285,0.9769547325102881,0.992
+6,0.0161,0.038870733231306076,0.9934156378600824,0.9774928774928775