End of training

README.md

@@ -0,0 +1,97 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+datasets:
+- image_folder
+metrics:
+- accuracy
+- f1
+model-index:
+- name: All-Plants-18-Epochs-Model
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: image_folder
+      type: image_folder
+      config: Dataset
+      split: train
+      args: Dataset
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9847645429362881
+    - name: F1
+      type: f1
+      value: 0.984922643975302
+---
+
+<!-- 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. -->
+
+# All-Plants-18-Epochs-Model
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the image_folder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0888
+- Accuracy: 0.9848
+- F1: 0.9849
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 18
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 0.9212        | 1.0   | 407  | 0.3931          | 0.9501   | 0.9579 |
+| 0.2659        | 2.0   | 814  | 0.2176          | 0.9668   | 0.9674 |
+| 0.137         | 3.0   | 1221 | 0.1481          | 0.9723   | 0.9731 |
+| 0.0865        | 4.0   | 1628 | 0.1043          | 0.9834   | 0.9836 |
+| 0.0557        | 5.0   | 2035 | 0.0888          | 0.9848   | 0.9849 |
+| 0.0408        | 6.0   | 2442 | 0.0839          | 0.9848   | 0.9848 |
+| 0.0289        | 7.0   | 2849 | 0.0920          | 0.9848   | 0.9849 |
+| 0.0229        | 8.0   | 3256 | 0.0817          | 0.9834   | 0.9837 |
+| 0.0175        | 9.0   | 3663 | 0.0890          | 0.9820   | 0.9823 |
+| 0.0156        | 10.0  | 4070 | 0.0966          | 0.9820   | 0.9823 |
+| 0.0121        | 11.0  | 4477 | 0.0809          | 0.9834   | 0.9837 |
+| 0.0102        | 12.0  | 4884 | 0.0875          | 0.9820   | 0.9823 |
+| 0.0086        | 13.0  | 5291 | 0.0873          | 0.9820   | 0.9823 |
+| 0.0077        | 14.0  | 5698 | 0.0860          | 0.9820   | 0.9823 |
+| 0.0068        | 15.0  | 6105 | 0.0876          | 0.9820   | 0.9823 |
+| 0.0062        | 16.0  | 6512 | 0.0896          | 0.9820   | 0.9823 |
+| 0.0059        | 17.0  | 6919 | 0.0890          | 0.9820   | 0.9823 |
+| 0.0056        | 18.0  | 7326 | 0.0894          | 0.9820   | 0.9823 |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.14.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 18.0,
+    "total_flos": 9.063271672992682e+18,
+    "train_loss": 0.09193798999723893,
+    "train_runtime": 3856.2397,
+    "train_samples": 6497,
+    "train_samples_per_second": 30.326,
+    "train_steps_per_second": 1.9
+}

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8,
+    "9": 9,
+    "10": 10,
+    "11": 11,
+    "12": 12
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8,
+    "9": 9,
+    "10": 10,
+    "11": 11,
+    "12": 12
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61017cddaabac38949ed4bf7e4487f3d9c396436fd4d79ee79751dfa2b4a8844
+size 343257812

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
+  }
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 18.0,
+    "total_flos": 9.063271672992682e+18,
+    "train_loss": 0.09193798999723893,
+    "train_runtime": 3856.2397,
+    "train_samples": 6497,
+    "train_samples_per_second": 30.326,
+    "train_steps_per_second": 1.9
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:236709df6e7c2d41b5f210153b8d59be5675439ee07566a98e7d9d131ff4ecc5
+size 4091