WOOL_CLASS_V2_trainer

README.md

@@ -0,0 +1,98 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-large-patch16-224
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: wool-classifier-finetuned
+  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: 0.7777777777777778
+    - name: F1
+      type: f1
+      value: 0.7681561135293505
+    - name: Precision
+      type: precision
+      value: 0.7982514741774002
+    - name: Recall
+      type: recall
+      value: 0.7777777777777778
+---
+
+<!-- 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. -->
+
+# wool-classifier-finetuned
+
+This model is a fine-tuned version of [google/vit-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6767
+- Accuracy: 0.7778
+- F1: 0.7682
+- Precision: 0.7983
+- Recall: 0.7778
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.7426        | 1.0   | 45   | 0.7618          | 0.7284   | 0.7285 | 0.7981    | 0.7284 |
+| 0.6744        | 2.0   | 90   | 0.8640          | 0.7284   | 0.7064 | 0.7190    | 0.7284 |
+| 0.4237        | 3.0   | 135  | 0.6118          | 0.8148   | 0.8115 | 0.8309    | 0.8148 |
+| 0.473         | 4.0   | 180  | 0.6418          | 0.8025   | 0.7843 | 0.8481    | 0.8025 |
+| 0.3436        | 5.0   | 225  | 0.4420          | 0.8765   | 0.8606 | 0.8928    | 0.8765 |
+| 0.2142        | 6.0   | 270  | 0.7575          | 0.7654   | 0.7508 | 0.8080    | 0.7654 |
+| 0.2729        | 7.0   | 315  | 0.6660          | 0.7901   | 0.7768 | 0.8183    | 0.7901 |
+| 0.3112        | 8.0   | 360  | 0.6767          | 0.7778   | 0.7682 | 0.7983    | 0.7778 |
+
+
+### Framework versions
+
+- Transformers 4.55.4
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.21.4

config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "CHECK - V",
+    "1": "GESSATI - V",
+    "2": "MICRO EFFETTI - V",
+    "3": "PIED DE POULE - V",
+    "4": "PRINCIPE DI GALLES - V",
+    "5": "QUADRETTO - V",
+    "6": "SPIGA - V",
+    "7": "UNITI"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "CHECK - V": 0,
+    "GESSATI - V": 1,
+    "MICRO EFFETTI - V": 2,
+    "PIED DE POULE - V": 3,
+    "PRINCIPE DI GALLES - V": 4,
+    "QUADRETTO - V": 5,
+    "SPIGA - V": 6,
+    "UNITI": 7
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 1024,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a330ebf1ba183a3bd45fcb08fd9c816d98243414af626211a3e01b769f7f9d21
+size 1213285872

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cce01b44f9423c878a2978b36c06702fdbb07aebe1c0c393103497f91449052
+size 5713