tta1301/xray-vit-classifier-v3

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+model-index:
+- name: xray-classifier
+  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. -->
+
+# xray-classifier
+
+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: 0.0066
+- Auc Macro: nan
+
+## 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: 32
+- eval_batch_size: 32
+- 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
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Auc Macro |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|
+| 0.0347        | 1.0   | 136  | 0.0178          | nan       |
+| 0.0124        | 2.0   | 272  | 0.0108          | nan       |
+| 0.0086        | 3.0   | 408  | 0.0081          | nan       |
+| 0.0074        | 4.0   | 544  | 0.0069          | nan       |
+| 0.0066        | 5.0   | 680  | 0.0065          | nan       |
+
+
+### Framework versions
+
+- Transformers 5.0.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "dtype": "float32",
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Atelectasis",
+    "1": "Cardiomegaly",
+    "2": "Consolidation",
+    "3": "Edema",
+    "4": "Effusion",
+    "5": "Emphysema",
+    "6": "Fibrosis",
+    "7": "Hernia",
+    "8": "Infiltration",
+    "9": "Mass",
+    "10": "No Finding",
+    "11": "Nodule",
+    "12": "Pleural_Thickening",
+    "13": "Pneumonia",
+    "14": "Pneumothorax"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Atelectasis": 0,
+    "Cardiomegaly": 1,
+    "Consolidation": 2,
+    "Edema": 3,
+    "Effusion": 4,
+    "Emphysema": 5,
+    "Fibrosis": 6,
+    "Hernia": 7,
+    "Infiltration": 8,
+    "Mass": 9,
+    "No Finding": 10,
+    "Nodule": 11,
+    "Pleural_Thickening": 12,
+    "Pneumonia": 13,
+    "Pneumothorax": 14
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "qkv_bias": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7cfa110a329aee6254b95b38eeb0b7fe5aaa85b4a9e41834f8754bcc960d5c2
+size 343263964

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a3ce2f35a853d005a30bc410de965307151c16e595030918a1f55041d159c8
+size 5201