Training complete for fold 8. Best accuracy: 0.9763

README.md

@@ -0,0 +1,82 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+datasets:
+- medmnist-v2
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: vit-base-patch16-224-in21k-bloodmnist-fold-8
+  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. -->
+
+# vit-base-patch16-224-in21k-bloodmnist-fold-8
+
+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 medmnist-v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0810
+- Accuracy: 0.9763
+- Precision: 0.9753
+- Recall: 0.9758
+- F1: 0.9754
+
+## 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: 0.005
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.478         | 1.0   | 196  | 0.2420          | 0.9140   | 0.9007    | 0.9087 | 0.8994 |
+| 0.3796        | 2.0   | 392  | 0.2008          | 0.9271   | 0.9211    | 0.9354 | 0.9225 |
+| 0.2443        | 3.0   | 588  | 0.1970          | 0.9359   | 0.9236    | 0.9235 | 0.9216 |
+| 0.3441        | 4.0   | 784  | 0.2070          | 0.9359   | 0.9267    | 0.9406 | 0.9320 |
+| 0.2523        | 5.0   | 980  | 0.1415          | 0.9517   | 0.9453    | 0.9502 | 0.9471 |
+| 0.2062        | 6.0   | 1176 | 0.1345          | 0.9561   | 0.9510    | 0.9495 | 0.9492 |
+| 0.2034        | 7.0   | 1372 | 0.1323          | 0.9535   | 0.9575    | 0.9420 | 0.9473 |
+| 0.1798        | 8.0   | 1568 | 0.0902          | 0.9675   | 0.9629    | 0.9652 | 0.9639 |
+| 0.1539        | 9.0   | 1764 | 0.0943          | 0.9684   | 0.9640    | 0.9705 | 0.9669 |
+| 0.1262        | 10.0  | 1960 | 0.0810          | 0.9763   | 0.9753    | 0.9758 | 0.9754 |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.2

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "ViTForImageClassification",
+    "parent_library": "transformers.models.vit.modeling_vit"
+  },
+  "base_model_name_or_path": "google/vit-base-patch16-224-in21k",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value",
+    "query"
+  ],
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:574ffbe028d082fb607e76bfb12387988c68a38bd701b851c2dd826975a842b6
+size 2391056

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 sha256:336af24c35808d7e3023f30a0a8b424840003f366ea5decfe69ac562011e4fd9
+size 5496