vit-base-patch16-224-in21k-lora

README.md

@@ -0,0 +1,66 @@
+---
+base_model: google/vit-base-patch16-224-in21k
+library_name: peft
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: vit-base-patch16-224-in21k-lora
+  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-lora
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3400
+
+## 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: 256
+- eval_batch_size: 256
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 1024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.8448        | 1.0   | 74   | 0.4689          |
+| 0.7281        | 2.0   | 148  | 0.4009          |
+| 0.6533        | 3.0   | 222  | 0.3697          |
+| 0.5799        | 4.0   | 296  | 0.3520          |
+| 0.5547        | 5.0   | 370  | 0.3400          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.43.4
+- Pytorch 2.2.1+cu118
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "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",
+  "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_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": [
+    "query",
+    "value"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198968268a45e42f097f1fd33a660ab40ac8e588aef5100a7e78324cd38f9528
+size 2677140

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
+  }
+}

runs/Sep06_07-33-25_cajal/events.out.tfevents.1725633249.cajal.58195.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7cfa5d62ca640cb09b823246556a8b1df2ae6ac0ed7463be386078417d5b704
+size 19160

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b58cc9367fd38e667ff5fb9b92217f42723e8e94dca481ac847e79d1ffb003
+size 5240