vit-base-patch16-224-in21k-AdaLora

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-AdaLora
+  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-AdaLora
+
+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: 0.3684
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.8653        | 1.0   | 74   | 0.4922          |
+| 0.7453        | 2.0   | 148  | 0.4185          |
+| 0.6864        | 3.0   | 222  | 0.3936          |
+| 0.6402        | 4.0   | 296  | 0.3748          |
+| 0.6194        | 5.0   | 370  | 0.3684          |
+
+
+### 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 +1,43 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "PeftModel",
+    "parent_library": "peft.peft_model"
+  },
+  "base_model_name_or_path": null,
+  "beta1": 0.85,
+  "beta2": 0.85,
+  "bias": "none",
+  "deltaT": 10,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "init_r": 12,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier"
+  ],
+  "orth_reg_weight": 0.5,
+  "peft_type": "ADALORA",
+  "r": 8,
+  "rank_pattern": null,
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "target_r": 8,
+  "task_type": null,
+  "tfinal": 1000,
+  "tinit": 200,
+  "total_step": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d426ee5b04f14987b77651a005fa1cbd79900279533645a5e1f64f19ce8fcd
+size 2092636

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_11-15-25_cajal/events.out.tfevents.1725646528.cajal.58195.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68545b2aa6ba20962af923aab23e0921451bd5d2b089e355a47476d5e0a4f822
+size 16552

runs/Sep06_11-53-40_cajal/events.out.tfevents.1725648822.cajal.80564.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f44f3f0b23ae7ce0d07630f523a6ce9366c9c0822b7c69fb5486a116a81184
+size 19136

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172824942d5e327bf36647cd9e915c1ecce99a1221a6c7ab738d794ed51d14bf
+size 5240