Model save

README.md

@@ -2,8 +2,6 @@
 base_model: google/vit-base-patch16-224-in21k
 library_name: peft
 license: apache-2.0
-metrics:
-- accuracy
 tags:
 - generated_from_trainer
 model-index:
@@ -14,16 +12,11 @@ model-index:
 <!-- 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. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sajjadi/Fast-PEFT/runs/96k6jbqw)
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sajjadi/Fast-PEFT/runs/96k6jbqw)
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sajjadi/Fast-PEFT/runs/96k6jbqw)
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sajjadi/Fast-PEFT/runs/96k6jbqw)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sajjadi/Fast-PEFT/runs/a5xjqfdt)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sajjadi/Fast-PEFT/runs/a5xjqfdt)
 # 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: 2.8427
-- Accuracy: 0.8389
 
 ## Model description
 
@@ -42,29 +35,17 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.005
+- learning_rate: 0.002
 - train_batch_size: 256
 - eval_batch_size: 256
 - seed: 42
-- gradient_accumulation_steps: 100
-- total_train_batch_size: 25600
+- 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: 10
+- num_epochs: 100
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 4.6217        | 0.5102 | 1    | 4.3498          | 0.4605   |
-| 4.1682        | 1.5306 | 3    | 3.8653          | 0.7667   |
-| 3.7481        | 2.5510 | 5    | 3.4273          | 0.8061   |
-| 3.3953        | 3.5714 | 7    | 3.0890          | 0.8274   |
-| 3.1465        | 4.5918 | 9    | 2.8856          | 0.838    |
-| 3.0693        | 5.1020 | 10   | 2.8427          | 0.8389   |
-
-
 ### Framework versions
 
 - PEFT 0.13.0

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f206f353751ffef1d226e1abd2ef765604ef2a3aa93698ace5b8f46ed15881
+oid sha256:e9e124abed4fdc44e093604e58d24117cfe0ef3391f8329420124b6edb56b8bd
 size 606152