Training in progress, epoch 0

README.md

@@ -2,6 +2,8 @@
 base_model: google/vit-base-patch16-224-in21k
 library_name: peft
 license: apache-2.0
+metrics:
+- accuracy
 tags:
 - generated_from_trainer
 model-index:
@@ -15,6 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 # vit-base-patch16-224-in21k-finetuned-lora-food101
 
 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: 0.2481
+- Accuracy: 0.9279
 
 ## Model description
 
@@ -34,21 +39,30 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.005
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 168
+- eval_batch_size: 168
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 64
+- total_train_batch_size: 672
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 1    | 4.6952          | 0.0      |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.8568        | 0.9933 | 74   | 0.3500          | 0.8978   |
+| 0.7674        | 2.0    | 149  | 0.3065          | 0.9089   |
+| 0.724         | 2.9933 | 223  | 0.2805          | 0.9164   |
+| 0.6316        | 4.0    | 298  | 0.2725          | 0.9197   |
+| 0.6462        | 4.9933 | 372  | 0.2659          | 0.9195   |
+| 0.5809        | 6.0    | 447  | 0.2623          | 0.9223   |
+| 0.5212        | 6.9933 | 521  | 0.2624          | 0.9217   |
+| 0.5561        | 8.0    | 596  | 0.2523          | 0.9259   |
+| 0.5061        | 8.9933 | 670  | 0.2502          | 0.9268   |
+| 0.4955        | 9.9329 | 740  | 0.2481          | 0.9279   |
 
 
 ### Framework versions

adapter_config.json

@@ -21,7 +21,7 @@
     "classifier"
   ],
   "peft_type": "LORA",
-  "r": 1,
+  "r": 3,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a8707eb6e59e4e4edfea91dfc2917d7500b6c15db552493239fa5df8cab54f9
-size 384968
+oid sha256:56789546fdb6023a143c07d38ee5f6d4bcf7ad89ce568f2dbf76d5ffa2344330
+size 532424

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0baf7def2b62c05bab251a353dd34922eb47fa36235bd217fc597dd6930c23a
+oid sha256:bfcb1f59566c364a2fdaba80322f1d152b06f46c17c2d2a126256dc5cf4c018d
 size 5304