🍻 cheers

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- image-classification
+- generated_from_trainer
+metrics:
+- accuracy
+base_model: google/vit-base-patch16-224-in21k
+model-index:
+- name: ViTLoRA-beans
+  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. -->
+
+# ViTLoRA-beans
+
+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 beans dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2620
+- Accuracy: 0.9549
+
+## 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: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.566         | 1.54  | 100  | 0.5027          | 0.9098   |
+| 0.2574        | 3.08  | 200  | 0.2620          | 0.9549   |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9548872180451128,
+    "eval_loss": 0.2619759738445282,
+    "eval_runtime": 3.1766,
+    "eval_samples_per_second": 41.869,
+    "eval_steps_per_second": 5.352,
+    "total_flos": 3.227216486845317e+17,
+    "train_loss": 0.5290748504491952,
+    "train_runtime": 97.5818,
+    "train_samples_per_second": 42.385,
+    "train_steps_per_second": 2.664
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9548872180451128,
+    "eval_loss": 0.2619759738445282,
+    "eval_runtime": 3.1766,
+    "eval_samples_per_second": 41.869,
+    "eval_steps_per_second": 5.352
+}

runs/Feb28_07-13-58_f11bcd49362a/events.out.tfevents.1709104532.f11bcd49362a.704.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da90a3142e0c52267254da131f05b5e23ddc0c5992495b75b71d58055a1a68c4
-size 8167
+oid sha256:032395802263b7b32026aef016266a34e8432c6d92087b10169c8bade5d3ca53
+size 9463

runs/Feb28_07-13-58_f11bcd49362a/events.out.tfevents.1709104696.f11bcd49362a.704.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a2e42182b8272f5673383aafadca24513bf61182efb0329ecc67a7db0ba6cd
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 3.227216486845317e+17,
+    "train_loss": 0.5290748504491952,
+    "train_runtime": 97.5818,
+    "train_samples_per_second": 42.385,
+    "train_steps_per_second": 2.664
+}