Model save

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: vit-dropout-0.4
+  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-dropout-0.4
+
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5599
+- Accuracy: 0.8752
+- Precision: 0.8758
+- Recall: 0.8752
+- F1: 0.8746
+
+## 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: 0.0001
+- 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: cosine
+- lr_scheduler_warmup_steps: 353
+- num_epochs: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 1.5638        | 1.0   | 321  | 0.9171          | 0.6259   | 0.7843    | 0.6259 | 0.6635 |
+| 1.1092        | 2.0   | 642  | 0.7739          | 0.7008   | 0.7903    | 0.7008 | 0.7193 |
+| 0.9892        | 3.0   | 963  | 0.6146          | 0.7781   | 0.7904    | 0.7781 | 0.7784 |
+| 0.8735        | 4.0   | 1284 | 0.6262          | 0.7455   | 0.8075    | 0.7455 | 0.7616 |
+| 0.8118        | 5.0   | 1605 | 0.7256          | 0.7164   | 0.8185    | 0.7164 | 0.7311 |
+| 0.7794        | 6.0   | 1926 | 0.6088          | 0.7819   | 0.8201    | 0.7819 | 0.7925 |
+| 0.6835        | 7.0   | 2247 | 0.5835          | 0.7625   | 0.8170    | 0.7625 | 0.7783 |
+| 0.5997        | 8.0   | 2568 | 0.6476          | 0.7653   | 0.8264    | 0.7653 | 0.7821 |
+| 0.5814        | 9.0   | 2889 | 0.4953          | 0.8402   | 0.8424    | 0.8402 | 0.8404 |
+| 0.5134        | 10.0  | 3210 | 0.5335          | 0.8103   | 0.8534    | 0.8103 | 0.8220 |
+| 0.5109        | 11.0  | 3531 | 0.5497          | 0.8124   | 0.8415    | 0.8124 | 0.8192 |
+| 0.4073        | 12.0  | 3852 | 0.5754          | 0.8311   | 0.8348    | 0.8311 | 0.8316 |
+| 0.3255        | 13.0  | 4173 | 0.5594          | 0.8575   | 0.8621    | 0.8575 | 0.8526 |
+| 0.3288        | 14.0  | 4494 | 0.6330          | 0.8332   | 0.8607    | 0.8332 | 0.8402 |
+| 0.2434        | 15.0  | 4815 | 0.5199          | 0.8606   | 0.8646    | 0.8606 | 0.8619 |
+| 0.2185        | 16.0  | 5136 | 0.5325          | 0.8589   | 0.8647    | 0.8589 | 0.8605 |
+| 0.1707        | 17.0  | 5457 | 0.5524          | 0.8641   | 0.8639    | 0.8641 | 0.8598 |
+| 0.1702        | 18.0  | 5778 | 0.5472          | 0.8523   | 0.8612    | 0.8523 | 0.8552 |
+| 0.128         | 19.0  | 6099 | 0.5599          | 0.8752   | 0.8758    | 0.8752 | 0.8746 |
+
+
+### Framework versions
+
+- Transformers 4.40.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e75f95ff15b62f09ecddd1e35c7f230608d6937931d1347a99f6a2d37ee785
+oid sha256:e3c82375dad990f3640bccd92d6a161ad1c9a403165cd814a8ea0f987a1ffb52
 size 343239356