End of training

README.md

@@ -0,0 +1,87 @@
+---
+license: other
+base_model: nvidia/mit-b0
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: architectural_styles_classifier
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7
+---
+
+<!-- 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. -->
+
+# architectural_styles_classifier
+
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0025
+- Accuracy: 0.7
+
+## 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: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-05
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.9827        | 1.0   | 442  | 1.8651          | 0.4065   |
+| 1.7182        | 2.0   | 884  | 1.6669          | 0.4501   |
+| 1.505         | 3.0   | 1326 | 1.4498          | 0.5246   |
+| 1.1271        | 4.0   | 1768 | 1.3259          | 0.5846   |
+| 1.1128        | 5.0   | 2210 | 1.2216          | 0.6045   |
+| 1.1869        | 6.0   | 2652 | 1.1650          | 0.6372   |
+| 1.0578        | 7.0   | 3094 | 1.1305          | 0.6447   |
+| 0.7803        | 8.0   | 3536 | 1.0496          | 0.6739   |
+| 0.7118        | 9.0   | 3978 | 1.0651          | 0.6958   |
+| 0.4558        | 10.0  | 4420 | 1.0164          | 0.6998   |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1