Model save

README.md

@@ -0,0 +1,82 @@
+---
+license: other
+base_model: nvidia/segformer-b0-finetuned-ade-512-512
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: segformer-original-5
+ results:
+ - task:
+ name: Image Classification
+ type: image-classification
+ dataset:
+ name: imagefolder
+ type: imagefolder
+ config: default
+ split: train
+ args: default
+ metrics:
+ - name: Accuracy
+ type: accuracy
+ value: 0.718299164768413
+---
+
+<!-- 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. -->
+
+# segformer-original-5
+
+This model is a fine-tuned version of [nvidia/segformer-b0-finetuned-ade-512-512](https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8862
+- Accuracy: 0.7183
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 5.8809 | 1.0 | 247 | 4.9508 | 0.0716 |
+| 4.6081 | 2.0 | 494 | 3.3703 | 0.3551 |
+| 3.4538 | 3.0 | 741 | 2.5005 | 0.5662 |
+| 3.0418 | 4.0 | 988 | 2.0606 | 0.6778 |
+| 2.7046 | 5.0 | 1235 | 1.8862 | 0.7183 |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu121
+- Datasets 3.0.0
+- Tokenizers 0.15.2