<!-- 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. -->
mobilenet_v2_1.0_224-finetuned-32bs-0.1lr
This model is a fine-tuned version of google/mobilenet_v2_1.0_224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.9270
- Accuracy: 0.6469
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: 0.1
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.99 | 53 | 1.3949 | 0.4049 |
| No log | 1.99 | 107 | 1.0455 | 0.5819 |
| No log | 2.96 | 159 | 0.9270 | 0.6469 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
