metadata
license: apache-2.0
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Train
results: []
Train
This model is a fine-tuned version of microsoft/resnet-101 on the TrashBox dataset. It achieves the following results on the evaluation set:
- Loss: 2.7726
- Accuracy: 0.4374
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: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.1529 | 0.13 | 100 | 3.2116 | 0.0590 |
| 3.1644 | 0.26 | 200 | 3.2096 | 0.0692 |
| 3.1549 | 0.39 | 300 | 3.1986 | 0.0692 |
| 3.2998 | 0.51 | 400 | 3.1968 | 0.1077 |
| 3.1344 | 0.64 | 500 | 3.1667 | 0.1718 |
| 3.3638 | 0.77 | 600 | 3.1384 | 0.1744 |
| 3.1482 | 0.9 | 700 | 3.0966 | 0.2026 |
| 3.1366 | 1.03 | 800 | 3.0484 | 0.1897 |
| 3.0206 | 1.16 | 900 | 3.0164 | 0.3026 |
| 2.921 | 1.29 | 1000 | 2.9846 | 0.3231 |
| 3.0027 | 1.41 | 1100 | 2.9338 | 0.3359 |
| 2.9047 | 1.54 | 1200 | 2.8917 | 0.3462 |
| 2.8579 | 1.67 | 1300 | 2.8616 | 0.4026 |
| 2.988 | 1.8 | 1400 | 2.7832 | 0.4077 |
| 2.8553 | 1.93 | 1500 | 2.8217 | 0.3872 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3