metadata
library_name: transformers
base_model: RobertZ2011/resnet-18-birb
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: classbird_1
results: []
classbird_1
This model is a fine-tuned version of RobertZ2011/resnet-18-birb on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0949
- Accuracy: 0.7726
- Precision: 0.7789
- Recall: 0.7726
- F1: 0.7680
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 2.5479 | 1.0 | 29 | 2.2789 | 0.2946 | 0.3112 | 0.2946 | 0.2571 |
| 1.9716 | 2.0 | 58 | 1.9112 | 0.4651 | 0.5401 | 0.4651 | 0.4270 |
| 1.506 | 3.0 | 87 | 1.6503 | 0.6202 | 0.6831 | 0.6202 | 0.5933 |
| 1.1838 | 4.0 | 116 | 1.4594 | 0.6667 | 0.6855 | 0.6667 | 0.6439 |
| 0.9704 | 5.0 | 145 | 1.3127 | 0.7183 | 0.7395 | 0.7183 | 0.7064 |
| 0.7997 | 6.0 | 174 | 1.2345 | 0.7468 | 0.7586 | 0.7468 | 0.7410 |
| 0.763 | 7.0 | 203 | 1.1520 | 0.7442 | 0.7493 | 0.7442 | 0.7332 |
| 0.6448 | 8.0 | 232 | 1.1172 | 0.7597 | 0.7745 | 0.7597 | 0.7531 |
| 0.5839 | 9.0 | 261 | 1.0984 | 0.7649 | 0.7753 | 0.7649 | 0.7621 |
| 0.5993 | 10.0 | 290 | 1.0949 | 0.7726 | 0.7789 | 0.7726 | 0.7680 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1