metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- recall
- precision
- accuracy
- f1
model-index:
- name: UBC-resnet-50-3eph-224
results: []
UBC-resnet-50-3eph-224
This model is a fine-tuned version of microsoft/resnet-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7999
- Recall: 0.6061
- Specificity: 0.8937
- Precision: 0.7089
- Npv: 0.9097
- Accuracy: 0.6860
- F1: 0.6373
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Recall | Specificity | Precision | Npv | Accuracy | F1 |
|---|---|---|---|---|---|---|---|---|---|
| 0.9759 | 1.0 | 6080 | 0.9368 | 0.5185 | 0.8740 | 0.6852 | 0.8972 | 0.6337 | 0.5423 |
| 0.8617 | 2.0 | 12160 | 0.8285 | 0.5921 | 0.8910 | 0.6964 | 0.9062 | 0.6757 | 0.6221 |
| 0.8362 | 3.0 | 18240 | 0.7999 | 0.6061 | 0.8937 | 0.7089 | 0.9097 | 0.6860 | 0.6373 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3