metadata
license: apache-2.0
base_model: NekoFi/portrait_cosu_exp4
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: portrait_cosu_exp5
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: 0.8611111111111112
- name: Precision
type: precision
value: 0.8760606060606061
- name: Recall
type: recall
value: 0.8611111111111112
- name: F1
type: f1
value: 0.8564659977703456
portrait_cosu_exp5
This model is a fine-tuned version of NekoFi/portrait_cosu_exp4 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2661
- Accuracy: 0.8611
- Precision: 0.8761
- Recall: 0.8611
- F1: 0.8565
- Confusion Matrix: [[41, 1], [9, 21]]
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Confusion Matrix |
|---|---|---|---|---|---|---|---|---|
| 0.4706 | 0.9756 | 10 | 0.6059 | 0.6667 | 0.7879 | 0.6667 | 0.5926 | [[42, 0], [24, 6]] |
| 0.3421 | 1.9512 | 20 | 0.4176 | 0.75 | 0.825 | 0.75 | 0.7185 | [[42, 0], [18, 12]] |
| 0.3131 | 2.9268 | 30 | 0.1941 | 0.9583 | 0.9621 | 0.9583 | 0.9586 | [[39, 3], [0, 30]] |
| 0.2716 | 3.9024 | 40 | 0.2661 | 0.8611 | 0.8761 | 0.8611 | 0.8565 | [[41, 1], [9, 21]] |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1