metadata
library_name: transformers
license: apache-2.0
base_model: facebook/convnext-tiny-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: convnext-tiny-224-afinaopalcaxarro
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: 0.8623853211009175
convnext-tiny-224-afinaopalcaxarro
This model is a fine-tuned version of facebook/convnext-tiny-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7981
- Accuracy: 0.8624
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 8 | 2.2682 | 0.3383 |
| 2.3684 | 2.0 | 16 | 1.9344 | 0.6869 |
| 2.0258 | 3.0 | 24 | 1.6364 | 0.7901 |
| 1.6828 | 4.0 | 32 | 1.3840 | 0.8165 |
| 1.3866 | 5.0 | 40 | 1.1854 | 0.8222 |
| 1.3866 | 6.0 | 48 | 1.0353 | 0.8337 |
| 1.1679 | 7.0 | 56 | 0.9255 | 0.8521 |
| 1.021 | 8.0 | 64 | 0.8538 | 0.8567 |
| 0.9338 | 9.0 | 72 | 0.8123 | 0.8612 |
| 0.8718 | 10.0 | 80 | 0.7981 | 0.8624 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1