metadata
license: apache-2.0
base_model: facebook/convnextv2-tiny-1k-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: convnextv2-tiny-1k-224-finetuned-galaxy10-decals
results: []
convnextv2-tiny-1k-224-finetuned-galaxy10-decals
This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4169
- Accuracy: 0.8673
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|
| 1.0664 | 0.9978 | 112 | 0.9818 | 0.6725 |
| 0.8019 | 1.9955 | 224 | 0.6333 | 0.7990 |
| 0.6524 | 2.9933 | 336 | 0.5248 | 0.8341 |
| 0.6339 | 4.0 | 449 | 0.4731 | 0.8447 |
| 0.5178 | 4.9978 | 561 | 0.4537 | 0.8503 |
| 0.5907 | 5.9955 | 673 | 0.4556 | 0.8472 |
| 0.5292 | 6.9933 | 785 | 0.4169 | 0.8673 |
| 0.5017 | 8.0 | 898 | 0.4107 | 0.8597 |
| 0.4605 | 8.9978 | 1010 | 0.4062 | 0.8635 |
| 0.4765 | 9.9777 | 1120 | 0.3980 | 0.8647 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1