metadata
license: apache-2.0
base_model: facebook/convnextv2-tiny-22k-384
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: convnextv2-tiny-22k-384-finetuned-spiderTraining50-2000
results: []
convnextv2-tiny-22k-384-finetuned-spiderTraining50-2000
This model is a fine-tuned version of facebook/convnextv2-tiny-22k-384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2220
- Accuracy: 0.9353
- Precision: 0.9355
- Recall: 0.9353
- F1: 0.9352
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.7311 | 1.0 | 1250 | 0.4761 | 0.8637 | 0.8682 | 0.8637 | 0.8637 |
| 0.5924 | 2.0 | 2500 | 0.3177 | 0.9084 | 0.9108 | 0.9087 | 0.9087 |
| 0.4035 | 3.0 | 3750 | 0.2668 | 0.9200 | 0.9211 | 0.9202 | 0.9198 |
| 0.4343 | 4.0 | 5000 | 0.2395 | 0.9290 | 0.9302 | 0.9289 | 0.9290 |
| 0.381 | 5.0 | 6250 | 0.2220 | 0.9353 | 0.9355 | 0.9353 | 0.9352 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3