convnextv2-tiny-22k-384-0.0005-finetuned-spiderTraining20-500
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: 0.1840
- Accuracy: 0.9439
- Precision: 0.9448
- Recall: 0.9411
- F1: 0.9424
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: 0.0005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- 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 |
|---|---|---|---|---|---|---|---|
| 0.934 | 1.0 | 125 | 0.6076 | 0.8118 | 0.8237 | 0.8060 | 0.8064 |
| 0.5826 | 2.0 | 250 | 0.4684 | 0.8529 | 0.8685 | 0.8506 | 0.8436 |
| 0.4743 | 3.0 | 375 | 0.3240 | 0.9059 | 0.9083 | 0.9006 | 0.9023 |
| 0.3488 | 4.0 | 500 | 0.2431 | 0.9369 | 0.9345 | 0.9348 | 0.9335 |
| 0.2307 | 5.0 | 625 | 0.1840 | 0.9439 | 0.9448 | 0.9411 | 0.9424 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3