convnextv2-tiny-22k-384-finetuned-spiderTraining5-2000

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: 0.0553
  • Accuracy: 0.9800
  • Precision: 0.9799
  • Recall: 0.9798
  • F1: 0.9798

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
0.1834 1.0 125 0.1125 0.9630 0.9646 0.9618 0.9628
0.1419 2.0 250 0.0716 0.9780 0.9783 0.9775 0.9779
0.1279 3.0 375 0.0678 0.9780 0.9778 0.9777 0.9777
0.0901 4.0 500 0.0538 0.9800 0.9799 0.9798 0.9798
0.0804 5.0 625 0.0553 0.9800 0.9799 0.9798 0.9798

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
9
Inference API
Unable to determine this model's library. Check the docs .

Model tree for zkdeng/convnextv2-tiny-22k-384-finetuned-spiderTraining5-2000

Finetuned
(39)
this model