Edit model card

2023MLMA_LAB9_task5

This model is a fine-tuned version of yujie07/2023MLMA_LAB9_task2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1449
  • Precision: 0.5578
  • Recall: 0.5875
  • F1: 0.5723
  • Accuracy: 0.9525

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.2325 1.0 591 0.1697 0.5117 0.4192 0.4608 0.9418
0.151 2.0 1182 0.1448 0.5302 0.5765 0.5524 0.9503
0.1139 3.0 1773 0.1449 0.5578 0.5875 0.5723 0.9525

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.11.0
  • Tokenizers 0.13.3
Downloads last month
2