Edit model card

trained_model_distilbert_0305

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5584
  • Accuracy: 0.8158

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 57 0.8234 0.6930
No log 2.0 114 0.7279 0.6930
No log 3.0 171 0.5902 0.7675
No log 4.0 228 0.5336 0.7632
No log 5.0 285 0.5117 0.7851
No log 6.0 342 0.5355 0.7807
No log 7.0 399 0.5005 0.8333
No log 8.0 456 0.5282 0.8289
0.4628 9.0 513 0.5481 0.8333
0.4628 10.0 570 0.5584 0.8158

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
67M params
Tensor type
F32
·

Finetuned from