distilroberta-base-wiki-mark

This model is a fine-tuned version of yochen/distilroberta-base-wiki-mark on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.2695
• eval_runtime: 4.3489
• eval_samples_per_second: 431.836
• eval_steps_per_second: 54.037
• epoch: 10.1
• step: 20489

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: 5000

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.0+cu102
• Datasets 2.3.2
• Tokenizers 0.12.1