distilroberta-base-finetuned-wikitext2

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

• Loss: 1.9194

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	39	2.1213
No log	2.0	78	1.9117
No log	3.0	117	1.9746
No log	4.0	156	1.9057
No log	5.0	195	1.7525
No log	6.0	234	1.7729
No log	7.0	273	2.0119
No log	8.0	312	1.7356
No log	9.0	351	2.0164
No log	10.0	390	1.8370

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3