stereoset_trainer_roberta-base_finetuned

This model is a fine-tuned version of roberta-base on the stereoset dataset. It achieves the following results on the evaluation set:

• Loss: 0.5749
• Accuracy: 0.7535

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.54	50	0.6919	0.5157
No log	1.08	100	0.6944	0.4843
No log	1.61	150	0.6275	0.6664
No log	2.15	200	0.5548	0.7355
No log	2.69	250	0.5613	0.7331
No log	3.23	300	0.6062	0.7331
No log	3.76	350	0.5455	0.7488
No log	4.3	400	0.6223	0.7488
No log	4.84	450	0.5749	0.7535

Framework versions

• Transformers 4.23.1
• Pytorch 1.12.1
• Datasets 2.6.1
• Tokenizers 0.13.1