roberta-base-finetuned-swag

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

• Loss: 0.4382
• Accuracy: 0.8390

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: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: IPU
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 40
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• training precision: Mixed Precision

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5707	1.0	574	0.4990	0.8097
0.5092	2.0	1148	0.4321	0.8361
0.3597	3.0	1722	0.4382	0.8390

Framework versions

• Transformers 4.20.1
• Pytorch 1.10.0+cpu
• Datasets 2.7.1
• Tokenizers 0.12.1