roberta-large-houlsby-few-shot-k-32-finetuned-squad-seed-2

This model is a fine-tuned version of roberta-large on the squad dataset.

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 128
• seed: 2
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 128
• total_eval_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 75

Training results

Framework versions

• Transformers 4.17.0
• Pytorch 1.11.0+cu113
• Datasets 2.0.0
• Tokenizers 0.11.6