baseline-roberta_pre_layer_norm-model

Model description

Base Model Architecture: Roberta Pre-Layer Norm

Training and evaluation data

BabyLM Dataset (CoNLL 2023 Workshop)

Training procedure

Masked language modeling

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.001
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 128
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100000
• training_steps: 400000

Framework versions

• Transformers 4.26.1
• Pytorch 1.12.0+cu113
• Datasets 2.10.0
• Tokenizers 0.13.2