opt-babylm-1.3b-ablated-20eps-seed964

This model was trained from scratch on the znhoughton/babylm-150m-ablated 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: 125
• eval_batch_size: 8
• seed: 964
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 1000
• 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: 293
• num_epochs: 20.0

Training results

Framework versions

• Transformers 4.40.2
• Pytorch 2.4.1+cu124
• Datasets 2.19.1
• Tokenizers 0.19.1