znhoughton/opt-babylm-350m-20eps-seed964

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

opt-babylm-350m-20eps-prenorm-seed964

This model was trained from scratch on the znhoughton/babylm-150m-v3 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: 0.00015
• —trainbatchsize: 50
• —evalbatchsize: 8
• —seed: 964
• —distributed_type: multi-GPU
• —num_devices: 4
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 400
• —totalevalbatch_size: 32
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 732
• —num_epochs: 20.0

Training results

Framework versions

• —Transformers 4.46.3
• —Pytorch 2.4.1+cu124
• —Datasets 3.1.0
• —Tokenizers 0.20.3