graphormer-ogbg-molhiv

This model was trained from clefourrier/pcqm4mv2_graphormer_base on the OGB/ogbg-molhiv dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.0728
• eval_runtime: 464.6027
• eval_samples_per_second: 8.853
• eval_steps_per_second: 0.555
• step: 0

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: 0.0002
• train_batch_size: 512
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 10
• total_train_batch_size: 5120
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.0+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2