distily_long_dataset_sweep / logs /dataset_split=train, dataset_subset=sample-10BT, dataset_uri=HuggingFaceFW_fineweb-edu, learning_rate=0.0002, lr_scheduler_type=constant_with_warmup, warmup_ratio=0

This model has 1 file scanned as suspicious.

lapp0's picture
Training in progress, step 5000
bd6b980 verified