numbered 1k testing runs
Collection
22 items
•
Updated
YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
warmup_steps = 5,
num_train_epochs = 3,
learning_rate = 5e-5,
optim = 'adamw_torch', #"adamw_8bit",
gradient_accumulation_steps = 4,
weight_decay = 0.03, #L2 reg
lr_scheduler_type = "linear",
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support