Settings
training_args = transformers.TrainingArguments( auto_find_batch_size=True, gradient_accumulation_steps=4, num_train_epochs=1, learning_rate=2e-4, fp16=True, save_total_limit=3, logging_steps=1, max_steps=80, output_dir="/home/gguells/finetuning/apoc/", save_strategy='epoch', optim="paged_adamw_8bit", lr_scheduler_type = 'cosine', warmup_ratio = 0.05, )
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support