---
license: gemma
tags:
- unsloth
- trl
- sft
---

Experiment 1 SFT ALPACA INDO

dataset: 9 millions token indo alpaca dataset

max_seq_length = 8192,
dataset_num_proc = 2,
packing = False, 
args = TrainingArguments(
    per_device_train_batch_size = 1,
    gradient_accumulation_steps = 8,
    warmup_steps = 5,
    num_train_epochs = 1,
    learning_rate = 5e-5,
    fp16 = not is_bfloat16_supported(),
    bf16 = is_bfloat16_supported(),
    logging_steps = 1,
    optim = "adamw_8bit",
    weight_decay = 0.01,
    lr_scheduler_type = "linear",
    seed = 3407,