base_model: microsoft/Phi-3.5-mini-instruct
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

load_in_8bit: true
load_in_4bit: false

chat_template: phi_3
datasets:
  - path: fozziethebeat/alpaca_messages_2k_test
    type: chat_template
    field_messages: messages
    message_property_mappings:
      role: role
      content: content
    roles:
      user:
        - user
      assistant:
        - assistant

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/lora-out

sequence_len: 4096
sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

bfloat16: true
bf16: true
fp16:
tf32: false

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 4
weight_decay: 0.0