Files
axolotl/examples/llama-3/instruct-dpo-lora-8b.yml
2025-06-13 10:00:35 -04:00

74 lines
1.4 KiB
YAML

base_model: meta-llama/Meta-Llama-3-8B-Instruct
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name
special_tokens:
pad_token: <|finetune_right_pad_id|>
eos_token: <|eot_id|>
load_in_8bit: true
load_in_4bit: false
chat_template: llama3
rl: dpo
datasets:
- path: fozziethebeat/alpaca_messages_2k_dpo_test
type: chat_template.default
field_messages: conversation
field_chosen: chosen
field_rejected: rejected
message_property_mappings:
role: role
content: content
roles:
system:
- system
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: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
bf16: auto
tf32: false
gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true
warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0