6aa41740df
* utilize accelerate prepare_data_loader with patching * lint * cleanup, fix * update to support DPO quirk * small change * coderabbit commits, cleanup, remove dead code * quarto fix * patch fix * review comments * moving monkeypatch up one level * fix
57 lines
1.0 KiB
YAML
57 lines
1.0 KiB
YAML
base_model: Qwen/Qwen2.5-0.5B
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
chat_template: qwen_25
|
|
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: 0.0
|
|
output_dir: ./outputs/dpo-out
|
|
|
|
sequence_len: 2048
|
|
sample_packing: false
|
|
pad_to_sequence_len: 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
|