521e62daf1
* remove the bos token from dpo outputs * don't forget to fix prompt_input_ids too * use processing_class instead of tokenizer * fix for processing class
68 lines
1.1 KiB
YAML
68 lines
1.1 KiB
YAML
base_model: Qwen/Qwen2.5-0.5B
|
|
|
|
strict: false
|
|
|
|
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_field_role: role
|
|
message_field_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
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: auto
|
|
fp16:
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch: 4
|
|
eval_table_size:
|
|
eval_max_new_tokens: 128
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|