DPO cleanup (#1126)
* cleanup dpo to be a little more extensible, add zephyr/nectar strategy * fix eos slash * support for eval split * fix kwargs * handle empty evals * don't load peft model for dpo * ensure dpo traning args gets bf16 for peft if applicable * fix duplicate kwargs for bf16 * make sure to respect the configured lr scheduler * supprt trainer callback to push config to wandb * set dataloader preload args * ensure that we are loading the lora when merging * Update src/axolotl/utils/data.py Co-authored-by: Agus <agustin.piqueres@gmail.com> * support local datasets for dpo Co-authored-by: Agus <agustin.piqueres@gmail.com> * chore: lint * dpo/kto/ipo smoke tests w lora, simplify dpo dataset type names * add split to dpo tests * fix rebase/merging error * handle edge case w logging * use accelerator for dpo datasets so it doesn't break the logger * missing args * validate checkpoint is an adapter for now * log warning when dataset strategy is not loadable --------- Co-authored-by: Agus <agustin.piqueres@gmail.com>
This commit is contained in:
Wing Lian
GitHub
157
tests/e2e/test_dpo.py
Normal file
157
tests/e2e/test_dpo.py
Normal file
@@ -0,0 +1,157 @@
|
||||
"""
|
||||
E2E tests for lora llama
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from axolotl.cli import load_rl_datasets
|
||||
from axolotl.common.cli import TrainerCliArgs
|
||||
from axolotl.train import train
|
||||
from axolotl.utils.config import normalize_config
|
||||
from axolotl.utils.dict import DictDefault
|
||||
|
||||
from .utils import with_temp_dir
|
||||
|
||||
LOG = logging.getLogger("axolotl.tests.e2e")
|
||||
os.environ["WANDB_DISABLED"] = "true"
|
||||
|
||||
|
||||
class TestDPOLlamaLora(unittest.TestCase):
|
||||
"""
|
||||
Test case for DPO Llama models using LoRA
|
||||
"""
|
||||
|
||||
@with_temp_dir
|
||||
def test_dpo_lora(self, temp_dir):
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "JackFram/llama-68m",
|
||||
"tokenizer_type": "LlamaTokenizer",
|
||||
"sequence_len": 1024,
|
||||
"load_in_8bit": True,
|
||||
"adapter": "lora",
|
||||
"lora_r": 64,
|
||||
"lora_alpha": 32,
|
||||
"lora_dropout": 0.1,
|
||||
"lora_target_linear": True,
|
||||
"special_tokens": {},
|
||||
"rl": "dpo",
|
||||
"datasets": [
|
||||
{
|
||||
"path": "Intel/orca_dpo_pairs",
|
||||
"type": "chatml.intel",
|
||||
"split": "train",
|
||||
},
|
||||
],
|
||||
"num_epochs": 1,
|
||||
"micro_batch_size": 4,
|
||||
"gradient_accumulation_steps": 1,
|
||||
"output_dir": temp_dir,
|
||||
"learning_rate": 0.00001,
|
||||
"optimizer": "paged_adamw_8bit",
|
||||
"lr_scheduler": "cosine",
|
||||
"max_steps": 20,
|
||||
"save_steps": 10,
|
||||
"warmup_steps": 5,
|
||||
"gradient_checkpointing": True,
|
||||
"gradient_checkpointing_kwargs": {"use_reentrant": True},
|
||||
}
|
||||
)
|
||||
normalize_config(cfg)
|
||||
cli_args = TrainerCliArgs()
|
||||
dataset_meta = load_rl_datasets(cfg=cfg, cli_args=cli_args)
|
||||
|
||||
train(cfg=cfg, cli_args=cli_args, dataset_meta=dataset_meta)
|
||||
assert (Path(temp_dir) / "checkpoint-20/adapter_model.safetensors").exists()
|
||||
|
||||
@with_temp_dir
|
||||
def test_kto_pair_lora(self, temp_dir):
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "JackFram/llama-68m",
|
||||
"tokenizer_type": "LlamaTokenizer",
|
||||
"sequence_len": 1024,
|
||||
"load_in_8bit": True,
|
||||
"adapter": "lora",
|
||||
"lora_r": 64,
|
||||
"lora_alpha": 32,
|
||||
"lora_dropout": 0.1,
|
||||
"lora_target_linear": True,
|
||||
"special_tokens": {},
|
||||
"rl": "kto_pair",
|
||||
"datasets": [
|
||||
{
|
||||
"path": "Intel/orca_dpo_pairs",
|
||||
"type": "chatml.intel",
|
||||
"split": "train",
|
||||
},
|
||||
],
|
||||
"num_epochs": 1,
|
||||
"micro_batch_size": 4,
|
||||
"gradient_accumulation_steps": 1,
|
||||
"output_dir": temp_dir,
|
||||
"learning_rate": 0.00001,
|
||||
"optimizer": "paged_adamw_8bit",
|
||||
"lr_scheduler": "cosine",
|
||||
"max_steps": 20,
|
||||
"save_steps": 10,
|
||||
"warmup_steps": 5,
|
||||
"gradient_checkpointing": True,
|
||||
"gradient_checkpointing_kwargs": {"use_reentrant": True},
|
||||
}
|
||||
)
|
||||
normalize_config(cfg)
|
||||
cli_args = TrainerCliArgs()
|
||||
dataset_meta = load_rl_datasets(cfg=cfg, cli_args=cli_args)
|
||||
|
||||
train(cfg=cfg, cli_args=cli_args, dataset_meta=dataset_meta)
|
||||
assert (Path(temp_dir) / "checkpoint-20/adapter_model.safetensors").exists()
|
||||
|
||||
@with_temp_dir
|
||||
def test_ipo_lora(self, temp_dir):
|
||||
# pylint: disable=duplicate-code
|
||||
cfg = DictDefault(
|
||||
{
|
||||
"base_model": "JackFram/llama-68m",
|
||||
"tokenizer_type": "LlamaTokenizer",
|
||||
"sequence_len": 1024,
|
||||
"load_in_8bit": True,
|
||||
"adapter": "lora",
|
||||
"lora_r": 64,
|
||||
"lora_alpha": 32,
|
||||
"lora_dropout": 0.1,
|
||||
"lora_target_linear": True,
|
||||
"special_tokens": {},
|
||||
"rl": "ipo",
|
||||
"datasets": [
|
||||
{
|
||||
"path": "Intel/orca_dpo_pairs",
|
||||
"type": "chatml.intel",
|
||||
"split": "train",
|
||||
},
|
||||
],
|
||||
"num_epochs": 1,
|
||||
"micro_batch_size": 4,
|
||||
"gradient_accumulation_steps": 1,
|
||||
"output_dir": temp_dir,
|
||||
"learning_rate": 0.00001,
|
||||
"optimizer": "paged_adamw_8bit",
|
||||
"lr_scheduler": "cosine",
|
||||
"max_steps": 20,
|
||||
"save_steps": 10,
|
||||
"warmup_steps": 5,
|
||||
"gradient_checkpointing": True,
|
||||
"gradient_checkpointing_kwargs": {"use_reentrant": True},
|
||||
}
|
||||
)
|
||||
normalize_config(cfg)
|
||||
cli_args = TrainerCliArgs()
|
||||
dataset_meta = load_rl_datasets(cfg=cfg, cli_args=cli_args)
|
||||
|
||||
train(cfg=cfg, cli_args=cli_args, dataset_meta=dataset_meta)
|
||||
assert (Path(temp_dir) / "checkpoint-20/adapter_model.safetensors").exists()
|
||||
Reference in New Issue
Block a user