00018629e7
* run tests again on Modal * make sure to run the full suite of tests on modal * run cicd steps via shell script * run tests in different runs * increase timeout * split tests into steps on modal * increase workflow timeout * retry doing this with only a single script * fix yml launch for modal ci * reorder tests to run on modal * skip dpo tests on modal * run on L4s, A10G takes too long * increase CPU and RAM for modal test * run modal tests on A100s * skip phi test on modal * env not arg in modal dockerfile * upgrade pydantic and fastapi for modal tests * cleanup stray character * use A10s instead of A100 for modal
161 lines
5.4 KiB
Python
161 lines
5.4 KiB
Python
"""
|
|
E2E tests for lora llama
|
|
"""
|
|
|
|
import logging
|
|
import os
|
|
import unittest
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
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"
|
|
|
|
|
|
@pytest.mark.skip(reason="doesn't seem to work on modal")
|
|
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()
|