788649fe95
* attempt to also run e2e tests that needs gpus * fix stray quote * checkout specific github ref * dockerfile for tests with proper checkout ensure wandb is dissabled for docker pytests clear wandb env after testing clear wandb env after testing make sure to provide a default val for pop tryin skipping wandb validation tests explicitly disable wandb in the e2e tests explicitly report_to None to see if that fixes the docker e2e tests split gpu from non-gpu unit tests skip bf16 check in test for now build docker w/o cache since it uses branch name ref revert some changes now that caching is fixed skip bf16 check if on gpu w support * pytest skip for auto-gptq requirements * skip mamba tests for now, split multipack and non packed lora llama tests * split tests that use monkeypatches * fix relative import for prev commit * move other tests using monkeypatches to the correct run
69 lines
2.0 KiB
Python
69 lines
2.0 KiB
Python
"""
|
|
E2E tests for lora llama
|
|
"""
|
|
|
|
import logging
|
|
import os
|
|
import unittest
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from axolotl.cli import load_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="skipping until upstreamed into transformers")
|
|
class TestMamba(unittest.TestCase):
|
|
"""
|
|
Test case for Mamba models
|
|
"""
|
|
|
|
@with_temp_dir
|
|
def test_fft(self, temp_dir):
|
|
# pylint: disable=duplicate-code
|
|
cfg = DictDefault(
|
|
{
|
|
"base_model": "state-spaces/mamba-130m",
|
|
"model_type": "MambaLMHeadModel",
|
|
"tokenizer_type": "AutoTokenizer",
|
|
"tokenizer_config": "EleutherAI/gpt-neox-20b",
|
|
"flash_attention": False,
|
|
"sequence_len": 1024,
|
|
"load_in_8bit": False,
|
|
"val_set_size": 0.0,
|
|
"datasets": [
|
|
{
|
|
"path": "mhenrichsen/alpaca_2k_test",
|
|
"type": "alpaca",
|
|
},
|
|
],
|
|
"gradient_checkpointing": False,
|
|
"num_epochs": 2,
|
|
"micro_batch_size": 2,
|
|
"gradient_accumulation_steps": 1,
|
|
"output_dir": temp_dir,
|
|
"learning_rate": 0.00001,
|
|
"optimizer": "adamw_torch",
|
|
"lr_scheduler": "cosine",
|
|
"max_steps": 20,
|
|
"save_steps": 10,
|
|
"eval_steps": None,
|
|
"save_safetensors": False,
|
|
}
|
|
)
|
|
normalize_config(cfg)
|
|
cli_args = TrainerCliArgs()
|
|
dataset_meta = load_datasets(cfg=cfg, cli_args=cli_args)
|
|
|
|
train(cfg=cfg, cli_args=cli_args, dataset_meta=dataset_meta)
|
|
assert (Path(temp_dir) / "pytorch_model.bin").exists()
|