170cdb5be9
* Update train.py add post_model_load and post_lora_load model calss. * Update train.py add post_train and post_train_unload function calls * Update train.py * Update base.py * Update train.py * chore: lint * clarify plugin hooks * Update src/axolotl/integrations/base.py Co-authored-by: Dan Saunders <danjsaund@gmail.com> * Update src/axolotl/utils/models.py Co-authored-by: Dan Saunders <danjsaund@gmail.com> * Update src/axolotl/utils/models.py Co-authored-by: Dan Saunders <danjsaund@gmail.com> * Update src/axolotl/integrations/base.py Co-authored-by: Dan Saunders <danjsaund@gmail.com> * Update models.py * Update models.py * remove extra call to post_model_load * chore: lint * add test for hooks and gc trainer * disable duplicated code check for test * fix the path and add better handling --------- Co-authored-by: Wing Lian <wing@axolotl.ai> Co-authored-by: Dan Saunders <danjsaund@gmail.com>
68 lines
2.0 KiB
Python
68 lines
2.0 KiB
Python
"""
|
|
E2E tests for lora llama
|
|
"""
|
|
|
|
import logging
|
|
import os
|
|
import unittest
|
|
|
|
from axolotl.cli.args import TrainerCliArgs
|
|
from axolotl.common.datasets import load_datasets
|
|
from axolotl.train import train
|
|
from axolotl.utils.config import normalize_config, validate_config
|
|
from axolotl.utils.dict import DictDefault
|
|
|
|
from .utils import check_model_output_exists, with_temp_dir
|
|
|
|
LOG = logging.getLogger("axolotl.tests.e2e")
|
|
os.environ["WANDB_DISABLED"] = "true"
|
|
|
|
|
|
class TestLoraLlama(unittest.TestCase):
|
|
"""
|
|
Test case for Llama models using LoRA
|
|
"""
|
|
|
|
@with_temp_dir
|
|
def test_lora(self, temp_dir):
|
|
# pylint: disable=duplicate-code
|
|
cfg = DictDefault(
|
|
{
|
|
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
|
"tokenizer_type": "AutoTokenizer",
|
|
"sequence_len": 1024,
|
|
"load_in_8bit": True,
|
|
"adapter": "lora",
|
|
"lora_r": 8,
|
|
"lora_alpha": 16,
|
|
"lora_dropout": 0.05,
|
|
"lora_target_linear": True,
|
|
"val_set_size": 0.02,
|
|
"special_tokens": {
|
|
"pad_token": "<|endoftext|>",
|
|
},
|
|
"datasets": [
|
|
{
|
|
"path": "mhenrichsen/alpaca_2k_test",
|
|
"type": "alpaca",
|
|
},
|
|
],
|
|
"num_epochs": 1,
|
|
"micro_batch_size": 2,
|
|
"gradient_accumulation_steps": 1,
|
|
"output_dir": temp_dir,
|
|
"learning_rate": 0.00001,
|
|
"optimizer": "adamw_torch_fused",
|
|
"lr_scheduler": "cosine",
|
|
"max_steps": 5,
|
|
}
|
|
)
|
|
|
|
cfg = validate_config(cfg)
|
|
normalize_config(cfg)
|
|
cli_args = TrainerCliArgs()
|
|
dataset_meta = load_datasets(cfg=cfg, cli_args=cli_args)
|
|
|
|
train(cfg=cfg, dataset_meta=dataset_meta)
|
|
check_model_output_exists(temp_dir, cfg)
|