cf0c79d52e
* fix: update chat_template * fix: handle gemma3 showing a lot of no content for turn 0 * fix: remove unknown config from examples * fix: test * fix: temporary disable gemma2 test * fix: stop overwriting config.text_config unnecessarily * fix: handling of set cache to the text_config section * feat: add liger gemma support and bump liger to 0.5.5 * fix: add double use_cache setting * fix: add support for final_logit_softcap in CCE for gemma2/3 * fix: set use_cache before model load * feat: add missing layernorm override * fix: handle gemma3 rmsnorm * fix: use wrapper to pass dim as hidden_size * fix: change dim to positional * fix: patch with wrong mlp * chore: refactor use_cache handling * fix import issues * fix tests.e2e.utils import --------- Co-authored-by: Wing Lian <wing@axolotl.ai>
110 lines
3.7 KiB
Python
110 lines
3.7 KiB
Python
"""
|
|
Simple end-to-end test for Liger integration
|
|
"""
|
|
|
|
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, prepare_plugins
|
|
from axolotl.utils.dict import DictDefault
|
|
|
|
from tests.e2e.utils import check_model_output_exists, require_torch_2_4_1
|
|
|
|
|
|
class LigerIntegrationTestCase:
|
|
"""
|
|
e2e tests for liger integration with Axolotl
|
|
"""
|
|
|
|
@require_torch_2_4_1
|
|
def test_llama_wo_flce(self, temp_dir):
|
|
# pylint: disable=duplicate-code
|
|
cfg = DictDefault(
|
|
{
|
|
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
|
"plugins": [
|
|
"axolotl.integrations.liger.LigerPlugin",
|
|
],
|
|
"liger_rope": True,
|
|
"liger_rms_norm": True,
|
|
"liger_glu_activation": True,
|
|
"liger_cross_entropy": True,
|
|
"liger_fused_linear_cross_entropy": False,
|
|
"sequence_len": 1024,
|
|
"val_set_size": 0.05,
|
|
"special_tokens": {
|
|
"pad_token": "<|endoftext|>",
|
|
},
|
|
"datasets": [
|
|
{
|
|
"path": "mhenrichsen/alpaca_2k_test",
|
|
"type": "alpaca",
|
|
},
|
|
],
|
|
"num_epochs": 1,
|
|
"micro_batch_size": 2,
|
|
"gradient_accumulation_steps": 2,
|
|
"output_dir": temp_dir,
|
|
"learning_rate": 0.00001,
|
|
"optimizer": "adamw_torch_fused",
|
|
"lr_scheduler": "cosine",
|
|
"save_safetensors": True,
|
|
"bf16": "auto",
|
|
"max_steps": 5,
|
|
}
|
|
)
|
|
# pylint: disable=duplicate-code
|
|
prepare_plugins(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)
|
|
|
|
@require_torch_2_4_1
|
|
def test_llama_w_flce(self, temp_dir):
|
|
# pylint: disable=duplicate-code
|
|
cfg = DictDefault(
|
|
{
|
|
"base_model": "HuggingFaceTB/SmolLM2-135M",
|
|
"plugins": [
|
|
"axolotl.integrations.liger.LigerPlugin",
|
|
],
|
|
"liger_rope": True,
|
|
"liger_rms_norm": True,
|
|
"liger_glu_activation": True,
|
|
"liger_cross_entropy": False,
|
|
"liger_fused_linear_cross_entropy": True,
|
|
"sequence_len": 1024,
|
|
"val_set_size": 0.05,
|
|
"special_tokens": {
|
|
"pad_token": "<|endoftext|>",
|
|
},
|
|
"datasets": [
|
|
{
|
|
"path": "mhenrichsen/alpaca_2k_test",
|
|
"type": "alpaca",
|
|
},
|
|
],
|
|
"num_epochs": 1,
|
|
"micro_batch_size": 2,
|
|
"gradient_accumulation_steps": 2,
|
|
"output_dir": temp_dir,
|
|
"learning_rate": 0.00001,
|
|
"optimizer": "adamw_torch_fused",
|
|
"lr_scheduler": "cosine",
|
|
"save_safetensors": True,
|
|
"bf16": "auto",
|
|
"max_steps": 5,
|
|
}
|
|
)
|
|
# pylint: disable=duplicate-code
|
|
prepare_plugins(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)
|