69cd49a7aa
* update transformers to 4.53.0 * remove attention_mask from signature columns if using packing * remove attention_mask column from dataloader * update signature of flash attn forward for ring attn patch * fix FSDP * patch ring-flash-attn with upstream signature fix * fix patch indentation level * fix the patch * add batch flattening smoke test with loss check that works in older transformers * fix patch * don't drop attention mask for flex * more fixes * patch create_causal_mask for packing w flex * global torch manual_seed fixture * tweak loss checks * fix patch and use single batch for flex * don't need to reload * fix causal mask patch * use transformers patch releasE * make sure env var is string * make sure to drop attention mask for flex w packing for latest transformers patch release * tweak loss * guard on signature columns before removing attention mask * bump loss * set remove isn't chainable * skip slow mistral test in 2.5.1
108 lines
3.4 KiB
Python
108 lines
3.4 KiB
Python
"""
|
|
E2E tests for lora llama
|
|
"""
|
|
|
|
import unittest
|
|
|
|
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, require_torch_2_6_0, with_temp_dir
|
|
|
|
|
|
class TestMistral(unittest.TestCase):
|
|
"""
|
|
Test case for Llama models using LoRA
|
|
"""
|
|
|
|
@require_torch_2_6_0
|
|
@with_temp_dir
|
|
def test_lora_packing(self, temp_dir):
|
|
# pylint: disable=duplicate-code
|
|
cfg = DictDefault(
|
|
{
|
|
"base_model": "trl-internal-testing/tiny-MistralForCausalLM-0.2",
|
|
"flash_attention": True,
|
|
"sample_packing": True,
|
|
"sequence_len": 1024,
|
|
"load_in_8bit": True,
|
|
"adapter": "lora",
|
|
"lora_r": 32,
|
|
"lora_alpha": 64,
|
|
"lora_dropout": 0.05,
|
|
"lora_target_linear": True,
|
|
"val_set_size": 0.05,
|
|
"special_tokens": {
|
|
"unk_token": "<unk>",
|
|
"bos_token": "<s>",
|
|
"eos_token": "</s>",
|
|
},
|
|
"datasets": [
|
|
{
|
|
"path": "mhenrichsen/alpaca_2k_test",
|
|
"type": "alpaca",
|
|
},
|
|
],
|
|
"num_epochs": 2,
|
|
"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,
|
|
"save_steps": 3,
|
|
"eval_steps": 4,
|
|
"bf16": "auto",
|
|
}
|
|
)
|
|
cfg = validate_config(cfg)
|
|
normalize_config(cfg)
|
|
dataset_meta = load_datasets(cfg=cfg)
|
|
|
|
train(cfg=cfg, dataset_meta=dataset_meta)
|
|
check_model_output_exists(temp_dir, cfg)
|
|
|
|
@with_temp_dir
|
|
def test_ft_packing(self, temp_dir):
|
|
# pylint: disable=duplicate-code
|
|
cfg = DictDefault(
|
|
{
|
|
"base_model": "trl-internal-testing/tiny-MistralForCausalLM-0.2",
|
|
"flash_attention": True,
|
|
"sample_packing": True,
|
|
"sequence_len": 1024,
|
|
"val_set_size": 0.05,
|
|
"special_tokens": {
|
|
"unk_token": "<unk>",
|
|
"bos_token": "<s>",
|
|
"eos_token": "</s>",
|
|
},
|
|
"datasets": [
|
|
{
|
|
"path": "mhenrichsen/alpaca_2k_test",
|
|
"type": "alpaca",
|
|
},
|
|
],
|
|
"num_epochs": 2,
|
|
"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,
|
|
"save_steps": 3,
|
|
"eval_steps": 4,
|
|
"bf16": "auto",
|
|
}
|
|
)
|
|
cfg = validate_config(cfg)
|
|
normalize_config(cfg)
|
|
dataset_meta = load_datasets(cfg=cfg)
|
|
|
|
train(cfg=cfg, dataset_meta=dataset_meta)
|
|
check_model_output_exists(temp_dir, cfg)
|