fc4e37920b
* Prepare for transformers v5 upgrade * fix hf cli * update for hf hub changes * fix tokenizer apply_chat_template args * remap include_tokens_per_second * fix tps * handle migration for warmup * use latest hf hub * Fix scan -> ls * fix import * fix for renaming of mistral common tokenizer -> backend * update for fixed tokenziation for llama * Skip phi35 tests for now * remove mistral patch fixed upstream in huggingface/transformers#41439 * use namespacing for patch * don't rely on sdist for e2e tests for now * run modal ci without waiting too * Fix dep for ci * fix imports * Fix fp8 check * fsdp2 fixes * fix version handling * update fsdp version tests for new v5 behavior * Fail multigpu tests after 3 failures * skip known v5 broken tests for now and cleanup * bump deps * unmark skipped test * re-enable test_fsdp_qlora_prequant_packed test * increase multigpu ci timeout * skip broken gemma3 test * reduce timout back to original 120min now that the hanging test is skipped * fix for un-necessary collator for pretraining with bsz=1 * fix: safe_serialization deprecated in transformers v5 rc01 (#3318) * torch_dtype deprecated * load model in float32 for consistency with tests * revert some test fixtures back * use hf cache ls instead of scan * don't strip fsdp_version more fdsp_Version fixes for v5 fix version in fsdp_config fix aliasing fix fsdp_version check check fsdp_version is 2 in both places * Transformers v5 rc2 (#3347) * bump dep * use latest fbgemm, grab model config as part of fixture, un-skip test * import AutoConfig * don't need more problematic autoconfig when specifying config.json manually * add fixtures for argilla ultrafeedback datasets * download phi4-reasoning * fix arg * update tests for phi fast tokenizer changes * use explicit model types for gemma3 --------- Co-authored-by: Wing Lian <wing@axolotl.ai> * fix: AutoModelForVision2Seq -> AutoModelForImageTextToText * chore: remove duplicate * fix: attempt fix gemma3 text mode * chore: lint * ga release of v5 * need property setter for name_or_path for mistral tokenizer * vllm not compatible with transformers v5 * setter for chat_template w mistral too --------- Co-authored-by: NanoCode012 <nano@axolotl.ai> Co-authored-by: salman <salman.mohammadi@outlook.com>
125 lines
4.2 KiB
Python
125 lines
4.2 KiB
Python
"""
|
||
E2E tests for deepseekv3
|
||
"""
|
||
|
||
from pathlib import Path
|
||
|
||
import pytest
|
||
|
||
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 tests.hf_offline_utils import enable_hf_offline
|
||
|
||
|
||
class TestDeepseekV3:
|
||
"""
|
||
Test case for DeepseekV3 models
|
||
"""
|
||
|
||
@enable_hf_offline
|
||
@pytest.mark.parametrize(
|
||
"sample_packing",
|
||
[True, False],
|
||
)
|
||
def test_lora_deepseekv3(self, temp_dir, sample_packing):
|
||
cfg = DictDefault(
|
||
{
|
||
"base_model": "axolotl-ai-co/DeepSeek-V3-11M",
|
||
"trust_remote_code": True,
|
||
"sample_packing": sample_packing,
|
||
"flash_attention": True,
|
||
"sequence_len": 2048,
|
||
"adapter": "lora",
|
||
"lora_r": 8,
|
||
"lora_alpha": 16,
|
||
"lora_dropout": 0.05,
|
||
"lora_target_linear": True,
|
||
"val_set_size": 0,
|
||
"datasets": [
|
||
{
|
||
"path": "mlabonne/FineTome-100k",
|
||
"type": "chat_template",
|
||
"field_messages": "conversations",
|
||
"message_property_mappings": {
|
||
"role": "from",
|
||
"content": "value",
|
||
},
|
||
"drop_system_message": True,
|
||
"split": "train[:1%]",
|
||
},
|
||
],
|
||
"special_tokens": {
|
||
"bos_token": "<｜begin▁of▁sentence｜>",
|
||
"eos_token": "<｜end▁of▁sentence｜>",
|
||
},
|
||
"chat_template": "deepseek_v3",
|
||
"num_epochs": 1,
|
||
"micro_batch_size": 1,
|
||
"gradient_accumulation_steps": 2,
|
||
"output_dir": temp_dir,
|
||
"learning_rate": 0.00001,
|
||
"optimizer": "adamw_bnb_8bit",
|
||
"lr_scheduler": "cosine",
|
||
"max_steps": 5,
|
||
"bf16": True,
|
||
"save_first_step": False,
|
||
}
|
||
)
|
||
cfg = validate_config(cfg)
|
||
normalize_config(cfg)
|
||
dataset_meta = load_datasets(cfg=cfg)
|
||
|
||
train(cfg=cfg, dataset_meta=dataset_meta)
|
||
assert (Path(temp_dir) / "adapter_model.safetensors").exists()
|
||
|
||
@enable_hf_offline
|
||
@pytest.mark.parametrize(
|
||
"sample_packing",
|
||
[True, False],
|
||
)
|
||
def test_fft_deepseekv3(self, temp_dir, sample_packing):
|
||
cfg = DictDefault(
|
||
{
|
||
"base_model": "axolotl-ai-co/DeepSeek-V3-11M",
|
||
"trust_remote_code": True,
|
||
"sample_packing": sample_packing,
|
||
"flash_attention": True,
|
||
"sequence_len": 2048,
|
||
"val_set_size": 0,
|
||
"datasets": [
|
||
{
|
||
"path": "mlabonne/FineTome-100k",
|
||
"type": "chat_template",
|
||
"field_messages": "conversations",
|
||
"message_field_role": "from",
|
||
"message_field_content": "value",
|
||
"split": "train[:1%]",
|
||
},
|
||
],
|
||
"chat_template": "deepseek_v3",
|
||
"special_tokens": {
|
||
"bos_token": "<｜begin▁of▁sentence｜>",
|
||
"eos_token": "<｜end▁of▁sentence｜>",
|
||
},
|
||
"num_epochs": 1,
|
||
"micro_batch_size": 1,
|
||
"gradient_accumulation_steps": 2,
|
||
"output_dir": temp_dir,
|
||
"learning_rate": 0.00001,
|
||
"optimizer": "adamw_bnb_8bit",
|
||
"lr_scheduler": "cosine",
|
||
"max_steps": 5,
|
||
"bf16": True,
|
||
"save_first_step": False,
|
||
}
|
||
)
|
||
cfg = validate_config(cfg)
|
||
normalize_config(cfg)
|
||
dataset_meta = load_datasets(cfg=cfg)
|
||
|
||
train(cfg=cfg, dataset_meta=dataset_meta)
|
||
assert (Path(temp_dir) / "model.safetensors").exists()
|