mirror of
https://github.com/huggingface/trl.git
synced 2025-10-20 18:43:52 +08:00
453db5cd79
* first commit * uncomment * other tests adaptations * Remove unused variable in test_setup_chat_format * Remove unused import statement * style * Add Bart model * Update BCOTrainerTester class in test_bco_trainer.py * Update model IDs and tokenizers in test files * Add new models and processors * Update model IDs in test files * Fix formatting issue in test_dataset_formatting.py * Refactor dataset formatting in test_dataset_formatting.py * Fix dataset sequence length in SFTTrainerTester * Remove tokenizer * Remove print statement * Add reward_model_path and sft_model_path to PPO trainer * Fix tokenizer padding issue * Add chat template for testing purposes in PaliGemma model * Update PaliGemma model and chat template * Increase learning rate to speed up test * Update model names in run_dpo.sh and run_sft.sh scripts * Update model and dataset names * Fix formatting issue in test_dataset_formatting.py * Fix formatting issue in test_dataset_formatting.py * Remove unused chat template * Update model generation script * additional models * Update model references in test files * Remove unused imports in test_online_dpo_trainer.py * Add is_llm_blender_available import and update reward_tokenizer * Refactor test_online_dpo_trainer.py: Move skipped test case decorator * remove models without chat templates * Update model names in scripts and tests * Update model_id in test_modeling_value_head.py * Update model versions in test files * Fix formatting issue in test_dataset_formatting.py * Update embedding model ID in BCOTrainerTester * Update test_online_dpo_trainer.py with reward model changes * Update expected formatted text in test_dataset_formatting.py * Add reward_tokenizer to TestOnlineDPOTrainer * fix tests * Add SIMPLE_CHAT_TEMPLATE to T5 tokenizer * Fix dummy_text format in test_rloo_trainer.py * Skip outdated test for chatML data collator * Add new vision language models * Commented out unused model IDs in test_vdpo_trainer * Update model and vision configurations in generate_tiny_models.py and test_dpo_trainer.py * Update model and tokenizer references * Don't push if it already exists * Add comment explaining test skip * Fix model_exists function call and add new models * Update LlavaForConditionalGeneration model and processor * `qgallouedec` -> `trl-internal-testing`
105 lines
3.5 KiB
Python
105 lines
3.5 KiB
Python
# Copyright 2022 The HuggingFace Team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
import platform
|
|
import subprocess
|
|
|
|
from transformers.testing_utils import require_peft
|
|
|
|
|
|
def test():
|
|
command = """\
|
|
python examples/scripts/ppo/ppo.py \
|
|
--dataset_name trl-internal-testing/descriptiveness-sentiment-trl-style \
|
|
--dataset_train_split descriptiveness \
|
|
--learning_rate 3e-6 \
|
|
--output_dir models/minimal/ppo \
|
|
--per_device_train_batch_size 4 \
|
|
--gradient_accumulation_steps 1 \
|
|
--total_episodes 10 \
|
|
--model_name_or_path trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 \
|
|
--reward_model_path trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 \
|
|
--sft_model_path trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 \
|
|
--missing_eos_penalty 1.0 \
|
|
--save_strategy no \
|
|
--stop_token eos
|
|
"""
|
|
if platform.system() == "Windows":
|
|
# windows CI does not work with subprocesses for some reason
|
|
# e.g., https://github.com/huggingface/trl/actions/runs/9600036224/job/26475286210?pr=1743
|
|
return
|
|
subprocess.run(
|
|
command,
|
|
shell=True,
|
|
check=True,
|
|
)
|
|
|
|
|
|
def test_num_train_epochs():
|
|
command = """\
|
|
python examples/scripts/ppo/ppo.py \
|
|
--dataset_name trl-internal-testing/descriptiveness-sentiment-trl-style \
|
|
--dataset_train_split descriptiveness \
|
|
--learning_rate 3e-6 \
|
|
--output_dir models/minimal/ppo \
|
|
--per_device_train_batch_size 4 \
|
|
--gradient_accumulation_steps 1 \
|
|
--num_train_epochs 0.003 \
|
|
--model_name_or_path trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 \
|
|
--reward_model_path trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 \
|
|
--sft_model_path trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 \
|
|
--missing_eos_penalty 1.0 \
|
|
--save_strategy no \
|
|
--stop_token eos
|
|
"""
|
|
if platform.system() == "Windows":
|
|
# windows CI does not work with subprocesses for some reason
|
|
# e.g., https://github.com/huggingface/trl/actions/runs/9600036224/job/26475286210?pr=1743
|
|
return
|
|
subprocess.run(
|
|
command,
|
|
shell=True,
|
|
check=True,
|
|
)
|
|
|
|
|
|
@require_peft
|
|
def test_peft_support():
|
|
command = """\
|
|
python examples/scripts/ppo/ppo.py \
|
|
--dataset_name trl-internal-testing/descriptiveness-sentiment-trl-style \
|
|
--dataset_train_split descriptiveness \
|
|
--learning_rate 3e-6 \
|
|
--output_dir models/minimal/ppo \
|
|
--per_device_train_batch_size 4 \
|
|
--gradient_accumulation_steps 1 \
|
|
--total_episodes 10 \
|
|
--model_name_or_path EleutherAI/pythia-14m \
|
|
--missing_eos_penalty 1.0 \
|
|
--save_strategy no \
|
|
--stop_token eos \
|
|
--use_peft \
|
|
--lora_r 32 \
|
|
--lora_alpha 16 \
|
|
--lora_target_modules query_key_value dense
|
|
"""
|
|
if platform.system() == "Windows":
|
|
# windows CI does not work with subprocesses for some reason
|
|
# e.g., https://github.com/huggingface/trl/actions/runs/9600036224/job/26475286210?pr=1743
|
|
return
|
|
subprocess.run(
|
|
command,
|
|
shell=True,
|
|
check=True,
|
|
)
|