ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

70 lines
3.1 KiB

# coding=utf-8
# Copyright 2020-present the HuggingFace Inc. team.
#
# 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.
"""
The Trainer class, to easily train a 🤗 Transformers from scratch or finetune it on a new task.
"""
import os
from typing import Optional
from transformers import Trainer
import torch
from transformers.modeling_utils import PreTrainedModel, unwrap_model
from transformers.utils import logging
logger = logging.get_logger(__name__)
WEIGHTS_NAME = "pytorch_model.bin"
TRAINING_ARGS_NAME = "training_args.bin"
class PrefixTrainer(Trainer):
def __init__(self, *args, save_changed=False, **kwargs):
self.save_changed = save_changed
super().__init__(*args, **kwargs)
def _save(self, output_dir: Optional[str] = None, state_dict=None):
# If we are executing this function, we are the process zero, so we don't check for that.
output_dir = output_dir if output_dir is not None else self.args.output_dir
os.makedirs(output_dir, exist_ok=True)
logger.info(f"Saving model checkpoint to {output_dir}")
# Save a trained model and configuration using `save_pretrained()`.
# They can then be reloaded using `from_pretrained()`
if not isinstance(self.model, PreTrainedModel):
if isinstance(unwrap_model(self.model), PreTrainedModel):
if state_dict is None:
state_dict = self.model.state_dict()
unwrap_model(self.model).save_pretrained(output_dir, state_dict=state_dict)
else:
logger.info("Trainer.model is not a `PreTrainedModel`, only saving its state dict.")
if state_dict is None:
state_dict = self.model.state_dict()
torch.save(state_dict, os.path.join(output_dir, WEIGHTS_NAME))
else:
if self.save_changed:
print("Saving PrefixEncoder")
state_dict = self.model.state_dict()
filtered_state_dict = {}
for k, v in self.model.named_parameters():
if v.requires_grad:
filtered_state_dict[k] = state_dict[k]
self.model.save_pretrained(output_dir, state_dict=filtered_state_dict)
else:
print("Saving the whole model")
self.model.save_pretrained(output_dir, state_dict=state_dict)
if self.tokenizer is not None:
self.tokenizer.save_pretrained(output_dir)
# Good practice: save your training arguments together with the trained model
torch.save(self.args, os.path.join(output_dir, TRAINING_ARGS_NAME))