我正在使用pytorch使用Hugging人脸模型训练一个简单的二元分类模型。
伯特PyTorch拥抱脸。
代码如下：

import transformers
from transformers import TFAutoModel, AutoTokenizer
from tokenizers import Tokenizer, models, pre_tokenizers, decoders, processors
from transformers import AutoTokenizer

 
from transformers import AdamW
from transformers import get_linear_schedule_with_warmup
from transformers import BertTokenizerFast as BertTokenizer, BertModel, AdamW, get_linear_schedule_with_warmup,BertConfig

def compute_metrics(eval_pred):
    logits, labels = eval_pred
   

    predictions = np.argmax(logits, axis=-1)
    
    acc = np.sum(predictions == labels) / predictions.shape[0]
    return {"accuracy": acc,
            'precision': metrics.precision_score(labels, predictions),
            'recall': metrics.recall_score(labels, predictions),
            'f1': metrics.f1_score(labels, predictions)}

training_args = tr.TrainingArguments(
    #report_to = 'wandb',
    output_dir='/home/pc/proj/Exp2_conv_stampy_data/results_exp0',          # output directory
    overwrite_output_dir = True,
    num_train_epochs=2,              # total number of training epochs
    per_device_train_batch_size=32,  # batch size per device during training
    per_device_eval_batch_size=32,   # batch size for evaluation
    learning_rate=2e-5,
    warmup_steps=200,                # number of warmup steps for learning rate scheduler
    weight_decay=0.01,               # strength of weight decay
    logging_dir='./logs_exp0',            # directory for storing logs
    logging_steps=137,
    evaluation_strategy="epoch"
    ,save_strategy="epoch"
    ,load_best_model_at_end=True
    ,fp16=True
    ,run_name="final_model0"
    
)

# counter = 0
# results_lst = []

from transformers import TrainerCallback
from copy import deepcopy

model = tr.XLMRobertaForSequenceClassification.from_pretrained("/home/pc/multilingual_toxic_xlm_roberta",problem_type="single_label_classification", num_labels=2,ignore_mismatched_sizes=True, id2label={0: 'negative', 1: 'positive'})

train_encodings = tokenizer(train_texts, truncation=True, padding=True, max_length=512, return_tensors="pt")
val_encodings = tokenizer(val_texts, truncation=True, padding=True, max_length=512, return_tensors="pt")

train_data = SEDataset(train_encodings, train_labels)
val_data = SEDataset(val_encodings, val_labels)

model.to(device)

class CustomCallback(TrainerCallback):
    
    def __init__(self, trainer) -> None:
        super().__init__()
        self._trainer = trainer
    
    def on_epoch_end(self, args, state, control, **kwargs):
        if control.should_evaluate:
            control_copy = deepcopy(control)
            self._trainer.evaluate(eval_dataset=self._trainer.train_dataset, metric_key_prefix="train")
            return control_copy

trainer = tr.Trainer(
    model=model,                         # the instantiated Transformers model to be trained
    args=training_args,                  # training arguments, defined above
    train_dataset=train_data,         # training dataset
    eval_dataset=val_data,          # evaluation dataset
    compute_metrics=compute_metrics    # the callback that computes metrics of interest
)
trainer.add_callback(CustomCallback(trainer)) 
train = trainer.train()


trainer.save_model("/home/pc/proj/Exp2_conv_stampy_data/result_toxic_model_exp0")

我看到默认情况下创建了mlruns目录。

什么是0' and what are these 2 folders inside 0？** **如何重命名为有用和可理解的东西。？** **如果我运行多个运行，我如何在同一个实验下记录每个运行的模型，例如run1，run2`？
我还看到工件文件夹是空的，如何记录最终模型？