微调后预测三元组不正确原因 about chatlm-mini-chinese HOT 5 CLOSED

SFTconfig(max_seq_len=512, tokenizer_dir='/home/xxx/mycode/demo2/model_save/', sft_train_file='./data/my_train.json', batch_size=16, num_train_epochs=6, save_steps=3000, gradient_accumulation_steps=4, learning_rate=5e-05, logging_first_step=True, logging_steps=20, output_dir='./model_save/ie_task', warmup_steps=1000, fp16=True, seed=23333)

training_args = Seq2SeqTrainingArguments(
        output_dir=config.output_dir,
        per_device_train_batch_size=config.batch_size,
        auto_find_batch_size=True,  # 防止OOM
        gradient_accumulation_steps=config.gradient_accumulation_steps,
        learning_rate=config.learning_rate,
        logging_steps=config.logging_steps,
        num_train_epochs=config.num_train_epochs,
        optim="adafactor",
        report_to='tensorboard',
        log_level='info',
        save_steps=config.save_steps,
        save_total_limit=3,
        fp16=config.fp16,
        logging_first_step=config.logging_first_step,
        warmup_steps=config.warmup_steps,
        seed=config.seed,
        generation_config=generation_config,
    )

def sft_train(config: SFTconfig) -> None:
    # step 1. 加载tokenizer
    tokenizer = PreTrainedTokenizerFast.from_pretrained(config.tokenizer_dir)
    tokenizer.add_special_tokens({'pad_token': '[PAD]'})  # add code in here
    ...

ValueError: Asking to pad but the tokenizer does not have a padding token. Please select a token to use as `pad_token` `(tokenizer.pad_token = tokenizer.eos_token e.g.)` or add a new pad token via `tokenizer.add_special_tokens({'pad_token': '[PAD]'})`

from modelscope import snapshot_download
model_id = 'charent/ChatLM-mini-Chinese'
model_id = snapshot_download(model_id, cache_dir='./model_save')