fix loss normalization for ddp training

haoneng.lhn

2023-12-08 ace42e5043be992c3a324fc637ba0594f10ad3b6

1
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}