[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2021 >> loading file tokenizer.model
[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2021 >> loading file added_tokens.json
[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2021 >> loading file special_tokens_map.json
[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2021 >> loading file tokenizer_config.json
[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2021 >> loading file chat_template.jinja
[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2299 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
[INFO|2025-07-09 13:10:52] configuration_utils.py:696 >> loading configuration file /home/chenjh2/disk_chenjh/models/models/Llama-3-8b-Instruct/config.json
[INFO|2025-07-09 13:10:52] configuration_utils.py:770 >> Model config LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128009,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.52.4",
  "use_cache": true,
  "vocab_size": 128256
}

[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2021 >> loading file tokenizer.json
[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2021 >> loading file tokenizer.model
[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2021 >> loading file added_tokens.json
[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2021 >> loading file special_tokens_map.json
[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2021 >> loading file tokenizer_config.json
[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2021 >> loading file chat_template.jinja
[INFO|2025-07-09 13:10:52] tokenization_utils_base.py:2299 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
[INFO|2025-07-09 13:10:52] logging.py:143 >> Add pad token: <|eot_id|>
[INFO|2025-07-09 13:10:52] logging.py:143 >> Add <|eom_id|> to stop words.
[WARNING|2025-07-09 13:10:52] logging.py:148 >> New tokens have been added, make sure `resize_vocab` is True.
[INFO|2025-07-09 13:10:52] logging.py:143 >> Loading dataset open-r1/OpenR1-Math-220k...