running_log.txt

[INFO|2025-05-12 13:05:10] configuration_utils.py:696 >> loading configuration file config.json from cache at /home/kiho/.cache/huggingface/hub/models--infly--OpenCoder-8B-Instruct/snapshots/01badbbf10c2dfd7e2a0b5f570065ef44548576c/config.json

[INFO|2025-05-12 13:05:10] configuration_utils.py:768 >> Model config LlamaConfig {
  "_name_or_path": "infly/OpenCoder-8B-Instruct",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 96540,
  "eos_token_id": 96539,
  "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": "4.48.2",
  "use_cache": true,
  "vocab_size": 96640
}


[INFO|2025-05-12 13:05:13] tokenization_utils_base.py:2034 >> loading file ./tokenizer.model from cache at /home/kiho/.cache/huggingface/hub/models--infly--OpenCoder-8B-Instruct/snapshots/01badbbf10c2dfd7e2a0b5f570065ef44548576c/./tokenizer.model

[INFO|2025-05-12 13:05:13] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at /home/kiho/.cache/huggingface/hub/models--infly--OpenCoder-8B-Instruct/snapshots/01badbbf10c2dfd7e2a0b5f570065ef44548576c/added_tokens.json

[INFO|2025-05-12 13:05:13] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at /home/kiho/.cache/huggingface/hub/models--infly--OpenCoder-8B-Instruct/snapshots/01badbbf10c2dfd7e2a0b5f570065ef44548576c/special_tokens_map.json

[INFO|2025-05-12 13:05:13] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at /home/kiho/.cache/huggingface/hub/models--infly--OpenCoder-8B-Instruct/snapshots/01badbbf10c2dfd7e2a0b5f570065ef44548576c/tokenizer_config.json

[INFO|2025-05-12 13:05:13] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at None

[INFO|2025-05-12 13:05:13] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None

[INFO|2025-05-12 13:05:13] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

[INFO|2025-05-12 13:05:14] configuration_utils.py:696 >> loading configuration file config.json from cache at /home/kiho/.cache/huggingface/hub/models--infly--OpenCoder-8B-Instruct/snapshots/01badbbf10c2dfd7e2a0b5f570065ef44548576c/config.json

[INFO|2025-05-12 13:05:14] configuration_utils.py:768 >> Model config LlamaConfig {
  "_name_or_path": "infly/OpenCoder-8B-Instruct",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 96540,
  "eos_token_id": 96539,
  "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": "4.48.2",
  "use_cache": true,
  "vocab_size": 96640
}


[INFO|2025-05-12 13:05:15] tokenization_utils_base.py:2034 >> loading file ./tokenizer.model from cache at /home/kiho/.cache/huggingface/hub/models--infly--OpenCoder-8B-Instruct/snapshots/01badbbf10c2dfd7e2a0b5f570065ef44548576c/./tokenizer.model

[INFO|2025-05-12 13:05:15] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at /home/kiho/.cache/huggingface/hub/models--infly--OpenCoder-8B-Instruct/snapshots/01badbbf10c2dfd7e2a0b5f570065ef44548576c/added_tokens.json

[INFO|2025-05-12 13:05:15] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at /home/kiho/.cache/huggingface/hub/models--infly--OpenCoder-8B-Instruct/snapshots/01badbbf10c2dfd7e2a0b5f570065ef44548576c/special_tokens_map.json

[INFO|2025-05-12 13:05:15] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at /home/kiho/.cache/huggingface/hub/models--infly--OpenCoder-8B-Instruct/snapshots/01badbbf10c2dfd7e2a0b5f570065ef44548576c/tokenizer_config.json

[INFO|2025-05-12 13:05:15] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at None

[INFO|2025-05-12 13:05:15] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None

[INFO|2025-05-12 13:05:15] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

[INFO|2025-05-12 13:05:15] logging.py:157 >> Add <|im_end|> to stop words.

[INFO|2025-05-12 13:05:15] logging.py:157 >> Loading dataset Codes3_query_filtered_330k_nlx.json...