07/16/2024 16:46:13 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

07/16/2024 16:46:13 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>

07/16/2024 16:46:13 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

07/16/2024 16:46:13 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>

[INFO|parser.py:325] 2024-07-16 16:46:13,724 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: None

[INFO|tokenization_utils_base.py:2159] 2024-07-16 16:46:13,726 >> loading file tokenizer.json

[INFO|tokenization_utils_base.py:2159] 2024-07-16 16:46:13,726 >> loading file added_tokens.json

07/16/2024 16:46:13 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

07/16/2024 16:46:13 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>

07/16/2024 16:46:13 - INFO - llamafactory.hparams.parser - Process rank: 3, device: cuda:3, n_gpu: 1, distributed training: True, compute dtype: None

07/16/2024 16:46:13 - INFO - llamafactory.hparams.parser - Process rank: 7, device: cuda:7, n_gpu: 1, distributed training: True, compute dtype: None

07/16/2024 16:46:13 - INFO - llamafactory.hparams.parser - Process rank: 6, device: cuda:6, n_gpu: 1, distributed training: True, compute dtype: None

[INFO|tokenization_utils_base.py:2159] 2024-07-16 16:46:13,726 >> loading file special_tokens_map.json

[INFO|tokenization_utils_base.py:2159] 2024-07-16 16:46:13,726 >> loading file tokenizer_config.json

[WARNING|logging.py:313] 2024-07-16 16:46:13,988 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

[INFO|template.py:270] 2024-07-16 16:46:13,989 >> Replace eos token: <|eot_id|>

[INFO|loader.py:50] 2024-07-16 16:46:13,989 >> Loading dataset 0716_truthfulqa_benchmark_test_2.json...

07/16/2024 16:46:13 - INFO - llamafactory.hparams.parser - Process rank: 5, device: cuda:5, n_gpu: 1, distributed training: True, compute dtype: None

07/16/2024 16:46:14 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

07/16/2024 16:46:14 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>

07/16/2024 16:46:14 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

07/16/2024 16:46:14 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>

07/16/2024 16:46:14 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

07/16/2024 16:46:14 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>

07/16/2024 16:46:14 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

07/16/2024 16:46:14 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>

07/16/2024 16:46:15 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test_2.json...

07/16/2024 16:46:15 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test_2.json...

07/16/2024 16:46:15 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test_2.json...

07/16/2024 16:46:15 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test_2.json...

07/16/2024 16:46:15 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test_2.json...

07/16/2024 16:46:15 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test_2.json...

07/16/2024 16:46:15 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test_2.json...

[INFO|configuration_utils.py:731] 2024-07-16 16:46:19,192 >> loading configuration file saves/LLaMA3-8B-Chat/full/train_2024-07-16-15-59-42_llama3_2/config.json

[INFO|configuration_utils.py:800] 2024-07-16 16:46:19,193 >> Model config LlamaConfig {
  "_name_or_path": "saves/LLaMA3-8B-Chat/full/train_2024-07-16-15-59-42_llama3_2",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128009,
  "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": "4.42.3",
  "use_cache": false,
  "vocab_size": 128256
}


[INFO|patcher.py:81] 2024-07-16 16:46:19,193 >> Using KV cache for faster generation.

[INFO|modeling_utils.py:3553] 2024-07-16 16:46:19,217 >> loading weights file saves/LLaMA3-8B-Chat/full/train_2024-07-16-15-59-42_llama3_2/model.safetensors.index.json

[INFO|modeling_utils.py:1531] 2024-07-16 16:46:19,218 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.

[INFO|configuration_utils.py:1000] 2024-07-16 16:46:19,219 >> Generate config GenerationConfig {
  "bos_token_id": 128000,
  "eos_token_id": 128009
}


07/16/2024 16:46:19 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.

07/16/2024 16:46:19 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.

07/16/2024 16:46:19 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.

07/16/2024 16:46:19 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.

07/16/2024 16:46:19 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.

07/16/2024 16:46:19 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.

07/16/2024 16:46:19 - INFO - llamafactory.model.patcher - Using KV cache for faster generation.

[INFO|modeling_utils.py:4364] 2024-07-16 16:46:23,245 >> All model checkpoint weights were used when initializing LlamaForCausalLM.


[INFO|modeling_utils.py:4372] 2024-07-16 16:46:23,245 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at saves/LLaMA3-8B-Chat/full/train_2024-07-16-15-59-42_llama3_2.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.

[INFO|configuration_utils.py:953] 2024-07-16 16:46:23,249 >> loading configuration file saves/LLaMA3-8B-Chat/full/train_2024-07-16-15-59-42_llama3_2/generation_config.json

[INFO|configuration_utils.py:1000] 2024-07-16 16:46:23,249 >> Generate config GenerationConfig {
  "bos_token_id": 128000,
  "do_sample": true,
  "eos_token_id": [
    128001,
    128009
  ],
  "max_length": 4096,
  "temperature": 0.6,
  "top_p": 0.9
}


[INFO|attention.py:80] 2024-07-16 16:46:23,255 >> Using torch SDPA for faster training and inference.

[INFO|loader.py:196] 2024-07-16 16:46:23,260 >> all params: 8,030,261,248

[INFO|trainer.py:3788] 2024-07-16 16:46:23,374 >> 
***** Running Prediction *****

[INFO|trainer.py:3790] 2024-07-16 16:46:23,375 >>   Num examples = 1253

[INFO|trainer.py:3793] 2024-07-16 16:46:23,375 >>   Batch size = 2

[WARNING|logging.py:328] 2024-07-16 16:46:24,023 >> We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co./docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)

07/16/2024 16:46:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.

07/16/2024 16:46:24 - INFO - llamafactory.model.loader - all params: 8,030,261,248

07/16/2024 16:46:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.

07/16/2024 16:46:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.

07/16/2024 16:46:24 - INFO - llamafactory.model.loader - all params: 8,030,261,248

07/16/2024 16:46:24 - INFO - llamafactory.model.loader - all params: 8,030,261,248

07/16/2024 16:46:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.

07/16/2024 16:46:24 - INFO - llamafactory.model.loader - all params: 8,030,261,248

07/16/2024 16:46:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.

07/16/2024 16:46:24 - INFO - llamafactory.model.loader - all params: 8,030,261,248

07/16/2024 16:46:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.

07/16/2024 16:46:24 - INFO - llamafactory.model.loader - all params: 8,030,261,248

07/16/2024 16:46:24 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.

07/16/2024 16:46:24 - INFO - llamafactory.model.loader - all params: 8,030,261,248

07/16/2024 16:46:25 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co./docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)

07/16/2024 16:46:25 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co./docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)

07/16/2024 16:46:25 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co./docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)

07/16/2024 16:46:25 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co./docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)

07/16/2024 16:46:25 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co./docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)

07/16/2024 16:46:25 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co./docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)

07/16/2024 16:46:25 - WARNING - transformers.models.llama.modeling_llama - We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co./docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)

[INFO|trainer.py:127] 2024-07-16 16:46:32,944 >> Saving prediction results to saves/LLaMA3-8B-Chat/full/eval_2024-07-16-16-45-32/generated_predictions.jsonl