07/23/2024 06:56:00 - INFO - llamafactory.hparams.parser - Process rank: 5, device: cuda:5, n_gpu: 1, distributed training: True, compute dtype: None 07/23/2024 06:56:00 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/23/2024 06:56:00 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> 07/23/2024 06:56:00 - INFO - llamafactory.hparams.parser - Process rank: 3, device: cuda:3, n_gpu: 1, distributed training: True, compute dtype: None 07/23/2024 06:56:00 - INFO - llamafactory.hparams.parser - Process rank: 4, device: cuda:4, n_gpu: 1, distributed training: True, compute dtype: None [INFO|parser.py:325] 2024-07-23 06:56:00,990 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: None [INFO|tokenization_utils_base.py:2159] 2024-07-23 06:56:00,992 >> loading file tokenizer.json [INFO|tokenization_utils_base.py:2159] 2024-07-23 06:56:00,992 >> loading file added_tokens.json 07/23/2024 06:56:01 - INFO - llamafactory.hparams.parser - Process rank: 6, device: cuda:6, n_gpu: 1, distributed training: True, compute dtype: None 07/23/2024 06:56:01 - INFO - llamafactory.hparams.parser - Process rank: 7, device: cuda:7, n_gpu: 1, distributed training: True, compute dtype: None 07/23/2024 06:56:01 - INFO - llamafactory.hparams.parser - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: None 07/23/2024 06:56:01 - INFO - llamafactory.hparams.parser - Process rank: 2, device: cuda:2, n_gpu: 1, distributed training: True, compute dtype: None 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> [INFO|tokenization_utils_base.py:2159] 2024-07-23 06:56:00,992 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2159] 2024-07-23 06:56:00,992 >> loading file tokenizer_config.json [WARNING|logging.py:313] 2024-07-23 06:56:01,268 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. [INFO|template.py:270] 2024-07-23 06:56:01,269 >> Replace eos token: <|eot_id|> [INFO|loader.py:50] 2024-07-23 06:56:01,269 >> Loading dataset 0716_truthfulqa_benchmark_test.json... 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> 07/23/2024 06:56:01 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/23/2024 06:56:01 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json... 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json... 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json... 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json... 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json... 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json... 07/23/2024 06:56:02 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_test.json... [INFO|configuration_utils.py:731] 2024-07-23 06:56:05,969 >> loading configuration file saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/config.json [INFO|configuration_utils.py:800] 2024-07-23 06:56:05,970 >> Model config LlamaConfig { "_name_or_path": "saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3", "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] 2024-07-23 06:56:05,971 >> Using KV cache for faster generation. [INFO|modeling_utils.py:3553] 2024-07-23 06:56:05,998 >> loading weights file saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/model.safetensors.index.json [INFO|modeling_utils.py:1531] 2024-07-23 06:56:05,999 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16. [INFO|configuration_utils.py:1000] 2024-07-23 06:56:06,002 >> Generate config GenerationConfig { "bos_token_id": 128000, "eos_token_id": 128009 } 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. 07/23/2024 06:56:06 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. [INFO|modeling_utils.py:4364] 2024-07-23 06:56:10,304 >> All model checkpoint weights were used when initializing LlamaForCausalLM. [INFO|modeling_utils.py:4372] 2024-07-23 06:56:10,304 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3. 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] 2024-07-23 06:56:10,308 >> loading configuration file saves/LLaMA3-8B-Chat/full/train_2024-07-23-06-00-05_llama3/generation_config.json [INFO|configuration_utils.py:1000] 2024-07-23 06:56:10,308 >> 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] 2024-07-23 06:56:10,317 >> Using torch SDPA for faster training and inference. [INFO|loader.py:196] 2024-07-23 06:56:10,322 >> all params: 8,030,261,248 [INFO|trainer.py:3788] 2024-07-23 06:56:10,436 >> ***** Running Prediction ***** [INFO|trainer.py:3790] 2024-07-23 06:56:10,436 >> Num examples = 1243 [INFO|trainer.py:3793] 2024-07-23 06:56:10,436 >> Batch size = 2 [WARNING|logging.py:328] 2024-07-23 06:56:11,121 >> 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) 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248 07/23/2024 06:56:11 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. 07/23/2024 06:56:11 - INFO - llamafactory.model.loader - all params: 8,030,261,248 07/23/2024 06:56:12 - 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) 07/23/2024 06:56:12 - 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) 07/23/2024 06:56:12 - 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) 07/23/2024 06:56:12 - 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) 07/23/2024 06:56:12 - 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) 07/23/2024 06:56:12 - 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) 07/23/2024 06:56:12 - 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] 2024-07-23 06:56:19,786 >> Saving prediction results to saves/LLaMA3-8B-Chat/full/eval_2024-07-23-06-52-5_llama3/generated_predictions.jsonl