| 07/30/2024 01:57:42 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> | |
| 07/30/2024 01:57:42 - INFO - llamafactory.hparams.parser - Process rank: 7, device: cuda:7, n_gpu: 1, distributed training: True, compute dtype: None | |
| [INFO|parser.py:344] 2024-07-30 01:57:42,511 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: None | |
| 07/30/2024 01:57:42 - INFO - llamafactory.hparams.parser - Process rank: 2, device: cuda:2, n_gpu: 1, distributed training: True, compute dtype: None | |
| 07/30/2024 01:57:42 - INFO - llamafactory.hparams.parser - Process rank: 3, device: cuda:3, n_gpu: 1, distributed training: True, compute dtype: None | |
| 07/30/2024 01:57:42 - INFO - llamafactory.hparams.parser - Process rank: 6, device: cuda:6, n_gpu: 1, distributed training: True, compute dtype: None | |
| 07/30/2024 01:57:42 - INFO - llamafactory.hparams.parser - Process rank: 4, device: cuda:4, n_gpu: 1, distributed training: True, compute dtype: None | |
| 07/30/2024 01:57:42 - INFO - llamafactory.hparams.parser - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: None | |
| 07/30/2024 01:57:42 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> | |
| [INFO|tokenization_utils_base.py:2287] 2024-07-30 01:57:42,516 >> loading file tokenizer.json | |
| [INFO|tokenization_utils_base.py:2287] 2024-07-30 01:57:42,516 >> loading file added_tokens.json | |
| [INFO|tokenization_utils_base.py:2287] 2024-07-30 01:57:42,516 >> loading file special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:2287] 2024-07-30 01:57:42,516 >> loading file tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2533] 2024-07-30 01:57:42,783 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| [INFO|template.py:270] 2024-07-30 01:57:42,784 >> Replace eos token: <|eot_id|> | |
| [INFO|loader.py:52] 2024-07-30 01:57:42,785 >> Loading dataset convert_finetune_truth_dev.json... | |
| 07/30/2024 01:57:42 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> | |
| 07/30/2024 01:57:42 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> | |
| 07/30/2024 01:57:42 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> | |
| 07/30/2024 01:57:42 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> | |
| 07/30/2024 01:57:42 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|> | |
| 07/30/2024 01:57:43 - INFO - llamafactory.data.loader - Loading dataset convert_finetune_truth_dev.json... | |
| 07/30/2024 01:57:43 - INFO - llamafactory.data.loader - Loading dataset convert_finetune_truth_dev.json... | |
| 07/30/2024 01:57:43 - INFO - llamafactory.data.loader - Loading dataset convert_finetune_truth_dev.json... | |
| 07/30/2024 01:57:43 - INFO - llamafactory.data.loader - Loading dataset convert_finetune_truth_dev.json... | |
| 07/30/2024 01:57:43 - INFO - llamafactory.data.loader - Loading dataset convert_finetune_truth_dev.json... | |
| 07/30/2024 01:57:43 - INFO - llamafactory.data.loader - Loading dataset convert_finetune_truth_dev.json... | |
| 07/30/2024 01:57:43 - INFO - llamafactory.data.loader - Loading dataset convert_finetune_truth_dev.json... | |
| [INFO|configuration_utils.py:731] 2024-07-30 01:57:47,547 >> loading configuration file saves/LLaMA3.1-8B-Chat/full/train_2024-07-29-19-43-56_llama3.1_reeval_final/config.json | |
| [INFO|configuration_utils.py:800] 2024-07-30 01:57:47,549 >> Model config LlamaConfig { | |
| "_name_or_path": "saves/LLaMA3.1-8B-Chat/full/train_2024-07-29-19-43-56_llama3.1_reeval_final", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 131072, | |
| "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": { | |
| "factor": 8.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.43.3", | |
| "use_cache": false, | |
| "vocab_size": 128256 | |
| } | |
| [INFO|patcher.py:81] 2024-07-30 01:57:47,549 >> Using KV cache for faster generation. | |
| [INFO|modeling_utils.py:3631] 2024-07-30 01:57:47,572 >> loading weights file saves/LLaMA3.1-8B-Chat/full/train_2024-07-29-19-43-56_llama3.1_reeval_final/model.safetensors.index.json | |
| [INFO|modeling_utils.py:1572] 2024-07-30 01:57:47,572 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16. | |
| [INFO|configuration_utils.py:1038] 2024-07-30 01:57:47,574 >> Generate config GenerationConfig { | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ] | |
| } | |
| 07/30/2024 01:57:47 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. | |
| 07/30/2024 01:57:47 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. | |
| 07/30/2024 01:57:47 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. | |
| 07/30/2024 01:57:47 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. | |
| 07/30/2024 01:57:47 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. | |
| 07/30/2024 01:57:47 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. | |
| 07/30/2024 01:57:47 - INFO - llamafactory.model.patcher - Using KV cache for faster generation. | |
| [INFO|modeling_utils.py:4463] 2024-07-30 01:57:52,260 >> All model checkpoint weights were used when initializing LlamaForCausalLM. | |
| [INFO|modeling_utils.py:4471] 2024-07-30 01:57:52,260 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at saves/LLaMA3.1-8B-Chat/full/train_2024-07-29-19-43-56_llama3.1_reeval_final. | |
| 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:991] 2024-07-30 01:57:52,264 >> loading configuration file saves/LLaMA3.1-8B-Chat/full/train_2024-07-29-19-43-56_llama3.1_reeval_final/generation_config.json | |
| [INFO|configuration_utils.py:1038] 2024-07-30 01:57:52,264 >> Generate config GenerationConfig { | |
| "bos_token_id": 128000, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "temperature": 0.6, | |
| "top_p": 0.9 | |
| } | |
| [INFO|attention.py:84] 2024-07-30 01:57:52,271 >> Using torch SDPA for faster training and inference. | |
| [INFO|loader.py:196] 2024-07-30 01:57:52,276 >> all params: 8,030,261,248 | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.loader - all params: 8,030,261,248 | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.loader - all params: 8,030,261,248 | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.loader - all params: 8,030,261,248 | |
| [INFO|trainer.py:3819] 2024-07-30 01:57:52,384 >> | |
| ***** Running Prediction ***** | |
| [INFO|trainer.py:3821] 2024-07-30 01:57:52,384 >> Num examples = 2554 | |
| [INFO|trainer.py:3824] 2024-07-30 01:57:52,384 >> Batch size = 2 | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.loader - all params: 8,030,261,248 | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.loader - all params: 8,030,261,248 | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.loader - all params: 8,030,261,248 | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference. | |
| 07/30/2024 01:57:52 - INFO - llamafactory.model.loader - all params: 8,030,261,248 | |
| [WARNING|logging.py:328] 2024-07-30 01:57:53,028 >> 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) | |
| 07/30/2024 01:57:53 - 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) | |
| 07/30/2024 01:57:53 - 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) | |
| 07/30/2024 01:57:53 - 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) | |
| 07/30/2024 01:57:53 - 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) | |
| 07/30/2024 01:57:53 - 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) | |
| 07/30/2024 01:57:53 - 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) | |
| 07/30/2024 01:57:53 - 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] 2024-07-30 01:58:07,421 >> Saving prediction results to saves/LLaMA3.1-8B-Chat/full/eval_2024-07-30-01-57-05/generated_predictions.jsonl | |