| 05/30/2024 22:53:40 - INFO - transformers.tokenization_utils_base - loading file tokenizer.model | |
| 05/30/2024 22:53:40 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json | |
| 05/30/2024 22:53:40 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json | |
| 05/30/2024 22:53:40 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json | |
| 05/30/2024 22:53:40 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json | |
| 05/30/2024 22:53:41 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| 05/30/2024 22:53:41 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/LangGPT_community.jsonl... | |
| 05/30/2024 22:53:41 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json. | |
| 05/30/2024 22:53:42 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/langgpt_alpaca.jsonl... | |
| 05/30/2024 22:53:42 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json. | |
| 05/30/2024 22:53:44 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/langgpt_seed.jsonl... | |
| 05/30/2024 22:53:44 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json. | |
| 05/30/2024 22:54:12 - INFO - transformers.configuration_utils - loading configuration file /datas/huggingface/deepseek-llm-7b-chat/config.json | |
| 05/30/2024 22:54:12 - INFO - transformers.configuration_utils - Model config LlamaConfig { | |
| "_name_or_path": "/datas/huggingface/deepseek-llm-7b-chat", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 100000, | |
| "eos_token_id": 100001, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.2", | |
| "use_cache": true, | |
| "vocab_size": 102400 | |
| } | |
| 05/30/2024 22:54:12 - INFO - transformers.modeling_utils - loading weights file /datas/huggingface/deepseek-llm-7b-chat/pytorch_model.bin.index.json | |
| 05/30/2024 22:54:12 - INFO - transformers.modeling_utils - Instantiating LlamaForCausalLM model under default dtype torch.bfloat16. | |
| 05/30/2024 22:54:12 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig { | |
| "bos_token_id": 100000, | |
| "eos_token_id": 100001 | |
| } | |
| 05/30/2024 22:55:19 - INFO - transformers.modeling_utils - All model checkpoint weights were used when initializing LlamaForCausalLM. | |
| 05/30/2024 22:55:19 - INFO - transformers.modeling_utils - All the weights of LlamaForCausalLM were initialized from the model checkpoint at /datas/huggingface/deepseek-llm-7b-chat. | |
| 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. | |
| 05/30/2024 22:55:19 - INFO - transformers.generation.configuration_utils - loading configuration file /datas/huggingface/deepseek-llm-7b-chat/generation_config.json | |
| 05/30/2024 22:55:19 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig { | |
| "bos_token_id": 100000, | |
| "do_sample": true, | |
| "eos_token_id": 100001, | |
| "temperature": 0.7, | |
| "top_p": 0.95 | |
| } | |
| 05/30/2024 22:55:19 - INFO - llmtuner.model.utils.checkpointing - Gradient checkpointing enabled. | |
| 05/30/2024 22:55:19 - INFO - llmtuner.model.utils.attention - Using torch SDPA for faster training and inference. | |
| 05/30/2024 22:55:19 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA | |
| 05/30/2024 22:55:19 - INFO - llmtuner.model.loader - trainable params: 3932160 || all params: 6914297856 || trainable%: 0.0569 | |
| 05/30/2024 22:55:19 - INFO - transformers.trainer - Using auto half precision backend | |
| 05/30/2024 22:55:19 - INFO - transformers.trainer - ***** Running training ***** | |
| 05/30/2024 22:55:19 - INFO - transformers.trainer - Num examples = 8,531 | |
| 05/30/2024 22:55:19 - INFO - transformers.trainer - Num Epochs = 5 | |
| 05/30/2024 22:55:19 - INFO - transformers.trainer - Instantaneous batch size per device = 2 | |
| 05/30/2024 22:55:19 - INFO - transformers.trainer - Total train batch size (w. parallel, distributed & accumulation) = 16 | |
| 05/30/2024 22:55:19 - INFO - transformers.trainer - Gradient Accumulation steps = 8 | |
| 05/30/2024 22:55:19 - INFO - transformers.trainer - Total optimization steps = 2,665 | |
| 05/30/2024 22:55:19 - INFO - transformers.trainer - Number of trainable parameters = 3,932,160 | |
| 05/30/2024 22:56:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.8631, 'learning_rate': 5.0000e-05, 'epoch': 0.01} | |
| 05/30/2024 22:57:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.8372, 'learning_rate': 4.9998e-05, 'epoch': 0.02} | |
| 05/30/2024 22:58:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7690, 'learning_rate': 4.9996e-05, 'epoch': 0.03} | |
| 05/30/2024 22:59:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7971, 'learning_rate': 4.9993e-05, 'epoch': 0.04} | |
| 05/30/2024 23:00:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7329, 'learning_rate': 4.9989e-05, 'epoch': 0.05} | |
| 05/30/2024 23:01:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.7026, 'learning_rate': 4.9984e-05, 'epoch': 0.06} | |
| 05/30/2024 23:03:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7233, 'learning_rate': 4.9979e-05, 'epoch': 0.07} | |
| 05/30/2024 23:04:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7185, 'learning_rate': 4.9972e-05, 'epoch': 0.08} | |
| 05/30/2024 23:05:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.7380, 'learning_rate': 4.9965e-05, 'epoch': 0.08} | |
| 05/30/2024 23:06:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6857, 'learning_rate': 4.9957e-05, 'epoch': 0.09} | |
| 05/30/2024 23:07:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6763, 'learning_rate': 4.9947e-05, 'epoch': 0.10} | |
| 05/30/2024 23:08:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6673, 'learning_rate': 4.9937e-05, 'epoch': 0.11} | |
| 05/30/2024 23:09:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6489, 'learning_rate': 4.9927e-05, 'epoch': 0.12} | |
| 05/30/2024 23:10:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6335, 'learning_rate': 4.9915e-05, 'epoch': 0.13} | |
| 05/30/2024 23:11:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6739, 'learning_rate': 4.9902e-05, 'epoch': 0.14} | |
| 05/30/2024 23:12:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6087, 'learning_rate': 4.9889e-05, 'epoch': 0.15} | |
| 05/30/2024 23:14:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6207, 'learning_rate': 4.9875e-05, 'epoch': 0.16} | |
| 05/30/2024 23:15:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6429, 'learning_rate': 4.9859e-05, 'epoch': 0.17} | |
| 05/30/2024 23:16:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6033, 'learning_rate': 4.9843e-05, 'epoch': 0.18} | |
| 05/30/2024 23:17:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5861, 'learning_rate': 4.9826e-05, 'epoch': 0.19} | |
| 05/30/2024 23:17:13 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-100 | |
| 05/30/2024 23:17:13 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-100/tokenizer_config.json | |
| 05/30/2024 23:17:13 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-100/special_tokens_map.json | |
| 05/30/2024 23:18:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6604, 'learning_rate': 4.9809e-05, 'epoch': 0.20} | |
| 05/30/2024 23:19:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6140, 'learning_rate': 4.9790e-05, 'epoch': 0.21} | |
| 05/30/2024 23:20:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6376, 'learning_rate': 4.9771e-05, 'epoch': 0.22} | |
| 05/30/2024 23:21:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6502, 'learning_rate': 4.9750e-05, 'epoch': 0.23} | |
| 05/30/2024 23:22:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6162, 'learning_rate': 4.9729e-05, 'epoch': 0.23} | |
| 05/30/2024 23:23:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6333, 'learning_rate': 4.9707e-05, 'epoch': 0.24} | |
| 05/30/2024 23:25:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6405, 'learning_rate': 4.9684e-05, 'epoch': 0.25} | |
| 05/30/2024 23:26:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.5961, 'learning_rate': 4.9660e-05, 'epoch': 0.26} | |
| 05/30/2024 23:27:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.5913, 'learning_rate': 4.9636e-05, 'epoch': 0.27} | |
| 05/30/2024 23:28:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6354, 'learning_rate': 4.9610e-05, 'epoch': 0.28} | |
| 05/30/2024 23:29:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5861, 'learning_rate': 4.9584e-05, 'epoch': 0.29} | |
| 05/30/2024 23:30:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6287, 'learning_rate': 4.9557e-05, 'epoch': 0.30} | |
| 05/30/2024 23:31:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6480, 'learning_rate': 4.9529e-05, 'epoch': 0.31} | |
| 05/30/2024 23:32:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6162, 'learning_rate': 4.9500e-05, 'epoch': 0.32} | |
| 05/30/2024 23:33:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6344, 'learning_rate': 4.9470e-05, 'epoch': 0.33} | |
| 05/30/2024 23:34:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6029, 'learning_rate': 4.9439e-05, 'epoch': 0.34} | |
| 05/30/2024 23:36:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5946, 'learning_rate': 4.9408e-05, 'epoch': 0.35} | |
| 05/30/2024 23:37:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.5829, 'learning_rate': 4.9376e-05, 'epoch': 0.36} | |
| 05/30/2024 23:38:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6590, 'learning_rate': 4.9342e-05, 'epoch': 0.37} | |
| 05/30/2024 23:39:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6483, 'learning_rate': 4.9308e-05, 'epoch': 0.38} | |
| 05/30/2024 23:39:23 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-200 | |
| 05/30/2024 23:39:23 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-200/tokenizer_config.json | |
| 05/30/2024 23:39:23 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-200/special_tokens_map.json | |
| 05/30/2024 23:40:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6110, 'learning_rate': 4.9274e-05, 'epoch': 0.38} | |
| 05/30/2024 23:41:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6201, 'learning_rate': 4.9238e-05, 'epoch': 0.39} | |
| 05/30/2024 23:42:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5775, 'learning_rate': 4.9201e-05, 'epoch': 0.40} | |
| 05/30/2024 23:43:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6115, 'learning_rate': 4.9164e-05, 'epoch': 0.41} | |
| 05/30/2024 23:45:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5879, 'learning_rate': 4.9126e-05, 'epoch': 0.42} | |
| 05/30/2024 23:46:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5617, 'learning_rate': 4.9087e-05, 'epoch': 0.43} | |
| 05/30/2024 23:47:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6132, 'learning_rate': 4.9047e-05, 'epoch': 0.44} | |
| 05/30/2024 23:48:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5923, 'learning_rate': 4.9006e-05, 'epoch': 0.45} | |
| 05/30/2024 23:49:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6131, 'learning_rate': 4.8965e-05, 'epoch': 0.46} | |
| 05/30/2024 23:50:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6137, 'learning_rate': 4.8922e-05, 'epoch': 0.47} | |
| 05/30/2024 23:51:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6239, 'learning_rate': 4.8879e-05, 'epoch': 0.48} | |
| 05/30/2024 23:52:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.5665, 'learning_rate': 4.8835e-05, 'epoch': 0.49} | |
| 05/30/2024 23:53:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5801, 'learning_rate': 4.8790e-05, 'epoch': 0.50} | |
| 05/30/2024 23:55:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5682, 'learning_rate': 4.8744e-05, 'epoch': 0.51} | |
| 05/30/2024 23:56:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5698, 'learning_rate': 4.8698e-05, 'epoch': 0.52} | |
| 05/30/2024 23:57:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.5948, 'learning_rate': 4.8650e-05, 'epoch': 0.53} | |
| 05/30/2024 23:58:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5660, 'learning_rate': 4.8602e-05, 'epoch': 0.53} | |
| 05/30/2024 23:59:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.5867, 'learning_rate': 4.8553e-05, 'epoch': 0.54} | |
| 05/31/2024 00:00:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6045, 'learning_rate': 4.8503e-05, 'epoch': 0.55} | |
| 05/31/2024 00:01:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.5963, 'learning_rate': 4.8453e-05, 'epoch': 0.56} | |
| 05/31/2024 00:01:32 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-300 | |
| 05/31/2024 00:01:32 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-300/tokenizer_config.json | |
| 05/31/2024 00:01:32 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-300/special_tokens_map.json | |
| 05/31/2024 00:02:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6019, 'learning_rate': 4.8401e-05, 'epoch': 0.57} | |
| 05/31/2024 00:03:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5811, 'learning_rate': 4.8349e-05, 'epoch': 0.58} | |
| 05/31/2024 00:04:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5702, 'learning_rate': 4.8296e-05, 'epoch': 0.59} | |
| 05/31/2024 00:05:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6386, 'learning_rate': 4.8242e-05, 'epoch': 0.60} | |
| 05/31/2024 00:06:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.5937, 'learning_rate': 4.8188e-05, 'epoch': 0.61} | |
| 05/31/2024 00:08:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.5537, 'learning_rate': 4.8132e-05, 'epoch': 0.62} | |
| 05/31/2024 00:09:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6272, 'learning_rate': 4.8076e-05, 'epoch': 0.63} | |
| 05/31/2024 00:10:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5732, 'learning_rate': 4.8019e-05, 'epoch': 0.64} | |
| 05/31/2024 00:11:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6062, 'learning_rate': 4.7961e-05, 'epoch': 0.65} | |
| 05/31/2024 00:12:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6212, 'learning_rate': 4.7902e-05, 'epoch': 0.66} | |
| 05/31/2024 00:13:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5662, 'learning_rate': 4.7843e-05, 'epoch': 0.67} | |
| 05/31/2024 00:14:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6173, 'learning_rate': 4.7782e-05, 'epoch': 0.68} | |
| 05/31/2024 00:15:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5543, 'learning_rate': 4.7721e-05, 'epoch': 0.68} | |
| 05/31/2024 00:16:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5608, 'learning_rate': 4.7659e-05, 'epoch': 0.69} | |
| 05/31/2024 00:17:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6113, 'learning_rate': 4.7597e-05, 'epoch': 0.70} | |
| 05/31/2024 00:19:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6040, 'learning_rate': 4.7533e-05, 'epoch': 0.71} | |
| 05/31/2024 00:20:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.5725, 'learning_rate': 4.7469e-05, 'epoch': 0.72} | |
| 05/31/2024 00:21:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5792, 'learning_rate': 4.7404e-05, 'epoch': 0.73} | |
| 05/31/2024 00:22:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6010, 'learning_rate': 4.7338e-05, 'epoch': 0.74} | |
| 05/31/2024 00:23:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6168, 'learning_rate': 4.7272e-05, 'epoch': 0.75} | |
| 05/31/2024 00:23:23 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-400 | |
| 05/31/2024 00:23:23 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-400/tokenizer_config.json | |
| 05/31/2024 00:23:23 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-400/special_tokens_map.json | |
| 05/31/2024 00:24:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5719, 'learning_rate': 4.7204e-05, 'epoch': 0.76} | |
| 05/31/2024 00:25:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5798, 'learning_rate': 4.7136e-05, 'epoch': 0.77} | |
| 05/31/2024 00:26:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5852, 'learning_rate': 4.7068e-05, 'epoch': 0.78} | |
| 05/31/2024 00:27:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6183, 'learning_rate': 4.6998e-05, 'epoch': 0.79} | |
| 05/31/2024 00:29:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.5900, 'learning_rate': 4.6928e-05, 'epoch': 0.80} | |
| 05/31/2024 00:30:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.5661, 'learning_rate': 4.6856e-05, 'epoch': 0.81} | |
| 05/31/2024 00:31:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5222, 'learning_rate': 4.6784e-05, 'epoch': 0.82} | |
| 05/31/2024 00:32:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5407, 'learning_rate': 4.6712e-05, 'epoch': 0.83} | |
| 05/31/2024 00:33:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.5922, 'learning_rate': 4.6638e-05, 'epoch': 0.83} | |
| 05/31/2024 00:34:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.5714, 'learning_rate': 4.6564e-05, 'epoch': 0.84} | |
| 05/31/2024 00:35:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.5588, 'learning_rate': 4.6489e-05, 'epoch': 0.85} | |
| 05/31/2024 00:36:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5935, 'learning_rate': 4.6414e-05, 'epoch': 0.86} | |
| 05/31/2024 00:37:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.5626, 'learning_rate': 4.6337e-05, 'epoch': 0.87} | |
| 05/31/2024 00:38:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5625, 'learning_rate': 4.6260e-05, 'epoch': 0.88} | |
| 05/31/2024 00:39:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.5860, 'learning_rate': 4.6182e-05, 'epoch': 0.89} | |
| 05/31/2024 00:40:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.5806, 'learning_rate': 4.6103e-05, 'epoch': 0.90} | |
| 05/31/2024 00:42:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5682, 'learning_rate': 4.6024e-05, 'epoch': 0.91} | |
| 05/31/2024 00:43:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.5594, 'learning_rate': 4.5944e-05, 'epoch': 0.92} | |
| 05/31/2024 00:44:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6643, 'learning_rate': 4.5863e-05, 'epoch': 0.93} | |
| 05/31/2024 00:45:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5672, 'learning_rate': 4.5782e-05, 'epoch': 0.94} | |
| 05/31/2024 00:45:21 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-500 | |
| 05/31/2024 00:45:21 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-500/tokenizer_config.json | |
| 05/31/2024 00:45:21 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-500/special_tokens_map.json | |
| 05/31/2024 00:46:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.5906, 'learning_rate': 4.5699e-05, 'epoch': 0.95} | |
| 05/31/2024 00:47:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6222, 'learning_rate': 4.5616e-05, 'epoch': 0.96} | |
| 05/31/2024 00:48:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.5787, 'learning_rate': 4.5533e-05, 'epoch': 0.97} | |
| 05/31/2024 00:49:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.5627, 'learning_rate': 4.5448e-05, 'epoch': 0.98} | |
| 05/31/2024 00:51:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.5704, 'learning_rate': 4.5363e-05, 'epoch': 0.98} | |
| 05/31/2024 00:52:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5879, 'learning_rate': 4.5277e-05, 'epoch': 0.99} | |
| 05/31/2024 00:53:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.5509, 'learning_rate': 4.5191e-05, 'epoch': 1.00} | |
| 05/31/2024 00:54:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.5293, 'learning_rate': 4.5103e-05, 'epoch': 1.01} | |
| 05/31/2024 00:55:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5393, 'learning_rate': 4.5016e-05, 'epoch': 1.02} | |
| 05/31/2024 00:56:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.5949, 'learning_rate': 4.4927e-05, 'epoch': 1.03} | |
| 05/31/2024 00:57:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5715, 'learning_rate': 4.4838e-05, 'epoch': 1.04} | |
| 05/31/2024 00:59:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5321, 'learning_rate': 4.4748e-05, 'epoch': 1.05} | |
| 05/31/2024 01:00:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.5910, 'learning_rate': 4.4657e-05, 'epoch': 1.06} | |
| 05/31/2024 01:01:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.5834, 'learning_rate': 4.4565e-05, 'epoch': 1.07} | |
| 05/31/2024 01:02:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.5609, 'learning_rate': 4.4473e-05, 'epoch': 1.08} | |
| 05/31/2024 01:03:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.5792, 'learning_rate': 4.4381e-05, 'epoch': 1.09} | |
| 05/31/2024 01:04:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5680, 'learning_rate': 4.4287e-05, 'epoch': 1.10} | |
| 05/31/2024 01:05:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5428, 'learning_rate': 4.4193e-05, 'epoch': 1.11} | |
| 05/31/2024 01:06:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5640, 'learning_rate': 4.4098e-05, 'epoch': 1.12} | |
| 05/31/2024 01:07:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.5625, 'learning_rate': 4.4003e-05, 'epoch': 1.13} | |
| 05/31/2024 01:07:45 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-600 | |
| 05/31/2024 01:07:45 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-600/tokenizer_config.json | |
| 05/31/2024 01:07:45 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-600/special_tokens_map.json | |
| 05/31/2024 01:08:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5716, 'learning_rate': 4.3907e-05, 'epoch': 1.13} | |
| 05/31/2024 01:09:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.5394, 'learning_rate': 4.3810e-05, 'epoch': 1.14} | |
| 05/31/2024 01:11:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5344, 'learning_rate': 4.3713e-05, 'epoch': 1.15} | |
| 05/31/2024 01:12:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.5440, 'learning_rate': 4.3615e-05, 'epoch': 1.16} | |
| 05/31/2024 01:13:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.5481, 'learning_rate': 4.3516e-05, 'epoch': 1.17} | |
| 05/31/2024 01:14:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.5715, 'learning_rate': 4.3417e-05, 'epoch': 1.18} | |
| 05/31/2024 01:15:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5602, 'learning_rate': 4.3317e-05, 'epoch': 1.19} | |
| 05/31/2024 01:16:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5441, 'learning_rate': 4.3216e-05, 'epoch': 1.20} | |
| 05/31/2024 01:17:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5369, 'learning_rate': 4.3115e-05, 'epoch': 1.21} | |
| 05/31/2024 01:18:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5770, 'learning_rate': 4.3013e-05, 'epoch': 1.22} | |
| 05/31/2024 01:19:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.5762, 'learning_rate': 4.2911e-05, 'epoch': 1.23} | |
| 05/31/2024 01:20:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.5726, 'learning_rate': 4.2807e-05, 'epoch': 1.24} | |
| 05/31/2024 01:22:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5686, 'learning_rate': 4.2704e-05, 'epoch': 1.25} | |
| 05/31/2024 01:23:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6473, 'learning_rate': 4.2599e-05, 'epoch': 1.26} | |
| 05/31/2024 01:24:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6009, 'learning_rate': 4.2494e-05, 'epoch': 1.27} | |
| 05/31/2024 01:25:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5301, 'learning_rate': 4.2389e-05, 'epoch': 1.28} | |
| 05/31/2024 01:26:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.5715, 'learning_rate': 4.2283e-05, 'epoch': 1.28} | |
| 05/31/2024 01:27:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6022, 'learning_rate': 4.2176e-05, 'epoch': 1.29} | |
| 05/31/2024 01:28:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5765, 'learning_rate': 4.2069e-05, 'epoch': 1.30} | |
| 05/31/2024 01:29:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5521, 'learning_rate': 4.1961e-05, 'epoch': 1.31} | |
| 05/31/2024 01:29:40 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-700 | |
| 05/31/2024 01:29:40 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-700/tokenizer_config.json | |
| 05/31/2024 01:29:40 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-700/special_tokens_map.json | |
| 05/31/2024 01:30:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5709, 'learning_rate': 4.1852e-05, 'epoch': 1.32} | |
| 05/31/2024 01:31:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5751, 'learning_rate': 4.1743e-05, 'epoch': 1.33} | |
| 05/31/2024 01:32:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.5276, 'learning_rate': 4.1633e-05, 'epoch': 1.34} | |
| 05/31/2024 01:34:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5654, 'learning_rate': 4.1523e-05, 'epoch': 1.35} | |
| 05/31/2024 01:35:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5771, 'learning_rate': 4.1412e-05, 'epoch': 1.36} | |
| 05/31/2024 01:36:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5849, 'learning_rate': 4.1301e-05, 'epoch': 1.37} | |
| 05/31/2024 01:37:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.5539, 'learning_rate': 4.1189e-05, 'epoch': 1.38} | |
| 05/31/2024 01:38:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5408, 'learning_rate': 4.1076e-05, 'epoch': 1.39} | |
| 05/31/2024 01:39:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.5717, 'learning_rate': 4.0963e-05, 'epoch': 1.40} | |
| 05/31/2024 01:40:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5612, 'learning_rate': 4.0849e-05, 'epoch': 1.41} | |
| 05/31/2024 01:41:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5587, 'learning_rate': 4.0735e-05, 'epoch': 1.42} | |
| 05/31/2024 01:42:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5965, 'learning_rate': 4.0620e-05, 'epoch': 1.43} | |
| 05/31/2024 01:43:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5576, 'learning_rate': 4.0505e-05, 'epoch': 1.43} | |
| 05/31/2024 01:44:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5481, 'learning_rate': 4.0389e-05, 'epoch': 1.44} | |
| 05/31/2024 01:46:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5343, 'learning_rate': 4.0273e-05, 'epoch': 1.45} | |
| 05/31/2024 01:47:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.5677, 'learning_rate': 4.0156e-05, 'epoch': 1.46} | |
| 05/31/2024 01:48:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5650, 'learning_rate': 4.0038e-05, 'epoch': 1.47} | |
| 05/31/2024 01:49:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6299, 'learning_rate': 3.9920e-05, 'epoch': 1.48} | |
| 05/31/2024 01:50:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5588, 'learning_rate': 3.9802e-05, 'epoch': 1.49} | |
| 05/31/2024 01:51:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6042, 'learning_rate': 3.9683e-05, 'epoch': 1.50} | |
| 05/31/2024 01:51:28 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-800 | |
| 05/31/2024 01:51:28 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-800/tokenizer_config.json | |
| 05/31/2024 01:51:28 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-800/special_tokens_map.json | |
| 05/31/2024 01:52:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5613, 'learning_rate': 3.9563e-05, 'epoch': 1.51} | |
| 05/31/2024 01:53:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5466, 'learning_rate': 3.9443e-05, 'epoch': 1.52} | |
| 05/31/2024 01:54:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5305, 'learning_rate': 3.9323e-05, 'epoch': 1.53} | |
| 05/31/2024 01:55:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5822, 'learning_rate': 3.9202e-05, 'epoch': 1.54} | |
| 05/31/2024 01:56:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5585, 'learning_rate': 3.9080e-05, 'epoch': 1.55} | |
| 05/31/2024 01:57:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.5693, 'learning_rate': 3.8958e-05, 'epoch': 1.56} | |
| 05/31/2024 01:59:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.5137, 'learning_rate': 3.8836e-05, 'epoch': 1.57} | |
| 05/31/2024 02:00:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5622, 'learning_rate': 3.8713e-05, 'epoch': 1.58} | |
| 05/31/2024 02:01:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5321, 'learning_rate': 3.8589e-05, 'epoch': 1.58} | |
| 05/31/2024 02:02:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5623, 'learning_rate': 3.8465e-05, 'epoch': 1.59} | |
| 05/31/2024 02:03:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.5781, 'learning_rate': 3.8341e-05, 'epoch': 1.60} | |
| 05/31/2024 02:04:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5724, 'learning_rate': 3.8216e-05, 'epoch': 1.61} | |
| 05/31/2024 02:05:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5351, 'learning_rate': 3.8091e-05, 'epoch': 1.62} | |
| 05/31/2024 02:06:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.5726, 'learning_rate': 3.7965e-05, 'epoch': 1.63} | |
| 05/31/2024 02:07:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5326, 'learning_rate': 3.7839e-05, 'epoch': 1.64} | |
| 05/31/2024 02:08:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5384, 'learning_rate': 3.7712e-05, 'epoch': 1.65} | |
| 05/31/2024 02:10:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.5808, 'learning_rate': 3.7585e-05, 'epoch': 1.66} | |
| 05/31/2024 02:11:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5123, 'learning_rate': 3.7457e-05, 'epoch': 1.67} | |
| 05/31/2024 02:12:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5437, 'learning_rate': 3.7329e-05, 'epoch': 1.68} | |
| 05/31/2024 02:13:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6003, 'learning_rate': 3.7201e-05, 'epoch': 1.69} | |
| 05/31/2024 02:13:20 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-900 | |
| 05/31/2024 02:13:20 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-900/tokenizer_config.json | |
| 05/31/2024 02:13:20 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-900/special_tokens_map.json | |
| 05/31/2024 02:14:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5941, 'learning_rate': 3.7072e-05, 'epoch': 1.70} | |
| 05/31/2024 02:15:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6019, 'learning_rate': 3.6943e-05, 'epoch': 1.71} | |
| 05/31/2024 02:16:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.5774, 'learning_rate': 3.6813e-05, 'epoch': 1.72} | |
| 05/31/2024 02:17:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6598, 'learning_rate': 3.6683e-05, 'epoch': 1.73} | |
| 05/31/2024 02:19:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5536, 'learning_rate': 3.6553e-05, 'epoch': 1.73} | |
| 05/31/2024 02:20:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5606, 'learning_rate': 3.6422e-05, 'epoch': 1.74} | |
| 05/31/2024 02:21:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5553, 'learning_rate': 3.6291e-05, 'epoch': 1.75} | |
| 05/31/2024 02:22:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5974, 'learning_rate': 3.6159e-05, 'epoch': 1.76} | |
| 05/31/2024 02:23:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.5381, 'learning_rate': 3.6027e-05, 'epoch': 1.77} | |
| 05/31/2024 02:24:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5858, 'learning_rate': 3.5894e-05, 'epoch': 1.78} | |
| 05/31/2024 02:25:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.5520, 'learning_rate': 3.5762e-05, 'epoch': 1.79} | |
| 05/31/2024 02:26:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6042, 'learning_rate': 3.5628e-05, 'epoch': 1.80} | |
| 05/31/2024 02:27:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.5418, 'learning_rate': 3.5495e-05, 'epoch': 1.81} | |
| 05/31/2024 02:29:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5743, 'learning_rate': 3.5361e-05, 'epoch': 1.82} | |
| 05/31/2024 02:30:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5245, 'learning_rate': 3.5227e-05, 'epoch': 1.83} | |
| 05/31/2024 02:31:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5232, 'learning_rate': 3.5092e-05, 'epoch': 1.84} | |
| 05/31/2024 02:32:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5354, 'learning_rate': 3.4957e-05, 'epoch': 1.85} | |
| 05/31/2024 02:33:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5296, 'learning_rate': 3.4822e-05, 'epoch': 1.86} | |
| 05/31/2024 02:34:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5486, 'learning_rate': 3.4686e-05, 'epoch': 1.87} | |
| 05/31/2024 02:35:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.5339, 'learning_rate': 3.4550e-05, 'epoch': 1.88} | |
| 05/31/2024 02:35:42 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1000 | |
| 05/31/2024 02:35:42 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1000/tokenizer_config.json | |
| 05/31/2024 02:35:42 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1000/special_tokens_map.json | |
| 05/31/2024 02:36:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5105, 'learning_rate': 3.4414e-05, 'epoch': 1.88} | |
| 05/31/2024 02:37:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.5353, 'learning_rate': 3.4277e-05, 'epoch': 1.89} | |
| 05/31/2024 02:38:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5740, 'learning_rate': 3.4140e-05, 'epoch': 1.90} | |
| 05/31/2024 02:40:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5580, 'learning_rate': 3.4003e-05, 'epoch': 1.91} | |
| 05/31/2024 02:41:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5312, 'learning_rate': 3.3865e-05, 'epoch': 1.92} | |
| 05/31/2024 02:42:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.5401, 'learning_rate': 3.3727e-05, 'epoch': 1.93} | |
| 05/31/2024 02:43:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5468, 'learning_rate': 3.3589e-05, 'epoch': 1.94} | |
| 05/31/2024 02:44:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.5533, 'learning_rate': 3.3450e-05, 'epoch': 1.95} | |
| 05/31/2024 02:45:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5615, 'learning_rate': 3.3312e-05, 'epoch': 1.96} | |
| 05/31/2024 02:46:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5201, 'learning_rate': 3.3172e-05, 'epoch': 1.97} | |
| 05/31/2024 02:47:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5404, 'learning_rate': 3.3033e-05, 'epoch': 1.98} | |
| 05/31/2024 02:48:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.5162, 'learning_rate': 3.2893e-05, 'epoch': 1.99} | |
| 05/31/2024 02:49:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5430, 'learning_rate': 3.2753e-05, 'epoch': 2.00} | |
| 05/31/2024 02:51:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.4996, 'learning_rate': 3.2613e-05, 'epoch': 2.01} | |
| 05/31/2024 02:52:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.5008, 'learning_rate': 3.2473e-05, 'epoch': 2.02} | |
| 05/31/2024 02:53:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5758, 'learning_rate': 3.2332e-05, 'epoch': 2.03} | |
| 05/31/2024 02:54:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5323, 'learning_rate': 3.2191e-05, 'epoch': 2.03} | |
| 05/31/2024 02:55:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5572, 'learning_rate': 3.2050e-05, 'epoch': 2.04} | |
| 05/31/2024 02:56:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.5761, 'learning_rate': 3.1908e-05, 'epoch': 2.05} | |
| 05/31/2024 02:57:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5328, 'learning_rate': 3.1767e-05, 'epoch': 2.06} | |
| 05/31/2024 02:57:46 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1100 | |
| 05/31/2024 02:57:46 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1100/tokenizer_config.json | |
| 05/31/2024 02:57:46 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1100/special_tokens_map.json | |
| 05/31/2024 02:58:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.4987, 'learning_rate': 3.1625e-05, 'epoch': 2.07} | |
| 05/31/2024 02:59:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.5158, 'learning_rate': 3.1482e-05, 'epoch': 2.08} | |
| 05/31/2024 03:01:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5462, 'learning_rate': 3.1340e-05, 'epoch': 2.09} | |
| 05/31/2024 03:02:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5337, 'learning_rate': 3.1197e-05, 'epoch': 2.10} | |
| 05/31/2024 03:03:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5591, 'learning_rate': 3.1054e-05, 'epoch': 2.11} | |
| 05/31/2024 03:04:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.5473, 'learning_rate': 3.0911e-05, 'epoch': 2.12} | |
| 05/31/2024 03:05:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.5381, 'learning_rate': 3.0768e-05, 'epoch': 2.13} | |
| 05/31/2024 03:06:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6433, 'learning_rate': 3.0625e-05, 'epoch': 2.14} | |
| 05/31/2024 03:07:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.5256, 'learning_rate': 3.0481e-05, 'epoch': 2.15} | |
| 05/31/2024 03:08:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.5120, 'learning_rate': 3.0337e-05, 'epoch': 2.16} | |
| 05/31/2024 03:09:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5319, 'learning_rate': 3.0193e-05, 'epoch': 2.17} | |
| 05/31/2024 03:10:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.5360, 'learning_rate': 3.0049e-05, 'epoch': 2.18} | |
| 05/31/2024 03:12:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.5440, 'learning_rate': 2.9904e-05, 'epoch': 2.18} | |
| 05/31/2024 03:13:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5989, 'learning_rate': 2.9760e-05, 'epoch': 2.19} | |
| 05/31/2024 03:14:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.5598, 'learning_rate': 2.9615e-05, 'epoch': 2.20} | |
| 05/31/2024 03:15:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.5667, 'learning_rate': 2.9470e-05, 'epoch': 2.21} | |
| 05/31/2024 03:16:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.5661, 'learning_rate': 2.9325e-05, 'epoch': 2.22} | |
| 05/31/2024 03:17:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5312, 'learning_rate': 2.9180e-05, 'epoch': 2.23} | |
| 05/31/2024 03:18:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5118, 'learning_rate': 2.9035e-05, 'epoch': 2.24} | |
| 05/31/2024 03:19:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5503, 'learning_rate': 2.8889e-05, 'epoch': 2.25} | |
| 05/31/2024 03:19:53 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1200 | |
| 05/31/2024 03:19:53 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1200/tokenizer_config.json | |
| 05/31/2024 03:19:53 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1200/special_tokens_map.json | |
| 05/31/2024 03:20:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.5345, 'learning_rate': 2.8743e-05, 'epoch': 2.26} | |
| 05/31/2024 03:22:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.5940, 'learning_rate': 2.8598e-05, 'epoch': 2.27} | |
| 05/31/2024 03:23:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5237, 'learning_rate': 2.8452e-05, 'epoch': 2.28} | |
| 05/31/2024 03:24:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.5142, 'learning_rate': 2.8306e-05, 'epoch': 2.29} | |
| 05/31/2024 03:25:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5414, 'learning_rate': 2.8160e-05, 'epoch': 2.30} | |
| 05/31/2024 03:26:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.5250, 'learning_rate': 2.8013e-05, 'epoch': 2.31} | |
| 05/31/2024 03:27:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5435, 'learning_rate': 2.7867e-05, 'epoch': 2.32} | |
| 05/31/2024 03:28:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5355, 'learning_rate': 2.7721e-05, 'epoch': 2.33} | |
| 05/31/2024 03:29:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.5647, 'learning_rate': 2.7574e-05, 'epoch': 2.33} | |
| 05/31/2024 03:30:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5580, 'learning_rate': 2.7428e-05, 'epoch': 2.34} | |
| 05/31/2024 03:31:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.5683, 'learning_rate': 2.7281e-05, 'epoch': 2.35} | |
| 05/31/2024 03:33:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.5172, 'learning_rate': 2.7134e-05, 'epoch': 2.36} | |
| 05/31/2024 03:34:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5339, 'learning_rate': 2.6987e-05, 'epoch': 2.37} | |
| 05/31/2024 03:35:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6172, 'learning_rate': 2.6840e-05, 'epoch': 2.38} | |
| 05/31/2024 03:36:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5337, 'learning_rate': 2.6693e-05, 'epoch': 2.39} | |
| 05/31/2024 03:37:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.5903, 'learning_rate': 2.6546e-05, 'epoch': 2.40} | |
| 05/31/2024 03:38:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5693, 'learning_rate': 2.6399e-05, 'epoch': 2.41} | |
| 05/31/2024 03:39:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5415, 'learning_rate': 2.6252e-05, 'epoch': 2.42} | |
| 05/31/2024 03:40:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.5063, 'learning_rate': 2.6105e-05, 'epoch': 2.43} | |
| 05/31/2024 03:41:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5556, 'learning_rate': 2.5958e-05, 'epoch': 2.44} | |
| 05/31/2024 03:41:53 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1300 | |
| 05/31/2024 03:41:53 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1300/tokenizer_config.json | |
| 05/31/2024 03:41:53 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1300/special_tokens_map.json | |
| 05/31/2024 03:43:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6267, 'learning_rate': 2.5810e-05, 'epoch': 2.45} | |
| 05/31/2024 03:44:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.5637, 'learning_rate': 2.5663e-05, 'epoch': 2.46} | |
| 05/31/2024 03:45:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5426, 'learning_rate': 2.5516e-05, 'epoch': 2.47} | |
| 05/31/2024 03:46:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.5028, 'learning_rate': 2.5368e-05, 'epoch': 2.48} | |
| 05/31/2024 03:47:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5536, 'learning_rate': 2.5221e-05, 'epoch': 2.48} | |
| 05/31/2024 03:48:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.5199, 'learning_rate': 2.5074e-05, 'epoch': 2.49} | |
| 05/31/2024 03:49:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.5328, 'learning_rate': 2.4926e-05, 'epoch': 2.50} | |
| 05/31/2024 03:50:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5625, 'learning_rate': 2.4779e-05, 'epoch': 2.51} | |
| 05/31/2024 03:51:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5238, 'learning_rate': 2.4632e-05, 'epoch': 2.52} | |
| 05/31/2024 03:52:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.5108, 'learning_rate': 2.4484e-05, 'epoch': 2.53} | |
| 05/31/2024 03:53:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5603, 'learning_rate': 2.4337e-05, 'epoch': 2.54} | |
| 05/31/2024 03:55:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5740, 'learning_rate': 2.4190e-05, 'epoch': 2.55} | |
| 05/31/2024 03:56:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5086, 'learning_rate': 2.4042e-05, 'epoch': 2.56} | |
| 05/31/2024 03:57:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.5052, 'learning_rate': 2.3895e-05, 'epoch': 2.57} | |
| 05/31/2024 03:58:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5636, 'learning_rate': 2.3748e-05, 'epoch': 2.58} | |
| 05/31/2024 03:59:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.5367, 'learning_rate': 2.3601e-05, 'epoch': 2.59} | |
| 05/31/2024 04:00:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5316, 'learning_rate': 2.3454e-05, 'epoch': 2.60} | |
| 05/31/2024 04:01:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.5161, 'learning_rate': 2.3307e-05, 'epoch': 2.61} | |
| 05/31/2024 04:02:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.5728, 'learning_rate': 2.3160e-05, 'epoch': 2.62} | |
| 05/31/2024 04:03:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5436, 'learning_rate': 2.3013e-05, 'epoch': 2.63} | |
| 05/31/2024 04:03:56 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1400 | |
| 05/31/2024 04:03:56 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1400/tokenizer_config.json | |
| 05/31/2024 04:03:56 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1400/special_tokens_map.json | |
| 05/31/2024 04:05:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5236, 'learning_rate': 2.2866e-05, 'epoch': 2.63} | |
| 05/31/2024 04:06:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5078, 'learning_rate': 2.2719e-05, 'epoch': 2.64} | |
| 05/31/2024 04:07:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5030, 'learning_rate': 2.2572e-05, 'epoch': 2.65} | |
| 05/31/2024 04:08:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5348, 'learning_rate': 2.2426e-05, 'epoch': 2.66} | |
| 05/31/2024 04:09:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.5343, 'learning_rate': 2.2279e-05, 'epoch': 2.67} | |
| 05/31/2024 04:10:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5586, 'learning_rate': 2.2133e-05, 'epoch': 2.68} | |
| 05/31/2024 04:11:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5474, 'learning_rate': 2.1987e-05, 'epoch': 2.69} | |
| 05/31/2024 04:12:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5474, 'learning_rate': 2.1840e-05, 'epoch': 2.70} | |
| 05/31/2024 04:13:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.5720, 'learning_rate': 2.1694e-05, 'epoch': 2.71} | |
| 05/31/2024 04:14:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5636, 'learning_rate': 2.1548e-05, 'epoch': 2.72} | |
| 05/31/2024 04:15:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.5305, 'learning_rate': 2.1402e-05, 'epoch': 2.73} | |
| 05/31/2024 04:16:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5273, 'learning_rate': 2.1257e-05, 'epoch': 2.74} | |
| 05/31/2024 04:17:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5383, 'learning_rate': 2.1111e-05, 'epoch': 2.75} | |
| 05/31/2024 04:18:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.5482, 'learning_rate': 2.0965e-05, 'epoch': 2.76} | |
| 05/31/2024 04:20:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.5226, 'learning_rate': 2.0820e-05, 'epoch': 2.77} | |
| 05/31/2024 04:21:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5276, 'learning_rate': 2.0675e-05, 'epoch': 2.78} | |
| 05/31/2024 04:22:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5636, 'learning_rate': 2.0530e-05, 'epoch': 2.78} | |
| 05/31/2024 04:23:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.5531, 'learning_rate': 2.0385e-05, 'epoch': 2.79} | |
| 05/31/2024 04:24:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5709, 'learning_rate': 2.0240e-05, 'epoch': 2.80} | |
| 05/31/2024 04:25:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.5300, 'learning_rate': 2.0096e-05, 'epoch': 2.81} | |
| 05/31/2024 04:25:34 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1500 | |
| 05/31/2024 04:25:34 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1500/tokenizer_config.json | |
| 05/31/2024 04:25:34 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1500/special_tokens_map.json | |
| 05/31/2024 04:26:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5258, 'learning_rate': 1.9951e-05, 'epoch': 2.82} | |
| 05/31/2024 04:27:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5360, 'learning_rate': 1.9807e-05, 'epoch': 2.83} | |
| 05/31/2024 04:28:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.5724, 'learning_rate': 1.9663e-05, 'epoch': 2.84} | |
| 05/31/2024 04:29:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5325, 'learning_rate': 1.9519e-05, 'epoch': 2.85} | |
| 05/31/2024 04:30:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.5505, 'learning_rate': 1.9375e-05, 'epoch': 2.86} | |
| 05/31/2024 04:32:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5153, 'learning_rate': 1.9232e-05, 'epoch': 2.87} | |
| 05/31/2024 04:33:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5411, 'learning_rate': 1.9089e-05, 'epoch': 2.88} | |
| 05/31/2024 04:34:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.5085, 'learning_rate': 1.8946e-05, 'epoch': 2.89} | |
| 05/31/2024 04:35:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5683, 'learning_rate': 1.8803e-05, 'epoch': 2.90} | |
| 05/31/2024 04:36:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5393, 'learning_rate': 1.8660e-05, 'epoch': 2.91} | |
| 05/31/2024 04:37:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5303, 'learning_rate': 1.8518e-05, 'epoch': 2.92} | |
| 05/31/2024 04:38:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5599, 'learning_rate': 1.8375e-05, 'epoch': 2.93} | |
| 05/31/2024 04:39:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5712, 'learning_rate': 1.8233e-05, 'epoch': 2.93} | |
| 05/31/2024 04:40:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.5459, 'learning_rate': 1.8092e-05, 'epoch': 2.94} | |
| 05/31/2024 04:41:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5754, 'learning_rate': 1.7950e-05, 'epoch': 2.95} | |
| 05/31/2024 04:43:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5615, 'learning_rate': 1.7809e-05, 'epoch': 2.96} | |
| 05/31/2024 04:44:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.5135, 'learning_rate': 1.7668e-05, 'epoch': 2.97} | |
| 05/31/2024 04:45:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5660, 'learning_rate': 1.7527e-05, 'epoch': 2.98} | |
| 05/31/2024 04:46:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5790, 'learning_rate': 1.7387e-05, 'epoch': 2.99} | |
| 05/31/2024 04:47:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5286, 'learning_rate': 1.7247e-05, 'epoch': 3.00} | |
| 05/31/2024 04:47:21 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1600 | |
| 05/31/2024 04:47:21 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1600/tokenizer_config.json | |
| 05/31/2024 04:47:21 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1600/special_tokens_map.json | |
| 05/31/2024 04:48:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.5806, 'learning_rate': 1.7107e-05, 'epoch': 3.01} | |
| 05/31/2024 04:49:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5340, 'learning_rate': 1.6967e-05, 'epoch': 3.02} | |
| 05/31/2024 04:50:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.5507, 'learning_rate': 1.6828e-05, 'epoch': 3.03} | |
| 05/31/2024 04:51:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5537, 'learning_rate': 1.6688e-05, 'epoch': 3.04} | |
| 05/31/2024 04:52:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.5575, 'learning_rate': 1.6550e-05, 'epoch': 3.05} | |
| 05/31/2024 04:53:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5043, 'learning_rate': 1.6411e-05, 'epoch': 3.06} | |
| 05/31/2024 04:55:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.4903, 'learning_rate': 1.6273e-05, 'epoch': 3.07} | |
| 05/31/2024 04:56:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.5934, 'learning_rate': 1.6135e-05, 'epoch': 3.08} | |
| 05/31/2024 04:57:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.4922, 'learning_rate': 1.5997e-05, 'epoch': 3.08} | |
| 05/31/2024 04:58:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5327, 'learning_rate': 1.5860e-05, 'epoch': 3.09} | |
| 05/31/2024 04:59:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5836, 'learning_rate': 1.5723e-05, 'epoch': 3.10} | |
| 05/31/2024 05:00:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.5270, 'learning_rate': 1.5586e-05, 'epoch': 3.11} | |
| 05/31/2024 05:01:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5466, 'learning_rate': 1.5450e-05, 'epoch': 3.12} | |
| 05/31/2024 05:02:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5162, 'learning_rate': 1.5314e-05, 'epoch': 3.13} | |
| 05/31/2024 05:03:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.4985, 'learning_rate': 1.5178e-05, 'epoch': 3.14} | |
| 05/31/2024 05:04:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.5674, 'learning_rate': 1.5043e-05, 'epoch': 3.15} | |
| 05/31/2024 05:05:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.5051, 'learning_rate': 1.4908e-05, 'epoch': 3.16} | |
| 05/31/2024 05:06:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.5327, 'learning_rate': 1.4773e-05, 'epoch': 3.17} | |
| 05/31/2024 05:07:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.5064, 'learning_rate': 1.4639e-05, 'epoch': 3.18} | |
| 05/31/2024 05:09:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.5338, 'learning_rate': 1.4505e-05, 'epoch': 3.19} | |
| 05/31/2024 05:09:06 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1700 | |
| 05/31/2024 05:09:06 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1700/tokenizer_config.json | |
| 05/31/2024 05:09:06 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1700/special_tokens_map.json | |
| 05/31/2024 05:10:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.4959, 'learning_rate': 1.4372e-05, 'epoch': 3.20} | |
| 05/31/2024 05:11:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5289, 'learning_rate': 1.4238e-05, 'epoch': 3.21} | |
| 05/31/2024 05:12:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5657, 'learning_rate': 1.4106e-05, 'epoch': 3.22} | |
| 05/31/2024 05:13:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5780, 'learning_rate': 1.3973e-05, 'epoch': 3.23} | |
| 05/31/2024 05:14:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5262, 'learning_rate': 1.3841e-05, 'epoch': 3.23} | |
| 05/31/2024 05:15:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5048, 'learning_rate': 1.3709e-05, 'epoch': 3.24} | |
| 05/31/2024 05:16:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.4904, 'learning_rate': 1.3578e-05, 'epoch': 3.25} | |
| 05/31/2024 05:17:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5938, 'learning_rate': 1.3447e-05, 'epoch': 3.26} | |
| 05/31/2024 05:18:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.5274, 'learning_rate': 1.3317e-05, 'epoch': 3.27} | |
| 05/31/2024 05:20:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5083, 'learning_rate': 1.3187e-05, 'epoch': 3.28} | |
| 05/31/2024 05:21:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5323, 'learning_rate': 1.3057e-05, 'epoch': 3.29} | |
| 05/31/2024 05:22:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.4991, 'learning_rate': 1.2928e-05, 'epoch': 3.30} | |
| 05/31/2024 05:23:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.4954, 'learning_rate': 1.2799e-05, 'epoch': 3.31} | |
| 05/31/2024 05:24:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.5194, 'learning_rate': 1.2671e-05, 'epoch': 3.32} | |
| 05/31/2024 05:25:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.5209, 'learning_rate': 1.2543e-05, 'epoch': 3.33} | |
| 05/31/2024 05:26:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5699, 'learning_rate': 1.2415e-05, 'epoch': 3.34} | |
| 05/31/2024 05:27:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5100, 'learning_rate': 1.2288e-05, 'epoch': 3.35} | |
| 05/31/2024 05:28:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.5497, 'learning_rate': 1.2161e-05, 'epoch': 3.36} | |
| 05/31/2024 05:29:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5660, 'learning_rate': 1.2035e-05, 'epoch': 3.37} | |
| 05/31/2024 05:30:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5246, 'learning_rate': 1.1909e-05, 'epoch': 3.38} | |
| 05/31/2024 05:30:54 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1800 | |
| 05/31/2024 05:30:54 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1800/tokenizer_config.json | |
| 05/31/2024 05:30:54 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1800/special_tokens_map.json | |
| 05/31/2024 05:32:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5261, 'learning_rate': 1.1784e-05, 'epoch': 3.38} | |
| 05/31/2024 05:33:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5497, 'learning_rate': 1.1659e-05, 'epoch': 3.39} | |
| 05/31/2024 05:34:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.5185, 'learning_rate': 1.1535e-05, 'epoch': 3.40} | |
| 05/31/2024 05:35:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5836, 'learning_rate': 1.1411e-05, 'epoch': 3.41} | |
| 05/31/2024 05:36:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5318, 'learning_rate': 1.1287e-05, 'epoch': 3.42} | |
| 05/31/2024 05:37:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.5141, 'learning_rate': 1.1164e-05, 'epoch': 3.43} | |
| 05/31/2024 05:38:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5626, 'learning_rate': 1.1042e-05, 'epoch': 3.44} | |
| 05/31/2024 05:39:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.4792, 'learning_rate': 1.0920e-05, 'epoch': 3.45} | |
| 05/31/2024 05:41:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5150, 'learning_rate': 1.0798e-05, 'epoch': 3.46} | |
| 05/31/2024 05:42:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.5393, 'learning_rate': 1.0677e-05, 'epoch': 3.47} | |
| 05/31/2024 05:43:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5096, 'learning_rate': 1.0557e-05, 'epoch': 3.48} | |
| 05/31/2024 05:44:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5266, 'learning_rate': 1.0437e-05, 'epoch': 3.49} | |
| 05/31/2024 05:45:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.5003, 'learning_rate': 1.0317e-05, 'epoch': 3.50} | |
| 05/31/2024 05:46:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5228, 'learning_rate': 1.0198e-05, 'epoch': 3.51} | |
| 05/31/2024 05:47:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5204, 'learning_rate': 1.0080e-05, 'epoch': 3.52} | |
| 05/31/2024 05:48:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.5138, 'learning_rate': 9.9618e-06, 'epoch': 3.53} | |
| 05/31/2024 05:49:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.5748, 'learning_rate': 9.8444e-06, 'epoch': 3.53} | |
| 05/31/2024 05:50:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.5042, 'learning_rate': 9.7274e-06, 'epoch': 3.54} | |
| 05/31/2024 05:52:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.5591, 'learning_rate': 9.6110e-06, 'epoch': 3.55} | |
| 05/31/2024 05:53:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.5268, 'learning_rate': 9.4952e-06, 'epoch': 3.56} | |
| 05/31/2024 05:53:07 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1900 | |
| 05/31/2024 05:53:07 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1900/tokenizer_config.json | |
| 05/31/2024 05:53:07 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-1900/special_tokens_map.json | |
| 05/31/2024 05:54:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.5592, 'learning_rate': 9.3799e-06, 'epoch': 3.57} | |
| 05/31/2024 05:55:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.5537, 'learning_rate': 9.2651e-06, 'epoch': 3.58} | |
| 05/31/2024 05:56:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5243, 'learning_rate': 9.1508e-06, 'epoch': 3.59} | |
| 05/31/2024 05:57:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.5264, 'learning_rate': 9.0372e-06, 'epoch': 3.60} | |
| 05/31/2024 05:58:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5062, 'learning_rate': 8.9240e-06, 'epoch': 3.61} | |
| 05/31/2024 05:59:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5729, 'learning_rate': 8.8115e-06, 'epoch': 3.62} | |
| 05/31/2024 06:00:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5901, 'learning_rate': 8.6995e-06, 'epoch': 3.63} | |
| 05/31/2024 06:01:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5517, 'learning_rate': 8.5880e-06, 'epoch': 3.64} | |
| 05/31/2024 06:03:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.5617, 'learning_rate': 8.4772e-06, 'epoch': 3.65} | |
| 05/31/2024 06:04:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5510, 'learning_rate': 8.3669e-06, 'epoch': 3.66} | |
| 05/31/2024 06:05:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5394, 'learning_rate': 8.2571e-06, 'epoch': 3.67} | |
| 05/31/2024 06:06:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5532, 'learning_rate': 8.1480e-06, 'epoch': 3.68} | |
| 05/31/2024 06:07:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.5242, 'learning_rate': 8.0395e-06, 'epoch': 3.68} | |
| 05/31/2024 06:08:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6371, 'learning_rate': 7.9315e-06, 'epoch': 3.69} | |
| 05/31/2024 06:09:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.5144, 'learning_rate': 7.8241e-06, 'epoch': 3.70} | |
| 05/31/2024 06:10:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5271, 'learning_rate': 7.7173e-06, 'epoch': 3.71} | |
| 05/31/2024 06:11:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5273, 'learning_rate': 7.6112e-06, 'epoch': 3.72} | |
| 05/31/2024 06:13:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.5249, 'learning_rate': 7.5056e-06, 'epoch': 3.73} | |
| 05/31/2024 06:14:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5625, 'learning_rate': 7.4006e-06, 'epoch': 3.74} | |
| 05/31/2024 06:15:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5701, 'learning_rate': 7.2963e-06, 'epoch': 3.75} | |
| 05/31/2024 06:15:27 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2000 | |
| 05/31/2024 06:15:27 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2000/tokenizer_config.json | |
| 05/31/2024 06:15:27 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2000/special_tokens_map.json | |
| 05/31/2024 06:16:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5830, 'learning_rate': 7.1926e-06, 'epoch': 3.76} | |
| 05/31/2024 06:17:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.4779, 'learning_rate': 7.0895e-06, 'epoch': 3.77} | |
| 05/31/2024 06:18:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.4985, 'learning_rate': 6.9870e-06, 'epoch': 3.78} | |
| 05/31/2024 06:19:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5305, 'learning_rate': 6.8851e-06, 'epoch': 3.79} | |
| 05/31/2024 06:21:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5356, 'learning_rate': 6.7839e-06, 'epoch': 3.80} | |
| 05/31/2024 06:22:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5269, 'learning_rate': 6.6833e-06, 'epoch': 3.81} | |
| 05/31/2024 06:23:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5563, 'learning_rate': 6.5833e-06, 'epoch': 3.82} | |
| 05/31/2024 06:24:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5146, 'learning_rate': 6.4840e-06, 'epoch': 3.83} | |
| 05/31/2024 06:25:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.5614, 'learning_rate': 6.3853e-06, 'epoch': 3.83} | |
| 05/31/2024 06:26:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.4988, 'learning_rate': 6.2872e-06, 'epoch': 3.84} | |
| 05/31/2024 06:27:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5621, 'learning_rate': 6.1898e-06, 'epoch': 3.85} | |
| 05/31/2024 06:28:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5282, 'learning_rate': 6.0931e-06, 'epoch': 3.86} | |
| 05/31/2024 06:29:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.5119, 'learning_rate': 5.9970e-06, 'epoch': 3.87} | |
| 05/31/2024 06:30:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5431, 'learning_rate': 5.9016e-06, 'epoch': 3.88} | |
| 05/31/2024 06:31:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5971, 'learning_rate': 5.8069e-06, 'epoch': 3.89} | |
| 05/31/2024 06:33:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5400, 'learning_rate': 5.7128e-06, 'epoch': 3.90} | |
| 05/31/2024 06:34:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5045, 'learning_rate': 5.6194e-06, 'epoch': 3.91} | |
| 05/31/2024 06:35:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5086, 'learning_rate': 5.5266e-06, 'epoch': 3.92} | |
| 05/31/2024 06:36:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.5774, 'learning_rate': 5.4345e-06, 'epoch': 3.93} | |
| 05/31/2024 06:37:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5541, 'learning_rate': 5.3432e-06, 'epoch': 3.94} | |
| 05/31/2024 06:37:19 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2100 | |
| 05/31/2024 06:37:19 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2100/tokenizer_config.json | |
| 05/31/2024 06:37:19 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2100/special_tokens_map.json | |
| 05/31/2024 06:38:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5170, 'learning_rate': 5.2524e-06, 'epoch': 3.95} | |
| 05/31/2024 06:39:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.5474, 'learning_rate': 5.1624e-06, 'epoch': 3.96} | |
| 05/31/2024 06:40:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5178, 'learning_rate': 5.0731e-06, 'epoch': 3.97} | |
| 05/31/2024 06:41:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.5671, 'learning_rate': 4.9845e-06, 'epoch': 3.98} | |
| 05/31/2024 06:42:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5148, 'learning_rate': 4.8965e-06, 'epoch': 3.98} | |
| 05/31/2024 06:43:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.5418, 'learning_rate': 4.8093e-06, 'epoch': 3.99} | |
| 05/31/2024 06:45:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5433, 'learning_rate': 4.7227e-06, 'epoch': 4.00} | |
| 05/31/2024 06:46:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5810, 'learning_rate': 4.6369e-06, 'epoch': 4.01} | |
| 05/31/2024 06:47:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5108, 'learning_rate': 4.5518e-06, 'epoch': 4.02} | |
| 05/31/2024 06:48:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.5533, 'learning_rate': 4.4673e-06, 'epoch': 4.03} | |
| 05/31/2024 06:49:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5372, 'learning_rate': 4.3836e-06, 'epoch': 4.04} | |
| 05/31/2024 06:50:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.5183, 'learning_rate': 4.3006e-06, 'epoch': 4.05} | |
| 05/31/2024 06:51:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5426, 'learning_rate': 4.2184e-06, 'epoch': 4.06} | |
| 05/31/2024 06:52:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5491, 'learning_rate': 4.1368e-06, 'epoch': 4.07} | |
| 05/31/2024 06:53:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.5401, 'learning_rate': 4.0560e-06, 'epoch': 4.08} | |
| 05/31/2024 06:54:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.4976, 'learning_rate': 3.9759e-06, 'epoch': 4.09} | |
| 05/31/2024 06:55:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.5103, 'learning_rate': 3.8965e-06, 'epoch': 4.10} | |
| 05/31/2024 06:56:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5443, 'learning_rate': 3.8179e-06, 'epoch': 4.11} | |
| 05/31/2024 06:58:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5377, 'learning_rate': 3.7400e-06, 'epoch': 4.12} | |
| 05/31/2024 06:59:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.5117, 'learning_rate': 3.6629e-06, 'epoch': 4.13} | |
| 05/31/2024 06:59:14 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2200 | |
| 05/31/2024 06:59:14 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2200/tokenizer_config.json | |
| 05/31/2024 06:59:14 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2200/special_tokens_map.json | |
| 05/31/2024 07:00:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5157, 'learning_rate': 3.5864e-06, 'epoch': 4.14} | |
| 05/31/2024 07:01:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5058, 'learning_rate': 3.5108e-06, 'epoch': 4.14} | |
| 05/31/2024 07:02:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.5233, 'learning_rate': 3.4358e-06, 'epoch': 4.15} | |
| 05/31/2024 07:03:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.5347, 'learning_rate': 3.3617e-06, 'epoch': 4.16} | |
| 05/31/2024 07:04:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5124, 'learning_rate': 3.2882e-06, 'epoch': 4.17} | |
| 05/31/2024 07:05:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.5641, 'learning_rate': 3.2156e-06, 'epoch': 4.18} | |
| 05/31/2024 07:06:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5416, 'learning_rate': 3.1436e-06, 'epoch': 4.19} | |
| 05/31/2024 07:07:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.5602, 'learning_rate': 3.0725e-06, 'epoch': 4.20} | |
| 05/31/2024 07:09:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.4998, 'learning_rate': 3.0021e-06, 'epoch': 4.21} | |
| 05/31/2024 07:10:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.5699, 'learning_rate': 2.9325e-06, 'epoch': 4.22} | |
| 05/31/2024 07:11:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5114, 'learning_rate': 2.8636e-06, 'epoch': 4.23} | |
| 05/31/2024 07:12:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5061, 'learning_rate': 2.7955e-06, 'epoch': 4.24} | |
| 05/31/2024 07:13:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.5334, 'learning_rate': 2.7282e-06, 'epoch': 4.25} | |
| 05/31/2024 07:14:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5867, 'learning_rate': 2.6616e-06, 'epoch': 4.26} | |
| 05/31/2024 07:15:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5287, 'learning_rate': 2.5959e-06, 'epoch': 4.27} | |
| 05/31/2024 07:16:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.5324, 'learning_rate': 2.5309e-06, 'epoch': 4.28} | |
| 05/31/2024 07:17:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5267, 'learning_rate': 2.4667e-06, 'epoch': 4.29} | |
| 05/31/2024 07:18:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5480, 'learning_rate': 2.4032e-06, 'epoch': 4.29} | |
| 05/31/2024 07:19:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.4996, 'learning_rate': 2.3406e-06, 'epoch': 4.30} | |
| 05/31/2024 07:21:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5294, 'learning_rate': 2.2787e-06, 'epoch': 4.31} | |
| 05/31/2024 07:21:02 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2300 | |
| 05/31/2024 07:21:02 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2300/tokenizer_config.json | |
| 05/31/2024 07:21:02 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2300/special_tokens_map.json | |
| 05/31/2024 07:22:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.4882, 'learning_rate': 2.2176e-06, 'epoch': 4.32} | |
| 05/31/2024 07:23:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5169, 'learning_rate': 2.1574e-06, 'epoch': 4.33} | |
| 05/31/2024 07:24:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5325, 'learning_rate': 2.0979e-06, 'epoch': 4.34} | |
| 05/31/2024 07:25:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.4942, 'learning_rate': 2.0392e-06, 'epoch': 4.35} | |
| 05/31/2024 07:26:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5117, 'learning_rate': 1.9813e-06, 'epoch': 4.36} | |
| 05/31/2024 07:27:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.5069, 'learning_rate': 1.9242e-06, 'epoch': 4.37} | |
| 05/31/2024 07:28:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5183, 'learning_rate': 1.8679e-06, 'epoch': 4.38} | |
| 05/31/2024 07:29:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.4979, 'learning_rate': 1.8124e-06, 'epoch': 4.39} | |
| 05/31/2024 07:30:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.5365, 'learning_rate': 1.7578e-06, 'epoch': 4.40} | |
| 05/31/2024 07:32:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5165, 'learning_rate': 1.7039e-06, 'epoch': 4.41} | |
| 05/31/2024 07:33:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5718, 'learning_rate': 1.6508e-06, 'epoch': 4.42} | |
| 05/31/2024 07:34:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.5244, 'learning_rate': 1.5986e-06, 'epoch': 4.43} | |
| 05/31/2024 07:35:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5609, 'learning_rate': 1.5471e-06, 'epoch': 4.44} | |
| 05/31/2024 07:36:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.4940, 'learning_rate': 1.4965e-06, 'epoch': 4.44} | |
| 05/31/2024 07:37:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5198, 'learning_rate': 1.4467e-06, 'epoch': 4.45} | |
| 05/31/2024 07:38:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5284, 'learning_rate': 1.3977e-06, 'epoch': 4.46} | |
| 05/31/2024 07:39:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5223, 'learning_rate': 1.3495e-06, 'epoch': 4.47} | |
| 05/31/2024 07:40:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5128, 'learning_rate': 1.3022e-06, 'epoch': 4.48} | |
| 05/31/2024 07:41:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.5634, 'learning_rate': 1.2557e-06, 'epoch': 4.49} | |
| 05/31/2024 07:43:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.5168, 'learning_rate': 1.2100e-06, 'epoch': 4.50} | |
| 05/31/2024 07:43:03 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2400 | |
| 05/31/2024 07:43:03 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2400/tokenizer_config.json | |
| 05/31/2024 07:43:03 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2400/special_tokens_map.json | |
| 05/31/2024 07:44:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.4968, 'learning_rate': 1.1651e-06, 'epoch': 4.51} | |
| 05/31/2024 07:45:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6302, 'learning_rate': 1.1210e-06, 'epoch': 4.52} | |
| 05/31/2024 07:46:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5114, 'learning_rate': 1.0778e-06, 'epoch': 4.53} | |
| 05/31/2024 07:47:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.5136, 'learning_rate': 1.0354e-06, 'epoch': 4.54} | |
| 05/31/2024 07:48:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.5265, 'learning_rate': 9.9389e-07, 'epoch': 4.55} | |
| 05/31/2024 07:49:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5299, 'learning_rate': 9.5317e-07, 'epoch': 4.56} | |
| 05/31/2024 07:50:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5940, 'learning_rate': 9.1329e-07, 'epoch': 4.57} | |
| 05/31/2024 07:51:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.5352, 'learning_rate': 8.7424e-07, 'epoch': 4.58} | |
| 05/31/2024 07:52:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.5262, 'learning_rate': 8.3604e-07, 'epoch': 4.59} | |
| 05/31/2024 07:53:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5779, 'learning_rate': 7.9867e-07, 'epoch': 4.59} | |
| 05/31/2024 07:54:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.5588, 'learning_rate': 7.6214e-07, 'epoch': 4.60} | |
| 05/31/2024 07:56:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.5025, 'learning_rate': 7.2645e-07, 'epoch': 4.61} | |
| 05/31/2024 07:57:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.5156, 'learning_rate': 6.9161e-07, 'epoch': 4.62} | |
| 05/31/2024 07:58:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.5750, 'learning_rate': 6.5761e-07, 'epoch': 4.63} | |
| 05/31/2024 07:59:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.5262, 'learning_rate': 6.2446e-07, 'epoch': 4.64} | |
| 05/31/2024 08:00:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5399, 'learning_rate': 5.9216e-07, 'epoch': 4.65} | |
| 05/31/2024 08:01:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.5328, 'learning_rate': 5.6070e-07, 'epoch': 4.66} | |
| 05/31/2024 08:02:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5403, 'learning_rate': 5.3009e-07, 'epoch': 4.67} | |
| 05/31/2024 08:03:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5219, 'learning_rate': 5.0033e-07, 'epoch': 4.68} | |
| 05/31/2024 08:04:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.5515, 'learning_rate': 4.7143e-07, 'epoch': 4.69} | |
| 05/31/2024 08:04:57 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2500 | |
| 05/31/2024 08:04:57 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2500/tokenizer_config.json | |
| 05/31/2024 08:04:57 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2500/special_tokens_map.json | |
| 05/31/2024 08:06:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.5270, 'learning_rate': 4.4337e-07, 'epoch': 4.70} | |
| 05/31/2024 08:07:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.5766, 'learning_rate': 4.1617e-07, 'epoch': 4.71} | |
| 05/31/2024 08:08:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5084, 'learning_rate': 3.8982e-07, 'epoch': 4.72} | |
| 05/31/2024 08:09:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5616, 'learning_rate': 3.6433e-07, 'epoch': 4.73} | |
| 05/31/2024 08:10:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5003, 'learning_rate': 3.3969e-07, 'epoch': 4.74} | |
| 05/31/2024 08:11:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5369, 'learning_rate': 3.1591e-07, 'epoch': 4.74} | |
| 05/31/2024 08:12:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5319, 'learning_rate': 2.9299e-07, 'epoch': 4.75} | |
| 05/31/2024 08:13:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.4929, 'learning_rate': 2.7093e-07, 'epoch': 4.76} | |
| 05/31/2024 08:14:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5774, 'learning_rate': 2.4972e-07, 'epoch': 4.77} | |
| 05/31/2024 08:15:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.5231, 'learning_rate': 2.2937e-07, 'epoch': 4.78} | |
| 05/31/2024 08:17:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.5563, 'learning_rate': 2.0989e-07, 'epoch': 4.79} | |
| 05/31/2024 08:18:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5601, 'learning_rate': 1.9127e-07, 'epoch': 4.80} | |
| 05/31/2024 08:19:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.5116, 'learning_rate': 1.7351e-07, 'epoch': 4.81} | |
| 05/31/2024 08:20:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5159, 'learning_rate': 1.5661e-07, 'epoch': 4.82} | |
| 05/31/2024 08:21:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.5555, 'learning_rate': 1.4057e-07, 'epoch': 4.83} | |
| 05/31/2024 08:22:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.5433, 'learning_rate': 1.2540e-07, 'epoch': 4.84} | |
| 05/31/2024 08:23:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.4752, 'learning_rate': 1.1109e-07, 'epoch': 4.85} | |
| 05/31/2024 08:24:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.4921, 'learning_rate': 9.7646e-08, 'epoch': 4.86} | |
| 05/31/2024 08:25:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.5313, 'learning_rate': 8.5068e-08, 'epoch': 4.87} | |
| 05/31/2024 08:26:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.5180, 'learning_rate': 7.3355e-08, 'epoch': 4.88} | |
| 05/31/2024 08:26:59 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2600 | |
| 05/31/2024 08:27:00 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2600/tokenizer_config.json | |
| 05/31/2024 08:27:00 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/checkpoint-2600/special_tokens_map.json | |
| 05/31/2024 08:28:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.5785, 'learning_rate': 6.2508e-08, 'epoch': 4.89} | |
| 05/31/2024 08:29:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.5209, 'learning_rate': 5.2528e-08, 'epoch': 4.89} | |
| 05/31/2024 08:30:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.5438, 'learning_rate': 4.3414e-08, 'epoch': 4.90} | |
| 05/31/2024 08:31:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.4971, 'learning_rate': 3.5167e-08, 'epoch': 4.91} | |
| 05/31/2024 08:32:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.4950, 'learning_rate': 2.7788e-08, 'epoch': 4.92} | |
| 05/31/2024 08:33:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5463, 'learning_rate': 2.1276e-08, 'epoch': 4.93} | |
| 05/31/2024 08:34:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5461, 'learning_rate': 1.5632e-08, 'epoch': 4.94} | |
| 05/31/2024 08:36:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.5319, 'learning_rate': 1.0856e-08, 'epoch': 4.95} | |
| 05/31/2024 08:37:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.5068, 'learning_rate': 6.9479e-09, 'epoch': 4.96} | |
| 05/31/2024 08:38:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.5091, 'learning_rate': 3.9083e-09, 'epoch': 4.97} | |
| 05/31/2024 08:39:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.5747, 'learning_rate': 1.7370e-09, 'epoch': 4.98} | |
| 05/31/2024 08:40:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5346, 'learning_rate': 4.3426e-10, 'epoch': 4.99} | |
| 05/31/2024 08:41:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.5285, 'learning_rate': 0.0000e+00, 'epoch': 5.00} | |
| 05/31/2024 08:41:35 - INFO - transformers.trainer - | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| 05/31/2024 08:41:35 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat | |
| 05/31/2024 08:41:35 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/tokenizer_config.json | |
| 05/31/2024 08:41:35 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/deepseek-llm-7b-chat/special_tokens_map.json | |
| 05/31/2024 08:41:35 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields: | |
| {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} | |