| 05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file vocab.json | |
| 05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file merges.txt | |
| 05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json | |
| 05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json | |
| 05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json | |
| 05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json | |
| 05/20/2024 11:37:54 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| 05/20/2024 11:37:54 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/LangGPT_community.jsonl... | |
| 05/20/2024 11:37:54 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json. | |
| 05/20/2024 11:37:55 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/langgpt_seed.jsonl... | |
| 05/20/2024 11:37:55 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json. | |
| 05/20/2024 11:38:03 - INFO - transformers.configuration_utils - loading configuration file /datas/huggingface/Qwen1.5-4B-Chat/config.json | |
| 05/20/2024 11:38:03 - INFO - transformers.configuration_utils - Model config Qwen2Config { | |
| "_name_or_path": "/datas/huggingface/Qwen1.5-4B-Chat", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6912, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 21, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 20, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 20, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 5000000.0, | |
| "sliding_window": 32768, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.2", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |
| 05/20/2024 11:38:04 - INFO - transformers.modeling_utils - loading weights file /datas/huggingface/Qwen1.5-4B-Chat/model.safetensors.index.json | |
| 05/20/2024 11:38:04 - INFO - transformers.modeling_utils - Instantiating Qwen2ForCausalLM model under default dtype torch.float16. | |
| 05/20/2024 11:38:04 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig { | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "use_cache": false | |
| } | |
| 05/20/2024 11:38:08 - INFO - transformers.modeling_utils - All model checkpoint weights were used when initializing Qwen2ForCausalLM. | |
| 05/20/2024 11:38:08 - INFO - transformers.modeling_utils - All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /datas/huggingface/Qwen1.5-4B-Chat. | |
| If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. | |
| 05/20/2024 11:38:08 - INFO - transformers.generation.configuration_utils - loading configuration file /datas/huggingface/Qwen1.5-4B-Chat/generation_config.json | |
| 05/20/2024 11:38:08 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig { | |
| "bos_token_id": 151643, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 151645, | |
| 151643 | |
| ], | |
| "pad_token_id": 151643, | |
| "repetition_penalty": 1.1, | |
| "top_p": 0.8 | |
| } | |
| 05/20/2024 11:38:09 - INFO - llmtuner.model.utils.checkpointing - Gradient checkpointing enabled. | |
| 05/20/2024 11:38:09 - INFO - llmtuner.model.utils.attention - Using torch SDPA for faster training and inference. | |
| 05/20/2024 11:38:09 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA | |
| 05/20/2024 11:38:09 - INFO - llmtuner.model.loader - trainable params: 3276800 || all params: 3953646080 || trainable%: 0.0829 | |
| 05/20/2024 11:38:09 - INFO - transformers.trainer - Using auto half precision backend | |
| 05/20/2024 11:38:09 - INFO - transformers.trainer - ***** Running training ***** | |
| 05/20/2024 11:38:09 - INFO - transformers.trainer - Num examples = 3,331 | |
| 05/20/2024 11:38:09 - INFO - transformers.trainer - Num Epochs = 10 | |
| 05/20/2024 11:38:09 - INFO - transformers.trainer - Instantaneous batch size per device = 2 | |
| 05/20/2024 11:38:09 - INFO - transformers.trainer - Total train batch size (w. parallel, distributed & accumulation) = 16 | |
| 05/20/2024 11:38:09 - INFO - transformers.trainer - Gradient Accumulation steps = 8 | |
| 05/20/2024 11:38:09 - INFO - transformers.trainer - Total optimization steps = 2,080 | |
| 05/20/2024 11:38:09 - INFO - transformers.trainer - Number of trainable parameters = 3,276,800 | |
| 05/20/2024 11:38:55 - INFO - llmtuner.extras.callbacks - {'loss': 1.2537, 'learning_rate': 4.9999e-05, 'epoch': 0.02} | |
| 05/20/2024 11:39:49 - INFO - llmtuner.extras.callbacks - {'loss': 1.1695, 'learning_rate': 4.9997e-05, 'epoch': 0.05} | |
| 05/20/2024 11:40:37 - INFO - llmtuner.extras.callbacks - {'loss': 1.1879, 'learning_rate': 4.9994e-05, 'epoch': 0.07} | |
| 05/20/2024 11:41:20 - INFO - llmtuner.extras.callbacks - {'loss': 1.0137, 'learning_rate': 4.9989e-05, 'epoch': 0.10} | |
| 05/20/2024 11:42:08 - INFO - llmtuner.extras.callbacks - {'loss': 1.1109, 'learning_rate': 4.9982e-05, 'epoch': 0.12} | |
| 05/20/2024 11:42:55 - INFO - llmtuner.extras.callbacks - {'loss': 1.0400, 'learning_rate': 4.9974e-05, 'epoch': 0.14} | |
| 05/20/2024 11:43:41 - INFO - llmtuner.extras.callbacks - {'loss': 1.0158, 'learning_rate': 4.9965e-05, 'epoch': 0.17} | |
| 05/20/2024 11:44:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.9004, 'learning_rate': 4.9954e-05, 'epoch': 0.19} | |
| 05/20/2024 11:45:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.9626, 'learning_rate': 4.9942e-05, 'epoch': 0.22} | |
| 05/20/2024 11:45:57 - INFO - llmtuner.extras.callbacks - {'loss': 1.0787, 'learning_rate': 4.9929e-05, 'epoch': 0.24} | |
| 05/20/2024 11:46:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.8533, 'learning_rate': 4.9914e-05, 'epoch': 0.26} | |
| 05/20/2024 11:47:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.9406, 'learning_rate': 4.9897e-05, 'epoch': 0.29} | |
| 05/20/2024 11:48:16 - INFO - llmtuner.extras.callbacks - {'loss': 1.0017, 'learning_rate': 4.9880e-05, 'epoch': 0.31} | |
| 05/20/2024 11:49:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.8902, 'learning_rate': 4.9860e-05, 'epoch': 0.34} | |
| 05/20/2024 11:49:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.9070, 'learning_rate': 4.9840e-05, 'epoch': 0.36} | |
| 05/20/2024 11:50:40 - INFO - llmtuner.extras.callbacks - {'loss': 1.0197, 'learning_rate': 4.9818e-05, 'epoch': 0.38} | |
| 05/20/2024 11:51:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.8131, 'learning_rate': 4.9794e-05, 'epoch': 0.41} | |
| 05/20/2024 11:52:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.8665, 'learning_rate': 4.9769e-05, 'epoch': 0.43} | |
| 05/20/2024 11:52:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.9219, 'learning_rate': 4.9743e-05, 'epoch': 0.46} | |
| 05/20/2024 11:53:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.9425, 'learning_rate': 4.9715e-05, 'epoch': 0.48} | |
| 05/20/2024 11:53:46 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-100 | |
| 05/20/2024 11:53:46 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-100/tokenizer_config.json | |
| 05/20/2024 11:53:46 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-100/special_tokens_map.json | |
| 05/20/2024 11:54:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.8781, 'learning_rate': 4.9686e-05, 'epoch': 0.50} | |
| 05/20/2024 11:55:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.8446, 'learning_rate': 4.9656e-05, 'epoch': 0.53} | |
| 05/20/2024 11:56:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.9453, 'learning_rate': 4.9624e-05, 'epoch': 0.55} | |
| 05/20/2024 11:56:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.8086, 'learning_rate': 4.9590e-05, 'epoch': 0.58} | |
| 05/20/2024 11:57:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.8657, 'learning_rate': 4.9556e-05, 'epoch': 0.60} | |
| 05/20/2024 11:58:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.9168, 'learning_rate': 4.9520e-05, 'epoch': 0.62} | |
| 05/20/2024 11:59:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.9192, 'learning_rate': 4.9482e-05, 'epoch': 0.65} | |
| 05/20/2024 11:59:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.7927, 'learning_rate': 4.9443e-05, 'epoch': 0.67} | |
| 05/20/2024 12:00:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.8486, 'learning_rate': 4.9403e-05, 'epoch': 0.70} | |
| 05/20/2024 12:01:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7937, 'learning_rate': 4.9361e-05, 'epoch': 0.72} | |
| 05/20/2024 12:02:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.8340, 'learning_rate': 4.9318e-05, 'epoch': 0.74} | |
| 05/20/2024 12:03:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7799, 'learning_rate': 4.9274e-05, 'epoch': 0.77} | |
| 05/20/2024 12:03:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.8608, 'learning_rate': 4.9228e-05, 'epoch': 0.79} | |
| 05/20/2024 12:04:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.8872, 'learning_rate': 4.9180e-05, 'epoch': 0.82} | |
| 05/20/2024 12:05:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.8681, 'learning_rate': 4.9132e-05, 'epoch': 0.84} | |
| 05/20/2024 12:06:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.8451, 'learning_rate': 4.9082e-05, 'epoch': 0.86} | |
| 05/20/2024 12:06:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.8662, 'learning_rate': 4.9030e-05, 'epoch': 0.89} | |
| 05/20/2024 12:07:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.8183, 'learning_rate': 4.8978e-05, 'epoch': 0.91} | |
| 05/20/2024 12:08:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.8887, 'learning_rate': 4.8924e-05, 'epoch': 0.94} | |
| 05/20/2024 12:09:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.8505, 'learning_rate': 4.8868e-05, 'epoch': 0.96} | |
| 05/20/2024 12:09:17 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-200 | |
| 05/20/2024 12:09:17 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-200/tokenizer_config.json | |
| 05/20/2024 12:09:17 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-200/special_tokens_map.json | |
| 05/20/2024 12:10:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.8350, 'learning_rate': 4.8811e-05, 'epoch': 0.98} | |
| 05/20/2024 12:10:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.8531, 'learning_rate': 4.8753e-05, 'epoch': 1.01} | |
| 05/20/2024 12:11:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.8679, 'learning_rate': 4.8693e-05, 'epoch': 1.03} | |
| 05/20/2024 12:12:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.8432, 'learning_rate': 4.8632e-05, 'epoch': 1.06} | |
| 05/20/2024 12:13:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.8362, 'learning_rate': 4.8570e-05, 'epoch': 1.08} | |
| 05/20/2024 12:13:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.7704, 'learning_rate': 4.8507e-05, 'epoch': 1.10} | |
| 05/20/2024 12:14:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.8357, 'learning_rate': 4.8442e-05, 'epoch': 1.13} | |
| 05/20/2024 12:15:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.7461, 'learning_rate': 4.8375e-05, 'epoch': 1.15} | |
| 05/20/2024 12:16:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.8821, 'learning_rate': 4.8308e-05, 'epoch': 1.18} | |
| 05/20/2024 12:17:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.8890, 'learning_rate': 4.8239e-05, 'epoch': 1.20} | |
| 05/20/2024 12:17:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7407, 'learning_rate': 4.8169e-05, 'epoch': 1.22} | |
| 05/20/2024 12:18:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.7822, 'learning_rate': 4.8097e-05, 'epoch': 1.25} | |
| 05/20/2024 12:19:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.9008, 'learning_rate': 4.8024e-05, 'epoch': 1.27} | |
| 05/20/2024 12:20:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7477, 'learning_rate': 4.7950e-05, 'epoch': 1.30} | |
| 05/20/2024 12:20:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7846, 'learning_rate': 4.7874e-05, 'epoch': 1.32} | |
| 05/20/2024 12:21:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.8544, 'learning_rate': 4.7797e-05, 'epoch': 1.34} | |
| 05/20/2024 12:22:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7706, 'learning_rate': 4.7719e-05, 'epoch': 1.37} | |
| 05/20/2024 12:23:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.8256, 'learning_rate': 4.7640e-05, 'epoch': 1.39} | |
| 05/20/2024 12:23:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.8185, 'learning_rate': 4.7559e-05, 'epoch': 1.42} | |
| 05/20/2024 12:24:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7356, 'learning_rate': 4.7477e-05, 'epoch': 1.44} | |
| 05/20/2024 12:24:41 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-300 | |
| 05/20/2024 12:24:41 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-300/tokenizer_config.json | |
| 05/20/2024 12:24:41 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-300/special_tokens_map.json | |
| 05/20/2024 12:25:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.8015, 'learning_rate': 4.7394e-05, 'epoch': 1.46} | |
| 05/20/2024 12:26:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.8103, 'learning_rate': 4.7309e-05, 'epoch': 1.49} | |
| 05/20/2024 12:27:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6949, 'learning_rate': 4.7224e-05, 'epoch': 1.51} | |
| 05/20/2024 12:27:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7790, 'learning_rate': 4.7136e-05, 'epoch': 1.54} | |
| 05/20/2024 12:28:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.8016, 'learning_rate': 4.7048e-05, 'epoch': 1.56} | |
| 05/20/2024 12:29:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7460, 'learning_rate': 4.6958e-05, 'epoch': 1.58} | |
| 05/20/2024 12:30:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7439, 'learning_rate': 4.6868e-05, 'epoch': 1.61} | |
| 05/20/2024 12:30:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7969, 'learning_rate': 4.6775e-05, 'epoch': 1.63} | |
| 05/20/2024 12:31:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.8580, 'learning_rate': 4.6682e-05, 'epoch': 1.66} | |
| 05/20/2024 12:32:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.8538, 'learning_rate': 4.6587e-05, 'epoch': 1.68} | |
| 05/20/2024 12:33:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.8241, 'learning_rate': 4.6492e-05, 'epoch': 1.70} | |
| 05/20/2024 12:34:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.7388, 'learning_rate': 4.6395e-05, 'epoch': 1.73} | |
| 05/20/2024 12:34:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7924, 'learning_rate': 4.6296e-05, 'epoch': 1.75} | |
| 05/20/2024 12:35:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7719, 'learning_rate': 4.6197e-05, 'epoch': 1.78} | |
| 05/20/2024 12:36:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.8365, 'learning_rate': 4.6096e-05, 'epoch': 1.80} | |
| 05/20/2024 12:37:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.8118, 'learning_rate': 4.5994e-05, 'epoch': 1.82} | |
| 05/20/2024 12:38:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.7881, 'learning_rate': 4.5891e-05, 'epoch': 1.85} | |
| 05/20/2024 12:38:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.7155, 'learning_rate': 4.5787e-05, 'epoch': 1.87} | |
| 05/20/2024 12:39:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.8555, 'learning_rate': 4.5681e-05, 'epoch': 1.90} | |
| 05/20/2024 12:40:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.8685, 'learning_rate': 4.5575e-05, 'epoch': 1.92} | |
| 05/20/2024 12:40:26 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-400 | |
| 05/20/2024 12:40:26 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-400/tokenizer_config.json | |
| 05/20/2024 12:40:26 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-400/special_tokens_map.json | |
| 05/20/2024 12:41:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.7708, 'learning_rate': 4.5467e-05, 'epoch': 1.94} | |
| 05/20/2024 12:42:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.8448, 'learning_rate': 4.5358e-05, 'epoch': 1.97} | |
| 05/20/2024 12:42:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7360, 'learning_rate': 4.5248e-05, 'epoch': 1.99} | |
| 05/20/2024 12:43:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7223, 'learning_rate': 4.5136e-05, 'epoch': 2.02} | |
| 05/20/2024 12:44:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.7504, 'learning_rate': 4.5024e-05, 'epoch': 2.04} | |
| 05/20/2024 12:45:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.8011, 'learning_rate': 4.4910e-05, 'epoch': 2.06} | |
| 05/20/2024 12:46:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.8665, 'learning_rate': 4.4795e-05, 'epoch': 2.09} | |
| 05/20/2024 12:46:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.7490, 'learning_rate': 4.4680e-05, 'epoch': 2.11} | |
| 05/20/2024 12:47:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7962, 'learning_rate': 4.4563e-05, 'epoch': 2.14} | |
| 05/20/2024 12:48:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7964, 'learning_rate': 4.4444e-05, 'epoch': 2.16} | |
| 05/20/2024 12:49:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.7516, 'learning_rate': 4.4325e-05, 'epoch': 2.18} | |
| 05/20/2024 12:50:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.8173, 'learning_rate': 4.4205e-05, 'epoch': 2.21} | |
| 05/20/2024 12:50:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.8038, 'learning_rate': 4.4084e-05, 'epoch': 2.23} | |
| 05/20/2024 12:51:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.8055, 'learning_rate': 4.3961e-05, 'epoch': 2.26} | |
| 05/20/2024 12:52:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.7459, 'learning_rate': 4.3837e-05, 'epoch': 2.28} | |
| 05/20/2024 12:53:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7959, 'learning_rate': 4.3713e-05, 'epoch': 2.30} | |
| 05/20/2024 12:53:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.8528, 'learning_rate': 4.3587e-05, 'epoch': 2.33} | |
| 05/20/2024 12:54:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7590, 'learning_rate': 4.3460e-05, 'epoch': 2.35} | |
| 05/20/2024 12:55:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7499, 'learning_rate': 4.3332e-05, 'epoch': 2.38} | |
| 05/20/2024 12:56:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.7279, 'learning_rate': 4.3204e-05, 'epoch': 2.40} | |
| 05/20/2024 12:56:18 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-500 | |
| 05/20/2024 12:56:18 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-500/tokenizer_config.json | |
| 05/20/2024 12:56:18 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-500/special_tokens_map.json | |
| 05/20/2024 12:57:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7453, 'learning_rate': 4.3074e-05, 'epoch': 2.42} | |
| 05/20/2024 12:57:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.8311, 'learning_rate': 4.2943e-05, 'epoch': 2.45} | |
| 05/20/2024 12:58:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7172, 'learning_rate': 4.2811e-05, 'epoch': 2.47} | |
| 05/20/2024 12:59:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.8084, 'learning_rate': 4.2678e-05, 'epoch': 2.50} | |
| 05/20/2024 13:00:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7020, 'learning_rate': 4.2544e-05, 'epoch': 2.52} | |
| 05/20/2024 13:00:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.7261, 'learning_rate': 4.2409e-05, 'epoch': 2.55} | |
| 05/20/2024 13:01:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7540, 'learning_rate': 4.2273e-05, 'epoch': 2.57} | |
| 05/20/2024 13:02:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7855, 'learning_rate': 4.2136e-05, 'epoch': 2.59} | |
| 05/20/2024 13:03:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.7584, 'learning_rate': 4.1998e-05, 'epoch': 2.62} | |
| 05/20/2024 13:04:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.8196, 'learning_rate': 4.1859e-05, 'epoch': 2.64} | |
| 05/20/2024 13:04:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6836, 'learning_rate': 4.1719e-05, 'epoch': 2.67} | |
| 05/20/2024 13:05:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.7656, 'learning_rate': 4.1578e-05, 'epoch': 2.69} | |
| 05/20/2024 13:06:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7787, 'learning_rate': 4.1436e-05, 'epoch': 2.71} | |
| 05/20/2024 13:07:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.7665, 'learning_rate': 4.1294e-05, 'epoch': 2.74} | |
| 05/20/2024 13:07:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7480, 'learning_rate': 4.1150e-05, 'epoch': 2.76} | |
| 05/20/2024 13:08:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.7761, 'learning_rate': 4.1005e-05, 'epoch': 2.79} | |
| 05/20/2024 13:09:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.7873, 'learning_rate': 4.0860e-05, 'epoch': 2.81} | |
| 05/20/2024 13:10:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.8288, 'learning_rate': 4.0713e-05, 'epoch': 2.83} | |
| 05/20/2024 13:10:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.7587, 'learning_rate': 4.0566e-05, 'epoch': 2.86} | |
| 05/20/2024 13:11:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7096, 'learning_rate': 4.0418e-05, 'epoch': 2.88} | |
| 05/20/2024 13:11:37 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-600 | |
| 05/20/2024 13:11:37 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-600/tokenizer_config.json | |
| 05/20/2024 13:11:37 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-600/special_tokens_map.json | |
| 05/20/2024 13:12:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7177, 'learning_rate': 4.0269e-05, 'epoch': 2.91} | |
| 05/20/2024 13:13:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.7244, 'learning_rate': 4.0119e-05, 'epoch': 2.93} | |
| 05/20/2024 13:13:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7627, 'learning_rate': 3.9968e-05, 'epoch': 2.95} | |
| 05/20/2024 13:14:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.7562, 'learning_rate': 3.9817e-05, 'epoch': 2.98} | |
| 05/20/2024 13:15:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.8271, 'learning_rate': 3.9664e-05, 'epoch': 3.00} | |
| 05/20/2024 13:16:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.7639, 'learning_rate': 3.9511e-05, 'epoch': 3.03} | |
| 05/20/2024 13:17:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7117, 'learning_rate': 3.9357e-05, 'epoch': 3.05} | |
| 05/20/2024 13:17:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7358, 'learning_rate': 3.9202e-05, 'epoch': 3.07} | |
| 05/20/2024 13:18:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7409, 'learning_rate': 3.9046e-05, 'epoch': 3.10} | |
| 05/20/2024 13:19:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.7052, 'learning_rate': 3.8889e-05, 'epoch': 3.12} | |
| 05/20/2024 13:20:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7602, 'learning_rate': 3.8732e-05, 'epoch': 3.15} | |
| 05/20/2024 13:21:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.8514, 'learning_rate': 3.8574e-05, 'epoch': 3.17} | |
| 05/20/2024 13:21:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7699, 'learning_rate': 3.8415e-05, 'epoch': 3.19} | |
| 05/20/2024 13:22:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.8067, 'learning_rate': 3.8255e-05, 'epoch': 3.22} | |
| 05/20/2024 13:23:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6783, 'learning_rate': 3.8095e-05, 'epoch': 3.24} | |
| 05/20/2024 13:24:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7315, 'learning_rate': 3.7933e-05, 'epoch': 3.27} | |
| 05/20/2024 13:24:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6999, 'learning_rate': 3.7772e-05, 'epoch': 3.29} | |
| 05/20/2024 13:25:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7182, 'learning_rate': 3.7609e-05, 'epoch': 3.31} | |
| 05/20/2024 13:26:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.7577, 'learning_rate': 3.7445e-05, 'epoch': 3.34} | |
| 05/20/2024 13:27:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7825, 'learning_rate': 3.7281e-05, 'epoch': 3.36} | |
| 05/20/2024 13:27:16 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-700 | |
| 05/20/2024 13:27:16 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-700/tokenizer_config.json | |
| 05/20/2024 13:27:16 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-700/special_tokens_map.json | |
| 05/20/2024 13:28:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7414, 'learning_rate': 3.7117e-05, 'epoch': 3.39} | |
| 05/20/2024 13:28:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7144, 'learning_rate': 3.6951e-05, 'epoch': 3.41} | |
| 05/20/2024 13:29:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.7516, 'learning_rate': 3.6785e-05, 'epoch': 3.43} | |
| 05/20/2024 13:30:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7484, 'learning_rate': 3.6618e-05, 'epoch': 3.46} | |
| 05/20/2024 13:31:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7775, 'learning_rate': 3.6451e-05, 'epoch': 3.48} | |
| 05/20/2024 13:31:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.7086, 'learning_rate': 3.6282e-05, 'epoch': 3.51} | |
| 05/20/2024 13:32:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.7165, 'learning_rate': 3.6114e-05, 'epoch': 3.53} | |
| 05/20/2024 13:33:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7668, 'learning_rate': 3.5944e-05, 'epoch': 3.55} | |
| 05/20/2024 13:34:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6595, 'learning_rate': 3.5774e-05, 'epoch': 3.58} | |
| 05/20/2024 13:34:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7469, 'learning_rate': 3.5603e-05, 'epoch': 3.60} | |
| 05/20/2024 13:35:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7063, 'learning_rate': 3.5432e-05, 'epoch': 3.63} | |
| 05/20/2024 13:36:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6694, 'learning_rate': 3.5260e-05, 'epoch': 3.65} | |
| 05/20/2024 13:37:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.7789, 'learning_rate': 3.5088e-05, 'epoch': 3.67} | |
| 05/20/2024 13:38:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7934, 'learning_rate': 3.4915e-05, 'epoch': 3.70} | |
| 05/20/2024 13:38:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.7295, 'learning_rate': 3.4741e-05, 'epoch': 3.72} | |
| 05/20/2024 13:39:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7474, 'learning_rate': 3.4567e-05, 'epoch': 3.75} | |
| 05/20/2024 13:40:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.7711, 'learning_rate': 3.4392e-05, 'epoch': 3.77} | |
| 05/20/2024 13:41:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7363, 'learning_rate': 3.4217e-05, 'epoch': 3.79} | |
| 05/20/2024 13:41:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.8531, 'learning_rate': 3.4041e-05, 'epoch': 3.82} | |
| 05/20/2024 13:42:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.8025, 'learning_rate': 3.3865e-05, 'epoch': 3.84} | |
| 05/20/2024 13:42:40 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-800 | |
| 05/20/2024 13:42:40 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-800/tokenizer_config.json | |
| 05/20/2024 13:42:40 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-800/special_tokens_map.json | |
| 05/20/2024 13:43:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6634, 'learning_rate': 3.3688e-05, 'epoch': 3.87} | |
| 05/20/2024 13:44:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.7664, 'learning_rate': 3.3511e-05, 'epoch': 3.89} | |
| 05/20/2024 13:45:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.8650, 'learning_rate': 3.3333e-05, 'epoch': 3.91} | |
| 05/20/2024 13:45:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7096, 'learning_rate': 3.3155e-05, 'epoch': 3.94} | |
| 05/20/2024 13:46:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.8476, 'learning_rate': 3.2976e-05, 'epoch': 3.96} | |
| 05/20/2024 13:47:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.7050, 'learning_rate': 3.2797e-05, 'epoch': 3.99} | |
| 05/20/2024 13:48:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7086, 'learning_rate': 3.2618e-05, 'epoch': 4.01} | |
| 05/20/2024 13:48:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6899, 'learning_rate': 3.2438e-05, 'epoch': 4.03} | |
| 05/20/2024 13:49:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.8088, 'learning_rate': 3.2257e-05, 'epoch': 4.06} | |
| 05/20/2024 13:50:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7096, 'learning_rate': 3.2076e-05, 'epoch': 4.08} | |
| 05/20/2024 13:51:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7646, 'learning_rate': 3.1895e-05, 'epoch': 4.11} | |
| 05/20/2024 13:51:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7525, 'learning_rate': 3.1713e-05, 'epoch': 4.13} | |
| 05/20/2024 13:52:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7231, 'learning_rate': 3.1531e-05, 'epoch': 4.15} | |
| 05/20/2024 13:53:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.7431, 'learning_rate': 3.1349e-05, 'epoch': 4.18} | |
| 05/20/2024 13:54:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7619, 'learning_rate': 3.1166e-05, 'epoch': 4.20} | |
| 05/20/2024 13:55:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7806, 'learning_rate': 3.0983e-05, 'epoch': 4.23} | |
| 05/20/2024 13:55:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7010, 'learning_rate': 3.0799e-05, 'epoch': 4.25} | |
| 05/20/2024 13:56:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7114, 'learning_rate': 3.0616e-05, 'epoch': 4.27} | |
| 05/20/2024 13:57:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7407, 'learning_rate': 3.0431e-05, 'epoch': 4.30} | |
| 05/20/2024 13:58:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7560, 'learning_rate': 3.0247e-05, 'epoch': 4.32} | |
| 05/20/2024 13:58:04 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-900 | |
| 05/20/2024 13:58:04 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-900/tokenizer_config.json | |
| 05/20/2024 13:58:04 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-900/special_tokens_map.json | |
| 05/20/2024 13:58:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6897, 'learning_rate': 3.0062e-05, 'epoch': 4.35} | |
| 05/20/2024 13:59:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7212, 'learning_rate': 2.9877e-05, 'epoch': 4.37} | |
| 05/20/2024 14:00:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.8578, 'learning_rate': 2.9692e-05, 'epoch': 4.39} | |
| 05/20/2024 14:01:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7116, 'learning_rate': 2.9506e-05, 'epoch': 4.42} | |
| 05/20/2024 14:01:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7693, 'learning_rate': 2.9321e-05, 'epoch': 4.44} | |
| 05/20/2024 14:02:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6641, 'learning_rate': 2.9134e-05, 'epoch': 4.47} | |
| 05/20/2024 14:03:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.7488, 'learning_rate': 2.8948e-05, 'epoch': 4.49} | |
| 05/20/2024 14:04:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6626, 'learning_rate': 2.8762e-05, 'epoch': 4.51} | |
| 05/20/2024 14:05:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7064, 'learning_rate': 2.8575e-05, 'epoch': 4.54} | |
| 05/20/2024 14:05:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7030, 'learning_rate': 2.8388e-05, 'epoch': 4.56} | |
| 05/20/2024 14:06:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.8085, 'learning_rate': 2.8201e-05, 'epoch': 4.59} | |
| 05/20/2024 14:07:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7251, 'learning_rate': 2.8013e-05, 'epoch': 4.61} | |
| 05/20/2024 14:08:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7358, 'learning_rate': 2.7826e-05, 'epoch': 4.63} | |
| 05/20/2024 14:09:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.7625, 'learning_rate': 2.7638e-05, 'epoch': 4.66} | |
| 05/20/2024 14:09:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.8123, 'learning_rate': 2.7450e-05, 'epoch': 4.68} | |
| 05/20/2024 14:10:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7068, 'learning_rate': 2.7262e-05, 'epoch': 4.71} | |
| 05/20/2024 14:11:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.7431, 'learning_rate': 2.7074e-05, 'epoch': 4.73} | |
| 05/20/2024 14:12:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.7161, 'learning_rate': 2.6886e-05, 'epoch': 4.75} | |
| 05/20/2024 14:13:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7311, 'learning_rate': 2.6698e-05, 'epoch': 4.78} | |
| 05/20/2024 14:13:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6689, 'learning_rate': 2.6509e-05, 'epoch': 4.80} | |
| 05/20/2024 14:13:45 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1000 | |
| 05/20/2024 14:13:46 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1000/tokenizer_config.json | |
| 05/20/2024 14:13:46 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1000/special_tokens_map.json | |
| 05/20/2024 14:14:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6888, 'learning_rate': 2.6321e-05, 'epoch': 4.83} | |
| 05/20/2024 14:15:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.7879, 'learning_rate': 2.6132e-05, 'epoch': 4.85} | |
| 05/20/2024 14:16:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6958, 'learning_rate': 2.5944e-05, 'epoch': 4.87} | |
| 05/20/2024 14:16:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6858, 'learning_rate': 2.5755e-05, 'epoch': 4.90} | |
| 05/20/2024 14:17:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6799, 'learning_rate': 2.5566e-05, 'epoch': 4.92} | |
| 05/20/2024 14:18:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7670, 'learning_rate': 2.5378e-05, 'epoch': 4.95} | |
| 05/20/2024 14:19:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7453, 'learning_rate': 2.5189e-05, 'epoch': 4.97} | |
| 05/20/2024 14:19:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.7559, 'learning_rate': 2.5000e-05, 'epoch': 4.99} | |
| 05/20/2024 14:20:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7729, 'learning_rate': 2.4811e-05, 'epoch': 5.02} | |
| 05/20/2024 14:21:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6956, 'learning_rate': 2.4622e-05, 'epoch': 5.04} | |
| 05/20/2024 14:22:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7124, 'learning_rate': 2.4434e-05, 'epoch': 5.07} | |
| 05/20/2024 14:23:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7472, 'learning_rate': 2.4245e-05, 'epoch': 5.09} | |
| 05/20/2024 14:23:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6805, 'learning_rate': 2.4056e-05, 'epoch': 5.11} | |
| 05/20/2024 14:24:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6898, 'learning_rate': 2.3868e-05, 'epoch': 5.14} | |
| 05/20/2024 14:25:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6664, 'learning_rate': 2.3679e-05, 'epoch': 5.16} | |
| 05/20/2024 14:26:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.7125, 'learning_rate': 2.3491e-05, 'epoch': 5.19} | |
| 05/20/2024 14:26:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7797, 'learning_rate': 2.3302e-05, 'epoch': 5.21} | |
| 05/20/2024 14:27:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7587, 'learning_rate': 2.3114e-05, 'epoch': 5.23} | |
| 05/20/2024 14:28:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7414, 'learning_rate': 2.2926e-05, 'epoch': 5.26} | |
| 05/20/2024 14:29:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6972, 'learning_rate': 2.2738e-05, 'epoch': 5.28} | |
| 05/20/2024 14:29:12 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1100 | |
| 05/20/2024 14:29:12 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1100/tokenizer_config.json | |
| 05/20/2024 14:29:12 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1100/special_tokens_map.json | |
| 05/20/2024 14:29:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.7168, 'learning_rate': 2.2550e-05, 'epoch': 5.31} | |
| 05/20/2024 14:30:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6441, 'learning_rate': 2.2362e-05, 'epoch': 5.33} | |
| 05/20/2024 14:31:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.7473, 'learning_rate': 2.2174e-05, 'epoch': 5.35} | |
| 05/20/2024 14:32:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6849, 'learning_rate': 2.1987e-05, 'epoch': 5.38} | |
| 05/20/2024 14:32:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6715, 'learning_rate': 2.1799e-05, 'epoch': 5.40} | |
| 05/20/2024 14:33:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7139, 'learning_rate': 2.1612e-05, 'epoch': 5.43} | |
| 05/20/2024 14:34:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.8102, 'learning_rate': 2.1425e-05, 'epoch': 5.45} | |
| 05/20/2024 14:35:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7772, 'learning_rate': 2.1238e-05, 'epoch': 5.47} | |
| 05/20/2024 14:36:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7506, 'learning_rate': 2.1052e-05, 'epoch': 5.50} | |
| 05/20/2024 14:37:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7174, 'learning_rate': 2.0866e-05, 'epoch': 5.52} | |
| 05/20/2024 14:37:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7339, 'learning_rate': 2.0679e-05, 'epoch': 5.55} | |
| 05/20/2024 14:38:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.7076, 'learning_rate': 2.0494e-05, 'epoch': 5.57} | |
| 05/20/2024 14:39:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7758, 'learning_rate': 2.0308e-05, 'epoch': 5.59} | |
| 05/20/2024 14:40:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7103, 'learning_rate': 2.0123e-05, 'epoch': 5.62} | |
| 05/20/2024 14:41:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7470, 'learning_rate': 1.9938e-05, 'epoch': 5.64} | |
| 05/20/2024 14:41:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7325, 'learning_rate': 1.9753e-05, 'epoch': 5.67} | |
| 05/20/2024 14:42:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7336, 'learning_rate': 1.9569e-05, 'epoch': 5.69} | |
| 05/20/2024 14:43:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7238, 'learning_rate': 1.9384e-05, 'epoch': 5.71} | |
| 05/20/2024 14:44:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6934, 'learning_rate': 1.9201e-05, 'epoch': 5.74} | |
| 05/20/2024 14:44:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7573, 'learning_rate': 1.9017e-05, 'epoch': 5.76} | |
| 05/20/2024 14:44:55 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1200 | |
| 05/20/2024 14:44:55 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1200/tokenizer_config.json | |
| 05/20/2024 14:44:55 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1200/special_tokens_map.json | |
| 05/20/2024 14:45:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.7232, 'learning_rate': 1.8834e-05, 'epoch': 5.79} | |
| 05/20/2024 14:46:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.7221, 'learning_rate': 1.8651e-05, 'epoch': 5.81} | |
| 05/20/2024 14:47:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7550, 'learning_rate': 1.8469e-05, 'epoch': 5.83} | |
| 05/20/2024 14:48:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6962, 'learning_rate': 1.8287e-05, 'epoch': 5.86} | |
| 05/20/2024 14:48:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7443, 'learning_rate': 1.8105e-05, 'epoch': 5.88} | |
| 05/20/2024 14:49:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6654, 'learning_rate': 1.7924e-05, 'epoch': 5.91} | |
| 05/20/2024 14:50:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7271, 'learning_rate': 1.7743e-05, 'epoch': 5.93} | |
| 05/20/2024 14:51:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7538, 'learning_rate': 1.7562e-05, 'epoch': 5.95} | |
| 05/20/2024 14:51:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6795, 'learning_rate': 1.7382e-05, 'epoch': 5.98} | |
| 05/20/2024 14:52:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6446, 'learning_rate': 1.7203e-05, 'epoch': 6.00} | |
| 05/20/2024 14:53:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6994, 'learning_rate': 1.7024e-05, 'epoch': 6.03} | |
| 05/20/2024 14:54:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6886, 'learning_rate': 1.6845e-05, 'epoch': 6.05} | |
| 05/20/2024 14:54:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7485, 'learning_rate': 1.6667e-05, 'epoch': 6.07} | |
| 05/20/2024 14:55:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6399, 'learning_rate': 1.6489e-05, 'epoch': 6.10} | |
| 05/20/2024 14:56:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.7799, 'learning_rate': 1.6312e-05, 'epoch': 6.12} | |
| 05/20/2024 14:57:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7589, 'learning_rate': 1.6135e-05, 'epoch': 6.15} | |
| 05/20/2024 14:58:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6969, 'learning_rate': 1.5959e-05, 'epoch': 6.17} | |
| 05/20/2024 14:58:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.7108, 'learning_rate': 1.5783e-05, 'epoch': 6.19} | |
| 05/20/2024 14:59:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7478, 'learning_rate': 1.5608e-05, 'epoch': 6.22} | |
| 05/20/2024 15:00:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.7225, 'learning_rate': 1.5433e-05, 'epoch': 6.24} | |
| 05/20/2024 15:00:35 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1300 | |
| 05/20/2024 15:00:35 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1300/tokenizer_config.json | |
| 05/20/2024 15:00:35 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1300/special_tokens_map.json | |
| 05/20/2024 15:01:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6964, 'learning_rate': 1.5259e-05, 'epoch': 6.27} | |
| 05/20/2024 15:02:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.7673, 'learning_rate': 1.5085e-05, 'epoch': 6.29} | |
| 05/20/2024 15:02:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.7194, 'learning_rate': 1.4912e-05, 'epoch': 6.31} | |
| 05/20/2024 15:03:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6869, 'learning_rate': 1.4740e-05, 'epoch': 6.34} | |
| 05/20/2024 15:04:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6851, 'learning_rate': 1.4568e-05, 'epoch': 6.36} | |
| 05/20/2024 15:05:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7242, 'learning_rate': 1.4397e-05, 'epoch': 6.39} | |
| 05/20/2024 15:05:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.7155, 'learning_rate': 1.4226e-05, 'epoch': 6.41} | |
| 05/20/2024 15:06:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6706, 'learning_rate': 1.4056e-05, 'epoch': 6.43} | |
| 05/20/2024 15:07:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6937, 'learning_rate': 1.3886e-05, 'epoch': 6.46} | |
| 05/20/2024 15:08:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.8316, 'learning_rate': 1.3718e-05, 'epoch': 6.48} | |
| 05/20/2024 15:09:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7229, 'learning_rate': 1.3549e-05, 'epoch': 6.51} | |
| 05/20/2024 15:09:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7025, 'learning_rate': 1.3382e-05, 'epoch': 6.53} | |
| 05/20/2024 15:10:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7420, 'learning_rate': 1.3215e-05, 'epoch': 6.55} | |
| 05/20/2024 15:11:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6737, 'learning_rate': 1.3049e-05, 'epoch': 6.58} | |
| 05/20/2024 15:12:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7577, 'learning_rate': 1.2883e-05, 'epoch': 6.60} | |
| 05/20/2024 15:12:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6495, 'learning_rate': 1.2719e-05, 'epoch': 6.63} | |
| 05/20/2024 15:13:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.7069, 'learning_rate': 1.2555e-05, 'epoch': 6.65} | |
| 05/20/2024 15:14:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7050, 'learning_rate': 1.2391e-05, 'epoch': 6.67} | |
| 05/20/2024 15:15:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6710, 'learning_rate': 1.2228e-05, 'epoch': 6.70} | |
| 05/20/2024 15:15:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7456, 'learning_rate': 1.2067e-05, 'epoch': 6.72} | |
| 05/20/2024 15:15:56 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1400 | |
| 05/20/2024 15:15:57 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1400/tokenizer_config.json | |
| 05/20/2024 15:15:57 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1400/special_tokens_map.json | |
| 05/20/2024 15:16:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6899, 'learning_rate': 1.1905e-05, 'epoch': 6.75} | |
| 05/20/2024 15:17:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.7024, 'learning_rate': 1.1745e-05, 'epoch': 6.77} | |
| 05/20/2024 15:18:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6571, 'learning_rate': 1.1585e-05, 'epoch': 6.79} | |
| 05/20/2024 15:19:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7290, 'learning_rate': 1.1426e-05, 'epoch': 6.82} | |
| 05/20/2024 15:19:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7971, 'learning_rate': 1.1268e-05, 'epoch': 6.84} | |
| 05/20/2024 15:20:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6376, 'learning_rate': 1.1111e-05, 'epoch': 6.87} | |
| 05/20/2024 15:21:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6663, 'learning_rate': 1.0954e-05, 'epoch': 6.89} | |
| 05/20/2024 15:22:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6898, 'learning_rate': 1.0798e-05, 'epoch': 6.91} | |
| 05/20/2024 15:22:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6860, 'learning_rate': 1.0643e-05, 'epoch': 6.94} | |
| 05/20/2024 15:23:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.7803, 'learning_rate': 1.0489e-05, 'epoch': 6.96} | |
| 05/20/2024 15:24:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6809, 'learning_rate': 1.0336e-05, 'epoch': 6.99} | |
| 05/20/2024 15:25:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6936, 'learning_rate': 1.0183e-05, 'epoch': 7.01} | |
| 05/20/2024 15:26:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.7005, 'learning_rate': 1.0032e-05, 'epoch': 7.03} | |
| 05/20/2024 15:26:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.8484, 'learning_rate': 9.8810e-06, 'epoch': 7.06} | |
| 05/20/2024 15:27:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.7897, 'learning_rate': 9.7311e-06, 'epoch': 7.08} | |
| 05/20/2024 15:28:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6696, 'learning_rate': 9.5820e-06, 'epoch': 7.11} | |
| 05/20/2024 15:29:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6867, 'learning_rate': 9.4339e-06, 'epoch': 7.13} | |
| 05/20/2024 15:29:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7372, 'learning_rate': 9.2866e-06, 'epoch': 7.15} | |
| 05/20/2024 15:30:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6718, 'learning_rate': 9.1402e-06, 'epoch': 7.18} | |
| 05/20/2024 15:31:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6819, 'learning_rate': 8.9947e-06, 'epoch': 7.20} | |
| 05/20/2024 15:31:24 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1500 | |
| 05/20/2024 15:31:24 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1500/tokenizer_config.json | |
| 05/20/2024 15:31:24 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1500/special_tokens_map.json | |
| 05/20/2024 15:32:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7094, 'learning_rate': 8.8501e-06, 'epoch': 7.23} | |
| 05/20/2024 15:32:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7423, 'learning_rate': 8.7064e-06, 'epoch': 7.25} | |
| 05/20/2024 15:33:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6957, 'learning_rate': 8.5637e-06, 'epoch': 7.27} | |
| 05/20/2024 15:34:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6382, 'learning_rate': 8.4219e-06, 'epoch': 7.30} | |
| 05/20/2024 15:35:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6939, 'learning_rate': 8.2811e-06, 'epoch': 7.32} | |
| 05/20/2024 15:36:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7682, 'learning_rate': 8.1412e-06, 'epoch': 7.35} | |
| 05/20/2024 15:36:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6319, 'learning_rate': 8.0023e-06, 'epoch': 7.37} | |
| 05/20/2024 15:37:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.7331, 'learning_rate': 7.8643e-06, 'epoch': 7.39} | |
| 05/20/2024 15:38:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7249, 'learning_rate': 7.7273e-06, 'epoch': 7.42} | |
| 05/20/2024 15:39:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6484, 'learning_rate': 7.5913e-06, 'epoch': 7.44} | |
| 05/20/2024 15:39:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7723, 'learning_rate': 7.4563e-06, 'epoch': 7.47} | |
| 05/20/2024 15:40:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7266, 'learning_rate': 7.3223e-06, 'epoch': 7.49} | |
| 05/20/2024 15:41:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6927, 'learning_rate': 7.1893e-06, 'epoch': 7.52} | |
| 05/20/2024 15:42:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7219, 'learning_rate': 7.0574e-06, 'epoch': 7.54} | |
| 05/20/2024 15:43:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6933, 'learning_rate': 6.9264e-06, 'epoch': 7.56} | |
| 05/20/2024 15:43:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7651, 'learning_rate': 6.7965e-06, 'epoch': 7.59} | |
| 05/20/2024 15:44:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6558, 'learning_rate': 6.6676e-06, 'epoch': 7.61} | |
| 05/20/2024 15:45:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6601, 'learning_rate': 6.5397e-06, 'epoch': 7.64} | |
| 05/20/2024 15:46:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6938, 'learning_rate': 6.4130e-06, 'epoch': 7.66} | |
| 05/20/2024 15:47:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.7301, 'learning_rate': 6.2872e-06, 'epoch': 7.68} | |
| 05/20/2024 15:47:01 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1600 | |
| 05/20/2024 15:47:01 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1600/tokenizer_config.json | |
| 05/20/2024 15:47:01 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1600/special_tokens_map.json | |
| 05/20/2024 15:47:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6848, 'learning_rate': 6.1626e-06, 'epoch': 7.71} | |
| 05/20/2024 15:48:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6372, 'learning_rate': 6.0390e-06, 'epoch': 7.73} | |
| 05/20/2024 15:49:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6736, 'learning_rate': 5.9165e-06, 'epoch': 7.76} | |
| 05/20/2024 15:50:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6915, 'learning_rate': 5.7951e-06, 'epoch': 7.78} | |
| 05/20/2024 15:50:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6960, 'learning_rate': 5.6747e-06, 'epoch': 7.80} | |
| 05/20/2024 15:51:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7064, 'learning_rate': 5.5555e-06, 'epoch': 7.83} | |
| 05/20/2024 15:52:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7497, 'learning_rate': 5.4374e-06, 'epoch': 7.85} | |
| 05/20/2024 15:53:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7025, 'learning_rate': 5.3204e-06, 'epoch': 7.88} | |
| 05/20/2024 15:53:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6823, 'learning_rate': 5.2045e-06, 'epoch': 7.90} | |
| 05/20/2024 15:54:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.8013, 'learning_rate': 5.0898e-06, 'epoch': 7.92} | |
| 05/20/2024 15:55:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7497, 'learning_rate': 4.9762e-06, 'epoch': 7.95} | |
| 05/20/2024 15:56:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.7817, 'learning_rate': 4.8637e-06, 'epoch': 7.97} | |
| 05/20/2024 15:57:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6150, 'learning_rate': 4.7524e-06, 'epoch': 8.00} | |
| 05/20/2024 15:57:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7037, 'learning_rate': 4.6422e-06, 'epoch': 8.02} | |
| 05/20/2024 15:58:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6747, 'learning_rate': 4.5332e-06, 'epoch': 8.04} | |
| 05/20/2024 15:59:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.7154, 'learning_rate': 4.4254e-06, 'epoch': 8.07} | |
| 05/20/2024 16:00:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7838, 'learning_rate': 4.3187e-06, 'epoch': 8.09} | |
| 05/20/2024 16:00:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7525, 'learning_rate': 4.2133e-06, 'epoch': 8.12} | |
| 05/20/2024 16:01:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6624, 'learning_rate': 4.1090e-06, 'epoch': 8.14} | |
| 05/20/2024 16:02:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6821, 'learning_rate': 4.0059e-06, 'epoch': 8.16} | |
| 05/20/2024 16:02:18 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1700 | |
| 05/20/2024 16:02:18 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1700/tokenizer_config.json | |
| 05/20/2024 16:02:18 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1700/special_tokens_map.json | |
| 05/20/2024 16:03:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6932, 'learning_rate': 3.9040e-06, 'epoch': 8.19} | |
| 05/20/2024 16:03:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7308, 'learning_rate': 3.8032e-06, 'epoch': 8.21} | |
| 05/20/2024 16:04:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7136, 'learning_rate': 3.7037e-06, 'epoch': 8.24} | |
| 05/20/2024 16:05:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6595, 'learning_rate': 3.6055e-06, 'epoch': 8.26} | |
| 05/20/2024 16:06:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.7671, 'learning_rate': 3.5084e-06, 'epoch': 8.28} | |
| 05/20/2024 16:06:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6561, 'learning_rate': 3.4126e-06, 'epoch': 8.31} | |
| 05/20/2024 16:07:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6876, 'learning_rate': 3.3180e-06, 'epoch': 8.33} | |
| 05/20/2024 16:08:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6819, 'learning_rate': 3.2246e-06, 'epoch': 8.36} | |
| 05/20/2024 16:09:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.7044, 'learning_rate': 3.1325e-06, 'epoch': 8.38} | |
| 05/20/2024 16:10:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6317, 'learning_rate': 3.0416e-06, 'epoch': 8.40} | |
| 05/20/2024 16:10:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6521, 'learning_rate': 2.9520e-06, 'epoch': 8.43} | |
| 05/20/2024 16:11:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7572, 'learning_rate': 2.8636e-06, 'epoch': 8.45} | |
| 05/20/2024 16:12:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7184, 'learning_rate': 2.7765e-06, 'epoch': 8.48} | |
| 05/20/2024 16:13:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6881, 'learning_rate': 2.6907e-06, 'epoch': 8.50} | |
| 05/20/2024 16:14:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6575, 'learning_rate': 2.6061e-06, 'epoch': 8.52} | |
| 05/20/2024 16:14:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7457, 'learning_rate': 2.5228e-06, 'epoch': 8.55} | |
| 05/20/2024 16:15:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7127, 'learning_rate': 2.4408e-06, 'epoch': 8.57} | |
| 05/20/2024 16:16:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7442, 'learning_rate': 2.3601e-06, 'epoch': 8.60} | |
| 05/20/2024 16:17:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6743, 'learning_rate': 2.2806e-06, 'epoch': 8.62} | |
| 05/20/2024 16:17:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7338, 'learning_rate': 2.2025e-06, 'epoch': 8.64} | |
| 05/20/2024 16:17:50 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1800 | |
| 05/20/2024 16:17:50 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1800/tokenizer_config.json | |
| 05/20/2024 16:17:50 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1800/special_tokens_map.json | |
| 05/20/2024 16:18:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.7514, 'learning_rate': 2.1257e-06, 'epoch': 8.67} | |
| 05/20/2024 16:19:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7774, 'learning_rate': 2.0501e-06, 'epoch': 8.69} | |
| 05/20/2024 16:20:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6895, 'learning_rate': 1.9759e-06, 'epoch': 8.72} | |
| 05/20/2024 16:21:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7218, 'learning_rate': 1.9030e-06, 'epoch': 8.74} | |
| 05/20/2024 16:21:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7553, 'learning_rate': 1.8314e-06, 'epoch': 8.76} | |
| 05/20/2024 16:22:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6779, 'learning_rate': 1.7612e-06, 'epoch': 8.79} | |
| 05/20/2024 16:23:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6946, 'learning_rate': 1.6922e-06, 'epoch': 8.81} | |
| 05/20/2024 16:24:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7149, 'learning_rate': 1.6246e-06, 'epoch': 8.84} | |
| 05/20/2024 16:24:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6681, 'learning_rate': 1.5583e-06, 'epoch': 8.86} | |
| 05/20/2024 16:25:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6519, 'learning_rate': 1.4934e-06, 'epoch': 8.88} | |
| 05/20/2024 16:26:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6957, 'learning_rate': 1.4298e-06, 'epoch': 8.91} | |
| 05/20/2024 16:27:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6942, 'learning_rate': 1.3675e-06, 'epoch': 8.93} | |
| 05/20/2024 16:28:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6578, 'learning_rate': 1.3066e-06, 'epoch': 8.96} | |
| 05/20/2024 16:28:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6994, 'learning_rate': 1.2470e-06, 'epoch': 8.98} | |
| 05/20/2024 16:29:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6430, 'learning_rate': 1.1888e-06, 'epoch': 9.00} | |
| 05/20/2024 16:30:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6307, 'learning_rate': 1.1320e-06, 'epoch': 9.03} | |
| 05/20/2024 16:31:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7088, 'learning_rate': 1.0765e-06, 'epoch': 9.05} | |
| 05/20/2024 16:31:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6603, 'learning_rate': 1.0224e-06, 'epoch': 9.08} | |
| 05/20/2024 16:32:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.8255, 'learning_rate': 9.6961e-07, 'epoch': 9.10} | |
| 05/20/2024 16:33:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6834, 'learning_rate': 9.1823e-07, 'epoch': 9.12} | |
| 05/20/2024 16:33:28 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1900 | |
| 05/20/2024 16:33:28 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1900/tokenizer_config.json | |
| 05/20/2024 16:33:28 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1900/special_tokens_map.json | |
| 05/20/2024 16:34:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6365, 'learning_rate': 8.6822e-07, 'epoch': 9.15} | |
| 05/20/2024 16:35:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7317, 'learning_rate': 8.1958e-07, 'epoch': 9.17} | |
| 05/20/2024 16:35:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7410, 'learning_rate': 7.7233e-07, 'epoch': 9.20} | |
| 05/20/2024 16:36:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6881, 'learning_rate': 7.2645e-07, 'epoch': 9.22} | |
| 05/20/2024 16:37:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7350, 'learning_rate': 6.8196e-07, 'epoch': 9.24} | |
| 05/20/2024 16:38:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7227, 'learning_rate': 6.3886e-07, 'epoch': 9.27} | |
| 05/20/2024 16:38:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6810, 'learning_rate': 5.9715e-07, 'epoch': 9.29} | |
| 05/20/2024 16:39:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7081, 'learning_rate': 5.5683e-07, 'epoch': 9.32} | |
| 05/20/2024 16:40:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7064, 'learning_rate': 5.1790e-07, 'epoch': 9.34} | |
| 05/20/2024 16:41:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6829, 'learning_rate': 4.8037e-07, 'epoch': 9.36} | |
| 05/20/2024 16:42:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6814, 'learning_rate': 4.4423e-07, 'epoch': 9.39} | |
| 05/20/2024 16:42:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7690, 'learning_rate': 4.0950e-07, 'epoch': 9.41} | |
| 05/20/2024 16:43:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7539, 'learning_rate': 3.7617e-07, 'epoch': 9.44} | |
| 05/20/2024 16:44:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6506, 'learning_rate': 3.4425e-07, 'epoch': 9.46} | |
| 05/20/2024 16:45:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6763, 'learning_rate': 3.1373e-07, 'epoch': 9.48} | |
| 05/20/2024 16:45:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6776, 'learning_rate': 2.8461e-07, 'epoch': 9.51} | |
| 05/20/2024 16:46:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7292, 'learning_rate': 2.5691e-07, 'epoch': 9.53} | |
| 05/20/2024 16:47:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.8111, 'learning_rate': 2.3062e-07, 'epoch': 9.56} | |
| 05/20/2024 16:48:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6473, 'learning_rate': 2.0574e-07, 'epoch': 9.58} | |
| 05/20/2024 16:48:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6774, 'learning_rate': 1.8228e-07, 'epoch': 9.60} | |
| 05/20/2024 16:48:54 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-2000 | |
| 05/20/2024 16:48:54 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-2000/tokenizer_config.json | |
| 05/20/2024 16:48:54 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-2000/special_tokens_map.json | |
| 05/20/2024 16:49:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6782, 'learning_rate': 1.6023e-07, 'epoch': 9.63} | |
| 05/20/2024 16:50:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6965, 'learning_rate': 1.3960e-07, 'epoch': 9.65} | |
| 05/20/2024 16:51:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6496, 'learning_rate': 1.2038e-07, 'epoch': 9.68} | |
| 05/20/2024 16:51:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6511, 'learning_rate': 1.0259e-07, 'epoch': 9.70} | |
| 05/20/2024 16:52:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7524, 'learning_rate': 8.6210e-08, 'epoch': 9.72} | |
| 05/20/2024 16:53:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6653, 'learning_rate': 7.1255e-08, 'epoch': 9.75} | |
| 05/20/2024 16:54:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6718, 'learning_rate': 5.7722e-08, 'epoch': 9.77} | |
| 05/20/2024 16:55:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7114, 'learning_rate': 4.5611e-08, 'epoch': 9.80} | |
| 05/20/2024 16:55:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.7125, 'learning_rate': 3.4924e-08, 'epoch': 9.82} | |
| 05/20/2024 16:56:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6236, 'learning_rate': 2.5660e-08, 'epoch': 9.84} | |
| 05/20/2024 16:57:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.7353, 'learning_rate': 1.7820e-08, 'epoch': 9.87} | |
| 05/20/2024 16:58:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7489, 'learning_rate': 1.1405e-08, 'epoch': 9.89} | |
| 05/20/2024 16:59:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7743, 'learning_rate': 6.4157e-09, 'epoch': 9.92} | |
| 05/20/2024 16:59:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6435, 'learning_rate': 2.8515e-09, 'epoch': 9.94} | |
| 05/20/2024 17:00:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7375, 'learning_rate': 7.1289e-10, 'epoch': 9.96} | |
| 05/20/2024 17:01:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7238, 'learning_rate': 0.0000e+00, 'epoch': 9.99} | |
| 05/20/2024 17:01:29 - INFO - transformers.trainer - | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| 05/20/2024 17:01:29 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed | |
| 05/20/2024 17:01:29 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/tokenizer_config.json | |
| 05/20/2024 17:01:29 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/special_tokens_map.json | |
| 05/20/2024 17:01:29 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields: | |
| {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} | |