diff --git "a/running_log.txt" "b/running_log.txt"
new file mode 100644--- /dev/null
+++ "b/running_log.txt"
@@ -0,0 +1,2583 @@
+05/20/2024 11:51:17 - INFO - transformers.tokenization_utils_base - loading file vocab.json
+
+05/20/2024 11:51:17 - INFO - transformers.tokenization_utils_base - loading file merges.txt
+
+05/20/2024 11:51:17 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json
+
+05/20/2024 11:51:17 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json
+
+05/20/2024 11:51:17 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json
+
+05/20/2024 11:51:17 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json
+
+05/20/2024 11:51:18 - 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 11:51:18 - INFO - llmtuner.data.template - Replace eos token: <|im_end|>
+
+05/20/2024 11:51:18 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/LangGPT_community.jsonl...
+
+05/20/2024 11:51:18 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
+
+05/20/2024 11:51:19 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/langgpt_alpaca.jsonl...
+
+05/20/2024 11:51:19 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
+
+05/20/2024 11:51:20 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/langgpt_seed.jsonl...
+
+05/20/2024 11:51:20 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
+
+05/20/2024 11:51:39 - INFO - transformers.configuration_utils - loading configuration file /datas/huggingface/Qwen1.5-4B-Chat/config.json
+
+05/20/2024 11:51:39 - 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 11:51:39 - INFO - transformers.modeling_utils - loading weights file /datas/huggingface/Qwen1.5-4B-Chat/model.safetensors.index.json
+
+05/20/2024 11:51:39 - INFO - transformers.modeling_utils - Instantiating Qwen2ForCausalLM model under default dtype torch.float16.
+
+05/20/2024 11:51:39 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "use_cache": false
+}
+
+
+05/20/2024 11:51:42 - INFO - transformers.modeling_utils - All model checkpoint weights were used when initializing Qwen2ForCausalLM.
+
+
+05/20/2024 11:51:42 - 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 11:51:42 - INFO - transformers.generation.configuration_utils - loading configuration file /datas/huggingface/Qwen1.5-4B-Chat/generation_config.json
+
+05/20/2024 11:51:42 - 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 11:51:42 - INFO - llmtuner.model.utils.checkpointing - Gradient checkpointing enabled.
+
+05/20/2024 11:51:42 - INFO - llmtuner.model.utils.attention - Using torch SDPA for faster training and inference.
+
+05/20/2024 11:51:42 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
+
+05/20/2024 11:51:43 - INFO - llmtuner.model.loader - trainable params: 3276800 || all params: 3953646080 || trainable%: 0.0829
+
+05/20/2024 11:51:43 - INFO - transformers.trainer - Using auto half precision backend
+
+05/20/2024 11:51:43 - INFO - transformers.trainer - ***** Running training *****
+
+05/20/2024 11:51:43 - INFO - transformers.trainer -   Num examples = 8,531
+
+05/20/2024 11:51:43 - INFO - transformers.trainer -   Num Epochs = 10
+
+05/20/2024 11:51:43 - INFO - transformers.trainer -   Instantaneous batch size per device = 2
+
+05/20/2024 11:51:43 - INFO - transformers.trainer -   Total train batch size (w. parallel, distributed & accumulation) = 16
+
+05/20/2024 11:51:43 - INFO - transformers.trainer -   Gradient Accumulation steps = 8
+
+05/20/2024 11:51:43 - INFO - transformers.trainer -   Total optimization steps = 5,330
+
+05/20/2024 11:51:43 - INFO - transformers.trainer -   Number of trainable parameters = 3,276,800
+
+05/20/2024 11:52:38 - INFO - llmtuner.extras.callbacks - {'loss': 1.0231, 'learning_rate': 5.0000e-05, 'epoch': 0.01}
+
+05/20/2024 11:53:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.9820, 'learning_rate': 5.0000e-05, 'epoch': 0.02}
+
+05/20/2024 11:54:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.9099, 'learning_rate': 4.9999e-05, 'epoch': 0.03}
+
+05/20/2024 11:55:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.9602, 'learning_rate': 4.9998e-05, 'epoch': 0.04}
+
+05/20/2024 11:55:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.9015, 'learning_rate': 4.9997e-05, 'epoch': 0.05}
+
+05/20/2024 11:56:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.8523, 'learning_rate': 4.9996e-05, 'epoch': 0.06}
+
+05/20/2024 11:57:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.8770, 'learning_rate': 4.9995e-05, 'epoch': 0.07}
+
+05/20/2024 11:58:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.8987, 'learning_rate': 4.9993e-05, 'epoch': 0.08}
+
+05/20/2024 11:59:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.8965, 'learning_rate': 4.9991e-05, 'epoch': 0.08}
+
+05/20/2024 12:00:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.8476, 'learning_rate': 4.9989e-05, 'epoch': 0.09}
+
+05/20/2024 12:00:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.8405, 'learning_rate': 4.9987e-05, 'epoch': 0.10}
+
+05/20/2024 12:01:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.8339, 'learning_rate': 4.9984e-05, 'epoch': 0.11}
+
+05/20/2024 12:02:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.8181, 'learning_rate': 4.9982e-05, 'epoch': 0.12}
+
+05/20/2024 12:03:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7948, 'learning_rate': 4.9979e-05, 'epoch': 0.13}
+
+05/20/2024 12:04:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.8546, 'learning_rate': 4.9976e-05, 'epoch': 0.14}
+
+05/20/2024 12:05:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7743, 'learning_rate': 4.9972e-05, 'epoch': 0.15}
+
+05/20/2024 12:05:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7901, 'learning_rate': 4.9969e-05, 'epoch': 0.16}
+
+05/20/2024 12:06:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7999, 'learning_rate': 4.9965e-05, 'epoch': 0.17}
+
+05/20/2024 12:07:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.7708, 'learning_rate': 4.9961e-05, 'epoch': 0.18}
+
+05/20/2024 12:08:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7508, 'learning_rate': 4.9957e-05, 'epoch': 0.19}
+
+05/20/2024 12:08:23 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-100
+
+05/20/2024 12:08:23 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-100/tokenizer_config.json
+
+05/20/2024 12:08:23 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-100/special_tokens_map.json
+
+05/20/2024 12:09:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.8244, 'learning_rate': 4.9952e-05, 'epoch': 0.20}
+
+05/20/2024 12:09:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7836, 'learning_rate': 4.9947e-05, 'epoch': 0.21}
+
+05/20/2024 12:10:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.8070, 'learning_rate': 4.9943e-05, 'epoch': 0.22}
+
+05/20/2024 12:11:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.8193, 'learning_rate': 4.9937e-05, 'epoch': 0.23}
+
+05/20/2024 12:12:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.7919, 'learning_rate': 4.9932e-05, 'epoch': 0.23}
+
+05/20/2024 12:13:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7959, 'learning_rate': 4.9927e-05, 'epoch': 0.24}
+
+05/20/2024 12:14:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.8108, 'learning_rate': 4.9921e-05, 'epoch': 0.25}
+
+05/20/2024 12:15:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7673, 'learning_rate': 4.9915e-05, 'epoch': 0.26}
+
+05/20/2024 12:15:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.7525, 'learning_rate': 4.9909e-05, 'epoch': 0.27}
+
+05/20/2024 12:16:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.8168, 'learning_rate': 4.9902e-05, 'epoch': 0.28}
+
+05/20/2024 12:17:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.7433, 'learning_rate': 4.9896e-05, 'epoch': 0.29}
+
+05/20/2024 12:18:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7820, 'learning_rate': 4.9889e-05, 'epoch': 0.30}
+
+05/20/2024 12:19:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.8031, 'learning_rate': 4.9882e-05, 'epoch': 0.31}
+
+05/20/2024 12:19:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.7699, 'learning_rate': 4.9875e-05, 'epoch': 0.32}
+
+05/20/2024 12:20:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7942, 'learning_rate': 4.9867e-05, 'epoch': 0.33}
+
+05/20/2024 12:21:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.7669, 'learning_rate': 4.9859e-05, 'epoch': 0.34}
+
+05/20/2024 12:22:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.7720, 'learning_rate': 4.9852e-05, 'epoch': 0.35}
+
+05/20/2024 12:23:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7559, 'learning_rate': 4.9843e-05, 'epoch': 0.36}
+
+05/20/2024 12:24:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.8186, 'learning_rate': 4.9835e-05, 'epoch': 0.37}
+
+05/20/2024 12:25:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.8191, 'learning_rate': 4.9826e-05, 'epoch': 0.38}
+
+05/20/2024 12:25:07 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-200
+
+05/20/2024 12:25:07 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-200/tokenizer_config.json
+
+05/20/2024 12:25:07 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-200/special_tokens_map.json
+
+05/20/2024 12:26:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.7851, 'learning_rate': 4.9818e-05, 'epoch': 0.38}
+
+05/20/2024 12:26:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7945, 'learning_rate': 4.9809e-05, 'epoch': 0.39}
+
+05/20/2024 12:27:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7480, 'learning_rate': 4.9800e-05, 'epoch': 0.40}
+
+05/20/2024 12:28:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7707, 'learning_rate': 4.9790e-05, 'epoch': 0.41}
+
+05/20/2024 12:29:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7440, 'learning_rate': 4.9780e-05, 'epoch': 0.42}
+
+05/20/2024 12:30:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7194, 'learning_rate': 4.9771e-05, 'epoch': 0.43}
+
+05/20/2024 12:31:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.7763, 'learning_rate': 4.9761e-05, 'epoch': 0.44}
+
+05/20/2024 12:31:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.7578, 'learning_rate': 4.9750e-05, 'epoch': 0.45}
+
+05/20/2024 12:32:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7803, 'learning_rate': 4.9740e-05, 'epoch': 0.46}
+
+05/20/2024 12:33:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7760, 'learning_rate': 4.9729e-05, 'epoch': 0.47}
+
+05/20/2024 12:34:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7924, 'learning_rate': 4.9718e-05, 'epoch': 0.48}
+
+05/20/2024 12:35:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7244, 'learning_rate': 4.9707e-05, 'epoch': 0.49}
+
+05/20/2024 12:36:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.7342, 'learning_rate': 4.9696e-05, 'epoch': 0.50}
+
+05/20/2024 12:37:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.7412, 'learning_rate': 4.9684e-05, 'epoch': 0.51}
+
+05/20/2024 12:37:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.7339, 'learning_rate': 4.9672e-05, 'epoch': 0.52}
+
+05/20/2024 12:38:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.7598, 'learning_rate': 4.9660e-05, 'epoch': 0.53}
+
+05/20/2024 12:39:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7276, 'learning_rate': 4.9648e-05, 'epoch': 0.53}
+
+05/20/2024 12:40:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7417, 'learning_rate': 4.9636e-05, 'epoch': 0.54}
+
+05/20/2024 12:40:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7690, 'learning_rate': 4.9623e-05, 'epoch': 0.55}
+
+05/20/2024 12:41:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7662, 'learning_rate': 4.9610e-05, 'epoch': 0.56}
+
+05/20/2024 12:41:50 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-300
+
+05/20/2024 12:41:50 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-300/tokenizer_config.json
+
+05/20/2024 12:41:50 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-300/special_tokens_map.json
+
+05/20/2024 12:42:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.7545, 'learning_rate': 4.9597e-05, 'epoch': 0.57}
+
+05/20/2024 12:43:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.7350, 'learning_rate': 4.9584e-05, 'epoch': 0.58}
+
+05/20/2024 12:44:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.7213, 'learning_rate': 4.9570e-05, 'epoch': 0.59}
+
+05/20/2024 12:45:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.8094, 'learning_rate': 4.9557e-05, 'epoch': 0.60}
+
+05/20/2024 12:46:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7590, 'learning_rate': 4.9543e-05, 'epoch': 0.61}
+
+05/20/2024 12:46:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7093, 'learning_rate': 4.9529e-05, 'epoch': 0.62}
+
+05/20/2024 12:47:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7900, 'learning_rate': 4.9514e-05, 'epoch': 0.63}
+
+05/20/2024 12:48:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7392, 'learning_rate': 4.9500e-05, 'epoch': 0.64}
+
+05/20/2024 12:49:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.7701, 'learning_rate': 4.9485e-05, 'epoch': 0.65}
+
+05/20/2024 12:50:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.7877, 'learning_rate': 4.9470e-05, 'epoch': 0.66}
+
+05/20/2024 12:50:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7257, 'learning_rate': 4.9455e-05, 'epoch': 0.67}
+
+05/20/2024 12:51:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7804, 'learning_rate': 4.9439e-05, 'epoch': 0.68}
+
+05/20/2024 12:52:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.7028, 'learning_rate': 4.9424e-05, 'epoch': 0.68}
+
+05/20/2024 12:53:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.7214, 'learning_rate': 4.9408e-05, 'epoch': 0.69}
+
+05/20/2024 12:54:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7756, 'learning_rate': 4.9392e-05, 'epoch': 0.70}
+
+05/20/2024 12:55:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7650, 'learning_rate': 4.9376e-05, 'epoch': 0.71}
+
+05/20/2024 12:55:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.7364, 'learning_rate': 4.9359e-05, 'epoch': 0.72}
+
+05/20/2024 12:56:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7402, 'learning_rate': 4.9342e-05, 'epoch': 0.73}
+
+05/20/2024 12:57:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.7613, 'learning_rate': 4.9325e-05, 'epoch': 0.74}
+
+05/20/2024 12:58:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.7663, 'learning_rate': 4.9308e-05, 'epoch': 0.75}
+
+05/20/2024 12:58:26 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-400
+
+05/20/2024 12:58:26 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-400/tokenizer_config.json
+
+05/20/2024 12:58:26 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-400/special_tokens_map.json
+
+05/20/2024 12:59:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7309, 'learning_rate': 4.9291e-05, 'epoch': 0.76}
+
+05/20/2024 13:00:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7383, 'learning_rate': 4.9274e-05, 'epoch': 0.77}
+
+05/20/2024 13:01:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7411, 'learning_rate': 4.9256e-05, 'epoch': 0.78}
+
+05/20/2024 13:01:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.7757, 'learning_rate': 4.9238e-05, 'epoch': 0.79}
+
+05/20/2024 13:02:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7579, 'learning_rate': 4.9220e-05, 'epoch': 0.80}
+
+05/20/2024 13:03:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7324, 'learning_rate': 4.9201e-05, 'epoch': 0.81}
+
+05/20/2024 13:04:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6632, 'learning_rate': 4.9183e-05, 'epoch': 0.82}
+
+05/20/2024 13:05:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6948, 'learning_rate': 4.9164e-05, 'epoch': 0.83}
+
+05/20/2024 13:06:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7472, 'learning_rate': 4.9145e-05, 'epoch': 0.83}
+
+05/20/2024 13:06:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7237, 'learning_rate': 4.9126e-05, 'epoch': 0.84}
+
+05/20/2024 13:07:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7129, 'learning_rate': 4.9106e-05, 'epoch': 0.85}
+
+05/20/2024 13:08:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.7616, 'learning_rate': 4.9087e-05, 'epoch': 0.86}
+
+05/20/2024 13:09:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7346, 'learning_rate': 4.9067e-05, 'epoch': 0.87}
+
+05/20/2024 13:10:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.7308, 'learning_rate': 4.9047e-05, 'epoch': 0.88}
+
+05/20/2024 13:11:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7562, 'learning_rate': 4.9027e-05, 'epoch': 0.89}
+
+05/20/2024 13:11:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7420, 'learning_rate': 4.9006e-05, 'epoch': 0.90}
+
+05/20/2024 13:12:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7235, 'learning_rate': 4.8985e-05, 'epoch': 0.91}
+
+05/20/2024 13:13:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.7269, 'learning_rate': 4.8965e-05, 'epoch': 0.92}
+
+05/20/2024 13:14:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.8267, 'learning_rate': 4.8943e-05, 'epoch': 0.93}
+
+05/20/2024 13:15:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7260, 'learning_rate': 4.8922e-05, 'epoch': 0.94}
+
+05/20/2024 13:15:16 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-500
+
+05/20/2024 13:15:16 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-500/tokenizer_config.json
+
+05/20/2024 13:15:16 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-500/special_tokens_map.json
+
+05/20/2024 13:16:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7461, 'learning_rate': 4.8901e-05, 'epoch': 0.95}
+
+05/20/2024 13:16:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.7821, 'learning_rate': 4.8879e-05, 'epoch': 0.96}
+
+05/20/2024 13:17:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.7279, 'learning_rate': 4.8857e-05, 'epoch': 0.97}
+
+05/20/2024 13:18:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7274, 'learning_rate': 4.8835e-05, 'epoch': 0.98}
+
+05/20/2024 13:19:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7260, 'learning_rate': 4.8813e-05, 'epoch': 0.98}
+
+05/20/2024 13:20:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.7350, 'learning_rate': 4.8790e-05, 'epoch': 0.99}
+
+05/20/2024 13:21:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6954, 'learning_rate': 4.8767e-05, 'epoch': 1.00}
+
+05/20/2024 13:22:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6782, 'learning_rate': 4.8744e-05, 'epoch': 1.01}
+
+05/20/2024 13:22:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6825, 'learning_rate': 4.8721e-05, 'epoch': 1.02}
+
+05/20/2024 13:23:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7514, 'learning_rate': 4.8698e-05, 'epoch': 1.03}
+
+05/20/2024 13:24:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.7240, 'learning_rate': 4.8674e-05, 'epoch': 1.04}
+
+05/20/2024 13:25:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6794, 'learning_rate': 4.8650e-05, 'epoch': 1.05}
+
+05/20/2024 13:26:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.7440, 'learning_rate': 4.8626e-05, 'epoch': 1.06}
+
+05/20/2024 13:27:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.7383, 'learning_rate': 4.8602e-05, 'epoch': 1.07}
+
+05/20/2024 13:28:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7203, 'learning_rate': 4.8578e-05, 'epoch': 1.08}
+
+05/20/2024 13:28:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.7248, 'learning_rate': 4.8553e-05, 'epoch': 1.09}
+
+05/20/2024 13:29:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7172, 'learning_rate': 4.8529e-05, 'epoch': 1.10}
+
+05/20/2024 13:30:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6991, 'learning_rate': 4.8503e-05, 'epoch': 1.11}
+
+05/20/2024 13:31:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.7219, 'learning_rate': 4.8478e-05, 'epoch': 1.12}
+
+05/20/2024 13:32:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7027, 'learning_rate': 4.8453e-05, 'epoch': 1.13}
+
+05/20/2024 13:32:23 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-600
+
+05/20/2024 13:32:23 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-600/tokenizer_config.json
+
+05/20/2024 13:32:23 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-600/special_tokens_map.json
+
+05/20/2024 13:33:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7226, 'learning_rate': 4.8427e-05, 'epoch': 1.13}
+
+05/20/2024 13:34:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6824, 'learning_rate': 4.8401e-05, 'epoch': 1.14}
+
+05/20/2024 13:34:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6828, 'learning_rate': 4.8375e-05, 'epoch': 1.15}
+
+05/20/2024 13:35:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6913, 'learning_rate': 4.8349e-05, 'epoch': 1.16}
+
+05/20/2024 13:36:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6998, 'learning_rate': 4.8323e-05, 'epoch': 1.17}
+
+05/20/2024 13:37:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7183, 'learning_rate': 4.8296e-05, 'epoch': 1.18}
+
+05/20/2024 13:38:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.7033, 'learning_rate': 4.8269e-05, 'epoch': 1.19}
+
+05/20/2024 13:39:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6958, 'learning_rate': 4.8242e-05, 'epoch': 1.20}
+
+05/20/2024 13:39:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6814, 'learning_rate': 4.8215e-05, 'epoch': 1.21}
+
+05/20/2024 13:40:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.7338, 'learning_rate': 4.8188e-05, 'epoch': 1.22}
+
+05/20/2024 13:41:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.7255, 'learning_rate': 4.8160e-05, 'epoch': 1.23}
+
+05/20/2024 13:42:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.7258, 'learning_rate': 4.8132e-05, 'epoch': 1.24}
+
+05/20/2024 13:43:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.7125, 'learning_rate': 4.8104e-05, 'epoch': 1.25}
+
+05/20/2024 13:44:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.8042, 'learning_rate': 4.8076e-05, 'epoch': 1.26}
+
+05/20/2024 13:44:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7592, 'learning_rate': 4.8047e-05, 'epoch': 1.27}
+
+05/20/2024 13:45:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6805, 'learning_rate': 4.8019e-05, 'epoch': 1.28}
+
+05/20/2024 13:46:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7303, 'learning_rate': 4.7990e-05, 'epoch': 1.28}
+
+05/20/2024 13:47:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.7529, 'learning_rate': 4.7961e-05, 'epoch': 1.29}
+
+05/20/2024 13:48:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7269, 'learning_rate': 4.7932e-05, 'epoch': 1.30}
+
+05/20/2024 13:49:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6959, 'learning_rate': 4.7902e-05, 'epoch': 1.31}
+
+05/20/2024 13:49:00 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-700
+
+05/20/2024 13:49:00 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-700/tokenizer_config.json
+
+05/20/2024 13:49:00 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-700/special_tokens_map.json
+
+05/20/2024 13:49:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7201, 'learning_rate': 4.7872e-05, 'epoch': 1.32}
+
+05/20/2024 13:50:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7234, 'learning_rate': 4.7843e-05, 'epoch': 1.33}
+
+05/20/2024 13:51:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6720, 'learning_rate': 4.7813e-05, 'epoch': 1.34}
+
+05/20/2024 13:52:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.7145, 'learning_rate': 4.7782e-05, 'epoch': 1.35}
+
+05/20/2024 13:53:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7251, 'learning_rate': 4.7752e-05, 'epoch': 1.36}
+
+05/20/2024 13:54:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7330, 'learning_rate': 4.7721e-05, 'epoch': 1.37}
+
+05/20/2024 13:54:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.7105, 'learning_rate': 4.7690e-05, 'epoch': 1.38}
+
+05/20/2024 13:55:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.7033, 'learning_rate': 4.7659e-05, 'epoch': 1.39}
+
+05/20/2024 13:56:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7228, 'learning_rate': 4.7628e-05, 'epoch': 1.40}
+
+05/20/2024 13:57:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.7081, 'learning_rate': 4.7597e-05, 'epoch': 1.41}
+
+05/20/2024 13:58:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7029, 'learning_rate': 4.7565e-05, 'epoch': 1.42}
+
+05/20/2024 13:58:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.7565, 'learning_rate': 4.7533e-05, 'epoch': 1.43}
+
+05/20/2024 13:59:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7151, 'learning_rate': 4.7501e-05, 'epoch': 1.43}
+
+05/20/2024 14:00:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.7070, 'learning_rate': 4.7469e-05, 'epoch': 1.44}
+
+05/20/2024 14:01:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6804, 'learning_rate': 4.7437e-05, 'epoch': 1.45}
+
+05/20/2024 14:02:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.7072, 'learning_rate': 4.7404e-05, 'epoch': 1.46}
+
+05/20/2024 14:03:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.7245, 'learning_rate': 4.7371e-05, 'epoch': 1.47}
+
+05/20/2024 14:03:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7946, 'learning_rate': 4.7338e-05, 'epoch': 1.48}
+
+05/20/2024 14:04:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7140, 'learning_rate': 4.7305e-05, 'epoch': 1.49}
+
+05/20/2024 14:05:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.7585, 'learning_rate': 4.7272e-05, 'epoch': 1.50}
+
+05/20/2024 14:05:36 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-800
+
+05/20/2024 14:05:36 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-800/tokenizer_config.json
+
+05/20/2024 14:05:36 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-800/special_tokens_map.json
+
+05/20/2024 14:06:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7038, 'learning_rate': 4.7238e-05, 'epoch': 1.51}
+
+05/20/2024 14:07:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6967, 'learning_rate': 4.7204e-05, 'epoch': 1.52}
+
+05/20/2024 14:08:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6763, 'learning_rate': 4.7171e-05, 'epoch': 1.53}
+
+05/20/2024 14:08:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.7462, 'learning_rate': 4.7136e-05, 'epoch': 1.54}
+
+05/20/2024 14:09:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7155, 'learning_rate': 4.7102e-05, 'epoch': 1.55}
+
+05/20/2024 14:10:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.7312, 'learning_rate': 4.7068e-05, 'epoch': 1.56}
+
+05/20/2024 14:11:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6432, 'learning_rate': 4.7033e-05, 'epoch': 1.57}
+
+05/20/2024 14:12:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.7201, 'learning_rate': 4.6998e-05, 'epoch': 1.58}
+
+05/20/2024 14:13:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6823, 'learning_rate': 4.6963e-05, 'epoch': 1.58}
+
+05/20/2024 14:13:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.7223, 'learning_rate': 4.6928e-05, 'epoch': 1.59}
+
+05/20/2024 14:14:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7287, 'learning_rate': 4.6892e-05, 'epoch': 1.60}
+
+05/20/2024 14:15:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7260, 'learning_rate': 4.6856e-05, 'epoch': 1.61}
+
+05/20/2024 14:16:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6740, 'learning_rate': 4.6820e-05, 'epoch': 1.62}
+
+05/20/2024 14:17:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.7254, 'learning_rate': 4.6784e-05, 'epoch': 1.63}
+
+05/20/2024 14:18:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6915, 'learning_rate': 4.6748e-05, 'epoch': 1.64}
+
+05/20/2024 14:18:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6880, 'learning_rate': 4.6712e-05, 'epoch': 1.65}
+
+05/20/2024 14:19:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7411, 'learning_rate': 4.6675e-05, 'epoch': 1.66}
+
+05/20/2024 14:20:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6591, 'learning_rate': 4.6638e-05, 'epoch': 1.67}
+
+05/20/2024 14:21:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7001, 'learning_rate': 4.6601e-05, 'epoch': 1.68}
+
+05/20/2024 14:22:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7710, 'learning_rate': 4.6564e-05, 'epoch': 1.69}
+
+05/20/2024 14:22:16 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-900
+
+05/20/2024 14:22:16 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-900/tokenizer_config.json
+
+05/20/2024 14:22:16 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-900/special_tokens_map.json
+
+05/20/2024 14:23:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7421, 'learning_rate': 4.6527e-05, 'epoch': 1.70}
+
+05/20/2024 14:24:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7583, 'learning_rate': 4.6489e-05, 'epoch': 1.71}
+
+05/20/2024 14:24:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.7220, 'learning_rate': 4.6451e-05, 'epoch': 1.72}
+
+05/20/2024 14:25:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.8245, 'learning_rate': 4.6414e-05, 'epoch': 1.73}
+
+05/20/2024 14:26:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6942, 'learning_rate': 4.6375e-05, 'epoch': 1.73}
+
+05/20/2024 14:27:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7210, 'learning_rate': 4.6337e-05, 'epoch': 1.74}
+
+05/20/2024 14:28:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.7177, 'learning_rate': 4.6299e-05, 'epoch': 1.75}
+
+05/20/2024 14:29:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7531, 'learning_rate': 4.6260e-05, 'epoch': 1.76}
+
+05/20/2024 14:29:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6917, 'learning_rate': 4.6221e-05, 'epoch': 1.77}
+
+05/20/2024 14:30:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.7319, 'learning_rate': 4.6182e-05, 'epoch': 1.78}
+
+05/20/2024 14:31:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6922, 'learning_rate': 4.6143e-05, 'epoch': 1.79}
+
+05/20/2024 14:32:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7665, 'learning_rate': 4.6103e-05, 'epoch': 1.80}
+
+05/20/2024 14:33:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6927, 'learning_rate': 4.6064e-05, 'epoch': 1.81}
+
+05/20/2024 14:34:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7262, 'learning_rate': 4.6024e-05, 'epoch': 1.82}
+
+05/20/2024 14:34:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6796, 'learning_rate': 4.5984e-05, 'epoch': 1.83}
+
+05/20/2024 14:35:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6571, 'learning_rate': 4.5944e-05, 'epoch': 1.84}
+
+05/20/2024 14:36:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6866, 'learning_rate': 4.5904e-05, 'epoch': 1.85}
+
+05/20/2024 14:37:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6772, 'learning_rate': 4.5863e-05, 'epoch': 1.86}
+
+05/20/2024 14:38:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.7010, 'learning_rate': 4.5822e-05, 'epoch': 1.87}
+
+05/20/2024 14:39:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6793, 'learning_rate': 4.5782e-05, 'epoch': 1.88}
+
+05/20/2024 14:39:15 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1000
+
+05/20/2024 14:39:15 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1000/tokenizer_config.json
+
+05/20/2024 14:39:15 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1000/special_tokens_map.json
+
+05/20/2024 14:40:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6591, 'learning_rate': 4.5741e-05, 'epoch': 1.88}
+
+05/20/2024 14:40:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6804, 'learning_rate': 4.5699e-05, 'epoch': 1.89}
+
+05/20/2024 14:41:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7242, 'learning_rate': 4.5658e-05, 'epoch': 1.90}
+
+05/20/2024 14:42:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.7182, 'learning_rate': 4.5616e-05, 'epoch': 1.91}
+
+05/20/2024 14:43:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6785, 'learning_rate': 4.5575e-05, 'epoch': 1.92}
+
+05/20/2024 14:44:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6945, 'learning_rate': 4.5533e-05, 'epoch': 1.93}
+
+05/20/2024 14:44:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6915, 'learning_rate': 4.5491e-05, 'epoch': 1.94}
+
+05/20/2024 14:45:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6930, 'learning_rate': 4.5448e-05, 'epoch': 1.95}
+
+05/20/2024 14:46:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7169, 'learning_rate': 4.5406e-05, 'epoch': 1.96}
+
+05/20/2024 14:47:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6627, 'learning_rate': 4.5363e-05, 'epoch': 1.97}
+
+05/20/2024 14:48:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6860, 'learning_rate': 4.5320e-05, 'epoch': 1.98}
+
+05/20/2024 14:49:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6592, 'learning_rate': 4.5277e-05, 'epoch': 1.99}
+
+05/20/2024 14:49:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6901, 'learning_rate': 4.5234e-05, 'epoch': 2.00}
+
+05/20/2024 14:50:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6402, 'learning_rate': 4.5191e-05, 'epoch': 2.01}
+
+05/20/2024 14:51:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6452, 'learning_rate': 4.5147e-05, 'epoch': 2.02}
+
+05/20/2024 14:52:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7219, 'learning_rate': 4.5103e-05, 'epoch': 2.03}
+
+05/20/2024 14:53:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6899, 'learning_rate': 4.5060e-05, 'epoch': 2.03}
+
+05/20/2024 14:54:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.7012, 'learning_rate': 4.5016e-05, 'epoch': 2.04}
+
+05/20/2024 14:55:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.7181, 'learning_rate': 4.4971e-05, 'epoch': 2.05}
+
+05/20/2024 14:55:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6739, 'learning_rate': 4.4927e-05, 'epoch': 2.06}
+
+05/20/2024 14:55:50 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1100
+
+05/20/2024 14:55:51 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1100/tokenizer_config.json
+
+05/20/2024 14:55:51 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1100/special_tokens_map.json
+
+05/20/2024 14:56:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6353, 'learning_rate': 4.4882e-05, 'epoch': 2.07}
+
+05/20/2024 14:57:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6594, 'learning_rate': 4.4838e-05, 'epoch': 2.08}
+
+05/20/2024 14:58:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6830, 'learning_rate': 4.4793e-05, 'epoch': 2.09}
+
+05/20/2024 14:59:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6797, 'learning_rate': 4.4748e-05, 'epoch': 2.10}
+
+05/20/2024 15:00:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7014, 'learning_rate': 4.4702e-05, 'epoch': 2.11}
+
+05/20/2024 15:00:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.7053, 'learning_rate': 4.4657e-05, 'epoch': 2.12}
+
+05/20/2024 15:01:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6772, 'learning_rate': 4.4611e-05, 'epoch': 2.13}
+
+05/20/2024 15:02:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7784, 'learning_rate': 4.4565e-05, 'epoch': 2.14}
+
+05/20/2024 15:03:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6638, 'learning_rate': 4.4520e-05, 'epoch': 2.15}
+
+05/20/2024 15:04:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6670, 'learning_rate': 4.4473e-05, 'epoch': 2.16}
+
+05/20/2024 15:04:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6724, 'learning_rate': 4.4427e-05, 'epoch': 2.17}
+
+05/20/2024 15:05:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6840, 'learning_rate': 4.4381e-05, 'epoch': 2.18}
+
+05/20/2024 15:06:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6881, 'learning_rate': 4.4334e-05, 'epoch': 2.18}
+
+05/20/2024 15:07:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.7376, 'learning_rate': 4.4287e-05, 'epoch': 2.19}
+
+05/20/2024 15:08:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.7025, 'learning_rate': 4.4240e-05, 'epoch': 2.20}
+
+05/20/2024 15:09:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.7118, 'learning_rate': 4.4193e-05, 'epoch': 2.21}
+
+05/20/2024 15:10:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7032, 'learning_rate': 4.4146e-05, 'epoch': 2.22}
+
+05/20/2024 15:10:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6707, 'learning_rate': 4.4098e-05, 'epoch': 2.23}
+
+05/20/2024 15:11:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6532, 'learning_rate': 4.4051e-05, 'epoch': 2.24}
+
+05/20/2024 15:12:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6961, 'learning_rate': 4.4003e-05, 'epoch': 2.25}
+
+05/20/2024 15:12:43 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1200
+
+05/20/2024 15:12:43 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1200/tokenizer_config.json
+
+05/20/2024 15:12:43 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1200/special_tokens_map.json
+
+05/20/2024 15:13:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6831, 'learning_rate': 4.3955e-05, 'epoch': 2.26}
+
+05/20/2024 15:14:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7393, 'learning_rate': 4.3907e-05, 'epoch': 2.27}
+
+05/20/2024 15:15:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6682, 'learning_rate': 4.3859e-05, 'epoch': 2.28}
+
+05/20/2024 15:15:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6547, 'learning_rate': 4.3810e-05, 'epoch': 2.29}
+
+05/20/2024 15:16:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6914, 'learning_rate': 4.3762e-05, 'epoch': 2.30}
+
+05/20/2024 15:17:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6692, 'learning_rate': 4.3713e-05, 'epoch': 2.31}
+
+05/20/2024 15:18:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6887, 'learning_rate': 4.3664e-05, 'epoch': 2.32}
+
+05/20/2024 15:19:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6821, 'learning_rate': 4.3615e-05, 'epoch': 2.33}
+
+05/20/2024 15:20:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7119, 'learning_rate': 4.3565e-05, 'epoch': 2.33}
+
+05/20/2024 15:20:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.7096, 'learning_rate': 4.3516e-05, 'epoch': 2.34}
+
+05/20/2024 15:21:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7202, 'learning_rate': 4.3466e-05, 'epoch': 2.35}
+
+05/20/2024 15:22:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6661, 'learning_rate': 4.3417e-05, 'epoch': 2.36}
+
+05/20/2024 15:23:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6934, 'learning_rate': 4.3367e-05, 'epoch': 2.37}
+
+05/20/2024 15:24:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.7644, 'learning_rate': 4.3317e-05, 'epoch': 2.38}
+
+05/20/2024 15:25:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6789, 'learning_rate': 4.3267e-05, 'epoch': 2.39}
+
+05/20/2024 15:26:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7373, 'learning_rate': 4.3216e-05, 'epoch': 2.40}
+
+05/20/2024 15:26:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7185, 'learning_rate': 4.3166e-05, 'epoch': 2.41}
+
+05/20/2024 15:27:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6901, 'learning_rate': 4.3115e-05, 'epoch': 2.42}
+
+05/20/2024 15:28:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6417, 'learning_rate': 4.3064e-05, 'epoch': 2.43}
+
+05/20/2024 15:29:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6996, 'learning_rate': 4.3013e-05, 'epoch': 2.44}
+
+05/20/2024 15:29:09 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1300
+
+05/20/2024 15:29:09 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1300/tokenizer_config.json
+
+05/20/2024 15:29:09 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1300/special_tokens_map.json
+
+05/20/2024 15:30:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7708, 'learning_rate': 4.2962e-05, 'epoch': 2.45}
+
+05/20/2024 15:30:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7154, 'learning_rate': 4.2911e-05, 'epoch': 2.46}
+
+05/20/2024 15:31:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6731, 'learning_rate': 4.2859e-05, 'epoch': 2.47}
+
+05/20/2024 15:32:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6479, 'learning_rate': 4.2807e-05, 'epoch': 2.48}
+
+05/20/2024 15:33:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6955, 'learning_rate': 4.2756e-05, 'epoch': 2.48}
+
+05/20/2024 15:34:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6611, 'learning_rate': 4.2704e-05, 'epoch': 2.49}
+
+05/20/2024 15:35:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6699, 'learning_rate': 4.2652e-05, 'epoch': 2.50}
+
+05/20/2024 15:35:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.7127, 'learning_rate': 4.2599e-05, 'epoch': 2.51}
+
+05/20/2024 15:36:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6551, 'learning_rate': 4.2547e-05, 'epoch': 2.52}
+
+05/20/2024 15:37:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6573, 'learning_rate': 4.2494e-05, 'epoch': 2.53}
+
+05/20/2024 15:38:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.7009, 'learning_rate': 4.2442e-05, 'epoch': 2.54}
+
+05/20/2024 15:39:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.7202, 'learning_rate': 4.2389e-05, 'epoch': 2.55}
+
+05/20/2024 15:39:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6513, 'learning_rate': 4.2336e-05, 'epoch': 2.56}
+
+05/20/2024 15:40:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6476, 'learning_rate': 4.2283e-05, 'epoch': 2.57}
+
+05/20/2024 15:41:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.7096, 'learning_rate': 4.2229e-05, 'epoch': 2.58}
+
+05/20/2024 15:42:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6730, 'learning_rate': 4.2176e-05, 'epoch': 2.59}
+
+05/20/2024 15:43:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6689, 'learning_rate': 4.2122e-05, 'epoch': 2.60}
+
+05/20/2024 15:44:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6444, 'learning_rate': 4.2069e-05, 'epoch': 2.61}
+
+05/20/2024 15:45:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7307, 'learning_rate': 4.2015e-05, 'epoch': 2.62}
+
+05/20/2024 15:45:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6846, 'learning_rate': 4.1961e-05, 'epoch': 2.63}
+
+05/20/2024 15:45:52 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1400
+
+05/20/2024 15:45:52 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1400/tokenizer_config.json
+
+05/20/2024 15:45:52 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1400/special_tokens_map.json
+
+05/20/2024 15:46:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6736, 'learning_rate': 4.1906e-05, 'epoch': 2.63}
+
+05/20/2024 15:47:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6575, 'learning_rate': 4.1852e-05, 'epoch': 2.64}
+
+05/20/2024 15:48:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6382, 'learning_rate': 4.1798e-05, 'epoch': 2.65}
+
+05/20/2024 15:49:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6813, 'learning_rate': 4.1743e-05, 'epoch': 2.66}
+
+05/20/2024 15:49:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6717, 'learning_rate': 4.1688e-05, 'epoch': 2.67}
+
+05/20/2024 15:50:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7011, 'learning_rate': 4.1633e-05, 'epoch': 2.68}
+
+05/20/2024 15:51:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6971, 'learning_rate': 4.1578e-05, 'epoch': 2.69}
+
+05/20/2024 15:52:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6814, 'learning_rate': 4.1523e-05, 'epoch': 2.70}
+
+05/20/2024 15:53:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7152, 'learning_rate': 4.1467e-05, 'epoch': 2.71}
+
+05/20/2024 15:53:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6975, 'learning_rate': 4.1412e-05, 'epoch': 2.72}
+
+05/20/2024 15:54:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6625, 'learning_rate': 4.1356e-05, 'epoch': 2.73}
+
+05/20/2024 15:55:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6765, 'learning_rate': 4.1301e-05, 'epoch': 2.74}
+
+05/20/2024 15:56:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6804, 'learning_rate': 4.1245e-05, 'epoch': 2.75}
+
+05/20/2024 15:57:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6848, 'learning_rate': 4.1189e-05, 'epoch': 2.76}
+
+05/20/2024 15:57:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6623, 'learning_rate': 4.1132e-05, 'epoch': 2.77}
+
+05/20/2024 15:58:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6625, 'learning_rate': 4.1076e-05, 'epoch': 2.78}
+
+05/20/2024 15:59:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7061, 'learning_rate': 4.1019e-05, 'epoch': 2.78}
+
+05/20/2024 16:00:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6998, 'learning_rate': 4.0963e-05, 'epoch': 2.79}
+
+05/20/2024 16:01:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7145, 'learning_rate': 4.0906e-05, 'epoch': 2.80}
+
+05/20/2024 16:02:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6712, 'learning_rate': 4.0849e-05, 'epoch': 2.81}
+
+05/20/2024 16:02:14 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1500
+
+05/20/2024 16:02:14 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1500/tokenizer_config.json
+
+05/20/2024 16:02:14 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1500/special_tokens_map.json
+
+05/20/2024 16:03:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6630, 'learning_rate': 4.0792e-05, 'epoch': 2.82}
+
+05/20/2024 16:03:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6768, 'learning_rate': 4.0735e-05, 'epoch': 2.83}
+
+05/20/2024 16:04:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7298, 'learning_rate': 4.0678e-05, 'epoch': 2.84}
+
+05/20/2024 16:05:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6752, 'learning_rate': 4.0620e-05, 'epoch': 2.85}
+
+05/20/2024 16:06:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6934, 'learning_rate': 4.0563e-05, 'epoch': 2.86}
+
+05/20/2024 16:06:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6522, 'learning_rate': 4.0505e-05, 'epoch': 2.87}
+
+05/20/2024 16:07:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6842, 'learning_rate': 4.0447e-05, 'epoch': 2.88}
+
+05/20/2024 16:08:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6394, 'learning_rate': 4.0389e-05, 'epoch': 2.89}
+
+05/20/2024 16:09:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.7243, 'learning_rate': 4.0331e-05, 'epoch': 2.90}
+
+05/20/2024 16:10:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6802, 'learning_rate': 4.0273e-05, 'epoch': 2.91}
+
+05/20/2024 16:11:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6736, 'learning_rate': 4.0214e-05, 'epoch': 2.92}
+
+05/20/2024 16:11:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6980, 'learning_rate': 4.0156e-05, 'epoch': 2.93}
+
+05/20/2024 16:12:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7142, 'learning_rate': 4.0097e-05, 'epoch': 2.93}
+
+05/20/2024 16:13:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6839, 'learning_rate': 4.0038e-05, 'epoch': 2.94}
+
+05/20/2024 16:14:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7121, 'learning_rate': 3.9979e-05, 'epoch': 2.95}
+
+05/20/2024 16:15:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.7018, 'learning_rate': 3.9920e-05, 'epoch': 2.96}
+
+05/20/2024 16:16:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6554, 'learning_rate': 3.9861e-05, 'epoch': 2.97}
+
+05/20/2024 16:16:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7283, 'learning_rate': 3.9802e-05, 'epoch': 2.98}
+
+05/20/2024 16:17:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.7318, 'learning_rate': 3.9742e-05, 'epoch': 2.99}
+
+05/20/2024 16:18:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6764, 'learning_rate': 3.9683e-05, 'epoch': 3.00}
+
+05/20/2024 16:18:37 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1600
+
+05/20/2024 16:18:37 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1600/tokenizer_config.json
+
+05/20/2024 16:18:37 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1600/special_tokens_map.json
+
+05/20/2024 16:19:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7079, 'learning_rate': 3.9623e-05, 'epoch': 3.01}
+
+05/20/2024 16:20:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6727, 'learning_rate': 3.9563e-05, 'epoch': 3.02}
+
+05/20/2024 16:20:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6895, 'learning_rate': 3.9503e-05, 'epoch': 3.03}
+
+05/20/2024 16:21:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6949, 'learning_rate': 3.9443e-05, 'epoch': 3.04}
+
+05/20/2024 16:22:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6967, 'learning_rate': 3.9383e-05, 'epoch': 3.05}
+
+05/20/2024 16:23:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6413, 'learning_rate': 3.9323e-05, 'epoch': 3.06}
+
+05/20/2024 16:24:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6263, 'learning_rate': 3.9262e-05, 'epoch': 3.07}
+
+05/20/2024 16:25:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7181, 'learning_rate': 3.9202e-05, 'epoch': 3.08}
+
+05/20/2024 16:25:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6215, 'learning_rate': 3.9141e-05, 'epoch': 3.08}
+
+05/20/2024 16:26:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6840, 'learning_rate': 3.9080e-05, 'epoch': 3.09}
+
+05/20/2024 16:27:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.7229, 'learning_rate': 3.9019e-05, 'epoch': 3.10}
+
+05/20/2024 16:28:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6617, 'learning_rate': 3.8958e-05, 'epoch': 3.11}
+
+05/20/2024 16:29:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6782, 'learning_rate': 3.8897e-05, 'epoch': 3.12}
+
+05/20/2024 16:30:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6472, 'learning_rate': 3.8836e-05, 'epoch': 3.13}
+
+05/20/2024 16:30:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6142, 'learning_rate': 3.8774e-05, 'epoch': 3.14}
+
+05/20/2024 16:31:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7085, 'learning_rate': 3.8713e-05, 'epoch': 3.15}
+
+05/20/2024 16:32:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6478, 'learning_rate': 3.8651e-05, 'epoch': 3.16}
+
+05/20/2024 16:33:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6706, 'learning_rate': 3.8589e-05, 'epoch': 3.17}
+
+05/20/2024 16:34:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6352, 'learning_rate': 3.8527e-05, 'epoch': 3.18}
+
+05/20/2024 16:34:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6702, 'learning_rate': 3.8465e-05, 'epoch': 3.19}
+
+05/20/2024 16:34:46 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1700
+
+05/20/2024 16:34:46 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1700/tokenizer_config.json
+
+05/20/2024 16:34:46 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1700/special_tokens_map.json
+
+05/20/2024 16:35:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6261, 'learning_rate': 3.8403e-05, 'epoch': 3.20}
+
+05/20/2024 16:36:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6632, 'learning_rate': 3.8341e-05, 'epoch': 3.21}
+
+05/20/2024 16:37:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.7037, 'learning_rate': 3.8279e-05, 'epoch': 3.22}
+
+05/20/2024 16:37:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7237, 'learning_rate': 3.8216e-05, 'epoch': 3.23}
+
+05/20/2024 16:38:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6602, 'learning_rate': 3.8153e-05, 'epoch': 3.23}
+
+05/20/2024 16:39:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6372, 'learning_rate': 3.8091e-05, 'epoch': 3.24}
+
+05/20/2024 16:40:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6223, 'learning_rate': 3.8028e-05, 'epoch': 3.25}
+
+05/20/2024 16:41:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7263, 'learning_rate': 3.7965e-05, 'epoch': 3.26}
+
+05/20/2024 16:42:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6699, 'learning_rate': 3.7902e-05, 'epoch': 3.27}
+
+05/20/2024 16:43:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6508, 'learning_rate': 3.7839e-05, 'epoch': 3.28}
+
+05/20/2024 16:43:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6742, 'learning_rate': 3.7775e-05, 'epoch': 3.29}
+
+05/20/2024 16:44:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6297, 'learning_rate': 3.7712e-05, 'epoch': 3.30}
+
+05/20/2024 16:45:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6377, 'learning_rate': 3.7649e-05, 'epoch': 3.31}
+
+05/20/2024 16:46:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6413, 'learning_rate': 3.7585e-05, 'epoch': 3.32}
+
+05/20/2024 16:47:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6518, 'learning_rate': 3.7521e-05, 'epoch': 3.33}
+
+05/20/2024 16:48:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7138, 'learning_rate': 3.7457e-05, 'epoch': 3.34}
+
+05/20/2024 16:48:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6522, 'learning_rate': 3.7394e-05, 'epoch': 3.35}
+
+05/20/2024 16:49:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6896, 'learning_rate': 3.7329e-05, 'epoch': 3.36}
+
+05/20/2024 16:50:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.7096, 'learning_rate': 3.7265e-05, 'epoch': 3.37}
+
+05/20/2024 16:51:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6700, 'learning_rate': 3.7201e-05, 'epoch': 3.38}
+
+05/20/2024 16:51:02 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1800
+
+05/20/2024 16:51:02 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1800/tokenizer_config.json
+
+05/20/2024 16:51:02 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1800/special_tokens_map.json
+
+05/20/2024 16:51:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6730, 'learning_rate': 3.7137e-05, 'epoch': 3.38}
+
+05/20/2024 16:52:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6838, 'learning_rate': 3.7072e-05, 'epoch': 3.39}
+
+05/20/2024 16:53:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6690, 'learning_rate': 3.7008e-05, 'epoch': 3.40}
+
+05/20/2024 16:54:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7300, 'learning_rate': 3.6943e-05, 'epoch': 3.41}
+
+05/20/2024 16:55:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6608, 'learning_rate': 3.6878e-05, 'epoch': 3.42}
+
+05/20/2024 16:56:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6411, 'learning_rate': 3.6813e-05, 'epoch': 3.43}
+
+05/20/2024 16:56:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6944, 'learning_rate': 3.6748e-05, 'epoch': 3.44}
+
+05/20/2024 16:57:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6121, 'learning_rate': 3.6683e-05, 'epoch': 3.45}
+
+05/20/2024 16:58:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6409, 'learning_rate': 3.6618e-05, 'epoch': 3.46}
+
+05/20/2024 16:59:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6814, 'learning_rate': 3.6553e-05, 'epoch': 3.47}
+
+05/20/2024 17:00:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6549, 'learning_rate': 3.6487e-05, 'epoch': 3.48}
+
+05/20/2024 17:01:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6519, 'learning_rate': 3.6422e-05, 'epoch': 3.49}
+
+05/20/2024 17:02:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6247, 'learning_rate': 3.6356e-05, 'epoch': 3.50}
+
+05/20/2024 17:03:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6619, 'learning_rate': 3.6291e-05, 'epoch': 3.51}
+
+05/20/2024 17:03:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6635, 'learning_rate': 3.6225e-05, 'epoch': 3.52}
+
+05/20/2024 17:04:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6422, 'learning_rate': 3.6159e-05, 'epoch': 3.53}
+
+05/20/2024 17:05:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7166, 'learning_rate': 3.6093e-05, 'epoch': 3.53}
+
+05/20/2024 17:06:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6402, 'learning_rate': 3.6027e-05, 'epoch': 3.54}
+
+05/20/2024 17:06:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.7039, 'learning_rate': 3.5961e-05, 'epoch': 3.55}
+
+05/20/2024 17:07:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6689, 'learning_rate': 3.5894e-05, 'epoch': 3.56}
+
+05/20/2024 17:07:43 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1900
+
+05/20/2024 17:07:43 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1900/tokenizer_config.json
+
+05/20/2024 17:07:43 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-1900/special_tokens_map.json
+
+05/20/2024 17:08:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6958, 'learning_rate': 3.5828e-05, 'epoch': 3.57}
+
+05/20/2024 17:09:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6904, 'learning_rate': 3.5762e-05, 'epoch': 3.58}
+
+05/20/2024 17:10:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6554, 'learning_rate': 3.5695e-05, 'epoch': 3.59}
+
+05/20/2024 17:11:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6682, 'learning_rate': 3.5628e-05, 'epoch': 3.60}
+
+05/20/2024 17:11:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6281, 'learning_rate': 3.5562e-05, 'epoch': 3.61}
+
+05/20/2024 17:12:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.7225, 'learning_rate': 3.5495e-05, 'epoch': 3.62}
+
+05/20/2024 17:13:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.7287, 'learning_rate': 3.5428e-05, 'epoch': 3.63}
+
+05/20/2024 17:14:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6872, 'learning_rate': 3.5361e-05, 'epoch': 3.64}
+
+05/20/2024 17:15:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7054, 'learning_rate': 3.5294e-05, 'epoch': 3.65}
+
+05/20/2024 17:16:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6890, 'learning_rate': 3.5227e-05, 'epoch': 3.66}
+
+05/20/2024 17:17:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6728, 'learning_rate': 3.5159e-05, 'epoch': 3.67}
+
+05/20/2024 17:17:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6960, 'learning_rate': 3.5092e-05, 'epoch': 3.68}
+
+05/20/2024 17:18:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6586, 'learning_rate': 3.5025e-05, 'epoch': 3.68}
+
+05/20/2024 17:19:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.7780, 'learning_rate': 3.4957e-05, 'epoch': 3.69}
+
+05/20/2024 17:20:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6579, 'learning_rate': 3.4889e-05, 'epoch': 3.70}
+
+05/20/2024 17:21:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6673, 'learning_rate': 3.4822e-05, 'epoch': 3.71}
+
+05/20/2024 17:22:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6760, 'learning_rate': 3.4754e-05, 'epoch': 3.72}
+
+05/20/2024 17:22:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6575, 'learning_rate': 3.4686e-05, 'epoch': 3.73}
+
+05/20/2024 17:23:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6913, 'learning_rate': 3.4618e-05, 'epoch': 3.74}
+
+05/20/2024 17:24:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.7119, 'learning_rate': 3.4550e-05, 'epoch': 3.75}
+
+05/20/2024 17:24:30 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2000
+
+05/20/2024 17:24:30 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2000/tokenizer_config.json
+
+05/20/2024 17:24:30 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2000/special_tokens_map.json
+
+05/20/2024 17:25:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7323, 'learning_rate': 3.4482e-05, 'epoch': 3.76}
+
+05/20/2024 17:26:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6033, 'learning_rate': 3.4414e-05, 'epoch': 3.77}
+
+05/20/2024 17:27:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6359, 'learning_rate': 3.4345e-05, 'epoch': 3.78}
+
+05/20/2024 17:27:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6634, 'learning_rate': 3.4277e-05, 'epoch': 3.79}
+
+05/20/2024 17:28:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6674, 'learning_rate': 3.4209e-05, 'epoch': 3.80}
+
+05/20/2024 17:29:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6690, 'learning_rate': 3.4140e-05, 'epoch': 3.81}
+
+05/20/2024 17:30:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6965, 'learning_rate': 3.4071e-05, 'epoch': 3.82}
+
+05/20/2024 17:31:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6543, 'learning_rate': 3.4003e-05, 'epoch': 3.83}
+
+05/20/2024 17:32:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6925, 'learning_rate': 3.3934e-05, 'epoch': 3.83}
+
+05/20/2024 17:32:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6264, 'learning_rate': 3.3865e-05, 'epoch': 3.84}
+
+05/20/2024 17:33:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7041, 'learning_rate': 3.3796e-05, 'epoch': 3.85}
+
+05/20/2024 17:34:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6742, 'learning_rate': 3.3727e-05, 'epoch': 3.86}
+
+05/20/2024 17:35:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6443, 'learning_rate': 3.3658e-05, 'epoch': 3.87}
+
+05/20/2024 17:36:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6803, 'learning_rate': 3.3589e-05, 'epoch': 3.88}
+
+05/20/2024 17:37:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7290, 'learning_rate': 3.3520e-05, 'epoch': 3.89}
+
+05/20/2024 17:37:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6758, 'learning_rate': 3.3450e-05, 'epoch': 3.90}
+
+05/20/2024 17:38:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6329, 'learning_rate': 3.3381e-05, 'epoch': 3.91}
+
+05/20/2024 17:39:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6459, 'learning_rate': 3.3312e-05, 'epoch': 3.92}
+
+05/20/2024 17:40:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7014, 'learning_rate': 3.3242e-05, 'epoch': 3.93}
+
+05/20/2024 17:41:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6988, 'learning_rate': 3.3172e-05, 'epoch': 3.94}
+
+05/20/2024 17:41:17 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2100
+
+05/20/2024 17:41:17 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2100/tokenizer_config.json
+
+05/20/2024 17:41:17 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2100/special_tokens_map.json
+
+05/20/2024 17:42:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6477, 'learning_rate': 3.3103e-05, 'epoch': 3.95}
+
+05/20/2024 17:43:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6662, 'learning_rate': 3.3033e-05, 'epoch': 3.96}
+
+05/20/2024 17:43:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6508, 'learning_rate': 3.2963e-05, 'epoch': 3.97}
+
+05/20/2024 17:44:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7064, 'learning_rate': 3.2893e-05, 'epoch': 3.98}
+
+05/20/2024 17:45:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6519, 'learning_rate': 3.2823e-05, 'epoch': 3.98}
+
+05/20/2024 17:46:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6661, 'learning_rate': 3.2753e-05, 'epoch': 3.99}
+
+05/20/2024 17:47:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6618, 'learning_rate': 3.2683e-05, 'epoch': 4.00}
+
+05/20/2024 17:48:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7196, 'learning_rate': 3.2613e-05, 'epoch': 4.01}
+
+05/20/2024 17:48:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6467, 'learning_rate': 3.2543e-05, 'epoch': 4.02}
+
+05/20/2024 17:49:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6721, 'learning_rate': 3.2473e-05, 'epoch': 4.03}
+
+05/20/2024 17:50:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6598, 'learning_rate': 3.2402e-05, 'epoch': 4.04}
+
+05/20/2024 17:51:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6549, 'learning_rate': 3.2332e-05, 'epoch': 4.05}
+
+05/20/2024 17:52:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6683, 'learning_rate': 3.2262e-05, 'epoch': 4.06}
+
+05/20/2024 17:53:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6801, 'learning_rate': 3.2191e-05, 'epoch': 4.07}
+
+05/20/2024 17:53:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6638, 'learning_rate': 3.2120e-05, 'epoch': 4.08}
+
+05/20/2024 17:54:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6084, 'learning_rate': 3.2050e-05, 'epoch': 4.09}
+
+05/20/2024 17:55:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6348, 'learning_rate': 3.1979e-05, 'epoch': 4.10}
+
+05/20/2024 17:56:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6711, 'learning_rate': 3.1908e-05, 'epoch': 4.11}
+
+05/20/2024 17:57:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6611, 'learning_rate': 3.1837e-05, 'epoch': 4.12}
+
+05/20/2024 17:58:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6385, 'learning_rate': 3.1767e-05, 'epoch': 4.13}
+
+05/20/2024 17:58:06 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2200
+
+05/20/2024 17:58:06 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2200/tokenizer_config.json
+
+05/20/2024 17:58:06 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2200/special_tokens_map.json
+
+05/20/2024 17:58:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6454, 'learning_rate': 3.1696e-05, 'epoch': 4.14}
+
+05/20/2024 17:59:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6207, 'learning_rate': 3.1625e-05, 'epoch': 4.14}
+
+05/20/2024 18:00:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6493, 'learning_rate': 3.1553e-05, 'epoch': 4.15}
+
+05/20/2024 18:01:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6667, 'learning_rate': 3.1482e-05, 'epoch': 4.16}
+
+05/20/2024 18:02:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6373, 'learning_rate': 3.1411e-05, 'epoch': 4.17}
+
+05/20/2024 18:02:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6952, 'learning_rate': 3.1340e-05, 'epoch': 4.18}
+
+05/20/2024 18:03:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6677, 'learning_rate': 3.1269e-05, 'epoch': 4.19}
+
+05/20/2024 18:04:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6952, 'learning_rate': 3.1197e-05, 'epoch': 4.20}
+
+05/20/2024 18:05:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6183, 'learning_rate': 3.1126e-05, 'epoch': 4.21}
+
+05/20/2024 18:06:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7075, 'learning_rate': 3.1054e-05, 'epoch': 4.22}
+
+05/20/2024 18:07:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6404, 'learning_rate': 3.0983e-05, 'epoch': 4.23}
+
+05/20/2024 18:08:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6347, 'learning_rate': 3.0911e-05, 'epoch': 4.24}
+
+05/20/2024 18:08:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6631, 'learning_rate': 3.0840e-05, 'epoch': 4.25}
+
+05/20/2024 18:09:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.7209, 'learning_rate': 3.0768e-05, 'epoch': 4.26}
+
+05/20/2024 18:10:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6520, 'learning_rate': 3.0696e-05, 'epoch': 4.27}
+
+05/20/2024 18:11:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6558, 'learning_rate': 3.0625e-05, 'epoch': 4.28}
+
+05/20/2024 18:12:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6557, 'learning_rate': 3.0553e-05, 'epoch': 4.29}
+
+05/20/2024 18:13:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6767, 'learning_rate': 3.0481e-05, 'epoch': 4.29}
+
+05/20/2024 18:13:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6316, 'learning_rate': 3.0409e-05, 'epoch': 4.30}
+
+05/20/2024 18:14:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6416, 'learning_rate': 3.0337e-05, 'epoch': 4.31}
+
+05/20/2024 18:14:39 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2300
+
+05/20/2024 18:14:39 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2300/tokenizer_config.json
+
+05/20/2024 18:14:39 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2300/special_tokens_map.json
+
+05/20/2024 18:15:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6132, 'learning_rate': 3.0265e-05, 'epoch': 4.32}
+
+05/20/2024 18:16:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6551, 'learning_rate': 3.0193e-05, 'epoch': 4.33}
+
+05/20/2024 18:17:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6691, 'learning_rate': 3.0121e-05, 'epoch': 4.34}
+
+05/20/2024 18:17:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6147, 'learning_rate': 3.0049e-05, 'epoch': 4.35}
+
+05/20/2024 18:18:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6393, 'learning_rate': 2.9977e-05, 'epoch': 4.36}
+
+05/20/2024 18:19:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6229, 'learning_rate': 2.9904e-05, 'epoch': 4.37}
+
+05/20/2024 18:20:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6413, 'learning_rate': 2.9832e-05, 'epoch': 4.38}
+
+05/20/2024 18:21:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6249, 'learning_rate': 2.9760e-05, 'epoch': 4.39}
+
+05/20/2024 18:22:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6721, 'learning_rate': 2.9687e-05, 'epoch': 4.40}
+
+05/20/2024 18:23:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6473, 'learning_rate': 2.9615e-05, 'epoch': 4.41}
+
+05/20/2024 18:23:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7117, 'learning_rate': 2.9543e-05, 'epoch': 4.42}
+
+05/20/2024 18:24:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6480, 'learning_rate': 2.9470e-05, 'epoch': 4.43}
+
+05/20/2024 18:25:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6945, 'learning_rate': 2.9398e-05, 'epoch': 4.44}
+
+05/20/2024 18:26:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6114, 'learning_rate': 2.9325e-05, 'epoch': 4.44}
+
+05/20/2024 18:27:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6605, 'learning_rate': 2.9252e-05, 'epoch': 4.45}
+
+05/20/2024 18:27:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6604, 'learning_rate': 2.9180e-05, 'epoch': 4.46}
+
+05/20/2024 18:28:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6448, 'learning_rate': 2.9107e-05, 'epoch': 4.47}
+
+05/20/2024 18:29:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6460, 'learning_rate': 2.9035e-05, 'epoch': 4.48}
+
+05/20/2024 18:30:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6882, 'learning_rate': 2.8962e-05, 'epoch': 4.49}
+
+05/20/2024 18:31:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6419, 'learning_rate': 2.8889e-05, 'epoch': 4.50}
+
+05/20/2024 18:31:25 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2400
+
+05/20/2024 18:31:25 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2400/tokenizer_config.json
+
+05/20/2024 18:31:25 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2400/special_tokens_map.json
+
+05/20/2024 18:32:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6161, 'learning_rate': 2.8816e-05, 'epoch': 4.51}
+
+05/20/2024 18:33:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7675, 'learning_rate': 2.8743e-05, 'epoch': 4.52}
+
+05/20/2024 18:33:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6339, 'learning_rate': 2.8671e-05, 'epoch': 4.53}
+
+05/20/2024 18:34:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6305, 'learning_rate': 2.8598e-05, 'epoch': 4.54}
+
+05/20/2024 18:35:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6572, 'learning_rate': 2.8525e-05, 'epoch': 4.55}
+
+05/20/2024 18:36:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6657, 'learning_rate': 2.8452e-05, 'epoch': 4.56}
+
+05/20/2024 18:37:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7297, 'learning_rate': 2.8379e-05, 'epoch': 4.57}
+
+05/20/2024 18:37:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6570, 'learning_rate': 2.8306e-05, 'epoch': 4.58}
+
+05/20/2024 18:38:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6588, 'learning_rate': 2.8233e-05, 'epoch': 4.59}
+
+05/20/2024 18:39:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7057, 'learning_rate': 2.8160e-05, 'epoch': 4.59}
+
+05/20/2024 18:40:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6867, 'learning_rate': 2.8087e-05, 'epoch': 4.60}
+
+05/20/2024 18:41:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6258, 'learning_rate': 2.8013e-05, 'epoch': 4.61}
+
+05/20/2024 18:42:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6465, 'learning_rate': 2.7940e-05, 'epoch': 4.62}
+
+05/20/2024 18:42:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.7121, 'learning_rate': 2.7867e-05, 'epoch': 4.63}
+
+05/20/2024 18:43:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6619, 'learning_rate': 2.7794e-05, 'epoch': 4.64}
+
+05/20/2024 18:44:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6751, 'learning_rate': 2.7721e-05, 'epoch': 4.65}
+
+05/20/2024 18:45:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6622, 'learning_rate': 2.7647e-05, 'epoch': 4.66}
+
+05/20/2024 18:46:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6729, 'learning_rate': 2.7574e-05, 'epoch': 4.67}
+
+05/20/2024 18:47:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6535, 'learning_rate': 2.7501e-05, 'epoch': 4.68}
+
+05/20/2024 18:48:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6974, 'learning_rate': 2.7428e-05, 'epoch': 4.69}
+
+05/20/2024 18:48:01 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2500
+
+05/20/2024 18:48:01 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2500/tokenizer_config.json
+
+05/20/2024 18:48:01 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2500/special_tokens_map.json
+
+05/20/2024 18:48:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6550, 'learning_rate': 2.7354e-05, 'epoch': 4.70}
+
+05/20/2024 18:49:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7232, 'learning_rate': 2.7281e-05, 'epoch': 4.71}
+
+05/20/2024 18:50:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6246, 'learning_rate': 2.7207e-05, 'epoch': 4.72}
+
+05/20/2024 18:51:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6886, 'learning_rate': 2.7134e-05, 'epoch': 4.73}
+
+05/20/2024 18:52:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6239, 'learning_rate': 2.7061e-05, 'epoch': 4.74}
+
+05/20/2024 18:52:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6553, 'learning_rate': 2.6987e-05, 'epoch': 4.74}
+
+05/20/2024 18:53:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6534, 'learning_rate': 2.6914e-05, 'epoch': 4.75}
+
+05/20/2024 18:54:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6224, 'learning_rate': 2.6840e-05, 'epoch': 4.76}
+
+05/20/2024 18:55:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.7181, 'learning_rate': 2.6767e-05, 'epoch': 4.77}
+
+05/20/2024 18:56:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6450, 'learning_rate': 2.6693e-05, 'epoch': 4.78}
+
+05/20/2024 18:57:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6806, 'learning_rate': 2.6620e-05, 'epoch': 4.79}
+
+05/20/2024 18:58:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6925, 'learning_rate': 2.6546e-05, 'epoch': 4.80}
+
+05/20/2024 18:58:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6294, 'learning_rate': 2.6473e-05, 'epoch': 4.81}
+
+05/20/2024 18:59:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6454, 'learning_rate': 2.6399e-05, 'epoch': 4.82}
+
+05/20/2024 19:00:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6852, 'learning_rate': 2.6326e-05, 'epoch': 4.83}
+
+05/20/2024 19:01:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6618, 'learning_rate': 2.6252e-05, 'epoch': 4.84}
+
+05/20/2024 19:02:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5952, 'learning_rate': 2.6178e-05, 'epoch': 4.85}
+
+05/20/2024 19:03:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6192, 'learning_rate': 2.6105e-05, 'epoch': 4.86}
+
+05/20/2024 19:03:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6552, 'learning_rate': 2.6031e-05, 'epoch': 4.87}
+
+05/20/2024 19:04:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6551, 'learning_rate': 2.5958e-05, 'epoch': 4.88}
+
+05/20/2024 19:04:45 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2600
+
+05/20/2024 19:04:45 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2600/tokenizer_config.json
+
+05/20/2024 19:04:45 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2600/special_tokens_map.json
+
+05/20/2024 19:05:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.7238, 'learning_rate': 2.5884e-05, 'epoch': 4.89}
+
+05/20/2024 19:06:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6509, 'learning_rate': 2.5810e-05, 'epoch': 4.89}
+
+05/20/2024 19:07:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6719, 'learning_rate': 2.5737e-05, 'epoch': 4.90}
+
+05/20/2024 19:08:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6197, 'learning_rate': 2.5663e-05, 'epoch': 4.91}
+
+05/20/2024 19:08:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6143, 'learning_rate': 2.5589e-05, 'epoch': 4.92}
+
+05/20/2024 19:09:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6730, 'learning_rate': 2.5516e-05, 'epoch': 4.93}
+
+05/20/2024 19:10:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6730, 'learning_rate': 2.5442e-05, 'epoch': 4.94}
+
+05/20/2024 19:11:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6606, 'learning_rate': 2.5368e-05, 'epoch': 4.95}
+
+05/20/2024 19:12:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6286, 'learning_rate': 2.5295e-05, 'epoch': 4.96}
+
+05/20/2024 19:13:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6334, 'learning_rate': 2.5221e-05, 'epoch': 4.97}
+
+05/20/2024 19:14:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7033, 'learning_rate': 2.5147e-05, 'epoch': 4.98}
+
+05/20/2024 19:14:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6652, 'learning_rate': 2.5074e-05, 'epoch': 4.99}
+
+05/20/2024 19:15:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6556, 'learning_rate': 2.5000e-05, 'epoch': 5.00}
+
+05/20/2024 19:16:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6150, 'learning_rate': 2.4926e-05, 'epoch': 5.01}
+
+05/20/2024 19:17:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6467, 'learning_rate': 2.4853e-05, 'epoch': 5.02}
+
+05/20/2024 19:18:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6490, 'learning_rate': 2.4779e-05, 'epoch': 5.03}
+
+05/20/2024 19:19:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6481, 'learning_rate': 2.4705e-05, 'epoch': 5.04}
+
+05/20/2024 19:19:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6379, 'learning_rate': 2.4632e-05, 'epoch': 5.04}
+
+05/20/2024 19:20:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6095, 'learning_rate': 2.4558e-05, 'epoch': 5.05}
+
+05/20/2024 19:21:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6294, 'learning_rate': 2.4484e-05, 'epoch': 5.06}
+
+05/20/2024 19:21:34 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2700
+
+05/20/2024 19:21:34 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2700/tokenizer_config.json
+
+05/20/2024 19:21:34 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2700/special_tokens_map.json
+
+05/20/2024 19:22:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6822, 'learning_rate': 2.4411e-05, 'epoch': 5.07}
+
+05/20/2024 19:23:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6328, 'learning_rate': 2.4337e-05, 'epoch': 5.08}
+
+05/20/2024 19:24:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6364, 'learning_rate': 2.4263e-05, 'epoch': 5.09}
+
+05/20/2024 19:24:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6233, 'learning_rate': 2.4190e-05, 'epoch': 5.10}
+
+05/20/2024 19:25:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6455, 'learning_rate': 2.4116e-05, 'epoch': 5.11}
+
+05/20/2024 19:26:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6207, 'learning_rate': 2.4042e-05, 'epoch': 5.12}
+
+05/20/2024 19:27:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6419, 'learning_rate': 2.3969e-05, 'epoch': 5.13}
+
+05/20/2024 19:28:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6588, 'learning_rate': 2.3895e-05, 'epoch': 5.14}
+
+05/20/2024 19:29:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.7394, 'learning_rate': 2.3822e-05, 'epoch': 5.15}
+
+05/20/2024 19:30:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6299, 'learning_rate': 2.3748e-05, 'epoch': 5.16}
+
+05/20/2024 19:30:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6370, 'learning_rate': 2.3674e-05, 'epoch': 5.17}
+
+05/20/2024 19:31:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6706, 'learning_rate': 2.3601e-05, 'epoch': 5.18}
+
+05/20/2024 19:32:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6283, 'learning_rate': 2.3527e-05, 'epoch': 5.19}
+
+05/20/2024 19:33:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6980, 'learning_rate': 2.3454e-05, 'epoch': 5.19}
+
+05/20/2024 19:34:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6816, 'learning_rate': 2.3380e-05, 'epoch': 5.20}
+
+05/20/2024 19:34:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6177, 'learning_rate': 2.3307e-05, 'epoch': 5.21}
+
+05/20/2024 19:35:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6357, 'learning_rate': 2.3233e-05, 'epoch': 5.22}
+
+05/20/2024 19:36:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6506, 'learning_rate': 2.3160e-05, 'epoch': 5.23}
+
+05/20/2024 19:37:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6338, 'learning_rate': 2.3086e-05, 'epoch': 5.24}
+
+05/20/2024 19:38:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6159, 'learning_rate': 2.3013e-05, 'epoch': 5.25}
+
+05/20/2024 19:38:16 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2800
+
+05/20/2024 19:38:16 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2800/tokenizer_config.json
+
+05/20/2024 19:38:16 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2800/special_tokens_map.json
+
+05/20/2024 19:39:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6624, 'learning_rate': 2.2939e-05, 'epoch': 5.26}
+
+05/20/2024 19:39:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6300, 'learning_rate': 2.2866e-05, 'epoch': 5.27}
+
+05/20/2024 19:40:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6864, 'learning_rate': 2.2793e-05, 'epoch': 5.28}
+
+05/20/2024 19:41:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6477, 'learning_rate': 2.2719e-05, 'epoch': 5.29}
+
+05/20/2024 19:42:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6205, 'learning_rate': 2.2646e-05, 'epoch': 5.30}
+
+05/20/2024 19:43:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6041, 'learning_rate': 2.2572e-05, 'epoch': 5.31}
+
+05/20/2024 19:44:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6521, 'learning_rate': 2.2499e-05, 'epoch': 5.32}
+
+05/20/2024 19:44:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6286, 'learning_rate': 2.2426e-05, 'epoch': 5.33}
+
+05/20/2024 19:45:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6239, 'learning_rate': 2.2353e-05, 'epoch': 5.34}
+
+05/20/2024 19:46:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6672, 'learning_rate': 2.2279e-05, 'epoch': 5.34}
+
+05/20/2024 19:47:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6627, 'learning_rate': 2.2206e-05, 'epoch': 5.35}
+
+05/20/2024 19:48:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6792, 'learning_rate': 2.2133e-05, 'epoch': 5.36}
+
+05/20/2024 19:49:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6213, 'learning_rate': 2.2060e-05, 'epoch': 5.37}
+
+05/20/2024 19:49:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6724, 'learning_rate': 2.1987e-05, 'epoch': 5.38}
+
+05/20/2024 19:50:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6551, 'learning_rate': 2.1913e-05, 'epoch': 5.39}
+
+05/20/2024 19:51:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6146, 'learning_rate': 2.1840e-05, 'epoch': 5.40}
+
+05/20/2024 19:52:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.7058, 'learning_rate': 2.1767e-05, 'epoch': 5.41}
+
+05/20/2024 19:53:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.7229, 'learning_rate': 2.1694e-05, 'epoch': 5.42}
+
+05/20/2024 19:54:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6209, 'learning_rate': 2.1621e-05, 'epoch': 5.43}
+
+05/20/2024 19:54:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6380, 'learning_rate': 2.1548e-05, 'epoch': 5.44}
+
+05/20/2024 19:54:51 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2900
+
+05/20/2024 19:54:51 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2900/tokenizer_config.json
+
+05/20/2024 19:54:51 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-2900/special_tokens_map.json
+
+05/20/2024 19:55:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6069, 'learning_rate': 2.1475e-05, 'epoch': 5.45}
+
+05/20/2024 19:56:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6218, 'learning_rate': 2.1402e-05, 'epoch': 5.46}
+
+05/20/2024 19:57:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6457, 'learning_rate': 2.1329e-05, 'epoch': 5.47}
+
+05/20/2024 19:58:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6438, 'learning_rate': 2.1257e-05, 'epoch': 5.48}
+
+05/20/2024 19:58:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6715, 'learning_rate': 2.1184e-05, 'epoch': 5.49}
+
+05/20/2024 19:59:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6063, 'learning_rate': 2.1111e-05, 'epoch': 5.49}
+
+05/20/2024 20:00:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6429, 'learning_rate': 2.1038e-05, 'epoch': 5.50}
+
+05/20/2024 20:01:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6404, 'learning_rate': 2.0965e-05, 'epoch': 5.51}
+
+05/20/2024 20:02:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6980, 'learning_rate': 2.0893e-05, 'epoch': 5.52}
+
+05/20/2024 20:03:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6514, 'learning_rate': 2.0820e-05, 'epoch': 5.53}
+
+05/20/2024 20:04:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6635, 'learning_rate': 2.0748e-05, 'epoch': 5.54}
+
+05/20/2024 20:04:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6492, 'learning_rate': 2.0675e-05, 'epoch': 5.55}
+
+05/20/2024 20:05:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6491, 'learning_rate': 2.0602e-05, 'epoch': 5.56}
+
+05/20/2024 20:06:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6171, 'learning_rate': 2.0530e-05, 'epoch': 5.57}
+
+05/20/2024 20:07:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6464, 'learning_rate': 2.0457e-05, 'epoch': 5.58}
+
+05/20/2024 20:08:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6901, 'learning_rate': 2.0385e-05, 'epoch': 5.59}
+
+05/20/2024 20:09:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6646, 'learning_rate': 2.0313e-05, 'epoch': 5.60}
+
+05/20/2024 20:09:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6571, 'learning_rate': 2.0240e-05, 'epoch': 5.61}
+
+05/20/2024 20:10:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6768, 'learning_rate': 2.0168e-05, 'epoch': 5.62}
+
+05/20/2024 20:11:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.5996, 'learning_rate': 2.0096e-05, 'epoch': 5.63}
+
+05/20/2024 20:11:36 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3000
+
+05/20/2024 20:11:36 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3000/tokenizer_config.json
+
+05/20/2024 20:11:36 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3000/special_tokens_map.json
+
+05/20/2024 20:12:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7040, 'learning_rate': 2.0023e-05, 'epoch': 5.64}
+
+05/20/2024 20:13:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6471, 'learning_rate': 1.9951e-05, 'epoch': 5.64}
+
+05/20/2024 20:14:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6432, 'learning_rate': 1.9879e-05, 'epoch': 5.65}
+
+05/20/2024 20:14:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6593, 'learning_rate': 1.9807e-05, 'epoch': 5.66}
+
+05/20/2024 20:15:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6298, 'learning_rate': 1.9735e-05, 'epoch': 5.67}
+
+05/20/2024 20:16:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6473, 'learning_rate': 1.9663e-05, 'epoch': 5.68}
+
+05/20/2024 20:17:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6091, 'learning_rate': 1.9591e-05, 'epoch': 5.69}
+
+05/20/2024 20:18:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6992, 'learning_rate': 1.9519e-05, 'epoch': 5.70}
+
+05/20/2024 20:19:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6190, 'learning_rate': 1.9447e-05, 'epoch': 5.71}
+
+05/20/2024 20:19:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6249, 'learning_rate': 1.9375e-05, 'epoch': 5.72}
+
+05/20/2024 20:20:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6192, 'learning_rate': 1.9304e-05, 'epoch': 5.73}
+
+05/20/2024 20:21:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6596, 'learning_rate': 1.9232e-05, 'epoch': 5.74}
+
+05/20/2024 20:22:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6903, 'learning_rate': 1.9160e-05, 'epoch': 5.75}
+
+05/20/2024 20:23:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6790, 'learning_rate': 1.9089e-05, 'epoch': 5.76}
+
+05/20/2024 20:24:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6517, 'learning_rate': 1.9017e-05, 'epoch': 5.77}
+
+05/20/2024 20:25:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6403, 'learning_rate': 1.8946e-05, 'epoch': 5.78}
+
+05/20/2024 20:25:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6380, 'learning_rate': 1.8874e-05, 'epoch': 5.79}
+
+05/20/2024 20:26:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6006, 'learning_rate': 1.8803e-05, 'epoch': 5.79}
+
+05/20/2024 20:27:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6913, 'learning_rate': 1.8731e-05, 'epoch': 5.80}
+
+05/20/2024 20:28:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6553, 'learning_rate': 1.8660e-05, 'epoch': 5.81}
+
+05/20/2024 20:28:26 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3100
+
+05/20/2024 20:28:26 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3100/tokenizer_config.json
+
+05/20/2024 20:28:26 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3100/special_tokens_map.json
+
+05/20/2024 20:29:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6955, 'learning_rate': 1.8589e-05, 'epoch': 5.82}
+
+05/20/2024 20:30:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6015, 'learning_rate': 1.8518e-05, 'epoch': 5.83}
+
+05/20/2024 20:30:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6500, 'learning_rate': 1.8447e-05, 'epoch': 5.84}
+
+05/20/2024 20:31:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6588, 'learning_rate': 1.8375e-05, 'epoch': 5.85}
+
+05/20/2024 20:32:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6569, 'learning_rate': 1.8304e-05, 'epoch': 5.86}
+
+05/20/2024 20:33:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6428, 'learning_rate': 1.8233e-05, 'epoch': 5.87}
+
+05/20/2024 20:34:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6301, 'learning_rate': 1.8163e-05, 'epoch': 5.88}
+
+05/20/2024 20:35:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6084, 'learning_rate': 1.8092e-05, 'epoch': 5.89}
+
+05/20/2024 20:36:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6192, 'learning_rate': 1.8021e-05, 'epoch': 5.90}
+
+05/20/2024 20:37:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6803, 'learning_rate': 1.7950e-05, 'epoch': 5.91}
+
+05/20/2024 20:37:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6554, 'learning_rate': 1.7880e-05, 'epoch': 5.92}
+
+05/20/2024 20:38:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6399, 'learning_rate': 1.7809e-05, 'epoch': 5.93}
+
+05/20/2024 20:39:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6213, 'learning_rate': 1.7738e-05, 'epoch': 5.94}
+
+05/20/2024 20:40:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.7025, 'learning_rate': 1.7668e-05, 'epoch': 5.94}
+
+05/20/2024 20:41:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6791, 'learning_rate': 1.7598e-05, 'epoch': 5.95}
+
+05/20/2024 20:42:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6635, 'learning_rate': 1.7527e-05, 'epoch': 5.96}
+
+05/20/2024 20:42:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6618, 'learning_rate': 1.7457e-05, 'epoch': 5.97}
+
+05/20/2024 20:43:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7120, 'learning_rate': 1.7387e-05, 'epoch': 5.98}
+
+05/20/2024 20:44:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6635, 'learning_rate': 1.7317e-05, 'epoch': 5.99}
+
+05/20/2024 20:45:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6311, 'learning_rate': 1.7247e-05, 'epoch': 6.00}
+
+05/20/2024 20:45:27 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3200
+
+05/20/2024 20:45:27 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3200/tokenizer_config.json
+
+05/20/2024 20:45:27 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3200/special_tokens_map.json
+
+05/20/2024 20:46:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6177, 'learning_rate': 1.7177e-05, 'epoch': 6.01}
+
+05/20/2024 20:47:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6234, 'learning_rate': 1.7107e-05, 'epoch': 6.02}
+
+05/20/2024 20:48:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6544, 'learning_rate': 1.7037e-05, 'epoch': 6.03}
+
+05/20/2024 20:49:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6936, 'learning_rate': 1.6967e-05, 'epoch': 6.04}
+
+05/20/2024 20:49:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6422, 'learning_rate': 1.6897e-05, 'epoch': 6.05}
+
+05/20/2024 20:50:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6795, 'learning_rate': 1.6828e-05, 'epoch': 6.06}
+
+05/20/2024 20:51:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6351, 'learning_rate': 1.6758e-05, 'epoch': 6.07}
+
+05/20/2024 20:52:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.5902, 'learning_rate': 1.6688e-05, 'epoch': 6.08}
+
+05/20/2024 20:53:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6478, 'learning_rate': 1.6619e-05, 'epoch': 6.09}
+
+05/20/2024 20:54:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6855, 'learning_rate': 1.6550e-05, 'epoch': 6.09}
+
+05/20/2024 20:54:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6555, 'learning_rate': 1.6480e-05, 'epoch': 6.10}
+
+05/20/2024 20:55:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6286, 'learning_rate': 1.6411e-05, 'epoch': 6.11}
+
+05/20/2024 20:56:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6900, 'learning_rate': 1.6342e-05, 'epoch': 6.12}
+
+05/20/2024 20:57:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6568, 'learning_rate': 1.6273e-05, 'epoch': 6.13}
+
+05/20/2024 20:58:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6583, 'learning_rate': 1.6204e-05, 'epoch': 6.14}
+
+05/20/2024 20:59:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6312, 'learning_rate': 1.6135e-05, 'epoch': 6.15}
+
+05/20/2024 20:59:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6252, 'learning_rate': 1.6066e-05, 'epoch': 6.16}
+
+05/20/2024 21:00:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6645, 'learning_rate': 1.5997e-05, 'epoch': 6.17}
+
+05/20/2024 21:01:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6523, 'learning_rate': 1.5929e-05, 'epoch': 6.18}
+
+05/20/2024 21:02:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6411, 'learning_rate': 1.5860e-05, 'epoch': 6.19}
+
+05/20/2024 21:02:22 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3300
+
+05/20/2024 21:02:22 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3300/tokenizer_config.json
+
+05/20/2024 21:02:22 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3300/special_tokens_map.json
+
+05/20/2024 21:03:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6789, 'learning_rate': 1.5791e-05, 'epoch': 6.20}
+
+05/20/2024 21:04:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6103, 'learning_rate': 1.5723e-05, 'epoch': 6.21}
+
+05/20/2024 21:04:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6843, 'learning_rate': 1.5655e-05, 'epoch': 6.22}
+
+05/20/2024 21:05:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6245, 'learning_rate': 1.5586e-05, 'epoch': 6.23}
+
+05/20/2024 21:06:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.5952, 'learning_rate': 1.5518e-05, 'epoch': 6.24}
+
+05/20/2024 21:07:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6218, 'learning_rate': 1.5450e-05, 'epoch': 6.24}
+
+05/20/2024 21:08:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7075, 'learning_rate': 1.5382e-05, 'epoch': 6.25}
+
+05/20/2024 21:09:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6521, 'learning_rate': 1.5314e-05, 'epoch': 6.26}
+
+05/20/2024 21:09:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6051, 'learning_rate': 1.5246e-05, 'epoch': 6.27}
+
+05/20/2024 21:10:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6262, 'learning_rate': 1.5178e-05, 'epoch': 6.28}
+
+05/20/2024 21:11:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6280, 'learning_rate': 1.5111e-05, 'epoch': 6.29}
+
+05/20/2024 21:12:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6191, 'learning_rate': 1.5043e-05, 'epoch': 6.30}
+
+05/20/2024 21:13:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6718, 'learning_rate': 1.4975e-05, 'epoch': 6.31}
+
+05/20/2024 21:14:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6838, 'learning_rate': 1.4908e-05, 'epoch': 6.32}
+
+05/20/2024 21:14:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6229, 'learning_rate': 1.4841e-05, 'epoch': 6.33}
+
+05/20/2024 21:15:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6131, 'learning_rate': 1.4773e-05, 'epoch': 6.34}
+
+05/20/2024 21:16:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6104, 'learning_rate': 1.4706e-05, 'epoch': 6.35}
+
+05/20/2024 21:17:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6644, 'learning_rate': 1.4639e-05, 'epoch': 6.36}
+
+05/20/2024 21:18:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6754, 'learning_rate': 1.4572e-05, 'epoch': 6.37}
+
+05/20/2024 21:19:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6394, 'learning_rate': 1.4505e-05, 'epoch': 6.38}
+
+05/20/2024 21:19:14 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3400
+
+05/20/2024 21:19:14 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3400/tokenizer_config.json
+
+05/20/2024 21:19:14 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3400/special_tokens_map.json
+
+05/20/2024 21:20:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6443, 'learning_rate': 1.4438e-05, 'epoch': 6.39}
+
+05/20/2024 21:21:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6257, 'learning_rate': 1.4372e-05, 'epoch': 6.39}
+
+05/20/2024 21:21:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6347, 'learning_rate': 1.4305e-05, 'epoch': 6.40}
+
+05/20/2024 21:22:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6371, 'learning_rate': 1.4238e-05, 'epoch': 6.41}
+
+05/20/2024 21:23:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6239, 'learning_rate': 1.4172e-05, 'epoch': 6.42}
+
+05/20/2024 21:24:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6641, 'learning_rate': 1.4106e-05, 'epoch': 6.43}
+
+05/20/2024 21:25:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6277, 'learning_rate': 1.4039e-05, 'epoch': 6.44}
+
+05/20/2024 21:26:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6517, 'learning_rate': 1.3973e-05, 'epoch': 6.45}
+
+05/20/2024 21:27:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6646, 'learning_rate': 1.3907e-05, 'epoch': 6.46}
+
+05/20/2024 21:27:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6798, 'learning_rate': 1.3841e-05, 'epoch': 6.47}
+
+05/20/2024 21:28:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6456, 'learning_rate': 1.3775e-05, 'epoch': 6.48}
+
+05/20/2024 21:29:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6504, 'learning_rate': 1.3709e-05, 'epoch': 6.49}
+
+05/20/2024 21:30:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5981, 'learning_rate': 1.3644e-05, 'epoch': 6.50}
+
+05/20/2024 21:31:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6268, 'learning_rate': 1.3578e-05, 'epoch': 6.51}
+
+05/20/2024 21:32:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6122, 'learning_rate': 1.3513e-05, 'epoch': 6.52}
+
+05/20/2024 21:32:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6297, 'learning_rate': 1.3447e-05, 'epoch': 6.53}
+
+05/20/2024 21:33:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6511, 'learning_rate': 1.3382e-05, 'epoch': 6.54}
+
+05/20/2024 21:34:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6413, 'learning_rate': 1.3317e-05, 'epoch': 6.54}
+
+05/20/2024 21:35:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6484, 'learning_rate': 1.3252e-05, 'epoch': 6.55}
+
+05/20/2024 21:36:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6383, 'learning_rate': 1.3187e-05, 'epoch': 6.56}
+
+05/20/2024 21:36:14 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3500
+
+05/20/2024 21:36:14 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3500/tokenizer_config.json
+
+05/20/2024 21:36:14 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3500/special_tokens_map.json
+
+05/20/2024 21:37:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6533, 'learning_rate': 1.3122e-05, 'epoch': 6.57}
+
+05/20/2024 21:37:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6404, 'learning_rate': 1.3057e-05, 'epoch': 6.58}
+
+05/20/2024 21:38:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6308, 'learning_rate': 1.2992e-05, 'epoch': 6.59}
+
+05/20/2024 21:39:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6452, 'learning_rate': 1.2928e-05, 'epoch': 6.60}
+
+05/20/2024 21:40:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6384, 'learning_rate': 1.2863e-05, 'epoch': 6.61}
+
+05/20/2024 21:41:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6986, 'learning_rate': 1.2799e-05, 'epoch': 6.62}
+
+05/20/2024 21:42:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6245, 'learning_rate': 1.2735e-05, 'epoch': 6.63}
+
+05/20/2024 21:42:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6334, 'learning_rate': 1.2671e-05, 'epoch': 6.64}
+
+05/20/2024 21:43:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6416, 'learning_rate': 1.2606e-05, 'epoch': 6.65}
+
+05/20/2024 21:44:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6249, 'learning_rate': 1.2543e-05, 'epoch': 6.66}
+
+05/20/2024 21:45:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6717, 'learning_rate': 1.2479e-05, 'epoch': 6.67}
+
+05/20/2024 21:46:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6619, 'learning_rate': 1.2415e-05, 'epoch': 6.68}
+
+05/20/2024 21:47:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6664, 'learning_rate': 1.2351e-05, 'epoch': 6.69}
+
+05/20/2024 21:48:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6100, 'learning_rate': 1.2288e-05, 'epoch': 6.69}
+
+05/20/2024 21:48:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6729, 'learning_rate': 1.2225e-05, 'epoch': 6.70}
+
+05/20/2024 21:49:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6270, 'learning_rate': 1.2161e-05, 'epoch': 6.71}
+
+05/20/2024 21:50:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6144, 'learning_rate': 1.2098e-05, 'epoch': 6.72}
+
+05/20/2024 21:51:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6348, 'learning_rate': 1.2035e-05, 'epoch': 6.73}
+
+05/20/2024 21:52:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6171, 'learning_rate': 1.1972e-05, 'epoch': 6.74}
+
+05/20/2024 21:52:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6406, 'learning_rate': 1.1909e-05, 'epoch': 6.75}
+
+05/20/2024 21:52:58 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3600
+
+05/20/2024 21:52:58 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3600/tokenizer_config.json
+
+05/20/2024 21:52:58 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3600/special_tokens_map.json
+
+05/20/2024 21:53:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7222, 'learning_rate': 1.1847e-05, 'epoch': 6.76}
+
+05/20/2024 21:54:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6395, 'learning_rate': 1.1784e-05, 'epoch': 6.77}
+
+05/20/2024 21:55:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6499, 'learning_rate': 1.1721e-05, 'epoch': 6.78}
+
+05/20/2024 21:56:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6176, 'learning_rate': 1.1659e-05, 'epoch': 6.79}
+
+05/20/2024 21:57:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6068, 'learning_rate': 1.1597e-05, 'epoch': 6.80}
+
+05/20/2024 21:57:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6861, 'learning_rate': 1.1535e-05, 'epoch': 6.81}
+
+05/20/2024 21:58:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6419, 'learning_rate': 1.1473e-05, 'epoch': 6.82}
+
+05/20/2024 21:59:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6520, 'learning_rate': 1.1411e-05, 'epoch': 6.83}
+
+05/20/2024 22:00:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5861, 'learning_rate': 1.1349e-05, 'epoch': 6.84}
+
+05/20/2024 22:01:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6548, 'learning_rate': 1.1287e-05, 'epoch': 6.84}
+
+05/20/2024 22:02:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6235, 'learning_rate': 1.1226e-05, 'epoch': 6.85}
+
+05/20/2024 22:02:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.5998, 'learning_rate': 1.1164e-05, 'epoch': 6.86}
+
+05/20/2024 22:03:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6461, 'learning_rate': 1.1103e-05, 'epoch': 6.87}
+
+05/20/2024 22:04:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6310, 'learning_rate': 1.1042e-05, 'epoch': 6.88}
+
+05/20/2024 22:05:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6181, 'learning_rate': 1.0981e-05, 'epoch': 6.89}
+
+05/20/2024 22:06:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6331, 'learning_rate': 1.0920e-05, 'epoch': 6.90}
+
+05/20/2024 22:07:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.5939, 'learning_rate': 1.0859e-05, 'epoch': 6.91}
+
+05/20/2024 22:07:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6963, 'learning_rate': 1.0798e-05, 'epoch': 6.92}
+
+05/20/2024 22:08:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6771, 'learning_rate': 1.0738e-05, 'epoch': 6.93}
+
+05/20/2024 22:09:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6191, 'learning_rate': 1.0677e-05, 'epoch': 6.94}
+
+05/20/2024 22:09:29 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3700
+
+05/20/2024 22:09:29 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3700/tokenizer_config.json
+
+05/20/2024 22:09:29 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3700/special_tokens_map.json
+
+05/20/2024 22:10:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6175, 'learning_rate': 1.0617e-05, 'epoch': 6.95}
+
+05/20/2024 22:11:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6433, 'learning_rate': 1.0557e-05, 'epoch': 6.96}
+
+05/20/2024 22:11:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6512, 'learning_rate': 1.0497e-05, 'epoch': 6.97}
+
+05/20/2024 22:12:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6796, 'learning_rate': 1.0437e-05, 'epoch': 6.98}
+
+05/20/2024 22:13:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5976, 'learning_rate': 1.0377e-05, 'epoch': 6.99}
+
+05/20/2024 22:14:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6333, 'learning_rate': 1.0317e-05, 'epoch': 6.99}
+
+05/20/2024 22:15:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6213, 'learning_rate': 1.0258e-05, 'epoch': 7.00}
+
+05/20/2024 22:16:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6018, 'learning_rate': 1.0198e-05, 'epoch': 7.01}
+
+05/20/2024 22:17:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6629, 'learning_rate': 1.0139e-05, 'epoch': 7.02}
+
+05/20/2024 22:17:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6203, 'learning_rate': 1.0080e-05, 'epoch': 7.03}
+
+05/20/2024 22:18:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6381, 'learning_rate': 1.0021e-05, 'epoch': 7.04}
+
+05/20/2024 22:19:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6406, 'learning_rate': 9.9618e-06, 'epoch': 7.05}
+
+05/20/2024 22:20:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6470, 'learning_rate': 9.9030e-06, 'epoch': 7.06}
+
+05/20/2024 22:21:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6327, 'learning_rate': 9.8444e-06, 'epoch': 7.07}
+
+05/20/2024 22:21:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6444, 'learning_rate': 9.7858e-06, 'epoch': 7.08}
+
+05/20/2024 22:22:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6476, 'learning_rate': 9.7274e-06, 'epoch': 7.09}
+
+05/20/2024 22:23:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7190, 'learning_rate': 9.6692e-06, 'epoch': 7.10}
+
+05/20/2024 22:24:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6337, 'learning_rate': 9.6110e-06, 'epoch': 7.11}
+
+05/20/2024 22:25:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6248, 'learning_rate': 9.5530e-06, 'epoch': 7.12}
+
+05/20/2024 22:26:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.5985, 'learning_rate': 9.4952e-06, 'epoch': 7.13}
+
+05/20/2024 22:26:14 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3800
+
+05/20/2024 22:26:14 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3800/tokenizer_config.json
+
+05/20/2024 22:26:14 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3800/special_tokens_map.json
+
+05/20/2024 22:27:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7081, 'learning_rate': 9.4375e-06, 'epoch': 7.14}
+
+05/20/2024 22:28:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6221, 'learning_rate': 9.3799e-06, 'epoch': 7.14}
+
+05/20/2024 22:28:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6067, 'learning_rate': 9.3224e-06, 'epoch': 7.15}
+
+05/20/2024 22:29:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6345, 'learning_rate': 9.2651e-06, 'epoch': 7.16}
+
+05/20/2024 22:30:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6200, 'learning_rate': 9.2079e-06, 'epoch': 7.17}
+
+05/20/2024 22:31:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6324, 'learning_rate': 9.1508e-06, 'epoch': 7.18}
+
+05/20/2024 22:32:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7198, 'learning_rate': 9.0939e-06, 'epoch': 7.19}
+
+05/20/2024 22:33:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6803, 'learning_rate': 9.0372e-06, 'epoch': 7.20}
+
+05/20/2024 22:33:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6183, 'learning_rate': 8.9805e-06, 'epoch': 7.21}
+
+05/20/2024 22:34:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6617, 'learning_rate': 8.9240e-06, 'epoch': 7.22}
+
+05/20/2024 22:35:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.7041, 'learning_rate': 8.8677e-06, 'epoch': 7.23}
+
+05/20/2024 22:36:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6304, 'learning_rate': 8.8115e-06, 'epoch': 7.24}
+
+05/20/2024 22:37:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7009, 'learning_rate': 8.7554e-06, 'epoch': 7.25}
+
+05/20/2024 22:38:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.5837, 'learning_rate': 8.6995e-06, 'epoch': 7.26}
+
+05/20/2024 22:38:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.7046, 'learning_rate': 8.6437e-06, 'epoch': 7.27}
+
+05/20/2024 22:39:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6082, 'learning_rate': 8.5880e-06, 'epoch': 7.28}
+
+05/20/2024 22:40:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6421, 'learning_rate': 8.5325e-06, 'epoch': 7.29}
+
+05/20/2024 22:41:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6215, 'learning_rate': 8.4772e-06, 'epoch': 7.29}
+
+05/20/2024 22:42:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.5967, 'learning_rate': 8.4219e-06, 'epoch': 7.30}
+
+05/20/2024 22:43:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6084, 'learning_rate': 8.3669e-06, 'epoch': 7.31}
+
+05/20/2024 22:43:00 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3900
+
+05/20/2024 22:43:00 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3900/tokenizer_config.json
+
+05/20/2024 22:43:00 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-3900/special_tokens_map.json
+
+05/20/2024 22:43:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6273, 'learning_rate': 8.3119e-06, 'epoch': 7.32}
+
+05/20/2024 22:44:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6401, 'learning_rate': 8.2571e-06, 'epoch': 7.33}
+
+05/20/2024 22:45:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6312, 'learning_rate': 8.2025e-06, 'epoch': 7.34}
+
+05/20/2024 22:46:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.5924, 'learning_rate': 8.1480e-06, 'epoch': 7.35}
+
+05/20/2024 22:47:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6141, 'learning_rate': 8.0937e-06, 'epoch': 7.36}
+
+05/20/2024 22:48:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6317, 'learning_rate': 8.0395e-06, 'epoch': 7.37}
+
+05/20/2024 22:49:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6695, 'learning_rate': 7.9854e-06, 'epoch': 7.38}
+
+05/20/2024 22:49:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6176, 'learning_rate': 7.9315e-06, 'epoch': 7.39}
+
+05/20/2024 22:50:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6156, 'learning_rate': 7.8777e-06, 'epoch': 7.40}
+
+05/20/2024 22:51:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6416, 'learning_rate': 7.8241e-06, 'epoch': 7.41}
+
+05/20/2024 22:52:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6372, 'learning_rate': 7.7707e-06, 'epoch': 7.42}
+
+05/20/2024 22:53:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6528, 'learning_rate': 7.7173e-06, 'epoch': 7.43}
+
+05/20/2024 22:53:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6058, 'learning_rate': 7.6642e-06, 'epoch': 7.44}
+
+05/20/2024 22:54:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6394, 'learning_rate': 7.6112e-06, 'epoch': 7.44}
+
+05/20/2024 22:55:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6391, 'learning_rate': 7.5583e-06, 'epoch': 7.45}
+
+05/20/2024 22:56:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6292, 'learning_rate': 7.5056e-06, 'epoch': 7.46}
+
+05/20/2024 22:57:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6023, 'learning_rate': 7.4531e-06, 'epoch': 7.47}
+
+05/20/2024 22:58:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6827, 'learning_rate': 7.4006e-06, 'epoch': 7.48}
+
+05/20/2024 22:58:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6715, 'learning_rate': 7.3484e-06, 'epoch': 7.49}
+
+05/20/2024 22:59:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6401, 'learning_rate': 7.2963e-06, 'epoch': 7.50}
+
+05/20/2024 22:59:41 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4000
+
+05/20/2024 22:59:42 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4000/tokenizer_config.json
+
+05/20/2024 22:59:42 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4000/special_tokens_map.json
+
+05/20/2024 23:00:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6002, 'learning_rate': 7.2444e-06, 'epoch': 7.51}
+
+05/20/2024 23:01:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6241, 'learning_rate': 7.1926e-06, 'epoch': 7.52}
+
+05/20/2024 23:02:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6437, 'learning_rate': 7.1409e-06, 'epoch': 7.53}
+
+05/20/2024 23:03:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6631, 'learning_rate': 7.0895e-06, 'epoch': 7.54}
+
+05/20/2024 23:03:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6351, 'learning_rate': 7.0381e-06, 'epoch': 7.55}
+
+05/20/2024 23:04:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6561, 'learning_rate': 6.9870e-06, 'epoch': 7.56}
+
+05/20/2024 23:05:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6398, 'learning_rate': 6.9359e-06, 'epoch': 7.57}
+
+05/20/2024 23:06:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6530, 'learning_rate': 6.8851e-06, 'epoch': 7.58}
+
+05/20/2024 23:07:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6254, 'learning_rate': 6.8344e-06, 'epoch': 7.59}
+
+05/20/2024 23:08:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6555, 'learning_rate': 6.7839e-06, 'epoch': 7.59}
+
+05/20/2024 23:08:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6346, 'learning_rate': 6.7335e-06, 'epoch': 7.60}
+
+05/20/2024 23:09:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6145, 'learning_rate': 6.6833e-06, 'epoch': 7.61}
+
+05/20/2024 23:10:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6711, 'learning_rate': 6.6332e-06, 'epoch': 7.62}
+
+05/20/2024 23:11:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6113, 'learning_rate': 6.5833e-06, 'epoch': 7.63}
+
+05/20/2024 23:12:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6523, 'learning_rate': 6.5335e-06, 'epoch': 7.64}
+
+05/20/2024 23:13:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6197, 'learning_rate': 6.4840e-06, 'epoch': 7.65}
+
+05/20/2024 23:13:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6517, 'learning_rate': 6.4345e-06, 'epoch': 7.66}
+
+05/20/2024 23:14:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6112, 'learning_rate': 6.3853e-06, 'epoch': 7.67}
+
+05/20/2024 23:15:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.5833, 'learning_rate': 6.3362e-06, 'epoch': 7.68}
+
+05/20/2024 23:16:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6820, 'learning_rate': 6.2872e-06, 'epoch': 7.69}
+
+05/20/2024 23:16:37 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4100
+
+05/20/2024 23:16:37 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4100/tokenizer_config.json
+
+05/20/2024 23:16:37 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4100/special_tokens_map.json
+
+05/20/2024 23:17:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6418, 'learning_rate': 6.2385e-06, 'epoch': 7.70}
+
+05/20/2024 23:18:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.5869, 'learning_rate': 6.1898e-06, 'epoch': 7.71}
+
+05/20/2024 23:19:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6196, 'learning_rate': 6.1414e-06, 'epoch': 7.72}
+
+05/20/2024 23:19:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.5902, 'learning_rate': 6.0931e-06, 'epoch': 7.73}
+
+05/20/2024 23:20:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5955, 'learning_rate': 6.0450e-06, 'epoch': 7.74}
+
+05/20/2024 23:21:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6442, 'learning_rate': 5.9970e-06, 'epoch': 7.74}
+
+05/20/2024 23:22:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.5615, 'learning_rate': 5.9492e-06, 'epoch': 7.75}
+
+05/20/2024 23:23:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6686, 'learning_rate': 5.9016e-06, 'epoch': 7.76}
+
+05/20/2024 23:24:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6800, 'learning_rate': 5.8542e-06, 'epoch': 7.77}
+
+05/20/2024 23:25:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6360, 'learning_rate': 5.8069e-06, 'epoch': 7.78}
+
+05/20/2024 23:25:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6220, 'learning_rate': 5.7597e-06, 'epoch': 7.79}
+
+05/20/2024 23:26:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6318, 'learning_rate': 5.7128e-06, 'epoch': 7.80}
+
+05/20/2024 23:27:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6412, 'learning_rate': 5.6660e-06, 'epoch': 7.81}
+
+05/20/2024 23:28:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6147, 'learning_rate': 5.6194e-06, 'epoch': 7.82}
+
+05/20/2024 23:29:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6327, 'learning_rate': 5.5729e-06, 'epoch': 7.83}
+
+05/20/2024 23:30:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6489, 'learning_rate': 5.5266e-06, 'epoch': 7.84}
+
+05/20/2024 23:30:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6879, 'learning_rate': 5.4805e-06, 'epoch': 7.85}
+
+05/20/2024 23:31:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6175, 'learning_rate': 5.4345e-06, 'epoch': 7.86}
+
+05/20/2024 23:32:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6248, 'learning_rate': 5.3888e-06, 'epoch': 7.87}
+
+05/20/2024 23:33:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6735, 'learning_rate': 5.3432e-06, 'epoch': 7.88}
+
+05/20/2024 23:33:24 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4200
+
+05/20/2024 23:33:24 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4200/tokenizer_config.json
+
+05/20/2024 23:33:24 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4200/special_tokens_map.json
+
+05/20/2024 23:34:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6363, 'learning_rate': 5.2977e-06, 'epoch': 7.89}
+
+05/20/2024 23:34:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.5949, 'learning_rate': 5.2524e-06, 'epoch': 7.89}
+
+05/20/2024 23:35:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6439, 'learning_rate': 5.2074e-06, 'epoch': 7.90}
+
+05/20/2024 23:36:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6363, 'learning_rate': 5.1624e-06, 'epoch': 7.91}
+
+05/20/2024 23:37:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6733, 'learning_rate': 5.1177e-06, 'epoch': 7.92}
+
+05/20/2024 23:38:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6168, 'learning_rate': 5.0731e-06, 'epoch': 7.93}
+
+05/20/2024 23:39:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6509, 'learning_rate': 5.0287e-06, 'epoch': 7.94}
+
+05/20/2024 23:39:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.5826, 'learning_rate': 4.9845e-06, 'epoch': 7.95}
+
+05/20/2024 23:40:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6473, 'learning_rate': 4.9404e-06, 'epoch': 7.96}
+
+05/20/2024 23:41:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6709, 'learning_rate': 4.8965e-06, 'epoch': 7.97}
+
+05/20/2024 23:42:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6249, 'learning_rate': 4.8528e-06, 'epoch': 7.98}
+
+05/20/2024 23:43:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6498, 'learning_rate': 4.8093e-06, 'epoch': 7.99}
+
+05/20/2024 23:44:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6610, 'learning_rate': 4.7659e-06, 'epoch': 8.00}
+
+05/20/2024 23:44:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6802, 'learning_rate': 4.7227e-06, 'epoch': 8.01}
+
+05/20/2024 23:45:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6544, 'learning_rate': 4.6797e-06, 'epoch': 8.02}
+
+05/20/2024 23:46:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6447, 'learning_rate': 4.6369e-06, 'epoch': 8.03}
+
+05/20/2024 23:47:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6454, 'learning_rate': 4.5942e-06, 'epoch': 8.04}
+
+05/20/2024 23:48:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6773, 'learning_rate': 4.5518e-06, 'epoch': 8.05}
+
+05/20/2024 23:49:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6645, 'learning_rate': 4.5095e-06, 'epoch': 8.05}
+
+05/20/2024 23:50:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6065, 'learning_rate': 4.4673e-06, 'epoch': 8.06}
+
+05/20/2024 23:50:03 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4300
+
+05/20/2024 23:50:03 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4300/tokenizer_config.json
+
+05/20/2024 23:50:03 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4300/special_tokens_map.json
+
+05/20/2024 23:50:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.5862, 'learning_rate': 4.4254e-06, 'epoch': 8.07}
+
+05/20/2024 23:51:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6838, 'learning_rate': 4.3836e-06, 'epoch': 8.08}
+
+05/20/2024 23:52:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6324, 'learning_rate': 4.3421e-06, 'epoch': 8.09}
+
+05/20/2024 23:53:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6593, 'learning_rate': 4.3006e-06, 'epoch': 8.10}
+
+05/20/2024 23:54:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6020, 'learning_rate': 4.2594e-06, 'epoch': 8.11}
+
+05/20/2024 23:55:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6228, 'learning_rate': 4.2184e-06, 'epoch': 8.12}
+
+05/20/2024 23:55:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6277, 'learning_rate': 4.1775e-06, 'epoch': 8.13}
+
+05/20/2024 23:56:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6003, 'learning_rate': 4.1368e-06, 'epoch': 8.14}
+
+05/20/2024 23:57:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6549, 'learning_rate': 4.0963e-06, 'epoch': 8.15}
+
+05/20/2024 23:58:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6435, 'learning_rate': 4.0560e-06, 'epoch': 8.16}
+
+05/20/2024 23:59:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6168, 'learning_rate': 4.0159e-06, 'epoch': 8.17}
+
+05/21/2024 00:00:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6234, 'learning_rate': 3.9759e-06, 'epoch': 8.18}
+
+05/21/2024 00:01:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6842, 'learning_rate': 3.9361e-06, 'epoch': 8.19}
+
+05/21/2024 00:01:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6069, 'learning_rate': 3.8965e-06, 'epoch': 8.20}
+
+05/21/2024 00:02:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7014, 'learning_rate': 3.8571e-06, 'epoch': 8.20}
+
+05/21/2024 00:03:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6156, 'learning_rate': 3.8179e-06, 'epoch': 8.21}
+
+05/21/2024 00:04:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5904, 'learning_rate': 3.7789e-06, 'epoch': 8.22}
+
+05/21/2024 00:05:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6112, 'learning_rate': 3.7400e-06, 'epoch': 8.23}
+
+05/21/2024 00:05:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6386, 'learning_rate': 3.7013e-06, 'epoch': 8.24}
+
+05/21/2024 00:06:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6145, 'learning_rate': 3.6629e-06, 'epoch': 8.25}
+
+05/21/2024 00:06:49 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4400
+
+05/21/2024 00:06:49 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4400/tokenizer_config.json
+
+05/21/2024 00:06:49 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4400/special_tokens_map.json
+
+05/21/2024 00:07:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6423, 'learning_rate': 3.6245e-06, 'epoch': 8.26}
+
+05/21/2024 00:08:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6283, 'learning_rate': 3.5864e-06, 'epoch': 8.27}
+
+05/21/2024 00:09:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6565, 'learning_rate': 3.5485e-06, 'epoch': 8.28}
+
+05/21/2024 00:10:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6035, 'learning_rate': 3.5108e-06, 'epoch': 8.29}
+
+05/21/2024 00:10:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6294, 'learning_rate': 3.4732e-06, 'epoch': 8.30}
+
+05/21/2024 00:11:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6513, 'learning_rate': 3.4358e-06, 'epoch': 8.31}
+
+05/21/2024 00:12:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6149, 'learning_rate': 3.3987e-06, 'epoch': 8.32}
+
+05/21/2024 00:13:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.5946, 'learning_rate': 3.3617e-06, 'epoch': 8.33}
+
+05/21/2024 00:14:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6897, 'learning_rate': 3.3248e-06, 'epoch': 8.34}
+
+05/21/2024 00:15:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6262, 'learning_rate': 3.2882e-06, 'epoch': 8.35}
+
+05/21/2024 00:15:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6700, 'learning_rate': 3.2518e-06, 'epoch': 8.35}
+
+05/21/2024 00:16:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6090, 'learning_rate': 3.2156e-06, 'epoch': 8.36}
+
+05/21/2024 00:17:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6664, 'learning_rate': 3.1795e-06, 'epoch': 8.37}
+
+05/21/2024 00:18:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6260, 'learning_rate': 3.1436e-06, 'epoch': 8.38}
+
+05/21/2024 00:19:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6498, 'learning_rate': 3.1080e-06, 'epoch': 8.39}
+
+05/21/2024 00:20:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6007, 'learning_rate': 3.0725e-06, 'epoch': 8.40}
+
+05/21/2024 00:20:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6150, 'learning_rate': 3.0372e-06, 'epoch': 8.41}
+
+05/21/2024 00:21:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6682, 'learning_rate': 3.0021e-06, 'epoch': 8.42}
+
+05/21/2024 00:22:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6249, 'learning_rate': 2.9672e-06, 'epoch': 8.43}
+
+05/21/2024 00:23:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6292, 'learning_rate': 2.9325e-06, 'epoch': 8.44}
+
+05/21/2024 00:23:31 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4500
+
+05/21/2024 00:23:31 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4500/tokenizer_config.json
+
+05/21/2024 00:23:31 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4500/special_tokens_map.json
+
+05/21/2024 00:24:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6227, 'learning_rate': 2.8979e-06, 'epoch': 8.45}
+
+05/21/2024 00:25:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6132, 'learning_rate': 2.8636e-06, 'epoch': 8.46}
+
+05/21/2024 00:25:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.5932, 'learning_rate': 2.8295e-06, 'epoch': 8.47}
+
+05/21/2024 00:26:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5928, 'learning_rate': 2.7955e-06, 'epoch': 8.48}
+
+05/21/2024 00:27:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6880, 'learning_rate': 2.7617e-06, 'epoch': 8.49}
+
+05/21/2024 00:28:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6179, 'learning_rate': 2.7282e-06, 'epoch': 8.50}
+
+05/21/2024 00:29:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6539, 'learning_rate': 2.6948e-06, 'epoch': 8.50}
+
+05/21/2024 00:29:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.5872, 'learning_rate': 2.6616e-06, 'epoch': 8.51}
+
+05/21/2024 00:30:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6199, 'learning_rate': 2.6287e-06, 'epoch': 8.52}
+
+05/21/2024 00:31:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6563, 'learning_rate': 2.5959e-06, 'epoch': 8.53}
+
+05/21/2024 00:32:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6084, 'learning_rate': 2.5633e-06, 'epoch': 8.54}
+
+05/21/2024 00:33:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.5984, 'learning_rate': 2.5309e-06, 'epoch': 8.55}
+
+05/21/2024 00:34:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6822, 'learning_rate': 2.4987e-06, 'epoch': 8.56}
+
+05/21/2024 00:35:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6120, 'learning_rate': 2.4667e-06, 'epoch': 8.57}
+
+05/21/2024 00:35:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6401, 'learning_rate': 2.4348e-06, 'epoch': 8.58}
+
+05/21/2024 00:36:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5922, 'learning_rate': 2.4032e-06, 'epoch': 8.59}
+
+05/21/2024 00:37:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6515, 'learning_rate': 2.3718e-06, 'epoch': 8.60}
+
+05/21/2024 00:38:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6676, 'learning_rate': 2.3406e-06, 'epoch': 8.61}
+
+05/21/2024 00:39:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6567, 'learning_rate': 2.3095e-06, 'epoch': 8.62}
+
+05/21/2024 00:40:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6738, 'learning_rate': 2.2787e-06, 'epoch': 8.63}
+
+05/21/2024 00:40:16 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4600
+
+05/21/2024 00:40:16 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4600/tokenizer_config.json
+
+05/21/2024 00:40:16 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4600/special_tokens_map.json
+
+05/21/2024 00:41:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7266, 'learning_rate': 2.2481e-06, 'epoch': 8.64}
+
+05/21/2024 00:41:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6497, 'learning_rate': 2.2176e-06, 'epoch': 8.65}
+
+05/21/2024 00:42:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6065, 'learning_rate': 2.1874e-06, 'epoch': 8.65}
+
+05/21/2024 00:43:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6856, 'learning_rate': 2.1574e-06, 'epoch': 8.66}
+
+05/21/2024 00:44:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6255, 'learning_rate': 2.1275e-06, 'epoch': 8.67}
+
+05/21/2024 00:45:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6456, 'learning_rate': 2.0979e-06, 'epoch': 8.68}
+
+05/21/2024 00:46:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.5966, 'learning_rate': 2.0684e-06, 'epoch': 8.69}
+
+05/21/2024 00:46:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6117, 'learning_rate': 2.0392e-06, 'epoch': 8.70}
+
+05/21/2024 00:47:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.5870, 'learning_rate': 2.0102e-06, 'epoch': 8.71}
+
+05/21/2024 00:48:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.5860, 'learning_rate': 1.9813e-06, 'epoch': 8.72}
+
+05/21/2024 00:49:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.5673, 'learning_rate': 1.9527e-06, 'epoch': 8.73}
+
+05/21/2024 00:50:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7131, 'learning_rate': 1.9242e-06, 'epoch': 8.74}
+
+05/21/2024 00:51:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6603, 'learning_rate': 1.8960e-06, 'epoch': 8.75}
+
+05/21/2024 00:51:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6448, 'learning_rate': 1.8679e-06, 'epoch': 8.76}
+
+05/21/2024 00:52:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6481, 'learning_rate': 1.8401e-06, 'epoch': 8.77}
+
+05/21/2024 00:53:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6046, 'learning_rate': 1.8124e-06, 'epoch': 8.78}
+
+05/21/2024 00:54:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6110, 'learning_rate': 1.7850e-06, 'epoch': 8.79}
+
+05/21/2024 00:55:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6439, 'learning_rate': 1.7578e-06, 'epoch': 8.80}
+
+05/21/2024 00:56:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6499, 'learning_rate': 1.7307e-06, 'epoch': 8.80}
+
+05/21/2024 00:57:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6387, 'learning_rate': 1.7039e-06, 'epoch': 8.81}
+
+05/21/2024 00:57:05 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4700
+
+05/21/2024 00:57:05 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4700/tokenizer_config.json
+
+05/21/2024 00:57:05 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4700/special_tokens_map.json
+
+05/21/2024 00:57:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6127, 'learning_rate': 1.6773e-06, 'epoch': 8.82}
+
+05/21/2024 00:58:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6008, 'learning_rate': 1.6508e-06, 'epoch': 8.83}
+
+05/21/2024 00:59:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6330, 'learning_rate': 1.6246e-06, 'epoch': 8.84}
+
+05/21/2024 01:00:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.5974, 'learning_rate': 1.5986e-06, 'epoch': 8.85}
+
+05/21/2024 01:01:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6304, 'learning_rate': 1.5727e-06, 'epoch': 8.86}
+
+05/21/2024 01:02:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6085, 'learning_rate': 1.5471e-06, 'epoch': 8.87}
+
+05/21/2024 01:02:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6164, 'learning_rate': 1.5217e-06, 'epoch': 8.88}
+
+05/21/2024 01:03:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6261, 'learning_rate': 1.4965e-06, 'epoch': 8.89}
+
+05/21/2024 01:04:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6201, 'learning_rate': 1.4715e-06, 'epoch': 8.90}
+
+05/21/2024 01:05:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6414, 'learning_rate': 1.4467e-06, 'epoch': 8.91}
+
+05/21/2024 01:06:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6370, 'learning_rate': 1.4221e-06, 'epoch': 8.92}
+
+05/21/2024 01:06:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6612, 'learning_rate': 1.3977e-06, 'epoch': 8.93}
+
+05/21/2024 01:07:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6023, 'learning_rate': 1.3735e-06, 'epoch': 8.94}
+
+05/21/2024 01:08:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6365, 'learning_rate': 1.3495e-06, 'epoch': 8.95}
+
+05/21/2024 01:09:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6477, 'learning_rate': 1.3258e-06, 'epoch': 8.95}
+
+05/21/2024 01:10:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6568, 'learning_rate': 1.3022e-06, 'epoch': 8.96}
+
+05/21/2024 01:11:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6284, 'learning_rate': 1.2788e-06, 'epoch': 8.97}
+
+05/21/2024 01:11:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6440, 'learning_rate': 1.2557e-06, 'epoch': 8.98}
+
+05/21/2024 01:12:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6061, 'learning_rate': 1.2327e-06, 'epoch': 8.99}
+
+05/21/2024 01:13:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6398, 'learning_rate': 1.2100e-06, 'epoch': 9.00}
+
+05/21/2024 01:13:32 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4800
+
+05/21/2024 01:13:32 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4800/tokenizer_config.json
+
+05/21/2024 01:13:32 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4800/special_tokens_map.json
+
+05/21/2024 01:14:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6009, 'learning_rate': 1.1874e-06, 'epoch': 9.01}
+
+05/21/2024 01:15:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.5853, 'learning_rate': 1.1651e-06, 'epoch': 9.02}
+
+05/21/2024 01:16:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6329, 'learning_rate': 1.1430e-06, 'epoch': 9.03}
+
+05/21/2024 01:16:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6441, 'learning_rate': 1.1210e-06, 'epoch': 9.04}
+
+05/21/2024 01:17:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5999, 'learning_rate': 1.0993e-06, 'epoch': 9.05}
+
+05/21/2024 01:18:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6711, 'learning_rate': 1.0778e-06, 'epoch': 9.06}
+
+05/21/2024 01:19:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6835, 'learning_rate': 1.0565e-06, 'epoch': 9.07}
+
+05/21/2024 01:20:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6101, 'learning_rate': 1.0354e-06, 'epoch': 9.08}
+
+05/21/2024 01:20:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6397, 'learning_rate': 1.0146e-06, 'epoch': 9.09}
+
+05/21/2024 01:21:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6406, 'learning_rate': 9.9389e-07, 'epoch': 9.10}
+
+05/21/2024 01:22:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6296, 'learning_rate': 9.7343e-07, 'epoch': 9.10}
+
+05/21/2024 01:23:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6493, 'learning_rate': 9.5317e-07, 'epoch': 9.11}
+
+05/21/2024 01:24:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6172, 'learning_rate': 9.3313e-07, 'epoch': 9.12}
+
+05/21/2024 01:25:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6670, 'learning_rate': 9.1329e-07, 'epoch': 9.13}
+
+05/21/2024 01:25:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5673, 'learning_rate': 8.9366e-07, 'epoch': 9.14}
+
+05/21/2024 01:26:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6604, 'learning_rate': 8.7424e-07, 'epoch': 9.15}
+
+05/21/2024 01:27:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6737, 'learning_rate': 8.5504e-07, 'epoch': 9.16}
+
+05/21/2024 01:28:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6476, 'learning_rate': 8.3604e-07, 'epoch': 9.17}
+
+05/21/2024 01:29:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6091, 'learning_rate': 8.1725e-07, 'epoch': 9.18}
+
+05/21/2024 01:30:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6731, 'learning_rate': 7.9867e-07, 'epoch': 9.19}
+
+05/21/2024 01:30:01 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4900
+
+05/21/2024 01:30:01 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4900/tokenizer_config.json
+
+05/21/2024 01:30:01 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-4900/special_tokens_map.json
+
+05/21/2024 01:30:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6248, 'learning_rate': 7.8030e-07, 'epoch': 9.20}
+
+05/21/2024 01:31:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6076, 'learning_rate': 7.6214e-07, 'epoch': 9.21}
+
+05/21/2024 01:32:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6068, 'learning_rate': 7.4419e-07, 'epoch': 9.22}
+
+05/21/2024 01:33:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6431, 'learning_rate': 7.2645e-07, 'epoch': 9.23}
+
+05/21/2024 01:34:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6468, 'learning_rate': 7.0893e-07, 'epoch': 9.24}
+
+05/21/2024 01:34:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6211, 'learning_rate': 6.9161e-07, 'epoch': 9.25}
+
+05/21/2024 01:35:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6377, 'learning_rate': 6.7451e-07, 'epoch': 9.25}
+
+05/21/2024 01:36:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6164, 'learning_rate': 6.5761e-07, 'epoch': 9.26}
+
+05/21/2024 01:37:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6690, 'learning_rate': 6.4093e-07, 'epoch': 9.27}
+
+05/21/2024 01:38:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.7301, 'learning_rate': 6.2446e-07, 'epoch': 9.28}
+
+05/21/2024 01:39:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.5822, 'learning_rate': 6.0820e-07, 'epoch': 9.29}
+
+05/21/2024 01:39:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6636, 'learning_rate': 5.9216e-07, 'epoch': 9.30}
+
+05/21/2024 01:40:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6325, 'learning_rate': 5.7632e-07, 'epoch': 9.31}
+
+05/21/2024 01:41:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.5589, 'learning_rate': 5.6070e-07, 'epoch': 9.32}
+
+05/21/2024 01:42:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6435, 'learning_rate': 5.4529e-07, 'epoch': 9.33}
+
+05/21/2024 01:43:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6859, 'learning_rate': 5.3009e-07, 'epoch': 9.34}
+
+05/21/2024 01:43:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6017, 'learning_rate': 5.1511e-07, 'epoch': 9.35}
+
+05/21/2024 01:44:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7363, 'learning_rate': 5.0033e-07, 'epoch': 9.36}
+
+05/21/2024 01:45:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6453, 'learning_rate': 4.8577e-07, 'epoch': 9.37}
+
+05/21/2024 01:46:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6083, 'learning_rate': 4.7143e-07, 'epoch': 9.38}
+
+05/21/2024 01:46:24 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5000
+
+05/21/2024 01:46:24 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5000/tokenizer_config.json
+
+05/21/2024 01:46:24 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5000/special_tokens_map.json
+
+05/21/2024 01:47:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.6062, 'learning_rate': 4.5729e-07, 'epoch': 9.39}
+
+05/21/2024 01:48:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6589, 'learning_rate': 4.4337e-07, 'epoch': 9.40}
+
+05/21/2024 01:48:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6953, 'learning_rate': 4.2966e-07, 'epoch': 9.40}
+
+05/21/2024 01:49:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6304, 'learning_rate': 4.1617e-07, 'epoch': 9.41}
+
+05/21/2024 01:50:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6166, 'learning_rate': 4.0289e-07, 'epoch': 9.42}
+
+05/21/2024 01:51:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.5931, 'learning_rate': 3.8982e-07, 'epoch': 9.43}
+
+05/21/2024 01:52:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6476, 'learning_rate': 3.7697e-07, 'epoch': 9.44}
+
+05/21/2024 01:53:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6320, 'learning_rate': 3.6433e-07, 'epoch': 9.45}
+
+05/21/2024 01:53:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6757, 'learning_rate': 3.5190e-07, 'epoch': 9.46}
+
+05/21/2024 01:54:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6144, 'learning_rate': 3.3969e-07, 'epoch': 9.47}
+
+05/21/2024 01:55:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.6074, 'learning_rate': 3.2769e-07, 'epoch': 9.48}
+
+05/21/2024 01:56:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.6448, 'learning_rate': 3.1591e-07, 'epoch': 9.49}
+
+05/21/2024 01:57:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.5808, 'learning_rate': 3.0434e-07, 'epoch': 9.50}
+
+05/21/2024 01:58:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6257, 'learning_rate': 2.9299e-07, 'epoch': 9.51}
+
+05/21/2024 01:59:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.6023, 'learning_rate': 2.8185e-07, 'epoch': 9.52}
+
+05/21/2024 01:59:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6195, 'learning_rate': 2.7093e-07, 'epoch': 9.53}
+
+05/21/2024 02:00:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.7082, 'learning_rate': 2.6022e-07, 'epoch': 9.54}
+
+05/21/2024 02:01:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6557, 'learning_rate': 2.4972e-07, 'epoch': 9.55}
+
+05/21/2024 02:02:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6380, 'learning_rate': 2.3944e-07, 'epoch': 9.55}
+
+05/21/2024 02:03:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6278, 'learning_rate': 2.2937e-07, 'epoch': 9.56}
+
+05/21/2024 02:03:12 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5100
+
+05/21/2024 02:03:12 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5100/tokenizer_config.json
+
+05/21/2024 02:03:12 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5100/special_tokens_map.json
+
+05/21/2024 02:04:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7008, 'learning_rate': 2.1952e-07, 'epoch': 9.57}
+
+05/21/2024 02:04:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.5853, 'learning_rate': 2.0989e-07, 'epoch': 9.58}
+
+05/21/2024 02:05:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.5957, 'learning_rate': 2.0047e-07, 'epoch': 9.59}
+
+05/21/2024 02:06:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6297, 'learning_rate': 1.9127e-07, 'epoch': 9.60}
+
+05/21/2024 02:07:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6377, 'learning_rate': 1.8228e-07, 'epoch': 9.61}
+
+05/21/2024 02:08:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6664, 'learning_rate': 1.7351e-07, 'epoch': 9.62}
+
+05/21/2024 02:09:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6183, 'learning_rate': 1.6495e-07, 'epoch': 9.63}
+
+05/21/2024 02:10:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7119, 'learning_rate': 1.5661e-07, 'epoch': 9.64}
+
+05/21/2024 02:10:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6166, 'learning_rate': 1.4848e-07, 'epoch': 9.65}
+
+05/21/2024 02:11:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6514, 'learning_rate': 1.4057e-07, 'epoch': 9.66}
+
+05/21/2024 02:12:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.6372, 'learning_rate': 1.3288e-07, 'epoch': 9.67}
+
+05/21/2024 02:13:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.5882, 'learning_rate': 1.2540e-07, 'epoch': 9.68}
+
+05/21/2024 02:14:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.5873, 'learning_rate': 1.1814e-07, 'epoch': 9.69}
+
+05/21/2024 02:14:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6399, 'learning_rate': 1.1109e-07, 'epoch': 9.70}
+
+05/21/2024 02:15:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7202, 'learning_rate': 1.0426e-07, 'epoch': 9.70}
+
+05/21/2024 02:16:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.5922, 'learning_rate': 9.7646e-08, 'epoch': 9.71}
+
+05/21/2024 02:17:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7081, 'learning_rate': 9.1249e-08, 'epoch': 9.72}
+
+05/21/2024 02:18:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.5845, 'learning_rate': 8.5068e-08, 'epoch': 9.73}
+
+05/21/2024 02:19:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.5956, 'learning_rate': 7.9103e-08, 'epoch': 9.74}
+
+05/21/2024 02:19:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6221, 'learning_rate': 7.3355e-08, 'epoch': 9.75}
+
+05/21/2024 02:19:58 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5200
+
+05/21/2024 02:19:58 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5200/tokenizer_config.json
+
+05/21/2024 02:19:58 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5200/special_tokens_map.json
+
+05/21/2024 02:20:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6277, 'learning_rate': 6.7823e-08, 'epoch': 9.76}
+
+05/21/2024 02:21:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6369, 'learning_rate': 6.2508e-08, 'epoch': 9.77}
+
+05/21/2024 02:22:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6062, 'learning_rate': 5.7410e-08, 'epoch': 9.78}
+
+05/21/2024 02:23:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6604, 'learning_rate': 5.2528e-08, 'epoch': 9.79}
+
+05/21/2024 02:24:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6366, 'learning_rate': 4.7862e-08, 'epoch': 9.80}
+
+05/21/2024 02:25:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6002, 'learning_rate': 4.3414e-08, 'epoch': 9.81}
+
+05/21/2024 02:25:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6214, 'learning_rate': 3.9182e-08, 'epoch': 9.82}
+
+05/21/2024 02:26:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.5874, 'learning_rate': 3.5167e-08, 'epoch': 9.83}
+
+05/21/2024 02:27:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6107, 'learning_rate': 3.1369e-08, 'epoch': 9.84}
+
+05/21/2024 02:28:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6103, 'learning_rate': 2.7788e-08, 'epoch': 9.85}
+
+05/21/2024 02:29:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6131, 'learning_rate': 2.4423e-08, 'epoch': 9.85}
+
+05/21/2024 02:30:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.5984, 'learning_rate': 2.1276e-08, 'epoch': 9.86}
+
+05/21/2024 02:30:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6575, 'learning_rate': 1.8345e-08, 'epoch': 9.87}
+
+05/21/2024 02:31:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.5926, 'learning_rate': 1.5632e-08, 'epoch': 9.88}
+
+05/21/2024 02:32:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7148, 'learning_rate': 1.3135e-08, 'epoch': 9.89}
+
+05/21/2024 02:33:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.5936, 'learning_rate': 1.0856e-08, 'epoch': 9.90}
+
+05/21/2024 02:34:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6215, 'learning_rate': 8.7934e-09, 'epoch': 9.91}
+
+05/21/2024 02:35:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6215, 'learning_rate': 6.9479e-09, 'epoch': 9.92}
+
+05/21/2024 02:35:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.6512, 'learning_rate': 5.3196e-09, 'epoch': 9.93}
+
+05/21/2024 02:36:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.5967, 'learning_rate': 3.9083e-09, 'epoch': 9.94}
+
+05/21/2024 02:36:54 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5300
+
+05/21/2024 02:36:54 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5300/tokenizer_config.json
+
+05/21/2024 02:36:54 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/checkpoint-5300/special_tokens_map.json
+
+05/21/2024 02:37:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6356, 'learning_rate': 2.7141e-09, 'epoch': 9.95}
+
+05/21/2024 02:38:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6437, 'learning_rate': 1.7370e-09, 'epoch': 9.96}
+
+05/21/2024 02:39:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6522, 'learning_rate': 9.7709e-10, 'epoch': 9.97}
+
+05/21/2024 02:40:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.6017, 'learning_rate': 4.3426e-10, 'epoch': 9.98}
+
+05/21/2024 02:41:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6095, 'learning_rate': 1.0857e-10, 'epoch': 9.99}
+
+05/21/2024 02:41:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6320, 'learning_rate': 0.0000e+00, 'epoch': 10.00}
+
+05/21/2024 02:41:51 - INFO - transformers.trainer - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+05/21/2024 02:41:51 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca
+
+05/21/2024 02:41:51 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/tokenizer_config.json
+
+05/21/2024 02:41:51 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed_alpaca/special_tokens_map.json
+
+05/21/2024 02:41:51 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+