--- library_name: peft tags: - axolotl - base_model:adapter:Qwen/Qwen3-4B-Instruct-2507 - lora - transformers datasets: - custom base_model: Qwen/Qwen3-4B-Instruct-2507 pipeline_tag: text-generation model-index: - name: agent-0910 results: [] --- [Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl)
See axolotl config axolotl version: `0.12.2` ```yaml # Automatically upload checkpoint and final model to HF # hub_model_id: username/custom_model_name # 是否以 8-bit 精度加载模型 load_in_8bit: false # 是否以 4-bit 精度加载模型（与QLoRA绑定, 强制使用） load_in_4bit: false # 是否严格匹配模型结构，关闭表示可加载少部分差异结构（如以适配 adapter） # strict: false base_model: /workspace/xuyiwei/merged_agent_model_0908 # 数据集设置 chat_template: qwen3 datasets: - path: /workspace/jiangqiyi/file_manage_agent_train/data/retrieval_agent_train_data.json # - 表示列表（list）中的一项, 即可以同时使用多个数据集 type: chat_template # chat_template(自定义格式) alpaca roles_to_train: ["assistant"] field_messages: messages # 标识的字段 message_property_mappings: # message_property_mappings={'role':'role', 'content':'content'}) role: role content: content dataset_prepared_path: val_set_size: 0.05 output_dir: models/0910 sequence_len: 8192 # 模型所能处理的最大上下文长度(默认2048) pad_to_sequence_len: true # context_parallel_size: 2 # 长序列拆分至多个GPU(强制要求 mirco_batch_size: 1) sample_packing: false # 在训练时将多个样本拼接（packing）成一个长序列(sequence_len)输入到模型中，以提高训练效率。 eval_sample_packing: false # 评估时拼接多个样本 # 训练超参数 adapter: lora # lora qlora lora_model_dir: lora_r: 16 # lora_r默认首选 16，平衡精度与显存 lora_alpha: 64 # 缩放系数，用于控制 LoRA 的影响力, 一般设为 2*r 或 4*r lora_dropout: 0.05 lora_target_linear: true micro_batch_size: 1 # 微批次大小 94G的H100可以设为4(Token为1w) gradient_accumulation_steps: 16 # 梯度累积: 将多个微批次的梯度(micro_batch_size)累积起来，然后更新模型权重 有效 Batch 常取 16: 小于 8 训练会抖，大于 32 只会更耗时、收益有限 auto_find_batch_size: false # 允许Axolotl不断调整batch_size ⚠️Zero-3不适用 num_epochs: 1 optimizer: adamw_torch_fused lr_scheduler: cosine learning_rate: 2e-5 # bf16: auto + tf32: true，可获得更好的稳定性和性能。 bf16: auto tf32: true # early_stopping_patience: gradient_checkpointing: true gradient_checkpointing_kwargs: use_reentrant: false # auto_resume_from_checkpoints: true #自动从output_dir寻找最新checkpoint断点恢复 logging_steps: 1 flash_attention: true # xformers_attention: true warmup_steps: 10 evals_per_epoch: 4 saves_per_epoch: 1 weight_decay: 0.0 # deepspeed: /workspace/deepspeed_configs/zero2.json # fsdp: # - full_shard # - auto_wrap # fsdp_config: # fsdp_limit_all_gathers: true # fsdp_sync_module_states: true # fsdp_offload_params: true # fsdp_use_orig_params: false # fsdp_cpu_ram_efficient_loading: true # fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP # fsdp_transformer_layer_cls_to_wrap: Qwen3DecoderLayer # fsdp_state_dict_type: FULL_STATE_DICT # fsdp_sharding_strategy: FULL_SHARD # special_tokens: # wandb_project: # wandb_entity: # wandb_watch: # wandb_name: # wandb_log_model: ```

# models/0910 This model was trained from scratch on the /workspace/jiangqiyi/file_manage_agent_train/data/retrieval_agent_train_data.json dataset. It achieves the following results on the evaluation set: - Loss: 0.0452 - Memory/max Mem Active(gib): 23.87 - Memory/max Mem Allocated(gib): 23.87 - Memory/device Mem Reserved(gib): 26.56 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 279 ### Training results | Training Loss | Epoch | Step | Validation Loss | Mem Active(gib) | Mem Allocated(gib) | Mem Reserved(gib) | |:-------------:|:------:|:----:|:---------------:|:---------------:|:------------------:|:-----------------:| | No log | 0 | 0 | 0.0491 | 19.7 | 19.7 | 19.8 | | 0.0547 | 0.2515 | 70 | 0.0482 | 23.87 | 23.87 | 26.56 | | 0.0423 | 0.5030 | 140 | 0.0461 | 23.87 | 23.87 | 26.56 | | 0.0449 | 0.7545 | 210 | 0.0452 | 23.87 | 23.87 | 26.56 | ### Framework versions - PEFT 0.17.0 - Transformers 4.55.2 - Pytorch 2.6.0+cu124 - Datasets 4.0.0 - Tokenizers 0.21.4