CoolFace
Modelpublic

cjkasbdkjnlakb/qwen3-4b-agent-0926-quancan

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes11downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>

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: Qwen/Qwen3-4B-Instruct-2507

# 数据集设置
chat_template: qwen3
datasets:
- path: /workspace/train_dir_0926-02/goal_data.json # 只使用新增的1500条数据
  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: 0.1 # 8卡训练可以适当减少验证集比例,提高训练数据利用率
output_dir: /workspace/train_dir_0926-02/checkpoints
sequence_len: 7000 # 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 # Function call数据通常较短,可以启用packing提高效率
eval_sample_packing: false # 评估时拼接多个样本

# 训练超参数 - 针对function call优化
lora_r: 32 # function call需要更强的表达能力,提高rank
lora_alpha: 64 # 设为 2*r,保持合理的缩放
lora_dropout: 0.1 # 8卡训练数据分布更均匀,可以适当降低dropout

# 批处理设置 - 充分利用8卡H100
micro_batch_size: 8 # H100显存大,可以增加batch size
gradient_accumulation_steps: 2 # 8卡并行,可以减少累积步数
auto_find_batch_size: false # 允许Axolotl不断调整batch_size ⚠️Zero-3不适用
num_epochs: 3 # function call数据质量高,可以多训练几轮

# 优化器设置
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 8e-5 # 在已有模型基础上微调function call,稍微提高学习率

# 精度设置
bf16: auto
tf32: true

# 日志和评估
logging_steps: 30 # 8卡训练速度快,可以适当减少日志频率
flash_attention: true
warmup_ratio: 0.1 # 已有基础模型,减少warmup
evals_per_epoch: 1 # 适中的评估频次
saves_per_epoch: 1 # 适中的保存频次
weight_decay: 0.01 # 8卡训练更稳定,减少正则化

# FSDP配置 - 针对8卡H100优化
fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: true
  fsdp_offload_params: false # H100显存充足,无需offload
  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
  fsdp_activation_checkpointing: true # 使用FSDP的activation checkpointing

</details><br>

workspace/traindir0926-02/checkpoints

This model is a fine-tuned version of Qwen/Qwen3-4B-Instruct-2507 on the /workspace/traindir0926-02/goal_data.json dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.0403
  • —Memory/max Mem Active(gib): 121.88
  • —Memory/max Mem Allocated(gib): 121.69
  • —Memory/device Mem Reserved(gib): 136.37

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: 8e-05
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —distributed_type: multi-GPU
  • —num_devices: 8
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 128
  • —totalevalbatch_size: 64
  • —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 16
  • —training_steps: 161

Training results

Training LossEpochStepValidation LossMem Active(gib)Mem Allocated(gib)Mem Reserved(gib)
No log001.122183.2183.0184.11
0.22951.0540.0622121.88121.69136.37
0.05122.01080.0403121.88121.69136.37

Framework versions

  • —Transformers 4.55.2
  • —Pytorch 2.6.0+cu126
  • —Datasets 4.0.0
  • —Tokenizers 0.21.4