docs: 修复文档中过时的字段、签名和缺失的类
- BaseConfig 的 from_json/to_json → from_file/to_file - InputConfig/ProcessingConfig/OutputConfig 字段对齐源码 - 移除不存在的 Registry 类,register() 去 category/priority - SchedulerFactory.create 参数顺序修正 - 架构图/训练/参数文档补全 WSDScheduler - CONTRIBUTING.md 克隆地址占位符修正 - params.md label_smoothing 默认值修正,补全 neftune_alpha - app 类更正为 get_app 函数
This commit is contained in:
@@ -86,11 +86,12 @@
|
||||
| Parameter | Description | Default | Used by |
|
||||
|-----------|-------------|---------|---------|
|
||||
| `--dpo_beta` | DPO beta value | 0.1 | `dpo` |
|
||||
| `--label_smoothing` | Label smoothing for cross-entropy loss | 0.05 | `seq`, `sft` |
|
||||
| `--label_smoothing` | Label smoothing for cross-entropy loss | 0.0 | `seq`, `sft` |
|
||||
| `--group_size` | GRPO group size | 4 | `grpo` |
|
||||
| `--grpo_clip_eps` | GRPO clipping epsilon | 0.2 | `grpo` |
|
||||
| `--grpo_kl_coef` | GRPO KL penalty coefficient | 0.01 | `grpo` |
|
||||
| `--grpo_sync_interval` | GRPO ref_model sync interval (steps) | 200 | `grpo` |
|
||||
| `--neftune_alpha` | NEFTune noise alpha (0=disabled, typical: 5.0) | 0.0 | `sft` |
|
||||
|
||||
### Usage Example
|
||||
|
||||
|
||||
Reference in New Issue
Block a user