Enhance training script and evaluation logic to support all-future model target mode and improve error handling for distribution modes

README.md

@@ -73,6 +73,8 @@ HealthDataset = NextStepHealthDataset
 collate_fn = next_step_collate_fn
 ```
 
+all-future 训练入口会显式使用 `AllFutureHealthDataset` 和 `all_future_collate_fn`。
+
 dataset 会输出：
 
 ```python
@@ -227,18 +229,21 @@ all-future / query-conditioned 监督：
   - 使用 `NextStepHealthDataset`
   - `--target_mode delphi2m` 默认搭配 `Delphi2MLoss` + `token` readout
   - `--target_mode uts` 默认搭配 `UniqueTimeSetExponentialLoss` + `same_time_group_end` readout
+  - 当前 next-token 训练只支持 `--dist_mode exponential`
 - `--model_target_mode all_future`
   - 使用 `AllFutureHealthDataset`
   - 不使用 readout，直接对 query hidden 计算风险
   - `--dist_mode exponential/weibull/mixed` 分别搭配 `ExponentialLoss`、`WeibullLoss`、`MixedLoss`
 
-模型结构组合由 `model_target_mode × time_mode × dist_mode` 决定：
+当前 `train.py` 支持所有已有训练目标定义的组合：
 
-| 维度 | 可选项 |
-| --- | --- |
-| `model_target_mode` | `next_token`, `all_future` |
-| `time_mode` | `relative`, `absolute` |
-| `dist_mode` | `exponential`, `weibull`, `mixed` |
+| 训练模式 | 时间模式 | 分布/监督 | 默认 loss/readout |
+| --- | --- | --- | --- |
+| `next_token` | `relative`, `absolute` | `target_mode=delphi2m`, `dist_mode=exponential` | `Delphi2MLoss` + `token` |
+| `next_token` | `relative`, `absolute` | `target_mode=uts`, `dist_mode=exponential` | `UniqueTimeSetExponentialLoss` + `same_time_group_end` |
+| `all_future` | `relative`, `absolute` | `dist_mode=exponential` | `ExponentialLoss`，无 readout |
+| `all_future` | `relative`, `absolute` | `dist_mode=weibull` | `WeibullLoss`，无 readout |
+| `all_future` | `relative`, `absolute` | `dist_mode=mixed` | `MixedLoss`，无 readout |
 
 示例：