diff --git a/deepspeed/runtime/engine.py b/deepspeed/runtime/engine.py old mode 100755 new mode 100644 index 5db39d237967..41761d772707 --- a/deepspeed/runtime/engine.py +++ b/deepspeed/runtime/engine.py @@ -1287,9 +1287,6 @@ def zero_model_persistence_threshold(self): def zero_gather_16bit_weights_on_model_save(self): return self._config.zero_config.gather_16bit_weights_on_model_save - def zero_grad_hooks(self): - return self._config.zero_config.grad_hooks - def zero_legacy_stage1(self): return self._config.zero_config.legacy_stage1 diff --git a/docs/_pages/config-json.md b/docs/_pages/config-json.md old mode 100755 new mode 100644 index 8f91414abd8f..c9abd8d817eb --- a/docs/_pages/config-json.md +++ b/docs/_pages/config-json.md @@ -531,12 +531,6 @@ Enabling and configuring ZeRO memory optimizations | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------- | | Initialize fp32 master weights from fp32 copies in checkpoint (no precision loss) or from model's fp16 copies (with precision loss). This can be used to initialize optimizer state even when checkpoint is missing optimizer state. | `True` | -**grad_hooks**: [boolean] - -| Description | Default | -| ----------------------------------------------------------------------------------------------------------------------------------------- | ------- | -| For use with ZeRO stage 1, enable backward hooks to reduce gradients during the backward pass or wait until the end of the backward pass. | `True` | - ***round_robin_gradients***: [boolean] | Description | Default |