diff --git a/ds_config.json b/deepspeed/zero3.json similarity index 89% rename from ds_config.json rename to deepspeed/zero3.json index 1e150ba95..69ad19259 100644 --- a/ds_config.json +++ b/deepspeed/zero3.json @@ -37,18 +37,18 @@ "lr": "auto", "betas": [ 0.9, - 0.999 + 0.95 ], "eps": 1e-8, "weight_decay": "auto" } }, "scheduler": { - "type": "OneCycle", + "type": "WarmupLR", "params": { - "cycle_min_lr": 0.00001, - "cycle_max_lr": 0.00003, - "cycle_first_step_size": 120 + "warmup_min_lr": "auto", + "warmup_max_lr": "auto", + "warmup_num_steps": "auto" } }, "train_batch_size": "auto",