chore: import upstream snapshot with attribution

examples/deepspeed_conf/ds_stage0.json

@@ -0,0 +1,30 @@
+{
+  "train_micro_batch_size_per_gpu": 1,
+  "gradient_accumulation_steps": 1,
+  "steps_per_print": 100,
+  "gradient_clipping": 5,
+  "fp16": {
+    "enabled": false,
+    "auto_cast": false,
+    "loss_scale": 0,
+    "initial_scale_power": 16,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "consecutive_hysteresis": false,
+    "min_loss_scale": 1
+  },
+  "bf16": {
+   "enabled": true
+  },
+  "zero_force_ds_cpu_optimizer": false,
+  "zero_optimization": {
+    "stage": 0,
+    "allgather_partitions": true,
+    "allgather_bucket_size": 5e8,
+    "overlap_comm": true,
+    "reduce_scatter": true,
+    "reduce_bucket_size": 5e8,
+    "contiguous_gradients": true,
+    "round_robin_gradients": true
+  }
+}

examples/deepspeed_conf/ds_stage1.json

@@ -0,0 +1,33 @@
+{
+  "train_micro_batch_size_per_gpu": 1,
+  "gradient_accumulation_steps": 1,
+  "steps_per_print": 100,
+  "gradient_clipping": 5,
+  "fp16": {
+    "enabled": false,
+    "auto_cast": false,
+    "loss_scale": 0,
+    "initial_scale_power": 16,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "consecutive_hysteresis": false,
+    "min_loss_scale": 1
+  },
+  "bf16": {
+   "enabled": true
+  },
+  "zero_force_ds_cpu_optimizer": false,
+  "zero_optimization": {
+    "stage": 1,
+    "offload_optimizer": {
+      "device": "none",
+      "pin_memory": true
+    },
+    "allgather_partitions": true,
+    "allgather_bucket_size": 5e8,
+    "overlap_comm": true,
+    "reduce_scatter": true,
+    "reduce_bucket_size": 5e8,
+    "contiguous_gradients" : true
+  }
+}

examples/deepspeed_conf/ds_stage2.json

@@ -0,0 +1,33 @@
+{
+  "train_micro_batch_size_per_gpu": 1,
+  "gradient_accumulation_steps": 1,
+  "steps_per_print": 100,
+  "gradient_clipping": 5,
+  "fp16": {
+    "enabled": false,
+    "auto_cast": false,
+    "loss_scale": 0,
+    "initial_scale_power": 16,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "consecutive_hysteresis": false,
+    "min_loss_scale": 1
+  },
+  "bf16": {
+   "enabled": true
+  },
+  "zero_force_ds_cpu_optimizer": false,
+  "zero_optimization": {
+    "stage": 2,
+    "offload_optimizer": {
+      "device": "none",
+      "pin_memory": true
+    },
+    "allgather_partitions": true,
+    "allgather_bucket_size": 5e8,
+    "overlap_comm": false,
+    "reduce_scatter": true,
+    "reduce_bucket_size": 5e8,
+    "contiguous_gradients" : true
+  }
+}

examples/deepspeed_conf/ds_stage3.json

@@ -0,0 +1,41 @@
+{
+  "train_micro_batch_size_per_gpu": 1,
+  "gradient_accumulation_steps": 1,
+  "steps_per_print": 100,
+  "gradient_clipping": 5,
+  "fp16": {
+    "enabled": false,
+    "auto_cast": false,
+    "loss_scale": 0,
+    "initial_scale_power": 16,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "consecutive_hysteresis": false,
+    "min_loss_scale": 1
+  },
+  "bf16": {
+   "enabled": true
+  },
+  "zero_force_ds_cpu_optimizer": false,
+  "zero_optimization": {
+    "stage": 3,
+    "offload_optimizer": {
+      "device": "none",
+      "pin_memory": true
+    },
+    "offload_param": {
+      "device": "none",
+      "pin_memory": true
+    },
+    "allgather_partitions": true,
+    "allgather_bucket_size": 5e8,
+    "overlap_comm": true,
+    "reduce_scatter": true,
+    "reduce_bucket_size": 5e8,
+    "contiguous_gradients" : true,
+    "stage3_max_live_parameters": 1e9,
+    "stage3_max_reuse_distance": 1e9,
+    "stage3_prefetch_bucket_size": 5e8,
+    "stage3_param_persistence_threshold": 1e5
+  }
+}