Initial commit: RL floating-point noise projectHEADmain

1 files changed, 38 insertions, 0 deletions

diff --git a/configs/deepspeed_zero3.json b/configs/deepspeed_zero3.json
new file mode 100644
index 0000000..6e68c8f
--- /dev/null
+++ b/configs/deepspeed_zero3.json
@@ -0,0 +1,38 @@
+{
+  "train_batch_size": "auto",
+  "train_micro_batch_size_per_gpu": "auto",
+  "gradient_accumulation_steps": "auto",
+
+  "zero_optimization": {
+    "stage": 3,
+    "offload_optimizer": {
+      "device": "none"
+    },
+    "offload_param": {
+      "device": "none"
+    },
+    "overlap_comm": true,
+    "contiguous_gradients": true,
+    "sub_group_size": 1e9,
+    "reduce_bucket_size": "auto",
+    "stage3_prefetch_bucket_size": "auto",
+    "stage3_param_persistence_threshold": "auto",
+    "stage3_max_live_parameters": 1e9,
+    "stage3_max_reuse_distance": 1e9,
+    "stage3_gather_16bit_weights_on_model_save": true
+  },
+
+  "bf16": {
+    "enabled": false
+  },
+
+  "fp16": {
+    "enabled": false
+  },
+
+  "gradient_clipping": 1.0,
+
+  "zero_allow_untested_optimizer": true,
+
+  "wall_clock_breakdown": false
+}