Run 4. Outer Step 23. Inner Step 1.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5527900,
-    5527904,
-    5527908,
-    5527911,
-    5527915
+    5527920,
+    5527923,
+    5527927,
+    5527931,
+    5527935
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21e8da496d65ee3334261546881956ad4cad9fccef4a71996b90bbc5e71b0083
+oid sha256:12fd7d5cf39f34e21052c6e1bfac597c371555de9c20a8e2a95a57cf89c72470
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a110bfd380dca4530cab0ed8ad08321fa9782cc3c0160f6e90d868890a013dd
+oid sha256:ba667795372df476c63469aa6380a9fbc018ab4d703bee299c6076b6c12606b7
 size 4040701744