Run 2. Outer Step 2. Inner Step 110.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5330452,
-    5330456,
-    5330461,
-    5330465,
-    5330469
+    5330503,
+    5330506,
+    5330512,
+    5330515,
+    5330520
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 103,
+  "inner_step": 110,
   "inner_steps": 0,
   "last_allreduce_block": 5323221,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec3d72fd29b908bed93fa77fa1c0fe5f6327f9cb1d9298bd6d71f6b68ba2a20
+oid sha256:b45da69e5e7c2a90a09c0d7c886516d2faed0cca4301c8c9d5ee779e9a9a6dbd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d2269bf9632c0e96201d8ffdaa8006fe36ed38e4fbb5b88b0c283ebb1d51a01
+oid sha256:b21ad997d00291af46fb3385476c1551611d1b60737195fc4a31b44f235e36f7
 size 4040701744