Run 3. Outer Step 6. Inner Step 252.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5389167,
-    5389171,
-    5389174,
-    5389178,
-    5389182
+    5389215,
+    5389218,
+    5389222,
+    5389225,
+    5389229
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 249,
+  "inner_step": 252,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c9a1dbd5c79d2e3e383a87d0641be6f16e61bafbaabec6a0575c0df07bc51f
+oid sha256:b0d89fe741bd7dd23a16a9157fd5f9119f6450b3c00f1c50e20d3e0c63195f6b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2746afc5ce7b69280a00364441a962b6fca7bd6d2ca063b619fe83904c4c7d5f
+oid sha256:8f5eee82b378b3123f8fb9fb1faf94d93a0b2b65988984440912a6f13f141b55
 size 4040701744