Run 4. Outer Step 29. Inner Step 11.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538877,
-    5538879,
-    5538882,
-    5538884,
-    5538886,
-    5538889,
-    5538891,
-    5538893,
-    5538894,
-    5538896,
-    5538898
+    5538900,
+    5538903,
+    5538906,
+    5538908,
+    5538909
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 10,
+  "inner_step": 11,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b91ad1af816c261c317287f9a9f14fb2df77024e434a35ed549b6bb288d42ae
+oid sha256:846cfa1cb4206533c33c3d6d509d853250ffe88a0372350848dabd560d062825
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdfe9eeb42b70de08a0ab6e9318a8a794f37ffb73699204969ea4cafc7fe1651
+oid sha256:f43f57d594d248d3eb4714532db1fd6302dcaf129d6dc1f192b1b98eead7d3f0
 size 4040701744