Run 4. Outer Step 29. Inner Step 12.

config.json

@@ -268,18 +268,26 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538900,
-    5538903,
-    5538906,
-    5538908,
-    5538909
+    5538912,
+    5538914,
+    5538915,
+    5538916,
+    5538918,
+    5538920,
+    5538922,
+    5538924,
+    5538926,
+    5538929,
+    5538931,
+    5538933,
+    5538935
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 11,
+  "inner_step": 12,
   "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 sha256:846cfa1cb4206533c33c3d6d509d853250ffe88a0372350848dabd560d062825
+oid sha256:058368aba579ae43197668ef0a544d9b232d61d5629c568d0981b8d945e56ed1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f43f57d594d248d3eb4714532db1fd6302dcaf129d6dc1f192b1b98eead7d3f0
+oid sha256:94524512e04c0f9eff0912e87a5cc19855447a8b3e3f0ebf884303f88d62cc26
 size 4040701744