Run 4. Outer Step 36. Inner Step 31.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550333,
-    5550337,
-    5550341,
-    5550345,
-    5550349
+    5550353,
+    5550358,
+    5550363,
+    5550366,
+    5550370
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 30,
+  "inner_step": 31,
   "inner_steps": 0,
   "last_allreduce_block": 5546853,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90f1731b2590b0a0a7d7fe8f80646085a7cfe6a389ee9b11ceeb1c7b526f460
+oid sha256:f07f52df18c80e3e81cf2fde9314dbdc099a48d33aaba7c1a7f38b2976eaae83
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f5ccb456f5940106e8b0b7fe0c9a549c0a6f19f1472aa08a0fe3b3d8bdae20e
+oid sha256:76499c321ea8e131bb68a21aa4f04f5925b85a6c4a53ad774387829b1068f5a4
 size 4040701744