Run 2. Outer Step 12. Inner Step 20.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5363559,
-    5363563,
-    5363567,
-    5363571,
-    5363575
+    5363605,
+    5363610,
+    5363614,
+    5363618,
+    5363623
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 13,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5339896,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283b8c76cd7ac81c65162b1b7ea3b391c748bdfd2dd52d7aab80c65b189f9cc2
+oid sha256:a6c2e13983ae6a171cf9eaf333b2379b774bdf0c9c4963a6040ee0d39eb31083
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006c5977fc91491b40fb9b76ce7a1a1814647aaf1b702395cce537eccc98e957
+oid sha256:e63ba64d7728b1281326195efe7b7062ccddf0b81538f1e5dbbe1018587b09c6
 size 4040701744