Run 4. Outer Step 12. Inner Step 1.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5508425,
-    5508429,
-    5508432,
-    5508436,
-    5508440,
-    5508444,
-    5508448
+    5508469,
+    5508473,
+    5508477,
+    5508480,
+    5508484,
+    5508488,
+    5508491
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 1,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e601b139f07b2223b4f9d945e1fe4884524d06198dd3a1fe3ee82e4d0dbb2eb1
+oid sha256:7829bbfdf73968c520b416bf7b02a2c47b936e1d6153475023bc8d744d5ebba0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d513ce0f4c374e336f168ca75bcb33bf0241990d62922be0ba596f840e272c1
+oid sha256:f2cf9149ff01b37536d8fb21eac1090a20fbdeaa7f3e70f4f4492de52dae1e58
 size 4040701744