Run 4. Outer Step 52. Inner Step 21.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575646,
-    5575649,
-    5575652,
-    5575653,
-    5575655,
-    5575658,
-    5575660,
-    5575662
+    5575665,
+    5575667,
+    5575669,
+    5575672,
+    5575674
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d2a6f6a9fa2f8c0e15981946365f85cf3d8c75d377dc5b807cad328bd995afe
+oid sha256:722e250b47c7d56741caedaffc111c04710225ed6e2efdaf22dd05c10c5f9302
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c3e0b89ab0f3255c5f70435dc22ae6ab86a020073bd406336879e6cf9dff80
+oid sha256:fabb6b19c2b8b63ac534f0949519d16839a38c2781fcb2bbbc255ef6fc1ef9f9
 size 4040701744