Run 4. Outer Step 61. Inner Step 71.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5643010,
-    5643015,
-    5643019,
-    5643023,
-    5643027
+    5643031,
+    5643036,
+    5643040,
+    5643044,
+    5643048
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 70,
+  "inner_step": 71,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f7775f9d6a803df18d5a28c686ac230c4d3b30a7ae93f466612b1cf65a3598b
+oid sha256:bee66cf45345f8a8cc3bf62e4fc5cde4103adbc3ae009c0be1efc968bd29962c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:607bac48b0847cb2e9ce079604c17195603ed5795e383bc2b48c0f0086aa0167
+oid sha256:b3e0b66cee84cefc3decb5dc12479b45ae69e5f803cbfeef3d842cdd43087b01
 size 4040701744