Run 4. Outer Step 43. Inner Step 80.

config.json

@@ -268,18 +268,14 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5562937,
-    5562941,
-    5562945,
-    5562949,
-    5562954
+    5563197
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 72,
+  "inner_step": 80,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8c8005c7c00c043d2027f95a5757e87a8cd76e948ab11d6b12aa3c7a0f4a643
+oid sha256:72fccec7191ee1f8983e7426a42546e0573fae9d681ac12c50a508756ad8a314
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa9e9cffd0a9c3df4772fac420256fbdafa8c0d40c6ea46c5d437c0e51e17801
+oid sha256:523af28a30011b064cf1ebff15dd60bf938ffcfd7fe4147990aba4ee99014cce
 size 4040701744