Run 4. Outer Step 28. Inner Step 36.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538147,
-    5538149,
-    5538152,
-    5538154,
-    5538157
+    5538159,
+    5538162,
+    5538164,
+    5538167,
+    5538169,
+    5538171,
+    5538173,
+    5538176,
+    5538178,
+    5538180
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a4b6ef064efc3fbc4b416a1fab238e9cbd7b4d58c7fcb3e4f9b1fb1e8058015
+oid sha256:366aed2f24239ebfb24d59dd880b6d9a73982dd809e720601f80cd1300fcd6a8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4e5fb5d3b5f1d308844c44e7ba21eeb575c2d55e56d697ca87aa158ef4f500
+oid sha256:37ef249002777b2ad7e6efd792dc852d192b1e0c7985f5b7fa010035e2e76576
 size 4040701744