Run 3. Outer Step 5. Inner Step 145.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5384313,
-    5384319,
-    5384324,
-    5384330,
-    5384335
+    5384363,
+    5384368,
+    5384374,
+    5384379,
+    5384384
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 143,
+  "inner_step": 145,
   "inner_steps": 0,
   "last_allreduce_block": 5373127,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d895a10b2c82e346c802cf64b84d6829e9bf6b6a41fd3fc380f07ab4f931e85
+oid sha256:af665a27982ff6f14fa7f49b2a5fa024a626574c773c7e10840435fbb48eced2
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db60521b97b4fb55c3129c992991d26ab1c3a85dfca7f33d620cd92a2522a132
+oid sha256:85d352ee57ec716a62a5fe9f30dda8192b15224d7b5788f3aa777260cfd73c9f
 size 4040701744