Run 4. Outer Step 58. Inner Step 18.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603153,
-    5603160,
-    5603167,
-    5603174,
-    5603181
+    5603189,
+    5603196,
+    5603202,
+    5603209,
+    5603217
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec37255ee8a994e5c6a29751d3256177035e98e30926b74d7655c7024df7f512
+oid sha256:ec71292b1f0d762866748d0c712a6792cc85ea9667c3b56c58840df74ea46e21
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ba159bef9f419abca550e94650037dde7573288fddb35c1954c1fb19b4c502
+oid sha256:763efe56687af97a45008636157b397cd80f77dd6a8fd648861119a32683083a
 size 4040701744