Run 4. Outer Step 3. Inner Step 135.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484750,
-    5484753,
-    5484756,
-    5484758,
-    5484760,
-    5484763,
-    5484766,
-    5484768
+    5484771,
+    5484773,
+    5484775,
+    5484777,
+    5484779
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 134,
+  "inner_step": 135,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c08439f9502967d84ce178d36a56ea86652d22d50787f51d8efdbca523dfc98
+oid sha256:e457e2a510ac95812f2e340602803a0d33c20b05f51b74458529a9813053ad0e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d51cffaa66ad929a4ea5e0c099360738f8ea5d36196e2a2fd91da881e876bc
+oid sha256:dcf12d215a49519b67199822d4e4c62423c517d51fc630a636761d9a0d86316b
 size 4040701744