Run 4. Outer Step 58. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604160,
-    5604165,
-    5604170,
-    5604175,
-    5604179
+    5604184,
+    5604189,
+    5604194,
+    5604198,
+    5604203
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b258b551adb177d6c6e5e60ec46a17055744aa17996233f8029771ca9a8dde12
+oid sha256:61fccdfd7ced79b29ed0ad49a567cfdefa159d0e68c6d0ce5d501614c655589f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ce6311f4df745f1222ce37aa98210bb8e547b4b2eab3767e282449d9e49e6f
+oid sha256:22e1353381fb03cec4faa4de7c5b983740d8569c7616cc86538370fab6fa190b
 size 4040701744