Run 4. Outer Step 61. Inner Step 9.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610051,
-    5610055,
-    5610060,
-    5610064,
-    5610068
+    5610073,
+    5610077,
+    5610081,
+    5610085,
+    5610090
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 9,
   "inner_steps": 0,
   "last_allreduce_block": 5608831,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a99e1c846ec556d551b63ee308c20d85b2095427363cca67e11e92d14fb30c
+oid sha256:892098af74f67fe1a488d1e16985b69612deb0a3165f258ec86750b2c3e1463e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c36aa56cc028301e6bc479911cac32a23a59ef2a29ba192f6d8ce33f9a684bb
+oid sha256:f1033488d39efe1d6e4ada01d108a4476444fbcfde8c5870b452fcefc2ea6d79
 size 4040701744