Run 4. Outer Step 36. Inner Step 17.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5550019,
-    5550022,
-    5550026,
-    5550039,
-    5550044
+    5550048,
+    5550053,
+    5550057,
+    5550065,
+    5550070
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5549491,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb61a285cfc6cabb61badd1144731a7f28aa632e957894fee492a15c7c79e98
+oid sha256:618e24749d00e9f487e249df6b17c90fa39df98148d7933cffac985f8d364516
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc667c222049dc20ded3f71e3c7f73958cf7561991d96e38958c5344c3f13b0
+oid sha256:a30148897c8dfbb475d12ab55ba77e86edec6d499d163f3ab9df66592a1543de
 size 4040701744