Run 4. Outer Step 53. Inner Step 25.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5577063,
-    5577065,
-    5577067,
-    5577070,
-    5577073,
-    5577076,
-    5577078
+    5577081,
+    5577084,
+    5577085,
+    5577089,
+    5577091
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "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 sha256:9e340ebc24df52cae2ed2b048dfb69a01e07262a1a4207cad9349ed17af41c4c
+oid sha256:81fc07dfa5bc6cd602585ad2b096764cd3035c37c88d4427a3ddf13e5bef507d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5a62f450ef532ab2b3658b5a0b397740f0ce415ab6f980b57d39f2a40437bc7
+oid sha256:4540721d5df0e92c07253a466742c2a19a12ae902ebff7ecf110dc70677b7ef7
 size 4040701744