Run 4. Outer Step 60. Inner Step 10.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5608031,
-    5608035,
-    5608039,
-    5608043,
-    5608047
+    5608052,
+    5608056,
+    5608060,
+    5608064,
+    5608068
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 9,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5607244,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c503aa5e55b05cf399a57f616155a7e271c11ccc753a0cb5323da1bc09a9cf8a
+oid sha256:1109de37f34c89b89f33823d09550074f032ba15653f0acfb9a23998fd8f7cbf
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79fb67639924e88f86f1bd8e731a06ff2533040ecd7166d55dec6569c87647d
+oid sha256:09103220fe00d2c57b6f2ffe74928dc414b891121cb2a00ee2a2e27cffef2522
 size 4040701744