Run 4. Outer Step 37. Inner Step 40.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5552010,
-    5552015,
-    5552020,
-    5552025,
-    5552030
+    5552035,
+    5552039,
+    5552044,
+    5552048,
+    5552053,
+    5552058
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f13597371fe976f43ec8f2dabe449b818b406c06d93776f7421d08dc987c099d
+oid sha256:202945f5ba5d89e2919ebdff4013713fd97188e279b743df425bce126824fad8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12fd4e26fb542df5f40cb83c93aefcabdabbd4af3769230155c4b0d9eadea846
+oid sha256:4c7fb861407e80c3a79331b16deb847b998f9e8fd5b11fcf05800b94d7fd39bd
 size 4040701744