Run 4. Outer Step 40. Inner Step 34.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556166,
-    5556170,
-    5556175,
-    5556179,
-    5556184
+    5556189,
+    5556193,
+    5556198,
+    5556202,
+    5556206
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563a7e616545c7c965f50bdc0dd7af5f9b81f75a280a636d552737aeba15946a
+oid sha256:2c8eff3c53cedf1d1e31ad83caedbbfe501a8efe65310e4109ba009075ea84b1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2984cb4ad9ba8c1a08ade13d6b7c0a61cae818b70e5ecdf98e2385f00e0b6608
+oid sha256:0d5c13db2b0d71cc45a7459f3bdb8057e6612b81c54daeefa2138155a21caef4
 size 4040701744