Run 4. Outer Step 58. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603406,
-    5603410,
-    5603414,
-    5603419,
-    5603423
+    5603428,
+    5603432,
+    5603436,
+    5603440,
+    5603444
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbe31340becae488e602f6706ff5ff9674dd90047eed9ee7020f766737b297de
+oid sha256:44d11e6dc163487621e43a8a3e47a7118982849176822e047dbf89d7f48e1f6d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c57eb8a3f89c8869cb1b2b0d91fa965c96e0302c7a27bb25f51cff97d1e64962
+oid sha256:10745c65f7e7f056ca84406b8a708fc5fda199b184fd26e0fa360cc9fb57b9d1
 size 4040701744