Run 3. Outer Step 9. Inner Step 1007.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5421322,
-    5421326,
-    5421329,
-    5421332,
-    5421336
+    5421363,
+    5421366,
+    5421370,
+    5421373,
+    5421376
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1006,
+  "inner_step": 1007,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4af3b3c8c750779ee6c882923c3d073af32d380c396c36765f93d89e32a0d651
+oid sha256:1d06cfea03d07d536e7a69c065b299c6e751da6883983846e205086f25587cc5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eda7b312b6e978c91c14a8b3a6f754b0d0790a0a642fbba7647539712bc1066
+oid sha256:4e825ab188800118ba70a8abf35dceb0540e4aa8f71de5fd949ee3f2a7149402
 size 4040701744