Run 4. Outer Step 15. Inner Step 61.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5514838,
-    5514841,
-    5514845,
-    5514848,
-    5514852,
-    5514856
+    5514860,
+    5514864,
+    5514868,
+    5514872,
+    5514875,
+    5514880
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 60,
+  "inner_step": 61,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85988f0a6ed828b8114ea0e1622ef4ac51893758a3c1b37f620ccb90774960ab
+oid sha256:032782ba2d2e6c90e6e43f67ae7fb11b540a367c41f1e2333f931b6704733537
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ac813de63288c5e7518580e972b49a4ab6354ffba043403cd3751e41bc2ace
+oid sha256:06be3c8cce555e795c6c28d1bea3525f8d6ca6534d1107942e27c19f2d2a4b6b
 size 4040701744