Run 4. Outer Step 65. Inner Step 32.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5649442,
-    5649474
+    5649507,
+    5649537
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5643114,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e36d32cbfc1ff1edb87b14fb168ebd5ea0195e81a23d99aa83e667bdb86dbeb
+oid sha256:97e4657ffbc52dfec8d56530a8056bef0410818ffded594a8c4266eefa6e81f6
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a683f054b6a8c834da683df20528601051690bb78d672530849401bc3894a8
+oid sha256:be55fdb8c3551b980de258a10641adaf8a4962d467b6de133f735c483fbb217f
 size 4040701744