Run 4. Outer Step 65. Inner Step 23.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5649034,
-    5649068
+    5649103,
+    5649153
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 23,
   "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 sha256:96186fd7fba7a0986c0eecace7f45fe8fad29da1e3f3ca42456b08cd46589383
+oid sha256:45f6ff99f3b3d491b843362e4e493a95751b4308f906d13831890c06ccd30447
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8fa05982fcf02b768e19605b5ef8335b93393a987d916f944134d9808b6fcc2
+oid sha256:6fbcf8526c622824f3db88ba37c3bf694175ad871c9d6148ccbb878086eb26ba
 size 4040701744