Run 4. Outer Step 5. Inner Step 38.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5489093,
-    5489099,
-    5489104,
-    5489110,
-    5489116
+    5489120,
+    5489120,
+    5489120,
+    5489120,
+    5489120
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c63c02298b690ddd5d5d376514647b1289068a4601df165dc8a090c40803065
+oid sha256:56c5c1b934e51dc7fc20b8547eab8d96f4ab15745ddcf08e2f3651e334def3a1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2e6500074f92b737186f41243e2a29c9421ee386c89cfa2d9c5445b0e9eb741
+oid sha256:cd84c577ca73b313af20970ccf4b6cfc8daa4048921d655a09f58f643f7300d0
 size 4040701744