Run 4. Outer Step 22. Inner Step 62.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5529154,
-    5529160,
-    5529165,
-    5529171,
-    5529176
+    5529182,
+    5529188,
+    5529193,
+    5529198,
+    5529204
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 61,
+  "inner_step": 62,
   "inner_steps": 0,
   "last_allreduce_block": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f4a6effbeb3bf09296fc4ac3565af88c5e9cbd854703e7558f9de0e8305826
+oid sha256:04fee594acf0aa6975f1eda7211f2ff4dcaec4cbf402ba36a8507d2a382d5e0d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b03fd212e8106109229b88853adfd688096673c6f3cc2645e87e16a6bb1334
+oid sha256:0c5852e3dee7946c8cbf752e3faa15553b8226b42a7c8775e70daa6582d9ce5d
 size 4040701744