Run 4. Outer Step 24. Inner Step 28.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5532394,
-    5532397,
-    5532399,
-    5532401,
-    5532403,
-    5532405,
-    5532406,
-    5532407,
-    5532409,
-    5532411,
-    5532413
+    5532416,
+    5532419,
+    5532422,
+    5532424,
+    5532425
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dabdc8a8cd14fd1eb7b7ecf8c73ca880e09e1b4feac70095860249bdbbecf0f
+oid sha256:8735b83a6461ad76dadd06254296b5dd1e2e15f48361bb2f42a06025c6021dde
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65e3476bf5f72d2e345706dd02388840660e329378a65220a1a87038ba1f8ec8
+oid sha256:0d1ec6ddccb0b65138821bdf70ffddc6183c5fa7a22dea69d756fdad4b64393d
 size 4040701744