Run 3. Outer Step 5. Inner Step 139.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5384110,
-    5384116,
-    5384121,
-    5384126,
-    5384131
+    5384160,
+    5384165,
+    5384171,
+    5384176,
+    5384182
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 138,
+  "inner_step": 139,
   "inner_steps": 0,
   "last_allreduce_block": 5373127,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac00437963d51658160c9e50f638d29daa9cc1efb35e2d2de4740b5d0b339fc0
+oid sha256:fdfb845b095b00b05f69a7a4a99afa4610669bc9b57fb78ca973a7a3bda47e13
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10765bf221870736306ad36e805359cd18cec47a538fcf3af5957db88f0b2c17
+oid sha256:680a34952fe5f586a7219931fb964b5b314ccc11c3055b59406ca5cce47141cc
 size 4040701744