Run 3. Outer Step 12. Inner Step 68.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5470089,
-    5470092,
-    5470095,
-    5470097,
-    5470099
+    5470136,
+    5470140,
+    5470142,
+    5470144,
+    5470146
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 67,
+  "inner_step": 68,
   "inner_steps": 0,
   "last_allreduce_block": 5450451,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e67eb0e8e2d44c83966e63c61319fd8b3a7d5d5b218abf9a9fecdb20d5d86ca6
+oid sha256:b53bf226402862fbfa5902871a9cd08f446c460e27bf92957a9976b1c5ed82e8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2737241b63140e9377878983594d3f120572286c6e7628f7b4e9789c5592991
+oid sha256:f0f87920e5ab29a2c2cd22f2323acff5733670fc241c90e9360f1817a30a8792
 size 4040701744