Run 4. Outer Step 52. Inner Step 33.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576032,
-    5576035,
-    5576037,
-    5576039,
-    5576041,
-    5576044,
-    5576046
+    5576048,
+    5576051,
+    5576053,
+    5576055,
+    5576058
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf927d321261638bf22c93749f49e67e060d719b602ba3d60f0f2258530464e
+oid sha256:20b1d04b2819c21ddafc8a1c0181c28b46dce1bee4a1c0a5f0aa3dda90133254
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f2cfa7f99d6ca0d1d333db46cd5149fc9c96da3e6861e8070848b61a656bef
+oid sha256:05bb43707692a3152d07199044183fbdbed307c79c4e1ed55a021139dc54dfb4
 size 4040701744