Run 4. Outer Step 61. Inner Step 53.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5610287,
-    5610291,
-    5610296,
-    5610300,
-    5610304
+    5610309,
+    5610313,
+    5610318,
+    5610322,
+    5610326
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 52,
+  "inner_step": 53,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce68550193b6d80b73f8335ebe033a0beb8468ed2ae3c33bfb792839504064e4
+oid sha256:efd1165990debb2357011c8ed7b5e4f597f4583c1ad17b0177c28797a0fbe68d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a982ae4650fc1169eb85ed371da191dcce3ce2898c3e1425598a3f3d4429683d
+oid sha256:9e0be270cbad172f5860ed15ab46098fec1c7271bd214310df6b7bf6a6b85193
 size 4040701744