Run 4. Outer Step 57. Inner Step 33.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5585728,
-    5585732,
-    5585736,
-    5585739,
-    5585743,
-    5585747
+    5585751,
+    5585755,
+    5585759,
+    5585763,
+    5585767
   ],
   "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": 5584811,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a222652b45dfad7bd9d9a039843aca27dd608b0ea7a249b850a4e7fa2219220
+oid sha256:de0144c330cf847461288f7eb563ca615d9df9687dfb19ed495367bd049e8b3f
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95722cb223c346dc014b7f108162297c5acac0a37b676b51b5ae8d0feb5f8e6f
+oid sha256:5ae4d51fa3f5cdd05740c3a569666a83c34359b9feff902f77de09dcfbf556cc
 size 4040701744