Run 4. Outer Step 58. Inner Step 25.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603353,
-    5603359,
-    5603365,
-    5603371,
-    5603377
+    5603384,
+    5603391,
+    5603396,
+    5603402,
+    5603408
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1caba234a8c632c3cd298176e47fb8d299323dd233497d908c22e2dd0aef690e
+oid sha256:0e3a5203ac220832da043d4a3d1e504917eba6e585cbe8db39a87b51ce905d50
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c25fa5c81ad3d542187a01226396f461c7ba671cc2db4ed33c2299b933fa10af
+oid sha256:d7bf553c0200b07d9b5ae7ce0e718bd277b6e1c4ce2712089d04112639fb79a0
 size 4040701744