Run 4. Outer Step 58. Inner Step 57.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604107,
-    5604109,
-    5604112,
-    5604115,
-    5604117,
-    5604119,
-    5604121
+    5604124,
+    5604127,
+    5604130,
+    5604132,
+    5604135
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 56,
+  "inner_step": 57,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab3caf177bb2ad61f7a745a1d0962a764f6b2f04ba7576b7b118f6c0f84697e
+oid sha256:f91d1bc3d104644c945b510d887f566bedb96827ca2184d471e673b894964bfc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f0f576499035ab81a51a5fa42f8bf740c3a156d99612ac6536ffdc3ca2bc95
+oid sha256:5cd1d7a9d24ede3c4b27472adf852b955da0a9dc193db457cd86dc1b528e4cac
 size 4040701744