Run 4. Outer Step 28. Inner Step 35.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538201,
-    5538203,
-    5538204,
-    5538207,
-    5538209,
-    5538213,
-    5538216
+    5538220,
+    5538223,
+    5538226,
+    5538228,
+    5538229
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221fa125ace1e0200bc39c0722267d8d6962d5e2024a9549d999be3235a524cf
+oid sha256:6e426361b5d2aaf3341cac54a391e14fa7c0df79b863f09b0e241f11d8aed2fa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ed54ccc031bd28936fff1ca32cf498f335025286ef2de4623eeef9a7f1bca9
+oid sha256:47f798af6c4cb6c70aa5f06b221037df810e37736f0399d2ea6d3a063e9367b9
 size 4040701744