Run 4. Outer Step 58. Inner Step 33.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604673,
-    5604678,
-    5604682,
-    5604686,
-    5604691
+    5604696,
+    5604700,
+    5604704,
+    5604709,
+    5604713
   ],
   "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": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d2b67941c09a1bac674f2708977072b7b1b9ef318ae74eb67ebf394b1b6ab9a
+oid sha256:d52c1e3e73096bb9128584dece345c265c405d4f3f8edb2f9a22211af04344ea
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c0ac2171e89a0e937ce7533ec55caa102b219a34985f74055d557a5066e519
+oid sha256:efc7f99fe63241fa4cf135115530948425a374cbdbf0ea8499788a65597b401f
 size 4040701744