Run 4. Outer Step 30. Inner Step 17.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5541037,
-    5541041,
-    5541045,
-    5541049,
-    5541054
+    5541059,
+    5541063,
+    5541067,
+    5541071,
+    5541076
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc31faf9de3b955fc0fc8aafd73d83a14f93d1a46f43252a4ec7005cf8d77262
+oid sha256:7250fd4421f679235611810dbbae589f494a1cb31dd562075368416418043724
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37887d373a2681d47d415ffa770912827355274f4f5bc5e6ecc82074155c26f
+oid sha256:65af1f9d2d227ab99671842c45f2468e4cdba2691c2ff734fd1d079ade10c1a0
 size 4040701744