Run 3. Outer Step 9. Inner Step 60.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5400304,
-    5400307,
-    5400314,
-    5400317,
-    5400320
+    5400386,
+    5400389,
+    5400392,
+    5400395,
+    5400399
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 56,
+  "inner_step": 60,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d28d25f863888f972f332059d8ebebcfa76a6e889059465c49b803b7b8eabfa1
+oid sha256:7813f92ef4e52be6e36c7f3479e8b1771322764006876820c514fd34a443ef8e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7060029d747b08033be6af224b0f716704ce71c9d9b755e37c1dcc0c0c67751f
+oid sha256:49d4e5c5ab2c31a8e1ae5b242392584972f4bd2cb3613b1ece3b8534205a399a
 size 4040701744