Run 4. Outer Step 40. Inner Step 40.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5556478,
-    5556482,
-    5556486,
-    5556490,
-    5556495
+    5556500,
+    5556504,
+    5556507,
+    5556513,
+    5556517
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5555115,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e33a039c8bfd0453a3b38277c8b12507b11e78ad9cea5b479a04dc634d786bb
+oid sha256:eef8a66b0ae2e373220f1411515490af4b4547630f2d904ee1a87dbfd2c82040
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44169e80d4b7a35057c97cea157d6342769cc5a0b2e30236939d83073967c27
+oid sha256:e1d958bfe8b7c6a9b5bf022e44b042a9431ce1c384b4e7b78f0c798289a0166f
 size 4040701744