Run 4. Outer Step 66. Inner Step 24.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5651931,
-    5651980
+    5652014,
+    5652047
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 24,
   "inner_steps": 0,
   "last_allreduce_block": 5643114,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb3e8aa6b1563c7b498f0bdd52e8a6e03493a2c4fad9072e10293883b21afa35
+oid sha256:27f85cb857cc70bdc09e729f4767de9a6122d84972f665ef8bc0be1f15b9b3d1
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa35c8bfe789e3a0d078b15e15379377b8c2708a24b2f95757d478c299cc9af8
+oid sha256:8e63b0738875dfd890732638d015d374797d0ea38cce4557643c6d8a1f150bab
 size 4040701744