Run 4. Outer Step 58. Inner Step 57.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604077,
-    5604082,
-    5604086,
-    5604090,
-    5604095,
-    5604099
+    5604104,
+    5604108,
+    5604113,
+    5604118,
+    5604122
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 56,
+  "inner_step": 57,
   "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 sha256:108082dae83a780026ca6f93869df39e1c25188859a810e382500d226b2bffa1
+oid sha256:f19149f7d5557c8a647e1159e19d60050a4ddad213b67b0f24ddb25da9ebe69d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e7c9399183e3212d462d3f06c37bb5ec77cc084d04e318c050a73977927d768
+oid sha256:16e6526617ce11d8250d7ea635383494124d719001fda9e4854b2b793449a706
 size 4040701744