Run 4. Outer Step 58. Inner Step 56.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604130,
-    5604133,
-    5604136,
-    5604137,
-    5604139,
-    5604142,
-    5604144
+    5604146,
+    5604148,
+    5604149,
+    5604151,
+    5604153
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 55,
+  "inner_step": 56,
   "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 sha256:565278ffbfa4a9dc13eca08489de3cb6cc4fc61d06ff1fa02785a6b49b8af049
+oid sha256:a33ce23edf6a4d6043c925dcf1d7bfe9816772b8af2fac4432763ed4133fff09
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c012470602dd5dee27a9572d3763b7c536ff6928f8d3b366ee4e18b0a4eb0d
+oid sha256:b3cac92f43e30311e09611e2b09e71a4abdc628f6e3135130c79b1ba1b87626b
 size 4040701744