Run 4. Outer Step 60. Inner Step 9.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5607454,
-    5607458,
-    5607463,
-    5607467,
-    5607472
+    5607476,
+    5607480,
+    5607484,
+    5607488,
+    5607493
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 9,
   "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:e600c2dcca81305895a766d361d31a3c808bfe0a73643c4b1f83e73c06caf761
+oid sha256:0292d16bf5215b83f470c1ef2de0fee120471d20b96f2b70343dde406b5bc8a3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc5c2b35766bfb8e918739edf3ee6ed2cddbf1e85ab722ecf4ffcc3a1e7f756
+oid sha256:89bf10fa06ce73518cecf11577760789e1f9b959a50ce1054df7e002d3454fa6
 size 4040701744