Run 3. Outer Step 9. Inner Step 1016.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5421525,
-    5421529,
-    5421532,
-    5421535,
-    5421538
+    5421566,
+    5421569,
+    5421572,
+    5421576,
+    5421579
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1015,
+  "inner_step": 1016,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16efcce713c214c0ae1c730db825c493608edfe110eaa6db5ad575f4136ffd63
+oid sha256:02588a24a317d9b0d6d0c32bcec5b3cf81e3ab4282495f3870c9df302a07513e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d18c4682abc24167a4ca9f74f3b490bf70ae6f056742325e525af903083165e
+oid sha256:d4b62b4e57a8878e0759e8c551c7643e32eec35bf225f438d041421e04dfa5fb
 size 4040701744