Run 4. Outer Step 63. Inner Step 7.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5612230,
-    5612230,
-    5612230,
-    5612230,
-    5612231
+    5612232,
+    5612232,
+    5612232,
+    5612233,
+    5612233
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 7,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0915797e91bb45fda80f0ff9d32306f9c12e4468e1edae0be26aab6b94ffe920
+oid sha256:5edc2e138a6a299b21ea443e988d6aa3e222e392aa9fceb08dbe7fd3e0d8fd5e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf81fcf3efcc074f74cfaa4310b06320a14dc1d5c7dd28d0e70634f50bb5343
+oid sha256:2ca0199792a44a245ef602e9e359746fd48c3e7be8c0ceb7fe98b0ab85f1f87c
 size 4040701744