Run 4. Outer Step 31. Inner Step 26.

config.json

@@ -268,21 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5541943,
-    5541945,
-    5541947,
-    5541950,
-    5541952,
-    5541955,
-    5541957,
-    5541960
+    5541962,
+    5541965,
+    5541967,
+    5541969,
+    5541971,
+    5541974,
+    5541976,
+    5541978
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e05bfe74a5b3b54494897c8b41164d1e89f5ae256d40b2a8ea8295a4a3db386
+oid sha256:43848af6b77245c587097178c16bb80253e60e1871a3940e1bbc88a71eb3af42
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0248a343396640e0a882f1b251a6516352a8edf2c4ddcbf102a1cb5495b400d4
+oid sha256:36351d758c6d71a68d47cec574358957f9cc8dfa1bd84ec89763096a0c56a020
 size 4040701744