Run 4. Outer Step 31. Inner Step 25.

config.json

@@ -268,22 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5541923,
-    5541925,
-    5541928,
-    5541931,
-    5541934,
-    5541936,
-    5541937,
-    5541939,
-    5541941
+    5541943,
+    5541945,
+    5541947,
+    5541950,
+    5541952,
+    5541955,
+    5541957,
+    5541960
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 25,
   "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:c61567c377b2fe61f04cb09a4e7574a5d21d18acae5f655b8817561d8414cc0c
+oid sha256:8e05bfe74a5b3b54494897c8b41164d1e89f5ae256d40b2a8ea8295a4a3db386
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4ca0f8b03d5e5615da02f5de640344f52fd2cfeae5cbde46c2ba689c6f1d9d
+oid sha256:0248a343396640e0a882f1b251a6516352a8edf2c4ddcbf102a1cb5495b400d4
 size 4040701744