Run 4. Outer Step 28. Inner Step 35.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538125,
-    5538127,
-    5538129,
-    5538131,
-    5538134,
-    5538136,
-    5538139,
-    5538141,
-    5538143,
-    5538144
+    5538147,
+    5538149,
+    5538152,
+    5538154,
+    5538157
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7020feff1ce6056599b5bd2a522ca65ddccbe93edda995ba47b9eed1b8265a8
+oid sha256:7a4b6ef064efc3fbc4b416a1fab238e9cbd7b4d58c7fcb3e4f9b1fb1e8058015
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a1ff81c5020a32a67dca0434f47c976eb86c6677166d8d35d19f36cdb0cb24
+oid sha256:fd4e5fb5d3b5f1d308844c44e7ba21eeb575c2d55e56d697ca87aa158ef4f500
 size 4040701744