Run 4. Outer Step 30. Inner Step 34.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5541183,
-    5541187,
-    5541192,
-    5541196,
-    5541200
+    5541205,
+    5541209,
+    5541213,
+    5541217,
+    5541221
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5539810,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f013efd203d5b2b35b22e70813d3bfcb160160207f718c12a1ef859af7a3c4d0
+oid sha256:3b259598e2d8b12aa0a32f4d272a15103976eb928943b19b6c64c339c59191a8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:358a9e0d4ac07c8d750cded30cc53198d73ae49fc88173522de6d80d97393fce
+oid sha256:dcf0667a5f08d6584a716550e2d9403db61dfa61e31f67ff7d698e646d96e8c6
 size 4040701744