Run 4. Outer Step 29. Inner Step 19.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539117,
-    5539120,
-    5539122,
-    5539125,
-    5539128,
-    5539131,
-    5539134
+    5539136,
+    5539139,
+    5539141,
+    5539143,
+    5539146
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 18,
+  "inner_step": 19,
   "inner_steps": 0,
   "last_allreduce_block": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b972819963ab66c9a02bb22966d6c31b8efa8f81f56f650d5f6cfe0dc49388af
+oid sha256:98221c5f993130251fa1868601ca05877e695d4d6515266d1472fa25bfe13192
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45142a0f2881565570e213a56ec449b2c4d9ce5ef295984b0ae46094ccff52ab
+oid sha256:967764014275c855430a3fd1aa73c75ae1545dd5e22ccdc8fc44f25726c9799f
 size 4040701744