Run 4. Outer Step 29. Inner Step 21.

config.json

@@ -268,24 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539143,
-    5539145,
-    5539147,
-    5539149,
-    5539152,
-    5539154,
-    5539157,
-    5539160,
-    5539161,
-    5539162,
-    5539165
+    5539166,
+    5539168,
+    5539170,
+    5539172,
+    5539173,
+    5539176,
+    5539179,
+    5539179,
+    5539183,
+    5539185,
+    5539188,
+    5539191
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 20,
+  "inner_step": 21,
   "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:e82352edd539d4964e5a189d1f3c0ce644d1f2bfb9871a2d341dfdd68e3d0997
+oid sha256:17a47c7305d8f924db6a7e4bdd352748513c498dda99aaeb66c4751b3bdb487f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc691dfa7b0c594208211d231b015820ce0ae4adb53ec265c6898d4c0f07107d
+oid sha256:7e4c4bd50901221c7202470f7f2dce9dba554a642bc22ee57181b03e6da33bce
 size 4040701744