Run 4. Outer Step 33. Inner Step 23.

config.json

@@ -268,26 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544651,
-    5544654,
-    5544656,
-    5544658,
-    5544661,
-    5544663,
-    5544666,
-    5544668,
-    5544669,
-    5544669,
-    5544673,
-    5544675,
-    5544676
+    5544679,
+    5544681,
+    5544684,
+    5544687,
+    5544690,
+    5544692,
+    5544693,
+    5544696
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 22,
+  "inner_step": 23,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be85640a184222f28a3cb79f4268436e6229cd2f61c6d8f7f64f00b24a9d4f9a
+oid sha256:de0491a765760517eeb4ca9a64b4dbf6778f74103963021e829efa26aa53bbb5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d20b599fe55419e87724f8e26796e47faad98124b2da072379a2782a0706040
+oid sha256:3c8f8f7f9e5a9b27f32f65f726ce22c865b7329dddda7322ed40df5b017cb1bb
 size 4040701744