Run 4. Outer Step 33. Inner Step 24.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544698,
-    5544702,
-    5544704,
-    5544706,
-    5544709,
-    5544711,
-    5544712,
-    5544715,
-    5544717,
-    5544720
+    5544723,
+    5544725,
+    5544726,
+    5544731,
+    5544733
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 24,
   "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:de0491a765760517eeb4ca9a64b4dbf6778f74103963021e829efa26aa53bbb5
+oid sha256:bc0590b68fcf74d2658d4af274439a96fb6bfb00f6833153b286a5648fcb8a1a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c8f8f7f9e5a9b27f32f65f726ce22c865b7329dddda7322ed40df5b017cb1bb
+oid sha256:868588e67b5ff5965d51ebfc8e0a70ff8cd168b0d175b60bc5fee73e37044080
 size 4040701744