Run 4. Outer Step 33. Inner Step 22.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544742,
-    5544745,
-    5544748,
-    5544751,
-    5544753,
-    5544756,
-    5544759,
-    5544762
+    5544765,
+    5544768,
+    5544769,
+    5544770,
+    5544775
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "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:e1f2437a1269ad9291f9312e7917bb31a392410144ec7e107928c7197c550a9b
+oid sha256:6b9992e15d522e5512d47e1be6d9cb32881295ab4f5f1d27504ac26a54112e3a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfd776f13a523c02f7e651e0d17cf911755b67996d7b869232dce14d6b713dd8
+oid sha256:35b3707cb0eb76f9df330a26881339f5c201449d5ff15b1f6b39db36a1e38a20
 size 4040701744