Run 4. Outer Step 40. Inner Step 5.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5555209,
-    5555213,
-    5555218,
-    5555222,
-    5555227
+    5555232,
+    5555236,
+    5555240,
+    5555244,
+    5555248,
+    5555253
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4,
+  "inner_step": 5,
   "inner_steps": 0,
   "last_allreduce_block": 5552497,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709a33702d81ebe36c94728a4a9bae53344ffb74e09144a01d9bd39360a1712b
+oid sha256:92d0468e7b22ff34a7e993c835aa06d7e333a1f8c5b7a954abcff35fd0d54808
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5691940e1bc17eb4f7b61fd4a243b7fe3809e20024f6729ec72b22910507c6b9
+oid sha256:04cee9ca4861af5c53a2bc2527ce16c9f31c1a4cc9320d35dc388cc6ba81a8c1
 size 4040701744