Run 4. Outer Step 11. Inner Step 24.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5507666,
-    5507669,
-    5507673,
-    5507676,
-    5507680,
-    5507683
+    5507687,
+    5507691,
+    5507694,
+    5507698,
+    5507702
   ],
   "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": 5506953,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc606fd13313bd58f6e0531b539762b7aba3ce0f8c29936401f6dfb07290cdd
+oid sha256:a39431b7e388e003566cb81aa735490e7bd34cee90ad8fda1134122cca80a890
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f82162127b60f9d5b4f47459fdbc00674fb6303a6c551d47270dd89b7d126af
+oid sha256:e513a525738b29d7ddcb5734a8dc68abfd86b9075b25a99de92dd378fb47b9fc
 size 4040701744