Run 4. Outer Step 28. Inner Step 15.

config.json

@@ -268,18 +268,27 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537534,
-    5537536,
-    5537539,
-    5537541,
-    5537542
+    5537544,
+    5537546,
+    5537548,
+    5537550,
+    5537551,
+    5537553,
+    5537554,
+    5537555,
+    5537557,
+    5537559,
+    5537561,
+    5537563,
+    5537566,
+    5537568
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 14,
+  "inner_step": 15,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba27ac8286dcf36d782a0c7ee3a309d9940839544427ebaacd775576c526be81
+oid sha256:760d3ee06847e6474c9592a6b811601a715e0a88f15d2149155a82229d3fb692
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffc24ae1c1d48bc552f5b4b5c6759203538ee551da9621d207b01ab1cd4ccea9
+oid sha256:5d3747478a27a0e6c6cd9c7d9f8648f39383c9b6b257303ae1601730eeef3c6a
 size 4040701744