Run 4. Outer Step 28. Inner Step 18.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537627,
-    5537630,
-    5537632,
-    5537634,
-    5537637,
-    5537639,
-    5537641,
-    5537644,
-    5537647,
-    5537648
+    5537650,
+    5537653,
+    5537656,
+    5537658,
+    5537660
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "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 sha256:95ee0b82f689814605f1b0baa0a09306e36769e9b3f36d4d035e51730a298f8c
+oid sha256:09b5021626f5a0deee8e992c31a11f6cd7b30601dbb5b51317431eae7ff734ef
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c878856af90d72f3a072d3c1fbb8714a392b45e85b7e063ecab3bb3cef90db
+oid sha256:b3388ca2a14fdebeac4434893fe6c7e5f922bd6cb0f72c92ab063cc7ab0e4175
 size 4040701744