Run 4. Outer Step 8. Inner Step 40.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5500998,
-    5501002,
-    5501006,
-    5501010,
-    5501014
+    5501019,
+    5501023,
+    5501027,
+    5501031,
+    5501035
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 39,
+  "inner_step": 40,
   "inner_steps": 0,
   "last_allreduce_block": 5499548,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d76fbaa4eafe38ec30d92140cb3ba254df738dbea181e5153296ce30849785
+oid sha256:3ca6f4347a690db435f081d1eb9b62bde834daa3a47d3e7d11a3f9db14530a9d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8367a2ac1795c02af467a117bc444f494710ea4bbc8f135eee73414648b5bf9
+oid sha256:4dcc548e311b36f34414b5b2255dff965f100c99be725194ca21a72d216d7c31
 size 4040701744