Run 4. Outer Step 7. Inner Step 162.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5499157,
-    5499159,
-    5499161,
-    5499163,
-    5499164,
-    5499168,
-    5499171
+    5499173,
+    5499176,
+    5499177,
+    5499180,
+    5499180
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 161,
+  "inner_step": 162,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:654272d8ac925f332aafa45227785aa89b0458a4bb3e07b31e71d07f5141d010
+oid sha256:2d5e6b67201fc7a82e6a10cf940e37c7060e31e1c3fcf1ab6d8c212d9a576a5c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad82a0fcd69a03edaef4dbe09fb0d73e95e1055b494ba64bfd806ac47ebca5a
+oid sha256:10ca06147b7482803ba45d4d98819ac99ce0f3ac2dfd716c44a5887ca5e16a79
 size 4040701744