Run 4. Outer Step 17. Inner Step 56.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5520590,
-    5520594,
-    5520598,
-    5520601,
-    5520605,
-    5520609
+    5520613,
+    5520616,
+    5520620,
+    5520624,
+    5520628,
+    5520631
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 55,
+  "inner_step": 56,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e315e69437aa45b8fd1ae60ec0e1f3f9daeb9971d99c5861549143715c36611a
+oid sha256:1cb1a5fd177fe7ccb40503055d442c7c4a091df6aaf5af169d7aa76640f84721
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8301ba559caa19cfe4442b71bd92eab7d655e23add48d0994dbe8f8042ec22cf
+oid sha256:a8f357ad36277bedfc967bbee75f6d8c1326fead2d153b5b769003e520c83309
 size 4040701744