Run 4. Outer Step 57. Inner Step 29.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5602019,
-    5602022,
-    5602024,
-    5602026,
-    5602029,
-    5602031,
-    5602033
+    5602036,
+    5602038,
+    5602041,
+    5602044,
+    5602046
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5600871,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e77e5a8d75855bb2174405aa37a09c98859a40f51726703d3dc89d172af3d4db
+oid sha256:46550f5669116015c3f44c6c3da473b34a0a595980e072b4dbbbc34889f4a052
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c98a639791ee11da7a4d16a20424b84bab18e3345ae4f0fe4ec8e23b0385ddb
+oid sha256:a65b3f8137dfcaa4aba0f7da51b2a8dbb93b4f2ca7ca454e5502102c7d66afdc
 size 4040701744