Run 4. Outer Step 55. Inner Step 33.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5599005,
-    5599010,
-    5599015,
-    5599020,
-    5599025
+    5599030,
+    5599034,
+    5599039,
+    5599044,
+    5599050
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4197de4cdad47b0b958947c9d38114305cf4f304cb745fd3852ab51a1e0e25
+oid sha256:74f013352bce5d883c436257ff15714ffa013423771f3af9ca8c2ac7a5e954db
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:471542e5601f9cedfe99b0b1d03c04ad66b8fcacbfc576469873ff6d92a53312
+oid sha256:f59da83b897768cf82f3292b7a4f8d1c8cb40b604e9270fb01f4e6151619139a
 size 4040701744