Run 4. Outer Step 85. Inner Step 10.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5675472,
-    5675487
+    5675505,
+    5675526
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5675035,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e867cfb670cf6284bb59fbf8b971723b984db700e4546558dba0e7ffed9231fc
+oid sha256:896717015c8a79e20e5539abe645296a18602a4c4623fc5dc4ba1be3bcb2128d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b6f8580b2a4e04786270a6bc00f8144337b41c31c3d1c3ad995f9ce62dbda22
+oid sha256:024086569f5abb25cbf2019d5ee53e6335d852b63a5c70ed804feea45b8578d6
 size 4040701744