Run 4. Outer Step 24. Inner Step 48.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5533061,
-    5533064,
-    5533066,
-    5533068,
-    5533071
+    5533072,
+    5533074,
+    5533077,
+    5533080,
+    5533083,
+    5533085,
+    5533088,
+    5533090,
+    5533092,
+    5533094
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 47,
+  "inner_step": 48,
   "inner_steps": 0,
   "last_allreduce_block": 5531651,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7c93b25089a1f032e3f6b6da7d84e95a4bdcbbd39f7c82cd6ba8bb585ae0a82
+oid sha256:68d92da5aab2529f929889aa38f51205b788e6455bf6bd8fc420d816534750eb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51e520270af8d27664572199a55af63a1ea82439440071a88dedccf9e69f8094
+oid sha256:abb6488b949aa9f25d1a34cafe14593c9737b388c764430ab61020ab1a17833e
 size 4040701744