Run 4. Outer Step 13. Inner Step 8.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5511580,
-    5511584,
-    5511588,
-    5511592,
-    5511596,
-    5511601,
-    5511605
+    5511609,
+    5511613,
+    5511617,
+    5511621,
+    5511625,
+    5511629,
+    5511633
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "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:d5fe05c601a6614d35b610de45b2cdec2d8773207990a293b73b5c84118f83c5
+oid sha256:f926178e9d25d49cc32851af1b83fce7c934a69cf7f9fedb0b074163343644e3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ce902b6a32662f07847b29252ffa523ab45bec20d40560b995930f2e84932d
+oid sha256:463f22260efe89dc33f331975d8476c3043d4de52d223e43d6617b0e3462d0b1
 size 4040701744