Run 4. Outer Step 15. Inner Step 70.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5515061,
-    5515064,
-    5515069,
-    5515072,
-    5515076,
-    5515080
+    5515085,
+    5515088,
+    5515092,
+    5515096,
+    5515100,
+    5515104,
+    5515107
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 69,
+  "inner_step": 70,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562fcc9e24d29f74a06cc54a32f172644879763f30ea226b8e19bc83517d6ec9
+oid sha256:99559d3857e2f40e64d05e9ad7a7f0d2d0b54e713f7d29f24364f5f5313b60b5
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc06195c7791d1ba2312608ec690bf764c8a3de320e8ef1689d67dba4829168
+oid sha256:3d8e2368c5b90156472e8b8751f99d84e7322fcfdb05c2c40b99e15da1370c25
 size 4040701744