Run 4. Outer Step 35. Inner Step 16.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5548653,
-    5548657,
-    5548662,
-    5548666,
-    5548671
+    5548676,
+    5548680,
+    5548685,
+    5548689,
+    5548694
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 15,
+  "inner_step": 16,
   "inner_steps": 0,
   "last_allreduce_block": 5546853,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d210c25c97b92e9c4f682afbc5e545cb2f77dd70abcf6e5e25db5732e2334b75
+oid sha256:c5194ea8ee359f91f1a028a3b26c242094b7440adf37af9409d7920287935a9e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680d2b5f86f7d00b7808c9ae2edf3916213bb6e1cc8376116a794b6976e1a0cd
+oid sha256:bfa28738107c959e5ef4882cfb13749763dbe5e0cc6532927cd360ce9776f722
 size 4040701744