Run 2. Outer Step 10. Inner Step 183.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5354709,
-    5354710,
-    5354712,
-    5354713,
-    5354715
+    5354744,
+    5354744,
+    5354746,
+    5354747,
+    5354748
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 175,
+  "inner_step": 183,
   "inner_steps": 0,
   "last_allreduce_block": 5351170,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e52dd0e6c1afcacc93d38a9cf0e6258e56e31606e4cddf23a7e4b957541bcba
+oid sha256:88aa6c3d9026dc3bd5dcd6cdaa26db46e8201ccb9b5cb66154dcc329e74b7c1e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed770163a2693593d518f97e0507d9a1b887e8f09ea6530930c6dcf9347092a1
+oid sha256:31c23501c3f33dbcd5b6e587be0b23f565fc4e539e27176811e46dcc65199868
 size 4040701744