Run 4. Outer Step 34. Inner Step 28.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5547947,
-    5547951,
-    5547956,
-    5547961,
-    5547965
+    5547970,
+    5547975,
+    5547979,
+    5547984,
+    5547988
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "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 sha256:4d0ca0dfe7d99e9d49f275c042796718e08cfb72ab5130e89efc208e2ac59f7e
+oid sha256:c4f253ca6bbb425d7f581c08b7dcfbb78582f7de89bfe1c727f1ab2c7f20dbbb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d456d15115d84ad05859792635714cd3b57663b7cae2aaf479f9619688f47f
+oid sha256:a87c4ab397ab1981de3b3dc4e731a63b4af984766e6a757ce3b70e919fa2c7f8
 size 4040701744