Run 4. Outer Step 85. Inner Step 8.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5675185,
-    5675214
+    5675248,
+    5675280
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 6,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5672513,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e8338c142305d5167f8f64f4f68838617cbdf38d7570198d62388e307b1e72a
+oid sha256:481d2e6eb2e85337c984a509fbca8f56da9015357d2b0ffb5a2f1ee1467b1133
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2ceb4daa3f9f46fb5c3df6abe9ff0b519b6e6a3ce3608199489e5a4acce7a9a
+oid sha256:076f820d7674cefd5db7de9c5a1713b46d6bbe7fe8af15d1f7f4ae5913d7cc5a
 size 4040701744