Run 4. Outer Step 64. Inner Step 225.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5617367,
-    5617371,
-    5617376,
-    5617380,
-    5617384
+    5617389,
+    5617393,
+    5617398,
+    5617402,
+    5617406
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 224,
+  "inner_step": 225,
   "inner_steps": 0,
   "last_allreduce_block": 5611658,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44424ff5105bcd7c951c82de5f32e63a19434df5e588575dc91581fc01e187c5
+oid sha256:6685118c249619565e54940d60c995973fb74e0d8273570aa79eb03aa7c27c24
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99525d6c6adfe1e9f240d2b943a0f16bdf1dba39769e828a8d409803b2e40b47
+oid sha256:abd1c9189fc6eb8449d80969d56a9a82597e3df7ee7215dc442f018ed18965b5
 size 4040701744