Outer Step 1. Inner Step 1609. Batch Size 240

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5184091,
-    5184096,
-    5184100,
-    5184104,
-    5184108,
-    5184112,
-    5184117,
-    5184121,
-    5184125,
-    5184130
+    5184159,
+    5184163,
+    5184168,
+    5184171,
+    5184176,
+    5184180,
+    5184183,
+    5184189,
+    5184193,
+    5184198
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1599,
+  "inner_step": 1609,
   "inner_steps": 0,
   "last_allreduce_block": 5160840,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3011b599a456bc42956c80eb96ab261d22c428b1ab74f217b6fcc6611fed5557
+oid sha256:becfc8d3f75a809e09c1d79d860a7e225fad63ffc136cd6b4e1b7d9d13ad9be1
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe676ef4a8cecab68adf401e4a41bf66a3a3474c6c840da5ed3f90dc2e48403
+oid sha256:b3b87add0912f7603983cde0d5c8b574fa744fd44dc1b6e60ebc988ff230610a
 size 4040701744