Outer Step 0. Inner Step 150. Batch Size 460

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5141526,
-    5141539,
-    5141556,
-    5141566,
-    5141586,
-    5141593,
-    5141601,
-    5141606,
-    5141614,
-    5141624
+    5141645,
+    5141663,
+    5141666,
+    5141671,
+    5141679,
+    5141684,
+    5141689,
+    5141696,
+    5141706,
+    5141712
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 143,
+  "inner_step": 150,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30f481cd786bfed42c62920e7dce3dfd82a3034446db3d7f7d2dee5ebcfc73ce
+oid sha256:3ecba5c9ccdc9b6047c0fc9ac24eab19c64d1550f996591db000014a7cfacc50
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9f4f6c779c6272e6cff57186d52b8ad4d9b6d279e5bc79d7a31b81b3f1f1ac
+oid sha256:b6a26a6c52be47d2c1808740899ad022b8ca3f01706200d729eab6d72e67cadb
 size 4040701744