Outer Step 0. Inner Step 131. Batch Size 164

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5155860,
-    5155865,
-    5155870,
-    5155874,
-    5155878,
-    5155883,
-    5155888,
-    5155893,
-    5155898,
-    5155903
+    5155933,
+    5155937,
+    5155941,
+    5155946,
+    5155950,
+    5155955,
+    5155964,
+    5155970,
+    5155980,
+    5155988
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 122,
+  "inner_step": 131,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73d6c2a7d9615e59d8362be2def99bff145441d80d470953010ee0ad4fd74dac
+oid sha256:ebfd45bdeb9e1921c5e892673169b5c8260643a51680ebb81a088bc901a0310f
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42e08e2862763302ec6b70d1cc4c1b31b1673c7f3c84299179c103d7d339c086
+oid sha256:d892c78fdd2cf77da05fed809c184f9cf751676aa5314fe633a751c39393ece3
 size 4040701744