Outer Step 0. Inner Step 72. Batch Size 232

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5140083,
-    5140088,
-    5140092,
-    5140099,
-    5140104,
-    5140110,
-    5140114,
-    5140119,
-    5140125,
-    5140130
+    5140158,
+    5140163,
+    5140167,
+    5140171,
+    5140175,
+    5140179,
+    5140184,
+    5140188,
+    5140192,
+    5140196
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 63,
+  "inner_step": 72,
   "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 sha256:6f24cbb6c6d56dc68a441cceddb9729bc4b12d688dd78b2b42007027b7836d5f
+oid sha256:86336812ee73b2f6d19cbea9f3a9ae5bc7406443eff43064b20f90edadaacd79
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3dc81b020a214d9ce39b909a9a4e77f0cc8f40439a18c1119c7956b665b7b8b
+oid sha256:8d27c367795785487b5604e91b09aa66fe0f8e7bdb6889c595b6060239c27e87
 size 4040701744