Outer Step 0. Inner Step 204. Batch Size 360

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5132590,
-    5132594,
-    5132599,
-    5132604,
-    5132608,
-    5132612,
-    5132617,
-    5132621,
-    5132625,
-    5132629
+    5132661,
+    5132665,
+    5132669,
+    5132673,
+    5132678,
+    5132682,
+    5132687,
+    5132691,
+    5132696,
+    5132700
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 195,
+  "inner_step": 204,
   "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 sha256:46fdf9a88f421c593db325967021c969fed2689ff7505272285fa4e166eebb92
+oid sha256:b39f64ed8a00cfce9e3701cbed6b0699c8094f6e3d351668a4767a3a37f7f7ae
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b8d0fa33cd343a778f6a7fa87b90e2f662b479af7200891fc20cf5fe9270eb
+oid sha256:5ac3ab592f57d16fa5b417d0bb13eab8b68aaac111b718d0722b6482d940b23a
 size 4040701744