Outer Step 0. Inner Step 211. Batch Size 188

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5132749,
-    5132754,
-    5132759,
-    5132765,
-    5132771,
-    5132781,
-    5132787,
-    5132794,
-    5132800,
-    5132806
+    5132840,
+    5132847,
+    5132855,
+    5132860,
+    5132867,
+    5132873,
+    5132879,
+    5132884,
+    5132891,
+    5132897
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 203,
+  "inner_step": 211,
   "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 sha256:274a5021c2aa4f32470464d6f413f32fa828d12f1cd89da898f8b0d8894fd57e
+oid sha256:9493d3b236fc726dee3df0200196ac82ef4f57212991c66a8006aff119606187
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2483278724095613b229df3517eee588f55988a3254435554e02ef9a03ddd9a1
+oid sha256:5f98d22d23ce57db0a0d7bac7dd7b431c50a110e04b1f5cde73f593f390d4aad
 size 4040701744