Outer Step 0. Inner Step 203. Batch Size 208

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5132680,
-    5132684,
-    5132689,
-    5132693,
-    5132698,
-    5132702,
-    5132706,
-    5132711,
-    5132715,
-    5132719
+    5132749,
+    5132754,
+    5132759,
+    5132765,
+    5132771,
+    5132781,
+    5132787,
+    5132794,
+    5132800,
+    5132806
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 194,
+  "inner_step": 203,
   "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 sha256:3027b10ba41ec10b8156c5e7ee4ff3fdf3f869139db41c801784de1b46a2f31a
+oid sha256:274a5021c2aa4f32470464d6f413f32fa828d12f1cd89da898f8b0d8894fd57e
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c102aa27107b45c92bd80dfde325f9b59392beed36978f701622414bad24a5cb
+oid sha256:2483278724095613b229df3517eee588f55988a3254435554e02ef9a03ddd9a1
 size 4040701744