Outer Step 0. Inner Step 226. Batch Size 392

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5132731,
-    5132736,
-    5132740,
-    5132745,
-    5132751,
-    5132756,
-    5132760,
-    5132765,
-    5132772,
-    5132782
+    5132811,
+    5132817,
+    5132822,
+    5132829,
+    5132836,
+    5132843,
+    5132848,
+    5132855,
+    5132860,
+    5132866
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 218,
+  "inner_step": 226,
   "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 sha256:296de18df47c4fda771d4843e2ebe252a92440dcf44f2923018a69b7ff381d89
+oid sha256:d83ea30f68de8b631d221f44fa60946ac2201bdabb0eb51ee3d3e4341c5bbd89
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c20ec94b93732efb37f6e2b2617a1a2db670006760b017a3d3e5cf79c762bc41
+oid sha256:898c890f6b8c5c6028e7c03a47e077d75eda668074faf21b30c1d625b7768353
 size 4040701744