Outer Step 0. Inner Step 113. Batch Size 156

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5155684,
-    5155689,
-    5155694,
-    5155699,
-    5155704,
-    5155708,
-    5155712,
-    5155716,
-    5155719,
-    5155725
+    5155758,
+    5155762,
+    5155765,
+    5155770,
+    5155774,
+    5155778,
+    5155782,
+    5155786,
+    5155790,
+    5155794
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 104,
+  "inner_step": 113,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:363a226383b390fadd207e77b3aece1689cf6578af29ce45077f2b53d9fcd446
+oid sha256:38174b42537e48abf793af18477f2704de394af80613b17d1b482dbab338d5cc
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca090293f5b3a464adc9b72ff8d819c81b7f071df28a75aeb1a951db31ee6125
+oid sha256:d9d4b332e37d743a7f8abae06210b88998d0ee4933945f062e1464abec228325
 size 4040701744