Outer Step 0. Inner Step 19. Batch Size 324

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5130208,
-    5130214,
-    5130222,
-    5130232,
-    5130244,
-    5130250,
-    5130261,
-    5130267,
-    5130277,
-    5130284
+    5130318,
+    5130325,
+    5130331,
+    5130338,
+    5130347,
+    5130353,
+    5130357,
+    5130363,
+    5130374,
+    5130384
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 19,
   "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:cf9db094b74d6ddc61ad1a6ec3e37c30abe4f1ec66053cc9eaab57e5f8613141
+oid sha256:5dbc142f57377b430b891be7c74cafe102602087de1b760b3dd23bae9071a82f
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ca75773d44c3dafd6fd7a0304591f9ccbf67a819af6082f684b84980fb1ae0
+oid sha256:6e4bb5d483d0a015a770188a1a7f63d583d05353750da538cbb0478cfc608a0c
 size 4040701744