Outer Step 8. Inner Step 29. Batch Size 92

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5291178,
-    5291182,
-    5291185,
-    5291188,
-    5291192,
-    5291196,
-    5291199,
-    5291203,
-    5291206,
-    5291211
+    5291375,
+    5291379,
+    5291383,
+    5291386,
+    5291390,
+    5291393,
+    5291397,
+    5291401,
+    5291404,
+    5291408
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5283755,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:416f441d885763a03def389b28766717a83d5109e438361e19c7f311ed55416c
+oid sha256:ada6b4d9e2c97fe8b8dd33e1a2029627e4168fe4993614653cc042883f39cc7d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c1aeaa11d8716a89b781b3235a4c39bb89f71f3d8c11b93ca5d9c0291c9737
+oid sha256:741865c46426beba6100f4b9668b2110493f6b5be3bba44e53ce4d457567a6fa
 size 4040701744