Run 4. Outer Step 24. Inner Step 33.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5532534,
-    5532535,
-    5532537,
-    5532540,
-    5532543,
-    5532545,
-    5532547,
-    5532550,
-    5532552,
-    5532554,
-    5532555
+    5532558,
+    5532561,
+    5532563,
+    5532566,
+    5532569
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 33,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43be6fa6cac40edc2487fef328ce8143d25535d50232d6ecf629bb13e1268b8c
+oid sha256:ecf0ac574561721cac11c96a7258419220c16cab8f5922679b76fd80aebc0b57
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b7937b36eaa488ef1673e0762caa1ed0bdb5c0c07a6f703ba3ce5dc74aaf7e
+oid sha256:ece311a3e0572c42161dec796cf22f4103dfb556061c2eba106c62c1846ba835
 size 4040701744