Run 4. Outer Step 54. Inner Step 96.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580419,
-    5580421,
-    5580424,
-    5580427,
-    5580429,
-    5580432,
-    5580434
+    5580437,
+    5580438,
+    5580440,
+    5580441,
+    5580443
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 95,
+  "inner_step": 96,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdcf69b73ee25b9a8e45e2799f277595f80821d6c29266752af7d55c8889156a
+oid sha256:ce5556fed48cd31a33d7fb6f49f1ec1588cef9b3bba4bd83120b1be630a32d79
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26fb9426d611f4957aac4c09dffd808a80e6d28fd6b5117f1929c0329fb131bc
+oid sha256:1d82d1ab7687d53c1a1db6d8ffadfcc47e873507f1b8962ea1eb287cad6fe6af
 size 4040701744