Run 4. Outer Step 54. Inner Step 140.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5598147,
-    5598156,
-    5598161,
-    5598165,
-    5598170
+    5598176,
+    5598181,
+    5598186,
+    5598191,
+    5598196
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 139,
+  "inner_step": 140,
   "inner_steps": 0,
   "last_allreduce_block": 5590498,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8d27d2cd2d0cb096887bdd996a6c61c21705797761e5f4cecea3a54a08da0b2
+oid sha256:e84fe2ab46175ae63040eb73f3f33e488efb241d1a033f802d3d502a74a56512
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf83a8bf55f639bec809a81a9963c038e052d9a11beca693ae9d41d79ebc548e
+oid sha256:1892f37ea208225c28140015348c6f4327e352b0e9b1054558633e6cfca4ebd0
 size 4040701744