Run 4. Outer Step 58. Inner Step 58.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604006,
-    5604010,
-    5604015,
-    5604019,
-    5604023
+    5604028,
+    5604033,
+    5604037,
+    5604041,
+    5604046
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 57,
+  "inner_step": 58,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a41194edace8608520593e7a11d3fbd3e0dcc53ff755e6d6ccf5b1232d64f0
+oid sha256:f22c3ea99d653e8f05b1e469d7e6e73d07585c57806ef1e4f284990460f99747
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95fbafe420ebba418e82e03d8ecd83b8ee0c31db4881dd8d33c30a98c58c70e0
+oid sha256:7e4dff13753a1d83c1b482e71fc83d0ffc5921b997012810567b65b2c01b63cd
 size 4040701744