Run 4. Outer Step 52. Inner Step 42.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576264,
-    5576266,
-    5576269,
-    5576270,
-    5576274,
-    5576276,
-    5576280
+    5576282,
+    5576285,
+    5576286,
+    5576287,
+    5576289
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b4486d74bbd018f47732b3e760f04196a40804ffa6434bed98f9aed62e41317
+oid sha256:ba2b0060104b3507f631f932d9a879c1d075c0bed2ed1b58825d0ee8131dcb79
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4332c65d35803ebf718fd97336103c632cc9263e7423b33b1d4ea4b4bf732bce
+oid sha256:50944dc50ec998485744a7f3e6f8580aa68781f91f4435c41363e834c16f05b3
 size 4040701744