Run 4. Outer Step 65. Inner Step 102.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5650918,
-    5650922,
-    5650927,
-    5650931,
-    5650935
+    5650940,
+    5650944,
+    5650949,
+    5650953,
+    5650957
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 101,
+  "inner_step": 102,
   "inner_steps": 0,
   "last_allreduce_block": 5648011,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d6a9d59c3055c95886d2c1b28015e2002898cc373b3f3f123054ad214be4247
+oid sha256:63236e88f9f5591ba17909606d26e082cdfa73de3d5f47cfcd72230ec9a37a65
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb68118a703222c24d63e3a8857451339c176c976959bcd3ff6cd680659856c7
+oid sha256:944b8511781a363d26fe2220a20362b532804f228716e7f9e7493d6ae95e1581
 size 4040701744