Run 4. Outer Step 65. Inner Step 103.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5650940,
-    5650944,
-    5650949,
-    5650953,
-    5650957
+    5650961,
+    5650966,
+    5650970,
+    5650974,
+    5650978
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 102,
+  "inner_step": 103,
   "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 sha256:63236e88f9f5591ba17909606d26e082cdfa73de3d5f47cfcd72230ec9a37a65
+oid sha256:071f60cc81a6b2730991fe322328630998fb7a95745c53b97f7a71a33a7fa7af
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944b8511781a363d26fe2220a20362b532804f228716e7f9e7493d6ae95e1581
+oid sha256:9ddaedca106cd4975702a3ef454c024a2a5f8fe5d9825f542398671034681a64
 size 4040701744