Run 4. Outer Step 52. Inner Step 36.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576159,
-    5576161,
-    5576163,
-    5576165,
-    5576168,
-    5576170,
-    5576172
+    5576174,
+    5576176,
+    5576178,
+    5576179,
+    5576183
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "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:fd23c1cdadc26714355ebcaea98ad87094f607f9633d791c96e47dec4d90c533
+oid sha256:53c23a2e4fd755599bbb95448a0458056ae1219629be5f2937d92205e55a237d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d39e1887bd8466d4c8f7bb9f0b580e64e4dda3b65a432bae983a536a1f7f268
+oid sha256:7d08bcd89ba84a4b1e50b8185a2b122cfd752ef0ec85be9ce2b9277de30f97a8
 size 4040701744