Run 4. Outer Step 33. Inner Step 9.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544269,
-    5544271,
-    5544274,
-    5544276,
-    5544278,
-    5544280,
-    5544283,
-    5544285
+    5544287,
+    5544289,
+    5544291,
+    5544293,
+    5544295
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 9,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c4fd5f4543d431d77c3c8e48061bc14096097cc95daf50ce9e8f32db7b3245f
+oid sha256:ce8b7ec11f1cdf3aec5cd1252be8ff7b641dc8537cd5251a949040c2b08723b4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9b3827325f811765612a8621dddb62cc04686491be91091c51ca6b770987f7
+oid sha256:5faad0c9133f750f57e1b0ba8c9b4de7c3c9e1d679fa5c7175b65fea5984cf2c
 size 4040701744