Run 4. Outer Step 32. Inner Step 30.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543636,
-    5543638,
-    5543641,
-    5543643,
-    5543646,
-    5543648,
-    5543650
+    5543653,
+    5543657,
+    5543660,
+    5543663,
+    5543666
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9715a47617ca0b1eca564f24a30d7e4e58e6a5f4dcdcfcd119e32ec1d3818ce9
+oid sha256:5725b25351aadc22a9fdd5dc1555999048ea300c5993beaa307784e098d24623
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b4f035a2131692e903e49f90b1cc25487f200519e108bb4fc1147e23758a81
+oid sha256:9a61203815f0a4d6dc608b639407fd3221deef5f89a14389373e9c29c04b838c
 size 4040701744