Run 4. Outer Step 24. Inner Step 34.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5532558,
-    5532561,
-    5532563,
-    5532566,
-    5532569
+    5532572,
+    5532574,
+    5532575,
+    5532577,
+    5532579,
+    5532581,
+    5532584,
+    5532586,
+    5532589,
+    5532592
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 33,
+  "inner_step": 34,
   "inner_steps": 0,
   "last_allreduce_block": 5529444,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf0ac574561721cac11c96a7258419220c16cab8f5922679b76fd80aebc0b57
+oid sha256:b70d7c236ba1e28cf5c4a77f02811ab334a0904757573a69ccbdf12fd4fb95b1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ece311a3e0572c42161dec796cf22f4103dfb556061c2eba106c62c1846ba835
+oid sha256:21c1df4c785a1a66e5fa8ece73c470d0637a6eea5e032f25959c2cb4548aec12
 size 4040701744