Run 2. Outer Step 10. Inner Step 269.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5353564,
-    5353568,
-    5353571,
-    5353574,
-    5353577
+    5353606,
+    5353609,
+    5353612,
+    5353615,
+    5353618
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 261,
+  "inner_step": 269,
   "inner_steps": 0,
   "last_allreduce_block": 5339896,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:883743aa7b4169c9273b1b13c94bc64f1998bec6ad1193110746a633b5f0387c
+oid sha256:d3e9404c7f299ae63f9b0935a0311c1bf1ba4758446853ab3e322e702e2792cd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1266ff14bf56a4897b61c2b25bb09acd843196c6ca2f5c0d0558588a9d513718
+oid sha256:ae6175aad66c6dc7b881114dd849fda40fda88fee0714e0cc9a6b2521c2fc537
 size 4040701744