Run 4. Outer Step 63. Inner Step 82.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5646449,
-    5646476
+    5646502,
+    5646529
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 80,
+  "inner_step": 82,
   "inner_steps": 0,
   "last_allreduce_block": 5644286,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a0557c76f3a027a71e0545dd31d1d45b9e596240fce2fd9292999e60ee981d
+oid sha256:5bfcabf03aa98b8a4bc865dfabed6884d1efe4f9d1833864d8f80b3aa1ab6b66
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e41ebc858f32c16c214748769c6df4ba0eaeedc6dbe0d2ba7e2426be011bba7e
+oid sha256:4b751a41b39daeb75c4a28dda90d949a94bf37bef05d009d3bbd4b11d63659b8
 size 4040701744