Run 3. Outer Step 11. Inner Step 247.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5444418,
-    5444422,
-    5444426,
-    5444430,
-    5444433
+    5444463,
+    5444466,
+    5444470,
+    5444474,
+    5444477
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 246,
+  "inner_step": 247,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f15d00567fd82a3ba2f7a7f012da2c594207e0dea2025dc2e7ae4664bba6aaa
+oid sha256:c1beb907e0f835ee4bd2f5c02a672bc91686711b04d7104ea645cd2646a2e8e4
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb08a97d18237f4c87add4a809c4f646e4a2f7adf51b59973183b20d775bf19
+oid sha256:404ed2d874cbd32430201aeecdd941400ad5cb0a300f9f837ed194dd95008c3f
 size 4040701744