Run 4. Outer Step 10. Inner Step 103.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506510,
-    5506514,
-    5506517,
-    5506521,
-    5506524,
-    5506528
+    5506534,
+    5506537,
+    5506541,
+    5506544,
+    5506548,
+    5506552
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 102,
+  "inner_step": 103,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ad3d2eabf568c5ab60d945eccdfb98d06353c292ace0856f5c28a39d1ae5b9
+oid sha256:46d8a61c1b63a0f83a8ada1422c2aa5b632a2b1d5d74b879ec98b3c9a9738332
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f60ef82a21aaffda6d254c21e1c5df84f636732a021634db9d220fbadd5bad94
+oid sha256:ea00120fddffe0ccb52554cd6f07e091686765fbdff22228dd388f7d2763e667
 size 4040701744