Run 4. Outer Step 10. Inner Step 104.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506534,
-    5506537,
-    5506541,
-    5506544,
-    5506548,
-    5506552
+    5506556,
+    5506560,
+    5506564,
+    5506568,
+    5506571,
+    5506575
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 103,
+  "inner_step": 104,
   "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 sha256:46d8a61c1b63a0f83a8ada1422c2aa5b632a2b1d5d74b879ec98b3c9a9738332
+oid sha256:f41b624128f2ee89d81924691ce83bab2e4ba2b70ac0c0a8e119f34ba004145c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea00120fddffe0ccb52554cd6f07e091686765fbdff22228dd388f7d2763e667
+oid sha256:43d80a174a28c4007cf30d88459630f1550b6874dd4a3fa39fd8c471d3094d95
 size 4040701744