Run 4. Outer Step 28. Inner Step 22.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5537744,
-    5537746,
-    5537747,
-    5537750,
-    5537753,
-    5537756,
-    5537758,
-    5537760,
-    5537761,
-    5537763
+    5537764,
+    5537767,
+    5537769,
+    5537772,
+    5537774
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 21,
+  "inner_step": 22,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d2b0a214fadad9a20a51b3f7040999719a1d06c375f49507dec66e76268eef6
+oid sha256:855900af5cf6af5f130c74a7da1ba65ddd20079d4589f28f584bbf4306fb3dcb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e1c32b395d50590329a71d689e51dadfeb40d49edcd9cca2acabb15f038047
+oid sha256:f1fef659e12635a56fc27d864ca9d18f5ee5c14c18edc725f4081bfd0df4873d
 size 4040701744