Run 4. Outer Step 50. Inner Step 20.

config.json

@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5572080,
-    5572084,
-    5572088,
-    5572092,
-    5572096,
-    5572100,
-    5572104
+    5572109,
+    5572113,
+    5572117,
+    5572121,
+    5572125,
+    5572129,
+    5572133
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 19,
+  "inner_step": 20,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403bc08367b403c002fd16a314c8db68b268245c4660ddf2cd94758a90b3476f
+oid sha256:78377eec45172dfc253e416067b3f148fdc457a1381b2c3d0ff525824d7c3686
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0baca79b035c8919b9ac9edef992aad5d3ad71c5b48f0644e1d4c5594c630055
+oid sha256:74756da94997d756f4ff3cf2094baf8910395fe5e5a029bbfe30fa0a89c9b8cd
 size 4040701744