Run 4. Outer Step 31. Inner Step 48.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5542646,
-    5542648,
-    5542650,
-    5542652,
-    5542655,
-    5542657,
-    5542659
+    5542662,
+    5542664,
+    5542666,
+    5542668,
+    5542671
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 47,
+  "inner_step": 48,
   "inner_steps": 0,
   "last_allreduce_block": 5541234,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:343e5520d74bb9eb491e732837f521e7b70b3e079a4f1177397f52a2bbc3e98b
+oid sha256:e1610552ffea5548d6a8d8a584c370aa3826b1276f6308025754230fa84a5a53
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7e53122c12b32694357817e35d6bd715ec670cc6a4476db9c6e6ee17f0feff
+oid sha256:e4dc63744e064b012ac3825926e6f03b58fcb699fd417d0c12eb826c742b05fb
 size 4040701744