Run 3. Outer Step 12. Inner Step 63.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5469963,
-    5469966,
-    5469969,
-    5469972,
-    5469975
+    5470008,
+    5470010,
+    5470013,
+    5470016,
+    5470018
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 62,
+  "inner_step": 63,
   "inner_steps": 0,
   "last_allreduce_block": 5450451,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd749226f5edb1ab8c40dce224ff3edefeafadace4e458d8bf23ba5bdd9bbe4b
+oid sha256:1c90a080258ad49dc4844c4ff037d05ef40df3c2bbca77456402abdce6922103
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c194bb07e54a9ebcea10a55bb140ad728f1db78f2e2bce68a5df665bae0061ac
+oid sha256:8f4370e4831b2ecb07b58626acbb0b4bee2d3f8ea4fcf8ee319b87bfeab4f081
 size 4040701744