Run 4. Outer Step 3. Inner Step 135.

config.json

@@ -268,18 +268,25 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484826,
-    5484828,
-    5484831,
-    5484834,
-    5484835
+    5484837,
+    5484840,
+    5484842,
+    5484844,
+    5484846,
+    5484849,
+    5484851,
+    5484853,
+    5484855,
+    5484856,
+    5484858,
+    5484862
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 134,
+  "inner_step": 135,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57528b21b21556e88940924b904c5a98ee41c70d23264cd0b5038736512834e9
+oid sha256:c06bd1f844da696d4054e3392d5f91d9799e5d42582f2c99c2b3d41cbcb64c69
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8da4596e20f5155c643381db27b44d9c0ec2557e46b38e00a144f4a62873100f
+oid sha256:976c628cbf6fda236f5d445ee9d791e62850b0b55ba631fe6e45055a900cc343
 size 4040701744