Run 4. Outer Step 3. Inner Step 141.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484851,
-    5484854,
-    5484856,
-    5484859,
-    5484862,
-    5484865,
-    5484868
+    5484871,
+    5484874,
+    5484876,
+    5484876,
+    5484879
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 140,
+  "inner_step": 141,
   "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 sha256:76a23b29474e2c61141b0755e69677a5b23f83ba79c71f653c1574703aca80f3
+oid sha256:11051497b85c4dd1149b86a5be7c112e9e194a9c3b3b6026aeec7d62f63dcede
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0034e9048523c72784f7d0791ed7972a2e4b172f32b1c59b2e811ea722a268
+oid sha256:e1c40b7a2f25e4e7a79fbf619f876a632a7e39e1bfecaf26ea8a4c46c3b263bc
 size 4040701744