Run 4. Outer Step 3. Inner Step 130.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484596,
-    5484599,
-    5484601,
-    5484603,
-    5484605,
-    5484608,
-    5484611,
-    5484613,
-    5484615,
-    5484617,
-    5484619
+    5484621,
+    5484623,
+    5484626,
+    5484627,
+    5484629
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 129,
+  "inner_step": 130,
   "inner_steps": 0,
   "last_allreduce_block": 5477809,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8509583ac36b46b2ee6cdc6f4a51c670aa77897dc40ec0ed8d8135c7dd8780f9
+oid sha256:63155703da0dfb7cb553076541260e54071605a08f922f9bd74bfef9f5309d60
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30da5b96b692e51193b5298cf741d2bc1f7d479c017dc8110fcb913a7cfbf0e8
+oid sha256:44c2b8ba5c9cb6a36724ea37785dd29e4aad6f3b641bdb667be9f136640091d8
 size 4040701744