Run 4. Outer Step 27. Inner Step 30.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5536856,
-    5536858,
-    5536861,
-    5536863,
-    5536865
+    5536868,
+    5536870,
+    5536872,
+    5536874,
+    5536877,
+    5536879,
+    5536881,
+    5536884,
+    5536887
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5535854,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be517c912dcd2af20daf988e57c800030c66164afd44f526e3d757ea7a0a212
+oid sha256:7364df18fb1e421d3f26c448ac86bac44b1a1e422f27b96d1f5bbb7569ca1c02
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e47b8cd5b9511d7907ce1d072b277e5d6bb0cee1af7fa12485e3ed0cb744fa9
+oid sha256:62a3646ae448bb0cd4d4d6e8ff925c6dd3dffbb56320429bcae61ecc7e6102a0
 size 4040701744