Run 4. Outer Step 4. Inner Step 17.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5486897,
-    5486898,
-    5486901,
-    5486904,
-    5486907,
-    5486908,
-    5486910,
-    5486912
+    5486915,
+    5486918,
+    5486922,
+    5486925,
+    5486929
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5485540,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c7ef9c9ba8a5fd26316262f8077cfa1b96a9c13463a45f523787b4cc95a303
+oid sha256:f0f0e68439e357e00f97898a7330bb8c889286eafc54686010db04e6286e54c1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75f123b1bdcf51f9f4b14d85cc50f68792f4441a0e87b97959bf09ee11e7b8ad
+oid sha256:240922bdbad38cca2c80f03ecbde87b32e03cc19cdd4516a390c216096508748
 size 4040701744