Run 4. Outer Step 59. Inner Step 53.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5606996,
-    5607000,
-    5607004,
-    5607008,
-    5607012,
-    5607015,
-    5607019
+    5607024,
+    5607027,
+    5607036,
+    5607040,
+    5607043
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 52,
+  "inner_step": 53,
   "inner_steps": 0,
   "last_allreduce_block": 5605539,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e42bc6a69a43a777c081683dd741893103ff31e7336a33cd257047f2335d91fc
+oid sha256:2b696aea14c467763a0a89675250ff9ba46e97103e235abed39fb88dba1547ec
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4131d9e5fb93d88ab7b3e90e2eaea1d0adf8a2c0715dce9f320374d55bcaf690
+oid sha256:4d8c05de1eef8179c03fd2c1449c01abe915fffcc381a8b43f30c33be22b5313
 size 4040701744